diff --git a/.github/actions/setup-gitnexus-web/action.yml b/.github/actions/setup-gitnexus-web/action.yml index 86331e36d..8f895423a 100644 --- a/.github/actions/setup-gitnexus-web/action.yml +++ b/.github/actions/setup-gitnexus-web/action.yml @@ -1,5 +1,5 @@ name: Setup GitNexus Web -description: Setup Node.js 20.19+ (vite 7 floor), build gitnexus-shared, install web dependencies +description: Setup Node.js 22, build gitnexus-shared, install web dependencies runs: using: composite @@ -7,9 +7,7 @@ runs: - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4 with: # Vite 7 requires Node ^20.19.0 || >=22.12.0 (require(esm) support). - # Pin explicitly so we don't depend on the floating "20" alias resolving - # to a high enough patch version on every runner image. - node-version: '20.19.0' + node-version: 22 cache: npm cache-dependency-path: gitnexus-web/package-lock.json diff --git a/.github/actions/setup-gitnexus/action.yml b/.github/actions/setup-gitnexus/action.yml index e946f1040..b9b4acb7e 100644 --- a/.github/actions/setup-gitnexus/action.yml +++ b/.github/actions/setup-gitnexus/action.yml @@ -1,5 +1,5 @@ name: Setup GitNexus -description: Setup Node.js 20, install dependencies, and optionally build +description: Setup Node.js 22, install dependencies, and optionally build inputs: build: @@ -12,7 +12,7 @@ runs: steps: - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4 with: - node-version: 20 + node-version: 22 cache: npm cache-dependency-path: gitnexus/package-lock.json diff --git a/.github/dependabot.yml b/.github/dependabot.yml index f3530e4d3..c99b666eb 100644 --- a/.github/dependabot.yml +++ b/.github/dependabot.yml @@ -7,6 +7,8 @@ updates: directory: / schedule: interval: weekly + cooldown: + default-days: 7 open-pull-requests-limit: 5 commit-message: prefix: chore @@ -15,6 +17,36 @@ updates: - dependencies - ci + # Keep pinned Docker base-image digests current for the root Dockerfiles. + - package-ecosystem: docker + directory: / + schedule: + interval: weekly + cooldown: + default-days: 7 + open-pull-requests-limit: 5 + commit-message: + prefix: chore(deps) + include: scope + labels: + - dependencies + - ci + + # Keep the nested test-image Docker base digest current as well. + - package-ecosystem: docker + directory: /gitnexus + schedule: + interval: weekly + cooldown: + default-days: 7 + open-pull-requests-limit: 5 + commit-message: + prefix: chore(deps) + include: scope + labels: + - dependencies + - ci + # Gitnexus npm deps — tree-sitter grammars checked daily so we catch # new releases that unblock the tree-sitter 0.25 upgrade ASAP. Grammars # are grouped so lockstep bumps produce a single PR. The tree-sitter @@ -25,6 +57,11 @@ updates: directory: /gitnexus schedule: interval: daily + cooldown: + default-days: 7 + semver-major-days: 30 + semver-minor-days: 7 + semver-patch-days: 3 open-pull-requests-limit: 10 commit-message: prefix: chore(deps) @@ -54,6 +91,11 @@ updates: directory: /gitnexus-web schedule: interval: weekly + cooldown: + default-days: 7 + semver-major-days: 30 + semver-minor-days: 7 + semver-patch-days: 3 open-pull-requests-limit: 5 commit-message: prefix: chore(deps) @@ -67,6 +109,11 @@ updates: directory: /gitnexus-shared schedule: interval: weekly + cooldown: + default-days: 7 + semver-major-days: 30 + semver-minor-days: 7 + semver-patch-days: 3 open-pull-requests-limit: 5 commit-message: prefix: chore(deps) diff --git a/.github/workflows/ci-e2e.yml b/.github/workflows/ci-e2e.yml index af0e2758d..96b0a4b26 100644 --- a/.github/workflows/ci-e2e.yml +++ b/.github/workflows/ci-e2e.yml @@ -3,6 +3,9 @@ name: E2E Tests on: workflow_call: +permissions: + contents: read + jobs: check-changes: name: Check web module changes diff --git a/.github/workflows/ci-quality.yml b/.github/workflows/ci-quality.yml index 36a936c82..a81876d9d 100644 --- a/.github/workflows/ci-quality.yml +++ b/.github/workflows/ci-quality.yml @@ -3,6 +3,9 @@ name: Quality Checks on: workflow_call: +permissions: + contents: read + jobs: format: runs-on: ubuntu-latest @@ -11,7 +14,7 @@ jobs: - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 with: - node-version: 20 + node-version: 22 cache: npm cache-dependency-path: package-lock.json - run: npm ci @@ -24,7 +27,7 @@ jobs: - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 with: - node-version: 20 + node-version: 22 cache: npm cache-dependency-path: package-lock.json - run: npm ci diff --git a/.github/workflows/ci-scope-parity.yml b/.github/workflows/ci-scope-parity.yml index cffdeb341..8e2926ba8 100644 --- a/.github/workflows/ci-scope-parity.yml +++ b/.github/workflows/ci-scope-parity.yml @@ -28,6 +28,9 @@ name: Scope Resolution Parity on: workflow_call: +permissions: + contents: read + jobs: discover: name: Discover migrated languages diff --git a/.github/workflows/ci-tests.yml b/.github/workflows/ci-tests.yml index 7010ee6f3..b044d9318 100644 --- a/.github/workflows/ci-tests.yml +++ b/.github/workflows/ci-tests.yml @@ -3,6 +3,9 @@ name: Tests on: workflow_call: +permissions: + contents: read + jobs: tests: name: ubuntu / coverage diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 3059a34dd..dd07337b7 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -6,6 +6,9 @@ on: paths-ignore: ['**.md', 'docs/**', 'LICENSE'] workflow_call: +permissions: + contents: read + # Concurrency convention: see CONTRIBUTING.md → "GitHub Actions — Concurrency Convention". # Hardcoded `CI-` prefix (not `${{ github.workflow }}`) because this workflow is # invoked as a reusable workflow from publish.yml and release-candidate.yml. In diff --git a/.github/workflows/claude.yml b/.github/workflows/claude.yml index cfba3ecbc..021a56930 100644 --- a/.github/workflows/claude.yml +++ b/.github/workflows/claude.yml @@ -19,6 +19,9 @@ on: pull_request_review: types: [submitted] +permissions: + contents: read + # Concurrency convention: see CONTRIBUTING.md → "GitHub Actions — Concurrency Convention". # Serialize per-PR/issue to avoid racing comments. concurrency: @@ -155,6 +158,8 @@ jobs: github_token: ${{ secrets.GITHUB_TOKEN }} allowed_non_write_users: '*' show_full_output: true + # Review posts use Bash (`gh`, etc.); default mode asks for approval — impossible in CI. + claude_args: '--dangerously-skip-permissions' plugin_marketplaces: 'https://github.com/anthropics/claude-code.git' plugins: 'code-review@claude-code-plugins' - prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ steps.pr.outputs.number }}' + prompt: '/code-review:code-review https://github.com/${{ github.repository }}/pull/${{ steps.pr.outputs.number }} --comment' diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml index d1dda8fb0..41f964cbe 100644 --- a/.github/workflows/codeql.yml +++ b/.github/workflows/codeql.yml @@ -17,6 +17,9 @@ on: # already-merged code without waiting for the next PR. - cron: '0 6 * * 1' +permissions: + contents: read + concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: ${{ github.event_name == 'pull_request' }} diff --git a/.github/workflows/dependency-review.yml b/.github/workflows/dependency-review.yml index ad06267c2..1e2ba1f19 100644 --- a/.github/workflows/dependency-review.yml +++ b/.github/workflows/dependency-review.yml @@ -10,6 +10,9 @@ on: pull_request: branches: [main] +permissions: + contents: read + concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml index 9e5750210..0cd526768 100644 --- a/.github/workflows/docker.yml +++ b/.github/workflows/docker.yml @@ -26,6 +26,9 @@ on: required: true type: string +permissions: + contents: read + # Concurrency convention: see CONTRIBUTING.md → "GitHub Actions — Concurrency Convention". # Tag refs are unique per release, so distinct tags run in parallel. # Re-pushes of the same tag serialize. cancel-in-progress: false — never cancel a publish mid-flight. @@ -132,7 +135,7 @@ jobs: uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v4.0.0 - name: Install Cosign - uses: sigstore/cosign-installer@cad07c2e89fa2edd6e2d7bab4c1aa38e53f76003 # v4.1.1 + uses: sigstore/cosign-installer@6f9f17788090df1f26f669e9d70d6ae9567deba6 # v4.1.2 - name: Log in to GitHub Container Registry if: ${{ github.event_name != 'pull_request' && !inputs.dry_run }} diff --git a/.github/workflows/gitleaks.yml b/.github/workflows/gitleaks.yml index cfe4d0856..7cfc3bc52 100644 --- a/.github/workflows/gitleaks.yml +++ b/.github/workflows/gitleaks.yml @@ -12,6 +12,9 @@ on: push: branches: [main] +permissions: + contents: read + concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: ${{ github.event_name == 'pull_request' }} diff --git a/.github/workflows/pr-autofix-apply.yml b/.github/workflows/pr-autofix-apply.yml new file mode 100644 index 000000000..73bf8ceb0 --- /dev/null +++ b/.github/workflows/pr-autofix-apply.yml @@ -0,0 +1,595 @@ +name: PR Autofix (apply) + +# CHATOPS HALF of the autofix pipeline. +# +# Triggered when a contributor comments `/autofix` on a PR. Validates +# permission, locates the most recent successful `pr-autofix.yml` +# artifact for the PR's current head SHA, applies the patch to the PR +# head, and pushes a commit back to the PR branch. +# +# This workflow runs from the default branch's copy of the file +# regardless of where the comment originates -- that's the trust +# anchor. Comment body and author login are untrusted; both flow +# through env vars and pattern-matched, never interpolated into shell. +# +# Fork PR support: `git push` with the GITHUB_TOKEN succeeds against +# fork branches only when the contributor enabled "Allow edits by +# maintainers" on the PR (the default). When they disabled it, we +# fail loud with a 👎 reaction and an explanation comment. + +on: + issue_comment: + types: [created] + +concurrency: + # Per-PR scope. issue_comment events expose `github.event.issue.number` + # for both PR and Issue comments; the `pull_request != null` guard on + # the job ensures we only run on PRs, so this number is the PR number. + # cancel-in-progress: false — a second `/autofix` should wait for the + # first to finish (idempotency check on the second invocation handles + # the no-op case). + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.event.issue.number }} + cancel-in-progress: false + +permissions: {} + +jobs: + apply: + name: apply-autofix + # Pre-filter at the workflow level so non-PR comments and unrelated + # comments don't even spawn a runner. The job-level body re-check + # below (Step 1) is the strict gate. + if: >- + github.event.issue.pull_request != null + && startsWith(github.event.comment.body, '/autofix') + runs-on: ubuntu-latest + timeout-minutes: 10 + permissions: + # React on the triggering comment + post reply comments. + pull-requests: write + # Push the apply commit to the PR head branch. + contents: write + # Required by actions/download-artifact to fetch artifacts produced + # by a different workflow run. + actions: read + steps: + - name: Validate comment body precisely + id: body + env: + BODY: ${{ github.event.comment.body }} + shell: bash + run: | + set -euo pipefail + # Whole-line, case-sensitive match: `^/autofix\s*$`. The + # workflow-level startsWith guard is coarse — `please don't + # /autofix this code` would pass that filter but fail this one. + # We exit silently (no reaction) on body mismatch so quoted + # text in unrelated discussions doesn't get a visible response. + if [[ ! "${BODY}" =~ ^/autofix[[:space:]]*$ ]]; then + echo "Body did not match strict /autofix regex — exiting silently." + echo "match=false" >> "$GITHUB_OUTPUT" + exit 0 + fi + echo "match=true" >> "$GITHUB_OUTPUT" + + - name: Validate commenter permission + id: perm + if: steps.body.outputs.match == 'true' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + COMMENTER: ${{ github.event.comment.user.login }} + PR_AUTHOR: ${{ github.event.issue.user.login }} + shell: bash + run: | + set -euo pipefail + + # Retry wrapper for transient 5xx / 429 / network blips. + # Mirrors the helper in pr-autofix-publish.yml. Used on + # idempotent GETs only; reactions/comment-POSTs are NOT + # wrapped (retrying a POST would dupe the resource). + gh_retry() { + local n=0 max=3 + while true; do + if gh "$@"; then return 0; fi + n=$((n+1)) + if [ "$n" -ge "$max" ]; then return 1; fi + sleep $((n * 2)) + done + } + + # Allowlist the commenter login before it flows into a URL. + # GitHub usernames: alphanumeric + dashes, max 39 chars. + if ! [[ "${COMMENTER}" =~ ^[A-Za-z0-9-]{1,39}$ ]]; then + echo "::error::Invalid commenter login format: $(printf '%q' "${COMMENTER}")" + echo "allowed=false" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Self-comparison: PR author can always /autofix their own PR. + if [ "${COMMENTER}" = "${PR_AUTHOR}" ]; then + echo "Commenter is PR author — granting access." + echo "allowed=true" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Repo permission lookup. admin/write/maintain are sufficient. + # Distinguish API failure (5xx, 429, network) from genuine + # permission denial (404 = not a collaborator). Conflating them + # would silently refuse a legitimate maintainer with a public + # 👎 every time GitHub blips. gh_retry handles transient blips; + # the stderr-grep distinguishes 404 from persistent failure. + perm_stderr=$(mktemp) + if permission=$(gh_retry api "repos/${GH_REPO}/collaborators/${COMMENTER}/permission" \ + --jq '.permission' 2>"$perm_stderr"); then + echo "Commenter permission: ${permission}" + case "${permission}" in + admin|write|maintain) + echo "allowed=true" >> "$GITHUB_OUTPUT" + ;; + *) + echo "allowed=false" >> "$GITHUB_OUTPUT" + ;; + esac + else + err=$(cat "$perm_stderr") + echo "Permission lookup stderr: ${err}" >&2 + # 404 (not a collaborator) is a genuine deny. + # Anything else is a transient API/network failure. + if grep -qE "HTTP 404|Not Found" "$perm_stderr"; then + echo "allowed=false" >> "$GITHUB_OUTPUT" + else + echo "::error::Permission lookup failed transiently — refusing to act." + echo "allowed=api-failed" >> "$GITHUB_OUTPUT" + fi + fi + + - name: React 😕 on transient permission-API failure + if: steps.body.outputs.match == 'true' && steps.perm.outputs.allowed == 'api-failed' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + COMMENT_ID: ${{ github.event.comment.id }} + PR: ${{ github.event.issue.number }} + RUN_ID: ${{ github.run_id }} + shell: bash + run: | + set -euo pipefail + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="confused" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⚠️ Couldn't verify your repo permission (transient GitHub API failure). Please comment \`/autofix\` again. ([apply run](https://github.com/${GH_REPO}/actions/runs/${RUN_ID}))" \ + >/dev/null + exit 1 + + - name: React 👎 on permission denial + if: steps.body.outputs.match == 'true' && steps.perm.outputs.allowed == 'false' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + COMMENT_ID: ${{ github.event.comment.id }} + PR: ${{ github.event.issue.number }} + shell: bash + run: | + set -euo pipefail + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="🚫 \`/autofix\` is restricted to users with write access or the PR author. Comment ignored." \ + >/dev/null + # Hard exit so the rest of the job is skipped. + exit 1 + + - name: React 👀 to acknowledge + if: steps.perm.outputs.allowed == 'true' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + COMMENT_ID: ${{ github.event.comment.id }} + shell: bash + run: | + set -euo pipefail + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="eyes" >/dev/null + + - name: Resolve PR head and locate autofix run + id: locate + if: steps.perm.outputs.allowed == 'true' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + PR: ${{ github.event.issue.number }} + shell: bash + run: | + set -euo pipefail + + # Same retry wrapper used in the permission step, repeated + # because each YAML `run:` block is a fresh bash session. + gh_retry() { + local n=0 max=3 + while true; do + if gh "$@"; then return 0; fi + n=$((n+1)) + if [ "$n" -ge "$max" ]; then return 1; fi + sleep $((n * 2)) + done + } + + # Fetch PR metadata. All fields here are server-controlled API + # output, but we still allowlist before exporting so anything + # weird short-circuits before $GITHUB_OUTPUT. Wrapped in + # gh_retry so transient blips don't surface as "no autofix run + # found" with a wrong remediation. + if ! pr_json=$(gh_retry api "repos/${GH_REPO}/pulls/${PR}"); then + echo "::error::PR metadata fetch failed after retries." + echo "found_status=api-failed" >> "$GITHUB_OUTPUT" + exit 0 + fi + head_sha=$(jq -r '.head.sha' <<< "${pr_json}") + head_ref=$(jq -r '.head.ref' <<< "${pr_json}") + head_repo=$(jq -r '.head.repo.full_name' <<< "${pr_json}") + + [[ "${head_sha}" =~ ^[0-9a-f]{40}$ ]] || { echo "::error::Bad head_sha"; exit 1; } + [[ "${head_ref}" =~ ^[A-Za-z0-9._/-]+$ ]] || { echo "::error::Bad head_ref"; exit 1; } + [[ "${head_repo}" =~ ^[A-Za-z0-9._-]+/[A-Za-z0-9._-]+$ ]] || { echo "::error::Bad head_repo"; exit 1; } + + # Find the latest successful pr-autofix.yml run for this head SHA. + if ! runs_json=$(gh_retry api "repos/${GH_REPO}/actions/workflows/pr-autofix.yml/runs?head_sha=${head_sha}&per_page=10"); then + echo "::error::Workflow run lookup failed after retries." + echo "found_status=api-failed" >> "$GITHUB_OUTPUT" + exit 0 + fi + + run_id=$(jq -r '[.workflow_runs[] | select(.conclusion == "success")] | .[0].id // empty' <<< "${runs_json}") + + if [ -n "${run_id}" ] && [[ "${run_id}" =~ ^[0-9]+$ ]]; then + echo "found_status=success" >> "$GITHUB_OUTPUT" + { + echo "found=true" + echo "head_sha=${head_sha}" + echo "head_ref=${head_ref}" + echo "head_repo=${head_repo}" + echo "run_id=${run_id}" + } >> "$GITHUB_OUTPUT" + exit 0 + fi + + # No successful run. Distinguish "still running" (producer in + # flight after a recent push) from "never ran / all failed". + # in_progress / queued / pending / waiting cover the GitHub + # workflow-run lifecycle states that precede success/failure. + in_progress=$(jq -r '[.workflow_runs[] | select(.status == "in_progress" or .status == "queued" or .status == "pending" or .status == "waiting")] | length' <<< "${runs_json}") + if [ "${in_progress:-0}" -gt 0 ]; then + echo "::warning::pr-autofix run is still in progress for head ${head_sha}." + echo "found_status=in-progress" >> "$GITHUB_OUTPUT" + else + echo "::warning::No successful pr-autofix run found for head ${head_sha}." + echo "found_status=not-found" >> "$GITHUB_OUTPUT" + fi + # Existing `found` boolean is preserved so downstream gates + # (`steps.locate.outputs.found == 'true'`) still work. + echo "found=false" >> "$GITHUB_OUTPUT" + + - name: Reply when locate did not yield a usable run + if: steps.perm.outputs.allowed == 'true' && steps.locate.outputs.found != 'true' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + COMMENT_ID: ${{ github.event.comment.id }} + PR: ${{ github.event.issue.number }} + FOUND_STATUS: ${{ steps.locate.outputs.found_status }} + RUN_ID: ${{ github.run_id }} + shell: bash + run: | + set -euo pipefail + run_url="https://github.com/${GH_REPO}/actions/runs/${RUN_ID}" + case "${FOUND_STATUS}" in + in-progress) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="confused" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⏳ A pr-autofix run is still in progress for this PR's current head SHA. Wait for it to finish, then comment \`/autofix\` again. ([apply run](${run_url}))" \ + >/dev/null + ;; + api-failed) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="confused" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⚠️ Couldn't reach the GitHub API to look up the autofix run (transient failure after retries). Please comment \`/autofix\` again. ([apply run](${run_url}))" \ + >/dev/null + ;; + *) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="🤔 No successful autofix run found for this PR's current head SHA. Push a new commit to trigger one, then comment \`/autofix\` again." \ + >/dev/null + ;; + esac + exit 1 + + # Pinned to v8.0.1. Same SHA as pr-autofix-publish.yml. + # `continue-on-error: true` lets the workflow proceed when the + # artifact is expired or pruned (1-day retention). The apply + # step distinguishes "patch file missing entirely" (artifact- + # expired) from "patch file zero bytes" (genuinely empty patch). + - name: Download autofix artifact + if: steps.locate.outputs.found == 'true' + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + continue-on-error: true + with: + name: autofix + run-id: ${{ steps.locate.outputs.run_id }} + github-token: ${{ secrets.GITHUB_TOKEN }} + path: autofix-in + + # Pinned to v5.0.4. Verify SHA via: + # gh api repos/actions/checkout/git/refs/tags/v5.0.4 + # + # `persist-credentials: false` disables the default behavior where + # actions/checkout writes the GITHUB_TOKEN into `.git/config` as an + # extraheader. That default is convenient (subsequent git commands + # auth automatically) but it means the token is sitting on disk in + # the checkout directory — an `actions/upload-artifact` step on + # this directory would leak the token. We don't upload, but + # zizmor's `credential-persistence` lint flags it defensively. + # Push auth is provided inline at push time via the URL. + - name: Checkout PR head + if: steps.locate.outputs.found == 'true' + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v5.0.4 + with: + repository: ${{ steps.locate.outputs.head_repo }} + ref: ${{ steps.locate.outputs.head_sha }} + token: ${{ secrets.GITHUB_TOKEN }} + persist-credentials: false + # Fetch full history so the push doesn't hit shallow-clone errors. + fetch-depth: 0 + path: pr-checkout + + - name: Apply patch and push + id: apply + if: steps.locate.outputs.found == 'true' + env: + HEAD_REF: ${{ steps.locate.outputs.head_ref }} + HEAD_REPO: ${{ steps.locate.outputs.head_repo }} + # The SHA we resolved earlier in `locate` — this is what the + # remote ref MUST still equal at push time. If the contributor + # force-pushed between resolve and now, the lease fails and + # we surface that distinctly from a fork-without-maintainer + # -edit push failure. + HEAD_SHA: ${{ steps.locate.outputs.head_sha }} + # Auth for the push only — never persisted to disk. Provided + # via env to avoid interpolating into the shell command line. + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + shell: bash + working-directory: pr-checkout + run: | + set -euo pipefail + patch="../autofix-in/autofix.patch" + + # Distinguish artifact-expired (file missing entirely, because + # actions/download-artifact ran with continue-on-error and the + # 1-day retention had elapsed) from genuinely empty patch + # (file present, zero bytes, formatter found nothing). + if [ ! -e "$patch" ]; then + echo "::warning::Patch file does not exist — autofix artifact likely expired." + echo "result=artifact-expired" >> "$GITHUB_OUTPUT" + exit 0 + fi + + if [ ! -s "$patch" ]; then + echo "::warning::Empty patch — nothing to apply." + echo "result=empty-patch" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Sensitive-paths guard: refuse to apply patches that touch + # `.github/` — workflow files, action definitions, CODEOWNERS, + # dependabot config, etc. A malicious PR could ship a custom + # prettier/ESLint config that reformats workflow YAML; the + # producer would then capture those edits in autofix.patch, + # and a maintainer running `/autofix` would push them under + # `contents: write`. The default GITHUB_TOKEN lacks `workflows` + # scope so the platform would reject workflow-file pushes + # anyway, but that surfaces as a generic `push-failed` and + # misleads users into enabling maintainer-edit. Reject early + # with a specific reason. CODEOWNERS and dependabot.yml live + # under .github/ but outside .github/workflows/ — the broader + # match is intentional (they all govern trust boundaries). + if grep -qE '^(diff --git|---|\+\+\+) [ab]?/?\.github/' "$patch"; then + echo "::warning::Patch touches .github/ — refusing to apply (sensitive paths)." + echo "result=sensitive-paths" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Re-entrancy guard: if HEAD itself is an autofix bot commit, + # refuse to apply again. Without this, lint/formatter config + # drift between runs could pump arbitrary apply commits into + # the same PR if an automated agent watches the sticky and + # re-fires `/autofix` on each new "fixes-available" surface. + # The contributor can still get out by force-pushing a + # human-authored commit to revert the autofix and re-trigger. + head_author=$(git log -1 --format='%ae' HEAD) + head_subject=$(git log -1 --format='%s' HEAD) + if [ "${head_author}" = "41898282+github-actions[bot]@users.noreply.github.com" ] \ + && [[ "${head_subject}" =~ ^chore\(autofix\) ]]; then + echo "::warning::HEAD is an autofix bot commit — refusing to re-apply (loop guard)." + echo "result=loop-prevented" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Idempotency probe: does the forward apply work? + if git apply --check "$patch" 2>/dev/null; then + echo "Patch applies cleanly — proceeding." + elif git apply --check --reverse "$patch" 2>/dev/null; then + # Reverse-check passes => the patch is already applied to + # the current tree. Treat as success no-op. + echo "Patch is already applied (reverse-check passed) — no-op." + echo "result=already-applied" >> "$GITHUB_OUTPUT" + exit 0 + else + echo "::error::Patch does not apply (stale or conflicting)." + echo "result=stale" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Wrap the apply/commit phase so any non-zero exit sets a + # meaningful `result=` instead of leaving it unset (which would + # send the user to the `*` "unexpected state" arm with a + # non-actionable confused-emoji reply). + if ! { + git config user.email "41898282+github-actions[bot]@users.noreply.github.com" && + git config user.name "github-actions[bot]" && + git apply "$patch" && + git add -A && + git commit -m "chore(autofix): apply prettier + eslint fixes via /autofix command" + }; then + echo "::error::git apply / config / commit failed after idempotency probe passed." + echo "result=apply-failed" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Push to the PR head branch with a lease against the resolved + # SHA. The lease ensures the remote ref still points at HEAD_SHA + # when the push lands — if the contributor force-pushed in the + # window between resolve and now, the lease fails and we return + # `lease-failed` (NOT `push-failed`, which would mislead users + # into enabling maintainer-edit). For fork PRs, the push still + # requires "Allow edits by maintainers" to be enabled. + # + # Auth is supplied inline via `-c http..extraheader` (NOT + # via a `https://x-access-token:TOKEN@…` URL — those leak into + # process listings and `git remote -v` output). The header is + # set per-invocation; it never lands in `.git/config` on disk. + # The token is base64-encoded for the Basic auth header per + # GitHub's documented pattern for this scope. + push_url="https://github.com/${HEAD_REPO}.git" + auth_header="Authorization: Basic $(printf 'x-access-token:%s' "${GITHUB_TOKEN}" | base64 -w0)" + # GitHub's secret-masker only masks the raw token, not its + # base64-encoded form. Mask the encoded value so any subsequent + # log line (set -x, GIT_TRACE, error spew) gets ***-redacted. + echo "::add-mask::${auth_header}" + push_stderr=$(mktemp) + if git -c http.extraheader="${auth_header}" \ + push --force-with-lease="refs/heads/${HEAD_REF}:${HEAD_SHA}" \ + "${push_url}" "HEAD:${HEAD_REF}" 2>"$push_stderr"; then + echo "result=applied" >> "$GITHUB_OUTPUT" + else + cat "$push_stderr" >&2 + # `--force-with-lease` reports "stale info" when the remote + # ref has moved past the expected SHA. Other lease-failure + # phrases git emits include "remote rejected" (server-side + # reject), "non-fast-forward", and the literal flag name. Match + # any of those to distinguish from auth/network/maintainer- + # edit failures. + if grep -qE "stale info|force-with-lease|rejected.*non-fast-forward|remote rejected|! \[rejected\]" "$push_stderr"; then + echo "::error::git push lease failed — branch moved during apply." + echo "result=lease-failed" >> "$GITHUB_OUTPUT" + else + echo "::error::git push failed — likely fork without maintainer-edit enabled." + echo "result=push-failed" >> "$GITHUB_OUTPUT" + fi + exit 0 + fi + + - name: React and reply on outcome + if: always() && steps.locate.outputs.found == 'true' && steps.apply.outcome != 'skipped' + env: + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + COMMENT_ID: ${{ github.event.comment.id }} + PR: ${{ github.event.issue.number }} + RESULT: ${{ steps.apply.outputs.result }} + RUN_ID: ${{ github.run_id }} + shell: bash + run: | + set -euo pipefail + run_url="https://github.com/${GH_REPO}/actions/runs/${RUN_ID}" + + case "${RESULT}" in + applied) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="+1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="✅ Applied autofix and pushed a commit. ([apply run](${run_url}))" \ + >/dev/null + ;; + already-applied) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="+1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="✅ Autofix is already applied — no changes needed." \ + >/dev/null + ;; + empty-patch) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="+1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="✅ No autofix to apply — formatter found nothing." \ + >/dev/null + ;; + artifact-expired) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="confused" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⏳ The autofix artifact for this PR's head SHA has expired (1-day retention). Push a new commit to regenerate it, then comment \`/autofix\` again. ([apply run](${run_url}))" \ + >/dev/null + exit 1 + ;; + loop-prevented) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="confused" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="🔁 Refusing to re-apply autofix on top of an existing autofix commit. If formatter rules drifted and you genuinely need another pass, push a human-authored commit (or revert the existing autofix commit) before commenting \`/autofix\` again. ([apply run](${run_url}))" \ + >/dev/null + exit 1 + ;; + sensitive-paths) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="🛑 Refusing to apply: the autofix patch touches files under \`.github/\` (workflow / CODEOWNERS / dependabot config). Apply formatter changes to those files manually in a regular commit so they get human review. ([apply run](${run_url}))" \ + >/dev/null + exit 1 + ;; + stale) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⚠️ The autofix patch is stale or conflicts with the current head — push a new commit to regenerate, then comment \`/autofix\` again. ([apply run](${run_url}))" \ + >/dev/null + exit 1 + ;; + apply-failed) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⚠️ Autofix applied cleanly in the dry run, but \`git apply\` / \`git commit\` failed when actually landing the patch. This usually means a race with concurrent edits or a corrupt patch. See logs: ${run_url}" \ + >/dev/null + exit 1 + ;; + push-failed) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⚠️ Couldn't push the autofix commit. If this is a fork PR, please tick **Allow edits by maintainers** in the PR sidebar, then comment \`/autofix\` again. ([apply run](${run_url}))" \ + >/dev/null + exit 1 + ;; + lease-failed) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="-1" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="⚠️ The PR head moved while autofix was applying — a new commit landed in the window between resolve and push. Comment \`/autofix\` again to retry against the latest head. ([apply run](${run_url}))" \ + >/dev/null + exit 1 + ;; + *) + gh api -X POST "repos/${GH_REPO}/issues/comments/${COMMENT_ID}/reactions" \ + -f content="confused" >/dev/null + gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" \ + -f body="❓ Autofix run finished in an unexpected state (\`${RESULT:-unknown}\`). See logs: ${run_url}" \ + >/dev/null + exit 1 + ;; + esac diff --git a/.github/workflows/pr-autofix-publish.yml b/.github/workflows/pr-autofix-publish.yml index a22f2cc7a..08ad1d60f 100644 --- a/.github/workflows/pr-autofix-publish.yml +++ b/.github/workflows/pr-autofix-publish.yml @@ -3,20 +3,19 @@ name: PR Autofix (publish) # TRUSTED HALF of the autofix pipeline. # # Triggered by `pr-autofix.yml` completing on a PR (including fork PRs). -# Downloads the diff artifact produced by the untrusted job and posts -# inline review-comment suggestions to the PR using `reviewdog`. This -# job NEVER checks out fork code — it only consumes the diff (data) and -# calls the GitHub API. That isolation is what makes it safe to run -# under `pull-requests: write` on fork-triggered events. +# Downloads the diff artifact produced by the untrusted job, verifies +# its claimed PR identity against the workflow_run authority, then +# posts (or edits) a single sticky summary comment plus a +# `gitnexus/autofix` Check Run. This job NEVER checks out fork code — +# it only consumes the diff (data) and calls the GitHub API. That +# isolation is what makes it safe to run under `pull-requests: write` +# on fork-triggered events. # -# Also posts (or edits) a single sticky summary comment so contributors -# and AI agents have one stable, machine-readable signal that says -# whether autofix had anything to suggest. Look for the heading -# "## :sparkles: PR Autofix" in the PR's top-level comments. -# -# Reviewdog reporter: `github-pr-review` reads $REVIEWDOG_GITHUB_API_TOKEN -# and posts via the GraphQL/REST PR-review API. It does not need a -# checkout because the diff itself encodes file paths + line numbers. +# The sticky comment is the contributor signal: heading +# "## :sparkles: PR Autofix" in the PR's top-level comments, with a +# fenced `gitnexus-autofix` JSON block carrying machine-readable state +# for AI agents. Contributors apply the patch by commenting `/autofix` +# on the PR — handled by the separate `pr-autofix-apply.yml` workflow. on: workflow_run: @@ -49,9 +48,9 @@ jobs: # by a different workflow run. actions: read # Required to create the `gitnexus/autofix` Check Run that reports - # the outcome (clean / suggestions-posted / skipped-too-large) to - # the PR's Checks tab. Branch protection or agents can grep the - # conclusion + output title without parsing the sticky comment. + # the outcome (clean / fixes-available) to the PR's Checks tab. + # Branch protection or agents can grep the conclusion + output + # title without parsing the sticky comment. checks: write steps: # Pinned to v8.0.1. Verify SHA via: @@ -114,71 +113,78 @@ jobs: echo "changed_lines=${CHANGED}" } >> "$GITHUB_OUTPUT" - # Pinned to v1.5.0. Verify SHA via: - # gh api repos/reviewdog/action-setup/git/refs/tags/v1.5.0 - # (annotated tag — resolve via .../git/tags/ --jq .object) - - name: Install reviewdog - if: steps.meta.outputs.changed_lines != '0' - uses: reviewdog/action-setup@d8a7baabd7f3e8544ee4dbde3ee41d0011c3a93f # v1.5.0 - with: - # Pin the binary, not just the action SHA — a bad reviewdog - # release otherwise breaks every PR with no rollback. Bump - # this knob deliberately when validating a new release. - reviewdog_version: v0.21.0 - - - name: Post inline suggestions - id: suggest + # Cross-verify the artifact's claimed identity against the + # GitHub-controlled workflow_run event. The previous step's + # allowlist only proves the fields are well-formed — not that + # they refer to the PR/SHA that actually triggered this run. + # A fork-controlled `npm run lint:fix` could plausibly mutate + # metadata.json to reference another PR or SHA, redirecting our + # write-scoped sticky/check-run onto an attacker-chosen target. + # + # Authority sources are all server-controlled GitHub event fields: + # - workflow_run.head_sha + # - workflow_run.head_repository.full_name + # - workflow_run.pull_requests[].number (within-repo PRs only; + # empty array on fork PRs — fall back to commits/{sha}/pulls) + # + # Mismatch => fail loud BEFORE any sticky/check-run side effect. + - name: Verify metadata against workflow_run authority + id: verify if: steps.meta.outputs.changed_lines != '0' env: - REVIEWDOG_GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }} - CI_REPO_OWNER: ${{ github.repository_owner }} - CI_REPO_NAME: ${{ github.event.repository.name }} - CI_PULL_REQUEST: ${{ steps.meta.outputs.pr_number }} - CI_COMMIT: ${{ steps.meta.outputs.head_sha }} - # Pull `changed_lines` through env so bash gets a real - # variable (and shellcheck SC2170 doesn't fire on `-gt` against - # a `${{ }}`-interpolated literal). - CHANGED_LINES: ${{ steps.meta.outputs.changed_lines }} + GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} + GH_REPO: ${{ github.repository }} + META_PR_NUMBER: ${{ steps.meta.outputs.pr_number }} + META_HEAD_SHA: ${{ steps.meta.outputs.head_sha }} + META_HEAD_REPO: ${{ steps.meta.outputs.head_repo }} + WF_HEAD_SHA: ${{ github.event.workflow_run.head_sha }} + WF_HEAD_REPO: ${{ github.event.workflow_run.head_repository.full_name }} + WF_PR_NUMBERS: ${{ toJSON(github.event.workflow_run.pull_requests.*.number) }} shell: bash run: | set -euo pipefail - patch=autofix-in/autofix.patch - if [ ! -s "$patch" ]; then - echo "Empty patch — nothing to suggest." - echo "posted=false" >> "$GITHUB_OUTPUT" - exit 0 + + # 1) head_sha must match exactly. workflow_run.head_sha is the + # commit GitHub actually ran the producer against — definitive. + if [ "${META_HEAD_SHA}" != "${WF_HEAD_SHA}" ]; then + echo "::error::Artifact head_sha (${META_HEAD_SHA}) does not match workflow_run.head_sha (${WF_HEAD_SHA}) — refusing to publish." + exit 1 fi - # GitHub's review-comment API returns 406 on diffs above ~3k - # changed lines. Bail out gracefully and let the summary - # comment carry the signal instead. - if [ "$CHANGED_LINES" -gt 3000 ]; then - echo "Diff too large ($CHANGED_LINES lines) — skipping inline suggestions." - echo "posted=skipped-too-large" >> "$GITHUB_OUTPUT" - exit 0 + # 2) head_repo must match exactly. Same authority anchor. + if [ "${META_HEAD_REPO}" != "${WF_HEAD_REPO}" ]; then + echo "::error::Artifact head_repo (${META_HEAD_REPO}) does not match workflow_run.head_repository (${WF_HEAD_REPO}) — refusing to publish." + exit 1 fi - # `-f.diff.strip=1` matches `git diff` output (a/foo b/foo). - # `-filter-mode=added` only suggests on lines the PR added, - # which avoids re-suggesting on already-resolved threads when - # the contributor re-adds the autoformat label. - reviewdog \ - -f=diff -f.diff.strip=1 \ - -name="prettier+eslint" \ - -reporter=github-pr-review \ - -filter-mode=added \ - -level=warning \ - -fail-on-error=false < "$patch" + # 3) pr_number must reference an open PR with this head SHA. + # Within-repo PRs: workflow_run.pull_requests[] is populated. + # Fork PRs: that array is empty by GitHub design — fall back + # to the REST commit-to-PRs lookup. Fail closed if the lookup + # finds no matching open PR (avoids attacker-forged PR ids). + allowed_numbers=$(jq -c '.' <<< "${WF_PR_NUMBERS}") + if [ "${allowed_numbers}" = "[]" ]; then + echo "workflow_run.pull_requests is empty (fork PR) — falling back to commits/{sha}/pulls." + allowed_numbers=$(gh api "repos/${GH_REPO}/commits/${WF_HEAD_SHA}/pulls" \ + --jq '[.[] | select(.state == "open") | .number]' 2>/dev/null || echo "[]") + if [ "${allowed_numbers}" = "[]" ]; then + echo "::error::No open PR found for head ${WF_HEAD_SHA} via commits/{sha}/pulls — refusing to publish." + exit 1 + fi + fi - echo "posted=true" >> "$GITHUB_OUTPUT" + if ! jq -e --argjson n "${META_PR_NUMBER}" 'index($n) != null' <<< "${allowed_numbers}" >/dev/null; then + echo "::error::Artifact pr_number (${META_PR_NUMBER}) is not in the authoritative PR list (${allowed_numbers}) — refusing to publish." + exit 1 + fi + + echo "Verified: metadata identity matches workflow_run authority (PR=${META_PR_NUMBER}, head_sha=${META_HEAD_SHA}, head_repo=${META_HEAD_REPO})." - name: Upsert sticky summary comment # Only post when ci-quality found something fixable (= the # autofix patch is non-empty). When prettier/eslint are clean # the patch is zero bytes and the sticky comment is pure noise, - # so we skip it. When the diff was too large for inline - # suggestions, the sticky is the only signal the contributor - # gets, so we still post in that case. + # so we skip it. if: >- always() && steps.meta.outputs.pr_number != '' @@ -189,8 +195,6 @@ jobs: PR: ${{ steps.meta.outputs.pr_number }} CHANGED: ${{ steps.meta.outputs.changed_lines }} HEAD_SHA: ${{ steps.meta.outputs.head_sha }} - SCHEMA: ${{ steps.meta.outputs.schema }} - POSTED: ${{ steps.suggest.outputs.posted }} RUN_ID: ${{ github.run_id }} shell: bash run: | @@ -200,25 +204,29 @@ jobs: marker="" heading="## :sparkles: PR Autofix" - if [ "${POSTED}" = "skipped-too-large" ]; then - ui_state="skipped-too-large" - prose="Diff is **${CHANGED}** lines — too large for inline suggestions (GitHub caps the review-comment API at ~3000). Run locally: \`npm run lint:fix && npm run format\`." - else - ui_state="suggestions-posted" - prose="Posted formatting / unused-import suggestions inline. Click **Apply suggestion** on each, or run locally: \`npm run lint:fix && npm run format\`." - fi + # Single state. The /autofix slash command works for any diff + # size — there's no 3K cap and no no-overlap dead-end because + # the apply workflow uses `git apply` + push, not the GitHub + # review-comment API. + ui_state="fixes-available" + prose="Found fixable formatting / unused-import issues across **${CHANGED}** changed lines. **Comment \`/autofix\` on this PR to apply them**, or run \`npm run lint:fix && npm run format\` locally." # Machine-readable JSON block — agents parse this instead of # regexing English. Fenced code-block info string is # `gitnexus-autofix` so agents can locate it without ambiguity. + # Schema bumped from v1 -> v2: adds `apply_command`. The v1 + # field set is preserved as a superset, but the `state` enum + # is redefined (v1: suggestions-posted | skipped-too-large | + # diff-no-overlap; v2: fixes-available). v1 readers checking + # `schema == 'gitnexus.pr-autofix/v1'` see an unfamiliar version + # and fall back to prose, which is the intended migration path. json=$(jq -n -c \ - --arg schema "${SCHEMA}" \ --arg state "${ui_state}" \ --argjson pr_number "${PR}" \ --argjson changed_lines "${CHANGED}" \ --arg head_sha "${HEAD_SHA}" \ --arg run_id "${RUN_ID}" \ - '{schema:$schema, state:$state, pr_number:$pr_number, changed_lines:$changed_lines, head_sha:$head_sha, run_id:$run_id}') + '{schema:"gitnexus.pr-autofix/v2", state:$state, pr_number:$pr_number, changed_lines:$changed_lines, head_sha:$head_sha, run_id:$run_id, apply_command:"/autofix"}') # Multi-line quoted string instead of a column-0 heredoc — YAML's # `run: |` block ends as soon as a content line dedents below the @@ -272,10 +280,9 @@ jobs: - name: Emit gitnexus/autofix Check Run # Stable check name `gitnexus/autofix` so PR-watching agents can # `gh pr checks ` and read the conclusion + title without - # parsing the sticky comment. Three outcomes: - # clean → conclusion: success - # suggestions-posted → conclusion: neutral (review suggestions) - # skipped-too-large → conclusion: neutral (diff > 3000 lines) + # parsing the sticky comment. Two outcomes: + # clean → conclusion: success + # fixes-available → conclusion: neutral # `neutral` does not block branch-protection required-checks but # is visually distinct from a green pass. if: always() && steps.meta.outputs.head_sha != '' @@ -284,7 +291,6 @@ jobs: GH_REPO: ${{ github.repository }} HEAD_SHA: ${{ steps.meta.outputs.head_sha }} CHANGED: ${{ steps.meta.outputs.changed_lines }} - POSTED: ${{ steps.suggest.outputs.posted }} shell: bash run: | set -euo pipefail @@ -293,14 +299,10 @@ jobs: conclusion="success" title="Formatting clean" summary="Prettier and ESLint --fix produced no changes." - elif [ "${POSTED}" = "skipped-too-large" ]; then - conclusion="neutral" - title="Diff too large for inline suggestions (${CHANGED} lines)" - summary="GitHub caps the review-comment API at ~3000 lines. Run \`npm run lint:fix && npm run format\` locally." else conclusion="neutral" - title="Suggestions posted" - summary="Inline review-comment suggestions posted. Click **Apply suggestion** on each, or run \`npm run lint:fix && npm run format\` locally." + title="Autofix available — comment /autofix to apply" + summary="Comment \`/autofix\` on this PR to apply formatter + unused-import fixes (works at any diff size). Or run \`npm run lint:fix && npm run format\` locally." fi gh api -X POST "repos/${GH_REPO}/check-runs" \ diff --git a/.github/workflows/pr-autofix.yml b/.github/workflows/pr-autofix.yml index f15e8c0e6..04eb2468d 100644 --- a/.github/workflows/pr-autofix.yml +++ b/.github/workflows/pr-autofix.yml @@ -6,7 +6,9 @@ name: PR Autofix # (including fork heads) and uploads the resulting diff as an artifact. # This job has NO privileged token and CANNOT post to the PR. The trusted # `pr-autofix-publish.yml` workflow downloads the artifact via -# `workflow_run` and posts the inline review-comment suggestions. +# `workflow_run` and posts a sticky summary comment + Check Run. +# Contributors apply the patch by commenting `/autofix` on the PR — +# handled by the separate `pr-autofix-apply.yml` ChatOps workflow. # # Why the split: # ESLint loads plugins from fork-controlled `node_modules`, so running @@ -14,8 +16,8 @@ name: PR Autofix # ship a poisoned eslint plugin and execute arbitrary code under that # token. By keeping fork code execution in this job (token: read-only) # and posting from a separate trusted job that never touches fork -# code, we get the inline-suggestion UX for fork PRs without the -# supply-chain hole. (See autofix.ci for the same pattern.) +# code, we get the autofix UX for fork PRs without the supply-chain +# hole. (See autofix.ci for the same pattern.) # # Removes unused imports via `eslint-plugin-unused-imports`, already in # devDependencies and wired into the `lint` config. @@ -59,7 +61,7 @@ jobs: - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 with: - node-version: 20 + node-version: 22 cache: npm cache-dependency-path: package-lock.json @@ -105,11 +107,9 @@ jobs: git diff --no-color > autofix-out/autofix.patch # NOTE: `changed_lines` is the line-count of the patch file, - # which includes hunk headers and context lines — NOT the - # added/removed source-line count. The 3000-line cap in - # pr-autofix-publish.yml is therefore conservative (fires - # before reviewdog hits GitHub's ~3k review-comment API - # ceiling). That bias is intentional. + # (hunk headers + context lines + added/removed). Surfaced in + # the sticky comment so contributors and AI agents have a + # quick size hint before invoking `/autofix`. changed_lines=$(wc -l < autofix-out/autofix.patch | tr -d ' ') echo "changed_lines=${changed_lines}" >> "$GITHUB_OUTPUT" diff --git a/.github/workflows/pr-labeler.yml b/.github/workflows/pr-labeler.yml index 51664bba8..4a219bfab 100644 --- a/.github/workflows/pr-labeler.yml +++ b/.github/workflows/pr-labeler.yml @@ -35,6 +35,9 @@ on: pull_request_target: types: [opened, edited, reopened] +permissions: + contents: read + # Concurrency convention: see CONTRIBUTING.md → "GitHub Actions — Concurrency Convention". # Include `github.event_name` so `pull_request` (validate-title) and # `pull_request_target` (autolabel) runs for the same PR do NOT share a slot diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml index d372c163a..0694b5e4c 100644 --- a/.github/workflows/publish.yml +++ b/.github/workflows/publish.yml @@ -6,6 +6,7 @@ on: - 'v*' # No workflow-level permissions — scoped per job below. +permissions: {} # Concurrency convention: see CONTRIBUTING.md → "GitHub Actions — Concurrency Convention". # Tag refs are unique per release, so distinct tags run in parallel. Re-pushes of the @@ -35,7 +36,7 @@ jobs: - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 with: - node-version: 20 + node-version: 22 registry-url: https://registry.npmjs.org # Hermetic install for the published artifact — no cache carry-over # from non-tag contexts. setup-node v5+ caches by default when a diff --git a/.github/workflows/release-candidate.yml b/.github/workflows/release-candidate.yml index 36f37b5c6..2129e765a 100644 --- a/.github/workflows/release-candidate.yml +++ b/.github/workflows/release-candidate.yml @@ -58,6 +58,7 @@ jobs: timeout-minutes: 5 permissions: contents: read + pull-requests: read # read PR labels on the merge commit outputs: should_run: ${{ steps.decide.outputs.should_run }} head_sha: ${{ steps.decide.outputs.head_sha }} @@ -74,6 +75,8 @@ jobs: FORCE: ${{ inputs.force }} BUMP_INPUT: ${{ inputs.bump }} EVENT_NAME: ${{ github.event_name }} + GH_TOKEN: ${{ github.token }} + REPO: ${{ github.repository }} run: | set -euo pipefail HEAD_SHA=$(git rev-parse HEAD) @@ -96,6 +99,49 @@ jobs: exit 0 fi + # ── Skip when the merge commit corresponds to a release ───────── + # Two complementary checks (belt-and-suspenders): + # 1. The HEAD commit subject matches `chore: release vX.Y.Z` + # (the canonical release-PR title in this repo). Anchored + # at both ends to require the bare title or the squash-merge + # `(#NNNN)` suffix exactly — rejects noisy variants like + # `chore: release v1.0.0 (something unrelated)`. + # 2. The squash-merged PR carries the `release` label. + # Either match suppresses the rc build — stable releases publish + # via publish.yml on the v-tag, so the rc cycle should pause for + # them rather than racing the npm publish. + HEAD_SUBJECT="$(git log -1 --pretty=%s HEAD)" + # Sanitise GitHub-Actions annotation prefixes before logging the + # raw subject — defence-in-depth so a hypothetical commit subject + # containing `::error::` or `::set-output::` cannot forge log + # annotations even though %s strips newlines. + HEAD_SUBJECT_SAFE="${HEAD_SUBJECT//::/__}" + RELEASE_SUBJECT_RE='^chore:[[:space:]]*release[[:space:]]+v[0-9]+\.[0-9]+\.[0-9]+([[:space:]]+\(#[0-9]+\))?$' + if [[ "$HEAD_SUBJECT" =~ $RELEASE_SUBJECT_RE ]]; then + echo "HEAD commit subject matches a release commit — skipping rc." + echo " subject (sanitised): $HEAD_SUBJECT_SAFE" + echo "should_run=false" >> "$GITHUB_OUTPUT" + exit 0 + fi + + # Squash-merge commits include `(#NNNN)` at the end of the subject. + if [[ "$HEAD_SUBJECT" =~ \(#([0-9]+)\)[[:space:]]*$ ]]; then + PR_NUM="${BASH_REMATCH[1]}" + echo "Detected squash-merge of PR #$PR_NUM — checking labels." + if LABELS_JSON="$(gh pr view "$PR_NUM" --repo "$REPO" --json labels 2>/dev/null)"; then + if printf '%s' "$LABELS_JSON" | jq -e '.labels[] | select(.name == "release")' >/dev/null; then + echo "PR #$PR_NUM has the 'release' label — skipping rc." + echo "should_run=false" >> "$GITHUB_OUTPUT" + exit 0 + fi + echo "PR #$PR_NUM has no 'release' label — proceeding." + else + # Lookup failure is not fatal — fall through to the dedup check + # so a transient GH API hiccup doesn't silently suppress rc builds. + echo "::warning::Could not read labels for PR #${PR_NUM} — falling through." + fi + fi + # Dedup: is there already an rc/ marker pointing at HEAD? MARKER="rc/${HEAD_SHA}" if git rev-parse "refs/tags/$MARKER" >/dev/null 2>&1; then @@ -149,7 +195,7 @@ jobs: - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 with: - node-version: 20 + node-version: 22 registry-url: https://registry.npmjs.org # Hermetic install — release-candidate produces shipped artifacts. # setup-node v5+ caches by default when a packageManager field is diff --git a/.github/workflows/trivy.yml b/.github/workflows/trivy.yml index f476ee7bc..1251fa4dd 100644 --- a/.github/workflows/trivy.yml +++ b/.github/workflows/trivy.yml @@ -1,19 +1,28 @@ name: Trivy Image Scan # Builds Dockerfile.cli and Dockerfile.web, then scans the resulting images -# for OS-package and language-package CVEs at HIGH/CRITICAL severity. +# for OS-package and language-package CVEs at MEDIUM+ severity. # Findings upload to the Security tab; record-only (does not block merges). # -# NOT triggered on PRs — image builds are slow and base-image CVE churn -# shouldn't gate feature delivery. +# Trigger on Dockerfile changes in PRs so base-image/npm-layer remediation can +# be verified before merge without running image scans on every PR. on: + pull_request: + paths: + - 'Dockerfile.cli' + - 'Dockerfile.web' + - 'gitnexus/Dockerfile.test' + - '.github/workflows/trivy.yml' push: branches: [main] schedule: - cron: '0 8 * * 1' workflow_dispatch: +permissions: + contents: read + concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: false @@ -61,7 +70,7 @@ jobs: image-ref: scan-target:${{ matrix.image.name }} format: sarif output: trivy-${{ matrix.image.name }}.sarif - severity: HIGH,CRITICAL + severity: MEDIUM,HIGH,CRITICAL # Hides CVEs with no available fix in the base image. ignore-unfixed: true exit-code: '0' diff --git a/.github/workflows/workflow-lint.yml b/.github/workflows/workflow-lint.yml index 7b38b8ddd..803c4d0bd 100644 --- a/.github/workflows/workflow-lint.yml +++ b/.github/workflows/workflow-lint.yml @@ -15,6 +15,9 @@ on: paths: - '.github/**' +permissions: + contents: read + concurrency: group: ${{ github.workflow }}-${{ github.ref }} cancel-in-progress: true diff --git a/AGENTS.md b/AGENTS.md index 60317d73d..b9b9138b1 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -149,11 +149,16 @@ Indexed as **GitNexus** (4325 symbols, 10556 relationships, 300 execution flows) ## Keeping the Index Fresh ```bash -npx gitnexus analyze # basic refresh; preserves any existing embeddings +npx gitnexus analyze # incremental by default; preserves embeddings +npx gitnexus analyze --force # full rebuild from scratch (opt out of incremental) npx gitnexus analyze --embeddings # also generate embeddings for new/changed nodes npx gitnexus analyze --drop-embeddings # explicit opt-in to wipe existing embeddings ``` +`analyze` runs **incrementally by default**. The pipeline still parses every file every run (cross-file resolution requires it), but tree-sitter parsing is **served from a content-addressed cache** at `.gitnexus/parse-cache.json` for chunks whose file contents haven't changed since the last run. Only changed-file rows (and their importers) are rewritten in LadybugDB; unchanged-file rows are preserved. Output is byte-equivalent to a full rebuild. Pass `--force` to wipe and re-index from scratch (e.g., to recover from a corrupt index, or after upgrading GitNexus). + +The parse cache key is **content-addressed and version-tagged**: it survives `--force` runs, and is automatically invalidated by a `gitnexus` package upgrade (so a new tree-sitter grammar doesn't silently replay stale parse output). Safe to delete `.gitnexus/parse-cache.json` at any time — it'll be rebuilt on the next analyze. + Check `.gitnexus/meta.json` `stats.embeddings` (0 = none). A plain `analyze` no longer drops existing vectors — pass `--drop-embeddings` to wipe. > Claude Code: PostToolUse hook detects a stale index after `git commit` and `git merge` and prompts the agent to run `analyze`. The hook does not invoke `analyze` itself. @@ -169,6 +174,20 @@ Check `.gitnexus/meta.json` `stats.embeddings` (0 = none). A plain `analyze` no | Tools/resources/schema reference | `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` | | CLI commands (index, status, clean, wiki) | `.claude/skills/gitnexus/gitnexus-cli/SKILL.md` | +## Hook env knobs + +The Claude Code hook (`gitnexus/hooks/claude/gitnexus-hook.cjs` and the mirrored plugin copy under `gitnexus-claude-plugin/hooks/`) honours these env vars. Defaults work for normal installations; set them only to override resolution. All path overrides ignore values that do not exist on disk and fall through to the standard resolution chain. + +| Env var | Type | Default | Purpose | +|---------|------|---------|---------| +| `GITNEXUS_HOOK_CLI_PATH` | path | resolved via package layout / `require.resolve` | Override path to the `gitnexus` CLI entry the hook spawns for `augment`. | +| `GITNEXUS_HOOK_LSOF_PATH` | path | `lsof` on `PATH` (with `/usr/bin/lsof`, `/usr/sbin/lsof`, `/sbin/lsof` fallbacks) | Override POSIX `lsof` location for the DB-lock probe. | +| `GITNEXUS_HOOK_PS_PATH` | path | `ps` on `PATH` (with `/bin/ps`, `/usr/bin/ps` fallbacks) | Override POSIX `ps` location. | +| `GITNEXUS_HOOK_POWERSHELL_PATH` | path | `%SystemRoot%\System32\WindowsPowerShell\v1.0\powershell.exe` (then `SysWOW64`, then `powershell.exe` on `PATH`) | Override Windows PowerShell location used by the Restart-Manager probe. | +| `GITNEXUS_HOOK_LINUX_PROC_BUDGET_MS` | integer ms | `1200` | Max wall-clock for the Linux `/proc` fd scan before bailing out to the `lsof` fallback. | +| `GITNEXUS_HOOK_RM_TARGET` | path | derived | Restart-Manager target file (the LadybugDB path under `.gitnexus/`). Set internally by the hook; rarely overridden manually. | +| `GITNEXUS_DEBUG` | boolean (`1`/`true`) | unset | Verbose stderr from the hook: prints discarded augment-stderr prefixes and one-shot `.ps1` load-failure warnings. | + ## Repo reference diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 99930cf0a..d4f6b12b2 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -30,17 +30,17 @@ Format: `[(scope)][!]: ` Allowed types and the release-notes section each one lands in (defined in `.github/release.yml`): -| Type | Label applied | Release-notes section | -|------|---------------|-----------------------| -| `feat` | `enhancement` | 🚀 Features | -| `fix` | `bug` | 🐛 Bug Fixes | -| `perf` | `performance` | 🏎️ Performance | -| `refactor` | `refactor` | 🔄 Refactoring | -| `test` | `test` | 🧪 Tests | -| `ci` | `ci` | 👷 CI/CD | -| `build` / `deps` | `dependencies` | 📦 Dependencies | -| `docs` | `documentation` | (grouped under Other Changes unless a Docs section is added) | -| `chore` / `revert` | `chore` | (excluded from release notes) | +| Type | Label applied | Release-notes section | +| ------------------ | --------------- | ------------------------------------------------------------ | +| `feat` | `enhancement` | 🚀 Features | +| `fix` | `bug` | 🐛 Bug Fixes | +| `perf` | `performance` | 🏎️ Performance | +| `refactor` | `refactor` | 🔄 Refactoring | +| `test` | `test` | 🧪 Tests | +| `ci` | `ci` | 👷 CI/CD | +| `build` / `deps` | `dependencies` | 📦 Dependencies | +| `docs` | `documentation` | (grouped under Other Changes unless a Docs section is added) | +| `chore` / `revert` | `chore` | (excluded from release notes) | Append `!` to the type (e.g. `feat(api)!: drop /v1 endpoint`) or include `BREAKING CHANGE:` in the PR body to flag a breaking change — the labeler then adds the `breaking` label and the 💥 Breaking Changes section is rendered first. @@ -81,17 +81,17 @@ Every workflow under `.github/workflows/` MUST declare a top-level `concurrency: - **Merge queue (`merge_group`)**: when this event is added, use `${{ github.workflow }}-${{ github.event.merge_group.head_ref }}` with `cancel-in-progress: false` (every queue entry is a distinct ref; never cancel). - **`cancel-in-progress` policy:** - | Event | `cancel-in-progress` | Why | - |-------|----------------------|-----| - | `pull_request` CI run | `true` | New push supersedes old run | - | `push` to `main` | `false` | Every main commit gets validated | - | Tag push (`v*` publish) | `false` | Never cancel mid-publish | - | `push` to `main` for release-candidate | `false` | Never cancel mid-RC publish | - | `workflow_dispatch` (release/publish) | `false` | Manual runs are intentional | - | `workflow_run` (sticky-comment reports) | `false` | Serialize, don't race | - | Per-PR bot workflows (`@claude`, review) | `false` | Serialize comments per PR | - | PR-meta re-checks (pr-description-check) | `true` | Cheap, latest wins | - | Single-slot utilities (triage sweep) | `true` | Latest dispatch supersedes | + | Event | `cancel-in-progress` | Why | + | ---------------------------------------- | -------------------- | -------------------------------- | + | `pull_request` CI run | `true` | New push supersedes old run | + | `push` to `main` | `false` | Every main commit gets validated | + | Tag push (`v*` publish) | `false` | Never cancel mid-publish | + | `push` to `main` for release-candidate | `false` | Never cancel mid-RC publish | + | `workflow_dispatch` (release/publish) | `false` | Manual runs are intentional | + | `workflow_run` (sticky-comment reports) | `false` | Serialize, don't race | + | Per-PR bot workflows (`@claude`, review) | `false` | Serialize comments per PR | + | PR-meta re-checks (pr-description-check) | `true` | Cheap, latest wins | + | Single-slot utilities (triage sweep) | `true` | Latest dispatch supersedes | - For workflows that serve multiple events at once (e.g. `ci.yml` handles `pull_request`, `push`, and `workflow_call`), make `cancel-in-progress` event-aware: @@ -109,18 +109,35 @@ Two workflows produce machine-readable signals on every PR. Coding agents and hu ### `gitnexus/autofix` -`pr-autofix.yml` (untrusted) + `pr-autofix-publish.yml` (trusted) run `prettier --write` and `eslint --fix` against the PR head and surface the diff as inline review-comment suggestions. Three signals are emitted: +`pr-autofix.yml` (untrusted) + `pr-autofix-publish.yml` (trusted) run `prettier --write` and `eslint --fix` against the PR head and surface a single ChatOps button on the PR. Three signals are emitted: -| Surface | Where | Notes | -|---|---|---| -| Sticky PR comment | Top-level comment with the HTML marker `` and heading `## :sparkles: PR Autofix`. Only posted when there is something to fix; clean PRs stay silent. | Edit-in-place via marker; one comment per PR. | -| Fenced JSON block | Inside the sticky, fenced as `gitnexus-autofix`. Schema `gitnexus.pr-autofix/v1` with fields `state` (`suggestions-posted` \| `skipped-too-large`), `pr_number`, `head_sha`, `changed_lines`, `run_id`. | Parseable signal — preferred over regexing prose. | -| Check Run | Stable name `gitnexus/autofix` on the PR head SHA. Conclusion: `success` (clean) or `neutral` (suggestions-posted / skipped-too-large). The output title disambiguates the two `neutral` cases. | Surfaced under PR Checks; readable via `gh pr checks `. | +| Surface | Where | Notes | +| ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------- | +| Sticky PR comment | Top-level comment with the HTML marker `` and heading `## :sparkles: PR Autofix`. Only posted when there is something to fix; clean PRs stay silent. | Edit-in-place via marker; one comment per PR. | +| Fenced JSON block | Inside the sticky, fenced as `gitnexus-autofix`. Schema `gitnexus.pr-autofix/v2` with fields `state` (`fixes-available`), `pr_number`, `head_sha`, `changed_lines`, `run_id`, and `apply_command` (literal `/autofix`). | Parseable signal — preferred over regexing prose. v1 fields preserved as a superset. | +| Check Run | Stable name `gitnexus/autofix` on the PR head SHA. Conclusion: `success` (clean) or `neutral` (`fixes-available`). The neutral title is `Autofix available — comment /autofix to apply`. | Surfaced under PR Checks; readable via `gh pr checks `. | To detect outcome from an agent: `gh pr checks --json name,conclusion,output | jq '.[] | select(.name == "gitnexus/autofix")'`. Forks are supported. The untrusted half runs fork code with `permissions: {}` and ships the diff as an artifact; the trusted publish job consumes only the diff (data, not code) and posts the comment + check run. +#### Applying autofix + +Comment `/autofix` on the PR (whole-line, no arguments). The `pr-autofix-apply.yml` workflow: + +1. Validates the comment body matches `^/autofix\s*$` exactly. Quoted or inline mentions are silently ignored. +2. Validates the commenter has `admin`, `write`, or `maintain` permission on the repo, OR is the PR author. Other commenters get a 👎 reaction and a refusal reply. +3. Locates the most recent successful `pr-autofix.yml` run for the PR's current head SHA, downloads its `autofix` artifact, applies the patch, and pushes a `chore(autofix): ...` commit back to the PR head branch. +4. Reacts ✅ on success, 👎 on stale-patch / push-failure, and posts a short reply with the apply-run URL in either case. + +The apply workflow runs from the default branch's copy of the file regardless of where the comment originates — that's the trust anchor. There is no diff-size cap (the apply workflow uses `git apply` + push, not the GitHub review-comment API). + +For fork PRs, the push succeeds only when the contributor has **Allow edits by maintainers** enabled on the PR (the default). When they have disabled it, the workflow fails loud with a 👎 reaction and an explanation comment. + +Re-invoking `/autofix` after a successful apply is a safe no-op — the workflow detects the already-applied state via `git apply --check --reverse` and reacts ✅ without pushing. + +**Sensitive paths.** The apply workflow refuses any patch that touches `.github/` (workflow files, CODEOWNERS, dependabot config). A malicious PR could ship a custom prettier or ESLint config that reformats workflow YAML; if accepted, those edits would be pushed under `contents: write` without human review. Apply formatter changes to files under `.github/` manually in a normal commit so they get the same review every other workflow change gets. + ## AI-assisted contributions If you use coding agents, follow project context files (e.g. `AGENTS.md`, `CLAUDE.md`) and avoid drive-by refactors unrelated to the issue. Prefer incremental, test-backed changes. @@ -182,8 +199,7 @@ Two publish workflows ship `gitnexus` to npm: the Docker build. - Manually run `docker build` + `docker push` locally and sign with Cosign against the same digest. - - Delete `rc/` and `v` tags, then redispatch with `force: - true` to re-run the full RC pipeline (cuts a new RC number). + - Delete `rc/` and `v` tags, then redispatch with `force: true` to re-run the full RC pipeline (cuts a new RC number). The rc workflow never moves `latest`. To verify after a change, inspect dist-tags: diff --git a/Dockerfile.cli b/Dockerfile.cli index c45292e06..3275c8f7e 100644 --- a/Dockerfile.cli +++ b/Dockerfile.cli @@ -1,24 +1,32 @@ ARG BUILDPLATFORM ARG TARGETPLATFORM +# Pinned npm version used to replace the bundled npm in the upstream Node +# image. Bumping requires a coordinated update in Dockerfile.web and +# gitnexus/Dockerfile.test so all images bootstrap the same npm. +ARG NPM_VERSION=11.14.1 -# ── Builder ──────────────────────────────────────────────────────────── +# -- Builder ----------------------------------------------------------- # Native modules (tree-sitter-*, onnxruntime-node, node-gyp builds for # tree-sitter-proto / tree-sitter-swift) require python3 + a C/C++ toolchain. -FROM node:22-trixie-slim AS builder +# node:22-bookworm-slim +FROM node:22-bookworm-slim@sha256:9f6d5975c7dca860947d3915877f85607946403fc55349f39b4bc3688448bb6e AS builder +ARG NPM_VERSION WORKDIR /app +RUN npx --yes npm@${NPM_VERSION} install -g npm@${NPM_VERSION} + # Toolchain for node-gyp / native builds. RUN apt-get update && apt-get install -y --no-install-recommends python3 make g++ git && rm -rf /var/lib/apt/lists/* -# Build gitnexus-shared first — gitnexus depends on it as a workspace. +# Build gitnexus-shared first - gitnexus depends on it as a workspace. COPY gitnexus-shared/package.json gitnexus-shared/package-lock.json ./gitnexus-shared/ RUN npm ci --prefix gitnexus-shared COPY gitnexus-shared ./gitnexus-shared RUN rm -f gitnexus-shared/tsconfig.tsbuildinfo RUN npm run build --prefix gitnexus-shared -# Copy the full gitnexus package before installing — `npm ci` triggers +# Copy the full gitnexus package before installing - `npm ci` triggers # `postinstall` (patches tree-sitter-swift, builds the vendored # tree-sitter-proto) and `prepare` (compiles TypeScript via scripts/build.js), # both of which need the source tree. @@ -28,11 +36,15 @@ RUN npm ci --prefix gitnexus # Drop dev dependencies for a smaller runtime layer. RUN npm prune --omit=dev --prefix gitnexus -# ── Runtime ──────────────────────────────────────────────────────────── -FROM node:22-trixie-slim AS runtime +# -- Runtime ----------------------------------------------------------- +# node:22-bookworm-slim +FROM node:22-bookworm-slim@sha256:9f6d5975c7dca860947d3915877f85607946403fc55349f39b4bc3688448bb6e AS runtime -# curl for the healthcheck; git so `gitnexus` can clone repos at runtime. -RUN apt-get update && apt-get install -y --no-install-recommends curl git && rm -rf /var/lib/apt/lists/* +# curl for the healthcheck; git for cloning; ca-certificates for TLS verification. +RUN apt-get update && apt-get install -y --no-install-recommends curl git ca-certificates && rm -rf /var/lib/apt/lists/* \ + && rm -rf /usr/local/lib/node_modules/npm \ + && rm -rf /usr/local/lib/node_modules/corepack \ + && rm -f /usr/local/bin/npm /usr/local/bin/npx /usr/local/bin/corepack WORKDIR /app @@ -43,11 +55,21 @@ RUN mkdir -p /data/gitnexus && chown -R node:node /data COPY --from=builder --chown=node:node /app/gitnexus/dist ./gitnexus/dist COPY --from=builder --chown=node:node /app/gitnexus/node_modules ./gitnexus/node_modules COPY --from=builder --chown=node:node /app/gitnexus/package.json ./gitnexus/package.json +COPY --from=builder --chown=node:node /app/gitnexus/scripts/install-duckdb-extension.mjs ./gitnexus/scripts/install-duckdb-extension.mjs COPY --from=builder --chown=node:node /app/gitnexus/vendor ./gitnexus/vendor +# Expose the `gitnexus` binary on PATH so the documented Docker workflow +# (`docker compose exec gitnexus-server gitnexus index /workspace/`) +# works without users having to invoke `node /app/gitnexus/dist/cli/index.js`. +# `npm prune --omit=dev` in the builder stage strips `node_modules/.bin/` +# entries, so the `gitnexus` bin declared in package.json (`dist/cli/index.js`, +# which already carries `#!/usr/bin/env node` and 755 perms) is otherwise +# unreachable from $PATH. +RUN ln -s /app/gitnexus/dist/cli/index.js /usr/local/bin/gitnexus + USER node -# The web UI defaults to http://localhost:4747 — keep that contract. +# The web UI defaults to http://localhost:4747 - keep that contract. ENV GITNEXUS_HOME=/data/gitnexus \ NODE_ENV=production \ PORT=4747 diff --git a/Dockerfile.web b/Dockerfile.web index 7d20e09ce..b102a700e 100644 --- a/Dockerfile.web +++ b/Dockerfile.web @@ -1,10 +1,17 @@ ARG BUILDPLATFORM ARG TARGETPLATFORM +# Pinned npm version — keep in sync with Dockerfile.cli and +# gitnexus/Dockerfile.test. +ARG NPM_VERSION=11.14.1 -FROM --platform=$BUILDPLATFORM node:22-alpine AS builder +# node:22-bookworm-slim +FROM --platform=$BUILDPLATFORM node:22-bookworm-slim@sha256:9f6d5975c7dca860947d3915877f85607946403fc55349f39b4bc3688448bb6e AS builder +ARG NPM_VERSION WORKDIR /app +RUN npx --yes npm@${NPM_VERSION} install -g npm@${NPM_VERSION} + COPY gitnexus-shared/package.json gitnexus-shared/package-lock.json ./gitnexus-shared/ RUN npm ci --prefix gitnexus-shared @@ -19,9 +26,13 @@ RUN npm ci --prefix gitnexus-web COPY gitnexus-web ./gitnexus-web RUN npm run build --prefix gitnexus-web -FROM node:22-alpine AS runtime +# node:22-bookworm-slim +FROM node:22-bookworm-slim@sha256:9f6d5975c7dca860947d3915877f85607946403fc55349f39b4bc3688448bb6e AS runtime -RUN apk add --no-cache curl +RUN apt-get update && apt-get install -y --no-install-recommends curl && rm -rf /var/lib/apt/lists/* \ + && rm -rf /usr/local/lib/node_modules/npm \ + && rm -rf /usr/local/lib/node_modules/corepack \ + && rm -f /usr/local/bin/npm /usr/local/bin/npx /usr/local/bin/corepack WORKDIR /app diff --git a/GUARDRAILS.md b/GUARDRAILS.md index 1cc032759..c09f0319a 100644 --- a/GUARDRAILS.md +++ b/GUARDRAILS.md @@ -30,9 +30,15 @@ Format: **Trigger → Instruction → Reason**. Append new Signs when the same m ### Stale graph after edits - **Trigger:** MCP warns index is behind `HEAD`, or search doesn't match latest commit. -- **Do:** `npx gitnexus analyze` (plus `--embeddings` if used). +- **Do:** `npx gitnexus analyze` (plus `--embeddings` if used). Runs incrementally by default — the pipeline parses every file every run (cross-file resolution requires it), but tree-sitter dispatch is skipped for unchanged file chunks via the content-addressed cache, and only changed-file rows (plus their importers, transitively) are rewritten in LadybugDB. - **Why:** Tools query LadybugDB from last analyze; git changes are invisible until re-indexed. +### Index seems corrupt or "incremental" is misbehaving + +- **Trigger:** `analyze` produces unexpected results, or `meta.json.incrementalInProgress` is set, or the index is in a half-state after a crash. +- **Do:** `npx gitnexus analyze --force` to rebuild from scratch. The dirty-flag check forces this automatically when a previous incremental run didn't complete cleanly, but `--force` is the manual escape hatch. Safe to delete `.gitnexus/parse-cache.json` at any time — content-addressed, will be regenerated. +- **Why:** Incremental writeback is selective DB row replacement; if the on-disk state is inconsistent for any reason, a full rebuild is the cheapest path back to a known-good index. + ### Embeddings vanished after analyze - **Trigger:** Semantic search quality drops; `stats.embeddings` in `meta.json` is 0 after refresh. diff --git a/README.md b/README.md index 6beadb63d..e08c0eb7d 100644 --- a/README.md +++ b/README.md @@ -120,7 +120,7 @@ To configure MCP for your editor, run `npx gitnexus setup` once — or set it up | Editor | MCP | Skills | Hooks (auto-augment) | Support | | --------------------- | --- | ------ | -------------------- | -------------- | | **Claude Code** | Yes | Yes | Yes (PreToolUse + PostToolUse) | **Full** | -| **Cursor** | Yes | Yes | — | MCP + Skills | +| **Cursor** | Yes | Yes | Yes (postToolUse, [manual install](gitnexus-cursor-integration/README.md#hook-install)) | **Full** | | **Codex** | Yes | Yes | — | MCP + Skills | | **Windsurf** | Yes | — | — | MCP | | **OpenCode** | Yes | Yes | — | MCP + Skills | @@ -722,6 +722,12 @@ gitnexus wiki --base-url https://api.anthropic.com/v1 # Force full regeneration gitnexus wiki --force + + +# Increase the timeout or retries for large codebase or slow LLM providers +gitnexus wiki --timeout # Per-attempt LLM request timeout in seconds (default: 60) +gitnexus wiki --retries # Max LLM retry attempts per request (default: 3) + ``` The wiki generator reads the indexed graph structure, groups files into modules via LLM, generates per-module documentation pages, and creates an overview page — all with cross-references to the knowledge graph. diff --git a/eslint-rules/require-safe-parse.mjs b/eslint-rules/require-safe-parse.mjs new file mode 100644 index 000000000..4ab9dbd8a --- /dev/null +++ b/eslint-rules/require-safe-parse.mjs @@ -0,0 +1,95 @@ +/** + * Custom ESLint rule: require `parseSourceSafe(parser, content, ...)` instead + * of direct `.parse(, ...)` calls. + * + * Background: tree-sitter's Node.js native binding crashes with SIGSEGV on + * Windows when handed a JS string longer than 32 767 chars. The crash happens + * inside the binding's V8 string-to-buffer conversion and cannot be intercepted + * by JavaScript `try/catch`. `parseSourceSafe` (in + * `gitnexus/src/core/tree-sitter/safe-parse.ts`) routes large inputs through + * the chunked-callback overload of `parser.parse(input, ...)` which bypasses + * the broken conversion path. PR #1433 fixed every direct call site at the + * time; this rule prevents new direct calls from creeping in. + * + * The rule is auto-fixable for the call-site rewrite. It does NOT auto-add the + * import (computing the correct relative path per file is brittle); after the + * call rewrite runs, the consumer file's `tsc` will complain about an + * undefined identifier and the developer adds the import. This is the same + * tradeoff `unused-imports/no-unused-imports` makes in the opposite direction. + * + * False-positive suppression: + * - Skips calls whose receiver is a known non-tree-sitter library (`JSON`, + * `URL`, `marked`, `Number`). + * - Skips calls whose first argument is a string-literal (grammar-load smoke + * tests like `_testParser.parse('service X { rpc Y (R) returns (R); }')`). + * - Skips test files (`.test.ts`/`.test.tsx`/`.spec.ts`). + * - Skips the `safe-parse.ts` helper itself. + */ + +const SKIPPED_RECEIVERS = new Set(['JSON', 'URL', 'marked', 'Number', 'Math']); + +export default { + meta: { + type: 'problem', + docs: { + description: + 'Require parseSourceSafe instead of direct tree-sitter `.parse(content, ...)` calls (Windows SIGSEGV protection)', + recommended: true, + }, + fixable: 'code', + schema: [], + messages: { + useSafeParse: + 'Direct `{{receiver}}.parse(...)` can SIGSEGV on Windows for inputs > 32 767 chars (uncatchable from JS). Use `parseSourceSafe({{receiver}}, ...)` from `core/tree-sitter/safe-parse.js`. Auto-fix rewrites the call; add the missing import yourself.', + }, + }, + create(context) { + const filename = context.filename ?? context.getFilename(); + // Don't lint the helper itself or test files. + if (filename.includes('safe-parse')) return {}; + if (/[.](?:test|spec)\.tsx?$/.test(filename)) return {}; + + const sourceCode = context.sourceCode ?? context.getSourceCode(); + + return { + CallExpression(node) { + const callee = node.callee; + if (callee.type !== 'MemberExpression') return; + if (callee.computed) return; + if (callee.property.type !== 'Identifier') return; + if (callee.property.name !== 'parse') return; + + // Skip known non-tree-sitter receivers. + if (callee.object.type === 'Identifier' && SKIPPED_RECEIVERS.has(callee.object.name)) { + return; + } + + // Smoke tests pass a string literal directly; those are trivially safe. + const firstArg = node.arguments[0]; + if (!firstArg) return; + if (firstArg.type === 'Literal' && typeof firstArg.value === 'string') return; + if (firstArg.type === 'TemplateLiteral' && firstArg.expressions.length === 0) return; + + const receiverText = sourceCode.getText(callee.object); + // Receiver-text-shape skip: anything matching well-known JS APIs that + // happen to have a `.parse()` shape but aren't tree-sitter. + if ( + /^(JSON|URL|marked|Number|Math|Date|globalThis\.JSON)\b/.test(receiverText) || + /\bjson\.parse\b/i.test(receiverText) + ) { + return; + } + + context.report({ + node, + messageId: 'useSafeParse', + data: { receiver: receiverText }, + fix(fixer) { + const argsText = node.arguments.map((arg) => sourceCode.getText(arg)).join(', '); + return fixer.replaceText(node, `parseSourceSafe(${receiverText}, ${argsText})`); + }, + }); + }, + }; + }, +}; diff --git a/eslint.config.mjs b/eslint.config.mjs index f377cba6c..e0779b71c 100644 --- a/eslint.config.mjs +++ b/eslint.config.mjs @@ -3,6 +3,15 @@ import tsParser from '@typescript-eslint/parser'; import unusedImports from 'eslint-plugin-unused-imports'; import reactHooks from 'eslint-plugin-react-hooks'; import prettierConfig from 'eslint-config-prettier'; +import requireSafeParse from './eslint-rules/require-safe-parse.mjs'; + +// Local plugin hosting custom rules that enforce GitNexus-specific invariants +// (currently: the Windows-SIGSEGV-safe parser entrypoint). +const gitnexusLocalPlugin = { + rules: { + 'require-safe-parse': requireSafeParse, + }, +}; // Selectors that protect MCP-reachable code from corrupting the JSON-RPC // stdio frame stream. The MCP-reachable block below uses these directly; @@ -135,6 +144,23 @@ export default [ }, }, + // Windows SIGSEGV protection: every tree-sitter parse in `core/` must route + // through parseSourceSafe. Direct `.parse(content, ...)` crashes on + // Windows for inputs > 32 767 chars (V8 string-conversion bug, uncatchable + // from JS). The rule auto-fixes the call site; the developer adds the + // missing import after the fix runs. Out of scope: tests (skipped by the + // rule), the helper itself (`safe-parse.ts`), and the `grpc-patterns/proto.ts` + // grammar-load smoke test (filtered by string-literal-arg skip in the rule). + { + files: ['gitnexus/src/core/**/*.ts'], + plugins: { + gitnexus: gitnexusLocalPlugin, + }, + rules: { + 'gitnexus/require-safe-parse': 'error', + }, + }, + // React-specific rules for gitnexus-web { files: ['gitnexus-web/src/**/*.{ts,tsx}'], diff --git a/eval/uv.lock b/eval/uv.lock index fcd666e75..04b89f336 100644 --- a/eval/uv.lock +++ b/eval/uv.lock @@ -2278,11 +2278,11 @@ wheels = [ [[package]] name = "urllib3" -version = "2.6.3" +version = "2.7.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" } +sdist = { url = "https://files.pythonhosted.org/packages/53/0c/06f8b233b8fd13b9e5ee11424ef85419ba0d8ba0b3138bf360be2ff56953/urllib3-2.7.0.tar.gz", hash = "sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c", size = 433602, upload-time = "2026-05-07T16:13:18.596Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" }, + { url = "https://files.pythonhosted.org/packages/7f/3e/5db95bcf282c52709639744ca2a8b149baccf648e39c8cc87553df9eae0c/urllib3-2.7.0-py3-none-any.whl", hash = "sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897", size = 131087, upload-time = "2026-05-07T16:13:17.151Z" }, ] [[package]] diff --git a/gitnexus-claude-plugin/hooks/gitnexus-hook.js b/gitnexus-claude-plugin/hooks/gitnexus-hook.js index 7d8fbfda4..7ff03e430 100644 --- a/gitnexus-claude-plugin/hooks/gitnexus-hook.js +++ b/gitnexus-claude-plugin/hooks/gitnexus-hook.js @@ -14,6 +14,8 @@ const fs = require('fs'); const path = require('path'); const { spawnSync } = require('child_process'); +const { acquireHookSlot } = require('./hook-lock.js'); +const { hasGitNexusDbLockedByGitNexusServer } = require('./hook-db-lock-probe.cjs'); /** * Read JSON input from stdin synchronously. @@ -102,6 +104,28 @@ function findGitNexusDir(startDir) { return null; } +function hasGitNexusServerOwner(gitNexusDir) { + return hasGitNexusDbLockedByGitNexusServer(path.join(gitNexusDir, 'lbug'), process.pid); +} + +function extractAugmentContext(stderr) { + const output = (stderr || '').trim(); + const marker = output.indexOf('[GitNexus]'); + const debug = process.env.GITNEXUS_DEBUG === '1' || process.env.GITNEXUS_DEBUG === 'true'; + if (debug && output.length > 0) { + // Emit the FULL discarded prefix (everything before the marker, or all of + // it when no marker is present) so suppressed diagnostics — LadybugDB lock + // warnings, parser errors, etc. — remain recoverable on the hook's own + // stderr. The untruncated payload lets operators see exactly what was + // filtered out instead of a 180-char JSON-quoted preview. + const discarded = marker === -1 ? output : output.slice(0, marker).trim(); + if (discarded.length > 0) { + process.stderr.write(`[GitNexus hook] augment stderr discarded prefix:\n${discarded}\n`); + } + } + return marker === -1 ? '' : output.slice(marker).trim(); +} + /** * Extract search pattern from tool input. */ @@ -169,6 +193,15 @@ function extractPattern(toolName, toolInput) { */ function runGitNexusCli(args, cwd, timeout) { const isWin = process.platform === 'win32'; + const hookCli = process.env.GITNEXUS_HOOK_CLI_PATH; + if (hookCli !== undefined && String(hookCli).trim() && fs.existsSync(String(hookCli))) { + return spawnSync(process.execPath, [String(hookCli), ...args], { + encoding: 'utf-8', + timeout, + cwd, + stdio: ['pipe', 'pipe', 'pipe'], + }); + } // Detect whether 'gitnexus' is on PATH (cheap check, no execution) let useDirectBinary = false; @@ -217,7 +250,8 @@ function sendHookResponse(hookEventName, message) { function handlePreToolUse(input) { const cwd = input.cwd || process.cwd(); if (!path.isAbsolute(cwd)) return; - if (!findGitNexusDir(cwd)) return; + const gitNexusDir = findGitNexusDir(cwd); + if (!gitNexusDir) return; const toolName = input.tool_name || ''; const toolInput = input.tool_input || {}; @@ -226,19 +260,28 @@ function handlePreToolUse(input) { const pattern = extractPattern(toolName, toolInput); if (!pattern || pattern.length < 3) return; + if (hasGitNexusServerOwner(gitNexusDir)) { + process.stderr.write('[GitNexus] augment skipped: MCP server owns DB\n'); + return; + } + + const release = acquireHookSlot(gitNexusDir); + if (!release) return; let result = ''; try { const child = runGitNexusCli(['augment', '--', pattern], cwd, 7000); if (!child.error && child.status === 0) { - result = child.stderr || ''; + result = extractAugmentContext(child.stderr || ''); } } catch { /* graceful failure */ + } finally { + release(); } - if (result && result.trim()) { - sendHookResponse('PreToolUse', result.trim()); + if (result) { + sendHookResponse('PreToolUse', result); } } diff --git a/gitnexus-claude-plugin/hooks/hook-db-lock-probe.cjs b/gitnexus-claude-plugin/hooks/hook-db-lock-probe.cjs new file mode 100644 index 000000000..783cd0804 --- /dev/null +++ b/gitnexus-claude-plugin/hooks/hook-db-lock-probe.cjs @@ -0,0 +1,238 @@ +/** + * Cross-platform best-effort probe: does another process hold dbPath open + * with a command line that looks like a GitNexus MCP/serve server? + * + * Backends (no user-installed Sysinternals): + * - Linux: scan procfs under /proc (per-PID fd entries) via stat(2) (dev+inode); works without lsof; + * optional lsof fallback when proc scan finds nothing. + * - macOS / *BSD / etc.: trusted lsof + ps (absolute paths first). + * - Windows: Restart Manager (rstrtmgr) via bundled PowerShell script + + * Win32_Process for command lines; trusted powershell.exe under %SystemRoot%. + * + * Fail-open on most errors; fail-closed only on lsof ETIMEDOUT (Unix) or + * PowerShell ETIMEDOUT (Windows), matching the hook contract. + */ + +const fs = require('fs'); +const path = require('path'); +const { spawnSync } = require('child_process'); + +function isGitNexusServerCommand(command) { + const hasServerMode = /(?:^|\s)(mcp|serve)(?:\s|$)/.test(command); + const hasGitNexus = + /(?:^|[/\\\s])gitnexus(?:\.cmd)?(?:\s|$)/.test(command) || + /node_modules[/\\]gitnexus[/\\]/.test(command); + return hasServerMode && hasGitNexus; +} + +function resolveHookBinary(tool) { + const envKey = tool === 'lsof' ? 'GITNEXUS_HOOK_LSOF_PATH' : 'GITNEXUS_HOOK_PS_PATH'; + const fromEnv = process.env[envKey]; + if (fromEnv && String(fromEnv).trim() && fs.existsSync(String(fromEnv))) { + return String(fromEnv); + } + const candidates = + tool === 'lsof' + ? ['/usr/bin/lsof', '/usr/sbin/lsof', '/sbin/lsof', tool] + : ['/bin/ps', '/usr/bin/ps', tool]; + for (const candidate of candidates) { + if (candidate === tool) return tool; + try { + if (fs.existsSync(candidate)) return candidate; + } catch { + /* ignore */ + } + } + return tool; +} + +function resolveWindowsPowerShellPath() { + const fromEnv = process.env.GITNEXUS_HOOK_POWERSHELL_PATH; + if (fromEnv && String(fromEnv).trim() && fs.existsSync(String(fromEnv).trim())) { + return String(fromEnv).trim(); + } + const root = process.env.SystemRoot || 'C:\\Windows'; + const ps = path.join(root, 'System32', 'WindowsPowerShell', 'v1.0', 'powershell.exe'); + if (fs.existsSync(ps)) return ps; + const psWow = path.join(root, 'SysWOW64', 'WindowsPowerShell', 'v1.0', 'powershell.exe'); + if (fs.existsSync(psWow)) return psWow; + return 'powershell.exe'; +} + +// Sentinel: +// undefined = not loaded yet (try the read) +// string = encoded PowerShell command (successful load) +// null = load attempted and failed (do not retry; warning already emitted) +let windowsRmListPsEncodedCommandCache; +let windowsRmListPsLoadFailureWarned = false; +function getWindowsRmListEncodedCommand() { + if (windowsRmListPsEncodedCommandCache !== undefined) { + return windowsRmListPsEncodedCommandCache; + } + try { + const ps1Path = path.join(__dirname, 'win-rm-list-json.ps1'); + const src = fs + .readFileSync(ps1Path, 'utf8') + .replace(/^\uFEFF/, '') + .replace(/\r\n/g, '\n'); + windowsRmListPsEncodedCommandCache = Buffer.from(src, 'utf16le').toString('base64'); + } catch (err) { + windowsRmListPsEncodedCommandCache = null; + if ( + !windowsRmListPsLoadFailureWarned && + (process.env.GITNEXUS_DEBUG === '1' || process.env.GITNEXUS_DEBUG === 'true') + ) { + windowsRmListPsLoadFailureWarned = true; + const msg = err && err.message ? String(err.message).slice(0, 200) : 'unknown'; + process.stderr.write(`[GitNexus hook] win-rm-list-json.ps1 load failed: ${msg}\n`); + } + } + return windowsRmListPsEncodedCommandCache; +} + +function hasGitNexusServerOwnerWindows(dbPathAbs, myPid) { + const encoded = getWindowsRmListEncodedCommand(); + if (!encoded) return false; + const psExe = resolveWindowsPowerShellPath(); + const r = spawnSync( + psExe, + [ + '-NoProfile', + '-NonInteractive', + '-ExecutionPolicy', + 'Bypass', + '-STA', + '-EncodedCommand', + encoded, + ], + { + encoding: 'utf-8', + timeout: 6000, + stdio: ['ignore', 'pipe', 'ignore'], + env: { ...process.env, GITNEXUS_HOOK_RM_TARGET: dbPathAbs }, + }, + ); + // ETIMEDOUT means the PowerShell probe didn't return in time; treat as 'unresponsive process holds DB' → fail-closed (skip augment). + if (r.error) return r.error.code === 'ETIMEDOUT'; + if (r.status !== 0) return false; + let rows; + try { + rows = JSON.parse(String(r.stdout || '').trim() || '[]'); + } catch { + return false; + } + if (!Array.isArray(rows)) return false; + for (const row of rows) { + const procId = Number(row.pid); + const cmd = String(row.cmd || ''); + if (!Number.isFinite(procId) || procId === myPid) continue; + if (isGitNexusServerCommand(cmd)) return true; + } + return false; +} + +function readLinuxCmdline(pidStr) { + try { + return fs.readFileSync(`/proc/${pidStr}/cmdline`, 'utf8').replace(/\0+/g, ' ').trim(); + } catch { + return ''; + } +} + +function linuxProcScanFindGitNexusServer(dbPathAbs, myPid) { + const raw = process.env.GITNEXUS_HOOK_LINUX_PROC_BUDGET_MS; + const budget = Number(raw && String(raw).trim()) ? Number.parseInt(String(raw), 10) : 1200; + const start = Date.now(); + let targetStat; + try { + targetStat = fs.statSync(dbPathAbs); + } catch { + return false; + } + let procEntries; + try { + procEntries = fs.readdirSync('/proc', { withFileTypes: true }); + } catch { + return false; + } + for (const ent of procEntries) { + if (Date.now() - start > budget) return false; + if (!ent.isDirectory() || !/^\d+$/.test(ent.name)) continue; + const pid = Number.parseInt(ent.name, 10); + if (!Number.isFinite(pid) || pid === myPid) continue; + const fdDir = path.join('/proc', ent.name, 'fd'); + let fds; + try { + fds = fs.readdirSync(fdDir); + } catch { + continue; + } + let holds = false; + for (const fd of fds) { + if (Date.now() - start > budget) return false; + try { + const st = fs.statSync(path.join(fdDir, fd)); + if (st.dev === targetStat.dev && st.ino === targetStat.ino) { + holds = true; + break; + } + } catch { + /* ignore */ + } + } + if (!holds) continue; + if (isGitNexusServerCommand(readLinuxCmdline(ent.name))) return true; + } + return false; +} + +function unixLsofPsFindGitNexusServer(dbPathAbs, myPid) { + const lsofPath = resolveHookBinary('lsof'); + const lsof = spawnSync(lsofPath, ['-nP', '-t', '--', dbPathAbs], { + encoding: 'utf-8', + timeout: 1000, + stdio: ['ignore', 'pipe', 'ignore'], + }); + if (lsof.error) return lsof.error.code === 'ETIMEDOUT'; + + const pids = (lsof.stdout || '').split(/\s+/).filter(Boolean); + const psPath = resolveHookBinary('ps'); + for (const pid of pids) { + if (Number(pid) === myPid) continue; + const ps = spawnSync(psPath, ['-p', pid, '-o', 'command='], { + encoding: 'utf-8', + timeout: 500, + stdio: ['ignore', 'pipe', 'ignore'], + }); + if (ps.error) { + if (ps.error.code === 'ETIMEDOUT') return true; + continue; + } + if (isGitNexusServerCommand(ps.stdout || '')) return true; + } + return false; +} + +/** + * @param {string} dbPath Absolute or relative path to the DB file (e.g. .../lbug). + * @param {number} myPid Current process PID (hook runner), excluded from matches. + */ +function hasGitNexusDbLockedByGitNexusServer(dbPath, myPid) { + if (!fs.existsSync(dbPath)) return false; + const dbPathAbs = path.resolve(dbPath); + + if (process.platform === 'win32') { + return hasGitNexusServerOwnerWindows(dbPathAbs, myPid); + } + + if (process.platform === 'linux') { + if (linuxProcScanFindGitNexusServer(dbPathAbs, myPid)) return true; + return unixLsofPsFindGitNexusServer(dbPathAbs, myPid); + } + + return unixLsofPsFindGitNexusServer(dbPathAbs, myPid); +} + +module.exports = { + hasGitNexusDbLockedByGitNexusServer, +}; diff --git a/gitnexus-claude-plugin/hooks/hook-lock.js b/gitnexus-claude-plugin/hooks/hook-lock.js new file mode 100644 index 000000000..759856384 --- /dev/null +++ b/gitnexus-claude-plugin/hooks/hook-lock.js @@ -0,0 +1,119 @@ +const fs = require('fs'); +const path = require('path'); + +const HOOK_LOCK_SUBDIR = '.hook-locks'; +const HOOK_LOCK_MAX_INFLIGHT = 3; +const HOOK_LOCK_STALE_MS = 30000; + +function acquireHookSlot(gitNexusDir) { + const lockDir = path.join(gitNexusDir, HOOK_LOCK_SUBDIR); + try { + fs.mkdirSync(lockDir, { recursive: true }); + } catch { + // Cannot create lock dir (read-only fs, cross-user perm denial, out of + // inodes, etc.) — fail closed by returning null. Caller skips augment. + // Fail-open here would let N concurrent hooks all proceed unguarded and + // reintroduce the #1486 fan-out the guard exists to prevent. + return null; + } + + const myPidStr = String(process.pid); + + for (let slot = 0; slot < HOOK_LOCK_MAX_INFLIGHT; slot++) { + const slotPath = path.join(lockDir, `slot-${slot}.lock`); + for (let attempt = 0; attempt < 2; attempt++) { + try { + fs.writeFileSync(slotPath, myPidStr, { flag: 'wx' }); + let released = false; + const release = () => { + if (released) return; + released = true; + try { + // Only unlink if we still own the slot. If we appeared stale and + // another hook took over, the file now belongs to it — leave alone. + const content = fs.readFileSync(slotPath, 'utf-8').trim(); + if (content === myPidStr) fs.unlinkSync(slotPath); + } catch { + /* already removed or unreadable */ + } + }; + process.on('exit', release); + return release; + } catch { + // Slot exists. Decide whether to take it over. + // Open once and inspect mtime + content via the same fd so there's + // no TOCTOU between the metadata check and the content read + // (codeql js/file-system-race). + let fd; + try { + fd = fs.openSync(slotPath, 'r'); + } catch { + continue; // Vanished between EEXIST and open — retry this slot. + } + let isLive = false; + let mtimeMs = Date.now(); + try { + mtimeMs = fs.fstatSync(fd).mtimeMs; + const buf = Buffer.alloc(32); + const n = fs.readSync(fd, buf, 0, 32, 0); + const ownerStr = buf.slice(0, n).toString('utf-8').trim(); + if (ownerStr === '') { + // Owner created the file but hasn't written its PID yet. The + // wx open+write window is microseconds; give it the benefit + // of the doubt and treat as live. + isLive = true; + } else { + const owner = Number.parseInt(ownerStr, 10); + if (Number.isFinite(owner) && owner > 0) { + try { + process.kill(owner, 0); + isLive = true; + } catch (e) { + // ESRCH = process gone → treat as dead. EPERM = process exists + // but owned by another user (cross-user lock dir) → still alive, + // keep the slot. Anything else: be conservative, assume alive. + if (e && e.code === 'ESRCH') { + isLive = false; + } else { + isLive = true; + } + } + } + } + } catch { + /* unreadable — treat as dead */ + } finally { + try { + fs.closeSync(fd); + } catch { + /* already closed */ + } + } + // For slots younger than HOOK_LOCK_STALE_MS, PID-liveness wins — + // a slow-but-alive hook is never wrongly evicted. For older slots, + // age is the final arbiter as a defense against PID reuse on long- + // abandoned slots. 30s >> the 7s augment timeout, so a healthy run + // never crosses this threshold. + if (isLive && Date.now() - mtimeMs > HOOK_LOCK_STALE_MS) { + isLive = false; + } + if (isLive) break; // Try the next slot. + try { + fs.unlinkSync(slotPath); + } catch { + /* another hook beat us to it — retry will hit EEXIST */ + } + // Loop and retry this slot. + } + } + } + + return null; +} + +module.exports = { + HOOK_LOCK_SUBDIR, + HOOK_LOCK_MAX_INFLIGHT, + HOOK_LOCK_STALE_MS, + acquireHookSlot, +}; diff --git a/gitnexus-claude-plugin/hooks/win-rm-list-json.ps1 b/gitnexus-claude-plugin/hooks/win-rm-list-json.ps1 new file mode 100644 index 000000000..5c1564e30 --- /dev/null +++ b/gitnexus-claude-plugin/hooks/win-rm-list-json.ps1 @@ -0,0 +1,76 @@ +$ErrorActionPreference = 'Stop' +$target = $env:GITNEXUS_HOOK_RM_TARGET +if ([string]::IsNullOrWhiteSpace($target)) { Write-Output '[]'; exit 0 } +$target = (Resolve-Path -LiteralPath $target).ProviderPath + +if (-not ([Management.Automation.PSTypeName]'GitNexusHookRm.Native').Type) { +Add-Type @' +using System; +using System.Runtime.InteropServices; +namespace GitNexusHookRm { + public static class Native { + public const int ErrorMoreData = 234; + [StructLayout(LayoutKind.Sequential, Pack = 4)] + public struct RM_UNIQUE_PROCESS { + public int dwProcessId; + public long ProcessStartTime; + } + [StructLayout(LayoutKind.Sequential, CharSet = CharSet.Unicode)] + public struct RM_PROCESS_INFO { + public RM_UNIQUE_PROCESS Process; + [MarshalAs(UnmanagedType.ByValTStr, SizeConst = 256)] + public string strAppName; + [MarshalAs(UnmanagedType.ByValTStr, SizeConst = 64)] + public string strServiceShortName; + public uint ApplicationType; + public uint AppStatus; + public uint TSSessionId; + public uint bRestartable; + } + [DllImport("rstrtmgr.dll", CharSet = CharSet.Unicode)] + public static extern int RmStartSession(out uint pSessionHandle, uint dwSessionFlags, string strSessionKey); + [DllImport("rstrtmgr.dll", CharSet = CharSet.Unicode)] + public static extern int RmRegisterResources(uint pSessionHandle, uint nFiles, string[] rgsFileNames, uint nApplications, IntPtr rgApplications, uint nServices, string[] rgsServiceNames); + [DllImport("rstrtmgr.dll")] + public static extern int RmGetList(uint dwSessionHandle, out uint pnProcInfoNeeded, ref uint pnProcInfo, [In, Out] RM_PROCESS_INFO[] rgAffectedApps, ref uint lpdwRebootReasons); + [DllImport("rstrtmgr.dll")] + public static extern int RmEndSession(uint pSessionHandle); + } +} +'@ +} + +$h = [uint32]0 +$key = [guid]::NewGuid().ToString('N') +$rmErr = [GitNexusHookRm.Native]::RmStartSession([ref]$h, 0, $key) +if ($rmErr -ne 0) { Write-Output '[]'; exit 0 } +$files = @($target) +$err = [GitNexusHookRm.Native]::RmRegisterResources($h, 1, $files, 0, [IntPtr]::Zero, 0, $null) +if ($err -ne 0) { + [void][GitNexusHookRm.Native]::RmEndSession($h) + Write-Output '[]' + exit 0 +} +$need = [uint32]0 +$n = [uint32]0 +$reboot = [uint32]0 +$err = [GitNexusHookRm.Native]::RmGetList($h, [ref]$need, [ref]$n, $null, [ref]$reboot) +if ($err -ne [GitNexusHookRm.Native]::ErrorMoreData) { + [void][GitNexusHookRm.Native]::RmEndSession($h) + Write-Output '[]' + exit 0 +} +$n = $need +$buf = New-Object GitNexusHookRm.Native+RM_PROCESS_INFO[] ([int]$n) +$err = [GitNexusHookRm.Native]::RmGetList($h, [ref]$need, [ref]$n, $buf, [ref]$reboot) +[void][GitNexusHookRm.Native]::RmEndSession($h) +if ($err -ne 0) { Write-Output '[]'; exit 0 } + +$out = @() +for ($i = 0; $i -lt [int]$n; $i++) { + $procId = $buf[$i].Process.dwProcessId + $p = Get-CimInstance -ClassName Win32_Process -Filter "ProcessId=$procId" -ErrorAction SilentlyContinue + $cmd = if ($p) { $p.CommandLine } else { '' } + $out += [PSCustomObject]@{ pid = [int]$procId; cmd = $cmd } +} +ConvertTo-Json -InputObject @($out) -Compress diff --git a/gitnexus-claude-plugin/skills/gitnexus-cli/SKILL.md b/gitnexus-claude-plugin/skills/gitnexus-cli/SKILL.md index 1c38face4..11945b8cc 100644 --- a/gitnexus-claude-plugin/skills/gitnexus-cli/SKILL.md +++ b/gitnexus-claude-plugin/skills/gitnexus-cli/SKILL.md @@ -62,6 +62,8 @@ Generates repository documentation from the knowledge graph using an LLM. Requir | `--api-key ` | LLM API key | | `--concurrency ` | Parallel LLM calls (default: 3) | | `--gist` | Publish wiki as a public GitHub Gist | +| `--timeout ` | Per-attempt LLM request timeout in seconds (default: 60) | +| `--retries ` | Max LLM retry attempts per request (default: 3) | ### list — Show all indexed repos diff --git a/gitnexus-cursor-integration/README.md b/gitnexus-cursor-integration/README.md new file mode 100644 index 000000000..6545bacec --- /dev/null +++ b/gitnexus-cursor-integration/README.md @@ -0,0 +1,91 @@ +# GitNexus — Cursor integration + +Static config that adds GitNexus knowledge-graph augmentation and skill files to Cursor. + +> **Hooks require Cursor 2.4+.** Earlier versions don't expose `postToolUse` and the hook will silently no-op. + +## What you get + +| Layer | What it does | How it's installed | +| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- | +| **MCP** | `gitnexus` MCP server with 16 tools (`query`, `context`, `impact`, `detect_changes`, `rename`, …) | `npx gitnexus setup` writes `~/.cursor/mcp.json` automatically. | +| **Skills** | `/gitnexus-exploring`, `/gitnexus-debugging`, `/gitnexus-impact-analysis`, `/gitnexus-refactoring`, `/gitnexus-pr-review` markdown skills | `npx gitnexus setup` copies them to `~/.cursor/skills/gitnexus/`. | +| **Hooks** _(this README)_ | `postToolUse` hook that enriches `Shell` / `Read` / `Grep` tool calls with graph context — same augmentation Claude Code gets | **Manual** — copy the files described below into your project's `.cursor/`. | + +## Hook install + +Cursor 2.4+ reads `.cursor/hooks.json` from the project root and runs hook commands with the project root as the working directory ([docs](https://cursor.com/docs/agent/hooks)). + +From this repo's `gitnexus-cursor-integration/hooks/`, copy the files below into your **project root**: + +```text +/ +├── .cursor/ +│ └── hooks.json ← from gitnexus-cursor-integration/hooks/hooks.json +└── hooks/ + ├── gitnexus-hook.cjs ← from gitnexus-cursor-integration/hooks/gitnexus-hook.cjs + └── hook-lock.cjs ← from gitnexus-cursor-integration/hooks/hook-lock.cjs +``` + +Equivalent shell commands (run from your project root, with `$GITNEXUS_REPO` pointing at a clone of this repo): + +```bash +mkdir -p .cursor hooks +cp "$GITNEXUS_REPO/gitnexus-cursor-integration/hooks/hooks.json" .cursor/hooks.json +cp "$GITNEXUS_REPO/gitnexus-cursor-integration/hooks/gitnexus-hook.cjs" hooks/gitnexus-hook.cjs +cp "$GITNEXUS_REPO/gitnexus-cursor-integration/hooks/hook-lock.cjs" hooks/hook-lock.cjs +``` + +If you already have a `.cursor/hooks.json`, merge the `hooks.postToolUse` array rather than overwriting. + +### Verify + +1. Index the project: `npx gitnexus analyze` +2. Reload the Cursor window so it picks up the new hook config. +3. Ask the agent something that triggers `Read` / `Grep` / `Shell rg`. You should see a `[GitNexus]` block appended to the tool result. +4. Diagnose silent no-ops by setting `GITNEXUS_DEBUG=1` in your shell environment — the hook will write Cursor's raw event payload to stderr so you can verify field names. + +### What's installed manually vs. automated + +| Step | Automated by `gitnexus setup`? | +| -------------------------------------------------------------------- | ------------------------------ | +| `~/.cursor/mcp.json` | ✅ | +| `~/.cursor/skills/gitnexus/*` | ✅ | +| `/.cursor/hooks.json` + `/hooks/gitnexus-hook.cjs` + `/hooks/hook-lock.cjs` | ❌ — copy manually (see above) | + +Hook install is per-project (Cursor scopes hooks to a project root); skills and MCP config are global. + +## Hook contract + +The hook receives a JSON event on stdin matching Cursor 2.4's `postToolUse` shape: + +```json +{ + "tool_name": "Grep" | "Read" | "Shell", + "tool_input": { /* tool-specific */ }, + "tool_output": { /* optional */ }, + "cwd": "/absolute/path/to/project" +} +``` + +It writes augmentation context to stdout as: + +```json +{ "additional_context": "[GitNexus] …" } +``` + +Empty stdout means "no augmentation, continue normally" — the hook never blocks the tool. + +### Pattern extraction per tool + +| Tool | Pattern source | Notes | +| ------- | ---------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | +| `Grep` | `tool_input.query` (also `pattern`, `regex`, `q`, `search`, `searchQuery`) | Last-resort fallback: longest string value in `tool_input` (≥ 3 chars). | +| `Read` | basename of `tool_input.target_file` (also `file_path`, `filePath`, `path`, `file`), stripped to identifier characters | `auth/handler.ts` → `handler`. | +| `Shell` | First positional argument after `rg` / `grep` in `tool_input.command` | Best-effort tokenizer; quoted multi-word patterns (`rg "User Service"`) extract the first word only. | + +## Troubleshooting + +- **Nothing happens** — Confirm Cursor is on 2.4+ and the project root has `.cursor/hooks.json` plus both hook files at `hooks/gitnexus-hook.cjs` and `hooks/hook-lock.cjs`. Then `npx gitnexus list` to confirm the project is indexed. +- **`gitnexus` not found** — The hook prefers a locally-resolvable `gitnexus/dist/cli/index.js` and falls back to `npx -y gitnexus`. Install globally with `npm i -g gitnexus` to skip the npx cold-start latency. +- **Wrong pattern extracted** — Set `GITNEXUS_DEBUG=1` and run a tool call. The raw stdin payload is logged to stderr; use it to confirm Cursor's actual `tool_input` field names against the table above. If they differ, file an issue with the captured payload. diff --git a/gitnexus-cursor-integration/hooks/augment-shell.sh b/gitnexus-cursor-integration/hooks/augment-shell.sh deleted file mode 100644 index 48ea185b0..000000000 --- a/gitnexus-cursor-integration/hooks/augment-shell.sh +++ /dev/null @@ -1,50 +0,0 @@ -#!/bin/bash -# GitNexus beforeShellExecution hook for Cursor -# Receives JSON on stdin with { command, cwd, timeout } -# Returns JSON on stdout with { permission, agent_message } -# -# Extracts search pattern from grep/rg commands, runs gitnexus augment, -# and injects the enriched context via agent_message. - -INPUT=$(cat) - -COMMAND=$(echo "$INPUT" | jq -r '.command // empty' 2>/dev/null) - -if [ -z "$COMMAND" ]; then - echo '{"permission":"allow"}' - exit 0 -fi - -# Skip non-search commands -case "$COMMAND" in - cd\ *|npm\ *|yarn\ *|pnpm\ *|git\ commit*|git\ push*|git\ pull*|mkdir\ *|rm\ *|cp\ *|mv\ *|echo\ *|cat\ *) - echo '{"permission":"allow"}' - exit 0 - ;; -esac - -# Extract search pattern from rg/grep commands -PATTERN="" -if echo "$COMMAND" | grep -qE '\brg\b'; then - PATTERN=$(echo "$COMMAND" | sed -n "s/.*\brg\s\+\(--[^ ]*\s\+\)*['\"]\\?\([^'\";\| >]*\\).*/\2/p") -elif echo "$COMMAND" | grep -qE '\bgrep\b'; then - PATTERN=$(echo "$COMMAND" | sed -n "s/.*\bgrep\s\+\(-[^ ]*\s\+\)*['\"]\\?\([^'\";\| >]*\\).*/\2/p") -fi - -if [ -z "$PATTERN" ] || [ ${#PATTERN} -lt 3 ]; then - echo '{"permission":"allow"}' - exit 0 -fi - -# Run gitnexus augment -RESULT=$(npx -y gitnexus augment "$PATTERN" 2>/dev/null) - -if [ -n "$RESULT" ]; then - # Escape for JSON - ESCAPED=$(echo "$RESULT" | jq -Rs .) - echo "{\"permission\":\"allow\",\"agent_message\":$ESCAPED}" -else - echo '{"permission":"allow"}' -fi - -exit 0 diff --git a/gitnexus-cursor-integration/hooks/gitnexus-hook.cjs b/gitnexus-cursor-integration/hooks/gitnexus-hook.cjs new file mode 100644 index 000000000..74c5587b3 --- /dev/null +++ b/gitnexus-cursor-integration/hooks/gitnexus-hook.cjs @@ -0,0 +1,266 @@ +#!/usr/bin/env node +/** + * GitNexus Cursor postToolUse Hook + * + * Receives a JSON event on stdin describing a finished tool call, derives a + * search pattern (Grep query, Read file basename, or rg/grep arg from a Shell + * command), runs `gitnexus augment `, and emits the enriched context + * back as `{ additional_context: "..." }` so the agent sees it alongside the + * tool result. + * + * Replaces the legacy beforeShellExecution / augment-shell.sh pipeline: + * - Cross-platform (no bash, no jq — runs on Windows out of the box) + * - Covers Read and Grep, not just Shell rg/grep + * + * Cursor 2.4+ generic hooks: https://cursor.com/docs/agent/hooks + */ + +const fs = require('fs'); +const path = require('path'); +const { spawnSync } = require('child_process'); +const { acquireHookSlot } = require('./hook-lock.cjs'); + +function readInput() { + try { + const data = fs.readFileSync(0, 'utf-8'); + return JSON.parse(data); + } catch { + return {}; + } +} + +function isGlobalRegistryDir(candidate) { + if (fs.existsSync(path.join(candidate, 'meta.json'))) return false; + return ( + fs.existsSync(path.join(candidate, 'registry.json')) || + fs.existsSync(path.join(candidate, 'repos')) + ); +} + +function walkForGitNexusDir(startDir) { + let dir = startDir; + for (let i = 0; i < 5; i++) { + const candidate = path.join(dir, '.gitnexus'); + if (fs.existsSync(candidate)) { + if (!isGlobalRegistryDir(candidate)) return candidate; + } + const parent = path.dirname(dir); + if (parent === dir) break; + dir = parent; + } + return null; +} + +function findCanonicalRepoRoot(cwd) { + try { + const result = spawnSync('git', ['rev-parse', '--path-format=absolute', '--git-common-dir'], { + encoding: 'utf-8', + timeout: 2000, + cwd, + stdio: ['pipe', 'pipe', 'pipe'], + }); + if (result.error || result.status !== 0) return null; + const commonDir = (result.stdout || '').trim(); + if (!commonDir || !path.isAbsolute(commonDir)) return null; + return path.dirname(commonDir); + } catch { + return null; + } +} + +function findGitNexusDir(startDir) { + const cwd = startDir || process.cwd(); + const fromCwd = walkForGitNexusDir(cwd); + if (fromCwd) return fromCwd; + const canonicalRoot = findCanonicalRepoRoot(cwd); + if (canonicalRoot && canonicalRoot !== cwd) { + return walkForGitNexusDir(canonicalRoot); + } + return null; +} + +function parseRgGrepPattern(cmd) { + const tokens = cmd.split(/\s+/); + let foundCmd = false; + let skipNext = false; + const flagsWithValues = new Set([ + '-e', + '-f', + '-m', + '-A', + '-B', + '-C', + '-g', + '--glob', + '-t', + '--type', + '--include', + '--exclude', + ]); + + for (const token of tokens) { + if (skipNext) { + skipNext = false; + continue; + } + if (!foundCmd) { + if (/\brg$|\bgrep$/.test(token)) foundCmd = true; + continue; + } + if (token.startsWith('-')) { + if (flagsWithValues.has(token)) skipNext = true; + continue; + } + const cleaned = token.replace(/['"]/g, ''); + return cleaned.length >= 3 ? cleaned : null; + } + return null; +} + +/** + * Extract a search pattern from the tool input. Cursor 2.4 docs at + * https://cursor.com/docs/agent/hooks list the tool *matchers* but do not + * formally specify the per-tool tool_input field names, so we probe a + * generous set of MCP-style aliases. As a last-resort fallback for Grep + * (the highest-frequency search path) we also accept the longest plausible + * string value in tool_input. Set GITNEXUS_DEBUG=1 to log the raw payload + * to stderr if Cursor changes the contract and aliases stop matching. + */ +function pickLongestStringValue(obj) { + let best = null; + if (!obj || typeof obj !== 'object') return null; + for (const v of Object.values(obj)) { + if (typeof v === 'string' && v.length >= 3 && (!best || v.length > best.length)) { + best = v; + } + } + return best; +} + +function extractPattern(toolName, toolInput) { + const t = (toolName || '').toLowerCase(); + + if (t === 'grep') { + const aliases = [ + toolInput.query, + toolInput.pattern, + toolInput.regex, + toolInput.q, + toolInput.search, + toolInput.searchQuery, + ]; + for (const a of aliases) { + if (typeof a === 'string' && a.length >= 3) return a; + } + // Last resort: scan tool_input for any reasonable-looking string value. + return pickLongestStringValue(toolInput); + } + + if (t === 'read') { + const filePath = + toolInput.target_file || + toolInput.file_path || + toolInput.filePath || + toolInput.path || + toolInput.file || + ''; + if (!filePath) return null; + const base = path.basename(String(filePath), path.extname(String(filePath))); + const cleaned = base.replace(/[^a-zA-Z0-9_]/g, ''); + return cleaned.length >= 3 ? cleaned : null; + } + + if (t === 'shell') { + const cmd = toolInput.command || ''; + if (!/\brg\b|\bgrep\b/.test(cmd)) return null; + // NOTE: parseRgGrepPattern uses split(/\s+/) and cannot handle shell + // quoting. `rg "User Service" src/` returns "User" (the first token + // after the rg/grep arg, with surrounding quotes stripped) — the + // multi-word pattern is intentionally not reconstructed since BM25 is + // already token-tolerant. Quoted single tokens (`rg "validateUser"`) + // work fine. + return parseRgGrepPattern(cmd); + } + + return null; +} + +function resolveCliPath() { + try { + return require.resolve('gitnexus/dist/cli/index.js'); + } catch { + return ''; + } +} + +function runGitNexusCli(cliPath, args, cwd, timeout) { + const isWin = process.platform === 'win32'; + if (cliPath) { + return spawnSync(process.execPath, [cliPath, ...args], { + encoding: 'utf-8', + timeout, + cwd, + stdio: ['pipe', 'pipe', 'pipe'], + }); + } + return spawnSync(isWin ? 'npx.cmd' : 'npx', ['-y', 'gitnexus', ...args], { + encoding: 'utf-8', + timeout: timeout + 5000, + cwd, + stdio: ['pipe', 'pipe', 'pipe'], + }); +} + +function main() { + try { + const input = readInput(); + if (process.env.GITNEXUS_DEBUG) { + // Echo the payload so users can capture Cursor's actual contract when + // diagnosing why augmentation isn't firing. Stderr only — stdout is + // reserved for the JSON response Cursor consumes. + try { + process.stderr.write( + `GitNexus Cursor hook stdin: ${JSON.stringify(input).slice(0, 500)}\n`, + ); + } catch { + /* never let debug logging break the hook */ + } + } + const cwd = input.cwd || process.cwd(); + if (!path.isAbsolute(cwd)) return; + const gitNexusDir = findGitNexusDir(cwd); + if (!gitNexusDir) return; + + const toolName = input.tool_name || ''; + const toolInput = input.tool_input || {}; + + const pattern = extractPattern(toolName, toolInput); + if (!pattern || pattern.length < 3) return; + + const release = acquireHookSlot(gitNexusDir); + if (!release) return; + + const cliPath = resolveCliPath(); + let result = ''; + try { + const child = runGitNexusCli(cliPath, ['augment', '--', pattern], cwd, 7000); + if (!child.error && child.status === 0) { + result = child.stderr || ''; + } + } catch { + /* graceful failure */ + } finally { + release(); + } + + if (result && result.trim()) { + console.log(JSON.stringify({ additional_context: result.trim() })); + } + } catch (err) { + if (process.env.GITNEXUS_DEBUG) { + console.error('GitNexus Cursor hook error:', (err.message || '').slice(0, 200)); + } + } +} + +main(); diff --git a/gitnexus-cursor-integration/hooks/hook-lock.cjs b/gitnexus-cursor-integration/hooks/hook-lock.cjs new file mode 100644 index 000000000..759856384 --- /dev/null +++ b/gitnexus-cursor-integration/hooks/hook-lock.cjs @@ -0,0 +1,119 @@ +const fs = require('fs'); +const path = require('path'); + +const HOOK_LOCK_SUBDIR = '.hook-locks'; +const HOOK_LOCK_MAX_INFLIGHT = 3; +const HOOK_LOCK_STALE_MS = 30000; + +function acquireHookSlot(gitNexusDir) { + const lockDir = path.join(gitNexusDir, HOOK_LOCK_SUBDIR); + try { + fs.mkdirSync(lockDir, { recursive: true }); + } catch { + // Cannot create lock dir (read-only fs, cross-user perm denial, out of + // inodes, etc.) — fail closed by returning null. Caller skips augment. + // Fail-open here would let N concurrent hooks all proceed unguarded and + // reintroduce the #1486 fan-out the guard exists to prevent. + return null; + } + + const myPidStr = String(process.pid); + + for (let slot = 0; slot < HOOK_LOCK_MAX_INFLIGHT; slot++) { + const slotPath = path.join(lockDir, `slot-${slot}.lock`); + for (let attempt = 0; attempt < 2; attempt++) { + try { + fs.writeFileSync(slotPath, myPidStr, { flag: 'wx' }); + let released = false; + const release = () => { + if (released) return; + released = true; + try { + // Only unlink if we still own the slot. If we appeared stale and + // another hook took over, the file now belongs to it — leave alone. + const content = fs.readFileSync(slotPath, 'utf-8').trim(); + if (content === myPidStr) fs.unlinkSync(slotPath); + } catch { + /* already removed or unreadable */ + } + }; + process.on('exit', release); + return release; + } catch { + // Slot exists. Decide whether to take it over. + // Open once and inspect mtime + content via the same fd so there's + // no TOCTOU between the metadata check and the content read + // (codeql js/file-system-race). + let fd; + try { + fd = fs.openSync(slotPath, 'r'); + } catch { + continue; // Vanished between EEXIST and open — retry this slot. + } + let isLive = false; + let mtimeMs = Date.now(); + try { + mtimeMs = fs.fstatSync(fd).mtimeMs; + const buf = Buffer.alloc(32); + const n = fs.readSync(fd, buf, 0, 32, 0); + const ownerStr = buf.slice(0, n).toString('utf-8').trim(); + if (ownerStr === '') { + // Owner created the file but hasn't written its PID yet. The + // wx open+write window is microseconds; give it the benefit + // of the doubt and treat as live. + isLive = true; + } else { + const owner = Number.parseInt(ownerStr, 10); + if (Number.isFinite(owner) && owner > 0) { + try { + process.kill(owner, 0); + isLive = true; + } catch (e) { + // ESRCH = process gone → treat as dead. EPERM = process exists + // but owned by another user (cross-user lock dir) → still alive, + // keep the slot. Anything else: be conservative, assume alive. + if (e && e.code === 'ESRCH') { + isLive = false; + } else { + isLive = true; + } + } + } + } + } catch { + /* unreadable — treat as dead */ + } finally { + try { + fs.closeSync(fd); + } catch { + /* already closed */ + } + } + // For slots younger than HOOK_LOCK_STALE_MS, PID-liveness wins — + // a slow-but-alive hook is never wrongly evicted. For older slots, + // age is the final arbiter as a defense against PID reuse on long- + // abandoned slots. 30s >> the 7s augment timeout, so a healthy run + // never crosses this threshold. + if (isLive && Date.now() - mtimeMs > HOOK_LOCK_STALE_MS) { + isLive = false; + } + if (isLive) break; // Try the next slot. + try { + fs.unlinkSync(slotPath); + } catch { + /* another hook beat us to it — retry will hit EEXIST */ + } + // Loop and retry this slot. + } + } + } + + return null; +} + +module.exports = { + HOOK_LOCK_SUBDIR, + HOOK_LOCK_MAX_INFLIGHT, + HOOK_LOCK_STALE_MS, + acquireHookSlot, +}; diff --git a/gitnexus-cursor-integration/hooks/hooks.json b/gitnexus-cursor-integration/hooks/hooks.json index ede0dfbf3..9ae542c14 100644 --- a/gitnexus-cursor-integration/hooks/hooks.json +++ b/gitnexus-cursor-integration/hooks/hooks.json @@ -1,11 +1,11 @@ { "version": 1, "hooks": { - "beforeShellExecution": [ + "postToolUse": [ { - "command": "./hooks/augment-shell.sh", - "timeout": 5, - "matcher": "\\brg\\b|\\bgrep\\b" + "matcher": "Shell|Read|Grep", + "command": "node ./hooks/gitnexus-hook.cjs", + "timeout": 10 } ] } diff --git a/gitnexus-shared/package.json b/gitnexus-shared/package.json index 7c1e6847a..0a5d7a2db 100644 --- a/gitnexus-shared/package.json +++ b/gitnexus-shared/package.json @@ -10,6 +10,10 @@ ".": { "types": "./dist/index.d.ts", "default": "./dist/index.js" + }, + "./test-helpers": { + "types": "./dist/test-helpers.d.ts", + "default": "./dist/test-helpers.js" } }, "scripts": { diff --git a/gitnexus-shared/src/index.ts b/gitnexus-shared/src/index.ts index faf136fe7..3c82658f1 100644 --- a/gitnexus-shared/src/index.ts +++ b/gitnexus-shared/src/index.ts @@ -143,6 +143,22 @@ export type { ScopeTree } from './scope-resolution/scope-tree.js'; export { buildPositionIndex } from './scope-resolution/position-index.js'; export type { PositionIndex } from './scope-resolution/position-index.js'; +// Resilient fetch primitives — bounded retries + per-process circuit breaker. +// Test-only helpers (`__resetBreakerRegistry__`, `classifyOutcome`) are +// reachable via the separate `gitnexus-shared/test-helpers` subpath; do +// NOT add them here. Production consumers must not call them. +export { withRetry, computeBackoffMs } from './integrations/retry.js'; +export type { RetryOptions, RetryDecision } from './integrations/retry.js'; +export { CircuitBreaker, CircuitOpenError, getBreaker } from './integrations/circuit-breaker.js'; +export type { CircuitBreakerOptions } from './integrations/circuit-breaker.js'; +export { + resilientFetch, + ResilientFetchExhaustedError, + RETRY_AFTER_CAP_MS, + parseRetryAfter, +} from './integrations/resilient-fetch.js'; +export type { ResilientFetchOptions } from './integrations/resilient-fetch.js'; + // Understand-Quickly registry integration (opt-in) export { UNDERSTAND_QUICKLY_DISPATCH_URL, diff --git a/gitnexus-shared/src/integrations/circuit-breaker.ts b/gitnexus-shared/src/integrations/circuit-breaker.ts new file mode 100644 index 000000000..29782a8fb --- /dev/null +++ b/gitnexus-shared/src/integrations/circuit-breaker.ts @@ -0,0 +1,273 @@ +/** + * Per-process circuit breaker. + * + * Closed -> Open transition fires after `failureThreshold` consecutive + * failures. While Open, `check` throws `CircuitOpenError` until + * `cooldownMs` has elapsed since the breaker tripped. The first call + * after the cooldown enters Half-Open and consumes the *probe permit*: + * a recorded success returns to Closed; a recorded failure flips back + * to Open with a fresh timestamp. + * + * Half-open admits exactly one in-flight probe at a time. Concurrent + * callers attempting `check()` while a probe is outstanding receive + * `CircuitOpenError` with `retryAfterMs = halfOpenRetryAfterMs` (default + * 1000ms; configurable). This prevents the recovery-time thundering + * herd that defeats the breaker's "fail fast" promise. + * + * Outcome reporting splits permit-release from state-resolution: + * - `recordSuccess` — releases the probe permit, resets the failure + * counter, transitions to Closed. Reserved for true 2xx/3xx outcomes. + * - `recordFailure` — releases the probe permit, increments the + * consecutive-failure counter, transitions to Open with a fresh + * `openedAt` (when called from Half-Open or when the threshold + * trips from Closed). + * - `recordNeutral` — releases the probe permit, BUT leaves state and + * counter untouched. Used for outcomes that are neither evidence of + * backend health nor evidence of backend failure (caller-driven + * cancellation, local timeout, terminal 4xx client errors). Critical + * design point: if `recordNeutral` did not release the permit, a + * single `TimeoutError` from per-attempt `AbortSignal.timeout` would + * route through `recordNeutral` and permanently park the breaker in + * half-open until process restart. Releasing the permit while leaving + * state half-open keeps the "neutral doesn't claim health" semantic + * without creating that wedge. + * + * Pairing invariant: every successful `check()` MUST be paired with + * exactly one `record*()` on every code path including throws. Direct + * consumers should wrap the protected operation in `try/finally`: + * + * breaker.check(); + * try { + * const result = await operation(); + * breaker.recordSuccess(); + * return result; + * } catch (err) { + * // classify err and call recordFailure / recordNeutral / etc. + * throw err; + * } + * + * `resilientFetch`'s catch-all on `fetchImpl` already satisfies this + * for that consumer. + * + * Atomicity model: the half-open gate relies on JavaScript event-loop + * single-threadedness within a synchronous `check()` body. There is no + * `await` inside `check()`; concurrent callers serialize on microtask + * order, and exactly one observes `probeInFlight === false`. Do not + * introduce `await` inside `check()` without revisiting the gate. If + * this code is ever ported to a runtime with shared-memory threads + * (Node `worker_threads` with `SharedArrayBuffer`, Web Workers with + * shared registries), the boolean must become an atomic CAS — Resilience4j + * and Hystrix use atomic permits *because* they run in JVM thread pools. + * + * Runtime-agnostic: depends only on a `now()` clock and standard JS — + * no Node-only imports. Tests inject `now` to advance the clock + * deterministically without `vi.useFakeTimers()`. + */ + +export class CircuitOpenError extends Error { + override readonly name = 'CircuitOpenError'; + /** Approximate wait time before the breaker may transition to Half-Open + * (or before the in-flight probe is expected to resolve). */ + readonly retryAfterMs: number; + + constructor(retryAfterMs: number, key?: string) { + super( + key + ? `Circuit '${key}' is open; retry in ${Math.ceil(retryAfterMs / 1000)}s` + : `Circuit is open; retry in ${Math.ceil(retryAfterMs / 1000)}s`, + ); + this.retryAfterMs = retryAfterMs; + } +} + +export interface CircuitBreakerOptions { + /** Consecutive failures required to trip Closed -> Open. */ + failureThreshold?: number; + /** Milliseconds Open before the next call may probe (Half-Open). */ + cooldownMs?: number; + /** + * Milliseconds to suggest in `CircuitOpenError.retryAfterMs` when the + * breaker is Half-Open with the probe permit consumed. Default 1000ms. + * Consumers with long-running protected ops (LLM streaming, large + * uploads) should raise this — the cooldown clock is no longer the + * right answer because cooldown has elapsed. Returning 0 invites + * retry storms; returning the full cooldown misleads about wait. + */ + halfOpenRetryAfterMs?: number; + /** Optional key for error messages and registry lookups. */ + key?: string; + /** Clock override — defaults to `Date.now`. Tests inject deterministic time. */ + now?: () => number; +} + +type State = 'closed' | 'open' | 'half-open'; + +export class CircuitBreaker { + private readonly failureThreshold: number; + private readonly cooldownMs: number; + private readonly halfOpenRetryAfterMs: number; + private readonly key: string | undefined; + private readonly now: () => number; + + private state: State = 'closed'; + private consecutiveFailures = 0; + private openedAt: number | null = null; + /** + * True between a successful `check()` and the next `record*()` call + * during Half-Open. Gates concurrent callers from stampeding a still- + * recovering dependency. Boolean rather than counter — single-permit + * is the conservative end of the Hystrix/Resilience4j spectrum. + */ + private probeInFlight = false; + + constructor(opts: CircuitBreakerOptions = {}) { + this.failureThreshold = opts.failureThreshold ?? 3; + this.cooldownMs = opts.cooldownMs ?? 30_000; + this.halfOpenRetryAfterMs = opts.halfOpenRetryAfterMs ?? 1_000; + this.key = opts.key; + this.now = opts.now ?? (() => Date.now()); + } + + /** + * Throw `CircuitOpenError` if the breaker won't admit this call. + * Otherwise consume the half-open probe permit (if applicable) and + * return so the caller can attempt the protected work. + * + * Three rejection paths: + * 1. Open and still in cooldown → throws with `retryAfterMs` = + * remaining cooldown. + * 2. Open with cooldown elapsed AND a probe is already in flight + * (race: another caller transitioned to half-open and grabbed + * the permit on a microtask before us) → throws with + * `halfOpenRetryAfterMs`. + * 3. Half-Open with probe in flight → throws with `halfOpenRetryAfterMs`. + * + * **Pairing invariant**: every successful return from `check()` MUST + * be paired with exactly one `recordSuccess` / `recordFailure` / + * `recordNeutral` on every code path including thrown exceptions. + * Failing to pair leaves the probe permit consumed forever and + * wedges the breaker. See file-header JSDoc for the canonical + * try/finally pattern. + */ + check(): void { + if (this.state === 'open' && this.openedAt !== null) { + const elapsed = this.now() - this.openedAt; + if (elapsed < this.cooldownMs) { + throw new CircuitOpenError(this.cooldownMs - elapsed, this.key); + } + // Cooldown elapsed — transition to Half-Open. The very next + // `probeInFlight` check below decides whether THIS caller gets + // the permit or hits the gate. + this.state = 'half-open'; + } + + if (this.state === 'half-open') { + if (this.probeInFlight) { + throw new CircuitOpenError(this.halfOpenRetryAfterMs, this.key); + } + this.probeInFlight = true; + } + // Closed state falls through silently. + } + + recordSuccess(): void { + this.probeInFlight = false; + this.consecutiveFailures = 0; + this.state = 'closed'; + this.openedAt = null; + } + + recordFailure(): void { + this.probeInFlight = false; + this.consecutiveFailures += 1; + if (this.state === 'half-open' || this.consecutiveFailures >= this.failureThreshold) { + this.state = 'open'; + this.openedAt = this.now(); + } + } + + /** + * Releases the probe permit BUT leaves state and counter untouched. + * Use when an attempt produced a response or error that should not + * influence breaker health in either direction — caller-driven aborts, + * local AbortSignal timeouts, terminal 4xx client errors. + * + * Why permit-release-without-state-resolution: if `recordNeutral` did + * not clear `probeInFlight`, a single `TimeoutError` from per-attempt + * `AbortSignal.timeout` (which routes through neutral classification) + * would permanently park the breaker in half-open. Since timeouts are + * an *expected* outcome under flaky-dependency conditions, the cited + * "per-attempt timeout bounds the stuck state" mitigation would itself + * be the trigger for a permanent wedge. Releasing the permit closes + * that loop while keeping the "neutral doesn't claim dependency + * health" semantic. + * + * Calling `recordSuccess` for these would erase legitimate prior + * failure signal; calling `recordFailure` would trip the breaker for + * outcomes the backend isn't responsible for. + */ + recordNeutral(): void { + this.probeInFlight = false; + // State and consecutiveFailures are preserved by design. + } + + /** + * Pure read — no state mutation, no permit accounting. Returns the + * *would-be* state at the current instant: 'half-open' if the breaker + * is open with cooldown elapsed (regardless of whether a probe is in + * flight), 'open' if open and still in cooldown, 'closed' otherwise. + * + * Inspection-only; safe to call from tests without consuming a probe + * permit. The implicit Open -> Half-Open transition that mutates + * `state` lives in `check()` only. + */ + getState(): State { + if (this.state === 'open' && this.openedAt !== null) { + const elapsed = this.now() - this.openedAt; + if (elapsed >= this.cooldownMs) return 'half-open'; + } + return this.state; + } + getConsecutiveFailures(): number { + return this.consecutiveFailures; + } + /** Inspection-only test accessor for the half-open probe permit. */ + isProbeInFlight(): boolean { + return this.probeInFlight; + } + /** Timestamp (ms since epoch) when the breaker last transitioned to Open, + * or `null` if it's currently Closed. Useful for computing remaining + * cooldown without consuming a probe permit via `check()`. */ + getOpenedAt(): number | null { + return this.openedAt; + } + /** Configured cooldown duration in milliseconds. */ + getCooldownMs(): number { + return this.cooldownMs; + } +} + +// ─── Per-process registry ──────────────────────────────────────────── +// +// Single shared map keyed on caller-chosen strings. Used by +// `resilient-fetch.ts` so multiple call sites targeting the same logical +// endpoint share breaker state. Per-process only — not persisted. + +const registry = new Map(); + +export function getBreaker(key: string, opts?: CircuitBreakerOptions): CircuitBreaker { + let breaker = registry.get(key); + if (!breaker) { + breaker = new CircuitBreaker({ ...opts, key }); + registry.set(key, breaker); + } + return breaker; +} + +/** + * Test-only: clear all registered breakers. Tests must call this in + * `beforeEach` to prevent breaker state from leaking across test cases. + */ +export function __resetBreakerRegistry__(): void { + registry.clear(); +} diff --git a/gitnexus-shared/src/integrations/resilient-fetch.ts b/gitnexus-shared/src/integrations/resilient-fetch.ts new file mode 100644 index 000000000..c91b9db3a --- /dev/null +++ b/gitnexus-shared/src/integrations/resilient-fetch.ts @@ -0,0 +1,279 @@ +/** + * `resilientFetch` — fetch wrapped in retry + circuit breaker, with + * GitHub-flavoured retry classification baked in (Retry-After parsing, + * 401/403/404/422 treated as terminal client errors). + * + * Designed for the `gitnexus publish` GitHub `repository_dispatch` + * call, but the classification rules apply to any GitHub REST endpoint. + * Runtime-agnostic — no Node-only imports. + */ + +import { + CircuitBreaker, + CircuitOpenError, + getBreaker, + type CircuitBreakerOptions, +} from './circuit-breaker.js'; +import { computeBackoffMs, type RetryOptions } from './retry.js'; + +export { CircuitOpenError }; + +export interface ResilientFetchOptions { + /** Optional fetch implementation override. Defaults to `globalThis.fetch`. */ + fetchImpl?: typeof fetch; + /** + * Logical key for the breaker. Defaults to `` of the + * request URL — call sites targeting the same endpoint share breaker + * state regardless of query-string differences. + */ + breakerKey?: string; + /** Per-call breaker override. Used for tests and one-off configuration. */ + breaker?: CircuitBreaker; + /** Tuning knobs for the breaker registered under `breakerKey`. */ + breakerOptions?: CircuitBreakerOptions; + /** Tuning knobs for the retry helper. */ + retry?: Partial> & { + sleep?: RetryOptions['sleep']; + random?: RetryOptions['random']; + }; + /** Clock override propagated into Retry-After HTTP-date math and breaker. */ + now?: () => number; +} + +/** Cap on any single Retry-After wait — protects CLI from a buggy registry. */ +export const RETRY_AFTER_CAP_MS = 30_000; + +const DEFAULT_RETRY = { + maxAttempts: 3, + baseDelayMs: 500, + capDelayMs: 5_000, +}; + +/** + * Parse a `Retry-After` header value into milliseconds. + * Accepts either a delta-seconds integer (`"30"`) or an HTTP-date. + * Returns null on parse failure or negative deltas. + */ +export function parseRetryAfter(value: string | null, now: () => number = Date.now): number | null { + if (!value) return null; + const trimmed = value.trim(); + if (trimmed === '') return null; + + if (/^[0-9]+$/.test(trimmed)) { + const seconds = parseInt(trimmed, 10); + if (Number.isNaN(seconds) || seconds < 0) return null; + return seconds * 1000; + } + + const target = Date.parse(trimmed); + if (Number.isNaN(target)) return null; + const delta = target - now(); + return delta >= 0 ? delta : 0; +} + +/** Internal: outcome classification used by the resilientFetch loop. */ +type Outcome = + | { kind: 'success'; resp: Response } + | { kind: 'terminal-client'; resp: Response } // 4xx other than 429: no retry, breaker neutral + | { kind: 'retryable-status'; resp: Response; afterMs: number | undefined } // 5xx, 429 + | { kind: 'terminal-network'; err: unknown } // TimeoutError or AbortError: no retry, breaker neutral + | { kind: 'retryable-network'; err: unknown }; // DNS, ECONNRESET, etc. + +/** Exported for unit tests. */ +export function classifyOutcome( + result: { kind: 'error'; err: unknown } | { kind: 'response'; resp: Response }, + now: () => number, +): Outcome { + if (result.kind === 'error') { + // Both timer-fired aborts (`AbortSignal.timeout()` → `TimeoutError`) + // and caller-driven aborts (`AbortController.abort()` → `AbortError`) + // are terminal: retrying against an already-aborted signal would + // fail again immediately, and neither outcome reflects backend + // health. They route through the breaker's neutral path. + if ( + result.err instanceof DOMException && + (result.err.name === 'TimeoutError' || result.err.name === 'AbortError') + ) { + return { kind: 'terminal-network', err: result.err }; + } + return { kind: 'retryable-network', err: result.err }; + } + const resp = result.resp; + if (resp.status >= 200 && resp.status < 400) return { kind: 'success', resp }; + if (resp.status === 429) { + // `resp.headers` is always present on a real `Response`, but tests + // sometimes stub `fetch` with a plain `{ ok, status }` object. Be + // defensive — a missing `Retry-After` falls through to exponential + // backoff, which is the correct behaviour anyway. + const retryAfterHeader = + typeof resp.headers?.get === 'function' ? resp.headers.get('Retry-After') : null; + const parsed = parseRetryAfter(retryAfterHeader, now); + return { + kind: 'retryable-status', + resp, + afterMs: parsed !== null ? Math.min(parsed, RETRY_AFTER_CAP_MS) : undefined, + }; + } + if (resp.status >= 500) return { kind: 'retryable-status', resp, afterMs: undefined }; + return { kind: 'terminal-client', resp }; +} + +const defaultSleep = (ms: number): Promise => + new Promise((resolve) => setTimeout(resolve, ms)); + +function defaultBreakerKey(input: string | URL): string { + try { + const url = typeof input === 'string' ? new URL(input) : input; + return `${url.host}${url.pathname}`; + } catch { + return String(input); + } +} + +/** Final error thrown when retries are exhausted on a 5xx / 429. */ +export class ResilientFetchExhaustedError extends Error { + override readonly name = 'ResilientFetchExhaustedError'; + constructor(public readonly response: Response) { + super(`Request failed after retries (HTTP ${response.status})`); + } +} + +/** + * Wrap `fetch` with bounded retries and a per-process circuit breaker. + * + * Semantics: + * - 5xx and 429 responses are retried; 429 honors `Retry-After` (capped). + * - Network throws are retried unless they are `TimeoutError` DOMExceptions. + * - Timeouts and 4xx (other than 429) are returned/thrown without retry + * AND without incrementing the breaker — they reflect caller config + * or local network state, not registry health. + * - Each `fetch` call carries the caller-supplied `signal` (e.g. an + * `AbortSignal.timeout()`) — that timeout bounds each individual + * attempt, not the whole retry sequence. + * - When the breaker is open, throws `CircuitOpenError` synchronously + * without invoking `fetch`. + * - When retries are exhausted on a 5xx / 429, throws + * `ResilientFetchExhaustedError` carrying the last response. + * + * Cumulative wall-clock budget: + * maxAttempts × (per-attempt-timeout + capDelayMs) + * With defaults (3, 500ms base, 5000ms cap) and a typical 15s per-attempt + * timeout from the caller's signal, worst case is ~3 × (15s + 5s) = 60s. + * Callers that want a tighter total bound should reduce `maxAttempts` or + * wrap `resilientFetch` in their own outer `AbortSignal.timeout()`. + */ +export async function resilientFetch( + input: string | URL, + init: RequestInit | undefined, + opts: ResilientFetchOptions = {}, +): Promise { + const fetchImpl = opts.fetchImpl ?? globalThis.fetch; + const now = opts.now ?? (() => Date.now()); + const breaker = + opts.breaker ?? getBreaker(opts.breakerKey ?? defaultBreakerKey(input), opts.breakerOptions); + + const retryConfig = { + maxAttempts: opts.retry?.maxAttempts ?? DEFAULT_RETRY.maxAttempts, + baseDelayMs: opts.retry?.baseDelayMs ?? DEFAULT_RETRY.baseDelayMs, + capDelayMs: opts.retry?.capDelayMs ?? DEFAULT_RETRY.capDelayMs, + }; + const sleep = opts.retry?.sleep ?? defaultSleep; + const random = opts.retry?.random ?? Math.random; + + // Fail fast on an open breaker, before invoking fetch. + breaker.check(); + + for (let attempt = 0; attempt < retryConfig.maxAttempts; attempt++) { + let result: { kind: 'error'; err: unknown } | { kind: 'response'; resp: Response }; + try { + // CodeQL js/server-side-request-forgery — flagged because `input` + // is caller-supplied. Suppressed: every concrete caller passes + // either a hardcoded URL constant (UNDERSTAND_QUICKLY_DISPATCH_URL, + // OpenRouter base URL) or a value derived from configuration + // (env vars, saved settings, the local backend URL). User-input + // request fields (e.g. PR title, repo name) never flow into + // `input`. Validating URL shape here would push false-positive + // rejection onto every caller — wrong layer for the check. + // lgtm[js/server-side-request-forgery] + // codeql[js/server-side-request-forgery] + const resp = await fetchImpl(input, init); + result = { kind: 'response', resp }; + } catch (err) { + result = { kind: 'error', err }; + } + + const outcome = classifyOutcome(result, now); + + switch (outcome.kind) { + case 'success': + breaker.recordSuccess(); + return outcome.resp; + + case 'terminal-client': + // 4xx: do not count as breaker failure (the server is healthy + // and rejecting our request — auth, scope, or routing). But + // also do NOT call recordSuccess: a 401 sandwiched between + // 5xx responses would otherwise erase the running outage + // signal. The breaker's neutral path leaves state untouched. + breaker.recordNeutral(); + return outcome.resp; + + case 'terminal-network': + // Either `AbortSignal.timeout()` fired locally OR an external + // caller cancelled the request via AbortController. The server + // never had a chance to answer; this reflects the user's + // network or an explicit cancel, not registry health. Don't + // punish the breaker AND don't reset its outage signal. + breaker.recordNeutral(); + throw outcome.err; + + case 'retryable-status': + if (attempt + 1 >= retryConfig.maxAttempts) { + breaker.recordFailure(); + throw new ResilientFetchExhaustedError(outcome.resp); + } + await sleep( + computeBackoffMs( + attempt, + retryConfig.baseDelayMs, + retryConfig.capDelayMs, + outcome.afterMs, + random, + ), + ); + break; + + case 'retryable-network': + if (attempt + 1 >= retryConfig.maxAttempts) { + breaker.recordFailure(); + throw outcome.err; + } + await sleep( + computeBackoffMs( + attempt, + retryConfig.baseDelayMs, + retryConfig.capDelayMs, + undefined, + random, + ), + ); + break; + + default: { + // Exhaustiveness guard. If a sixth `Outcome` kind is added in + // future, TypeScript will refuse to assign it to `never` and + // this line forces the maintainer to add an explicit arm + // rather than silently fall through to retry/no-retry behaviour. + const _exhaustive: never = outcome; + throw new Error(`resilientFetch: unhandled outcome ${JSON.stringify(_exhaustive)}`); + } + } + } + + // Unreachable: every iteration of the loop either returns (success + // / terminal-client) or throws (terminal-network / retry exhaustion). + // The throw is here purely so TypeScript's control-flow analysis sees + // the function never falls off the end without producing `Promise`. + /* c8 ignore next 2 */ + throw new Error('resilientFetch: retry loop terminated unexpectedly'); +} diff --git a/gitnexus-shared/src/integrations/retry.ts b/gitnexus-shared/src/integrations/retry.ts new file mode 100644 index 000000000..774ca2542 --- /dev/null +++ b/gitnexus-shared/src/integrations/retry.ts @@ -0,0 +1,105 @@ +/** + * Bounded retry helper with full-jitter exponential backoff. + * + * Runtime-agnostic: depends only on `setTimeout`, `Math.random`, and the + * Promise machinery — no Node-only imports. Safe to consume from CLI, + * server, or browser callers. + * + * Pattern reference: gitnexus/src/core/embeddings/http-client.ts. This + * helper is the upgraded form: classification is caller-supplied (so + * 4xx-vs-5xx-vs-timeout decisions live with the protocol that knows + * them), backoff is exponential with full jitter, and an optional + * `afterMs` lets callers honor `Retry-After` headers. + */ + +export interface RetryOptions { + /** Initial delay before the first retry attempt, in milliseconds. */ + baseDelayMs: number; + /** Upper bound on any single delay, in milliseconds. */ + capDelayMs: number; + /** Total attempts including the first call. Must be >= 1. */ + maxAttempts: number; + /** + * Decide whether to retry after a thrown error. + * Return `{retry:false}` to terminate immediately and rethrow. + * Return `{retry:true}` to retry with exponential-backoff jitter. + * Return `{retry:true, afterMs}` to wait at least `afterMs` (still + * subject to `capDelayMs`) — used by callers parsing `Retry-After`. + */ + isRetryable: (err: unknown, attempt: number) => RetryDecision; + /** Sleep override — defaults to `setTimeout`. Tests inject fake timers. */ + sleep?: (ms: number) => Promise; + /** Random override — defaults to `Math.random`. Tests inject seeded values. */ + random?: () => number; +} + +export type RetryDecision = { retry: false } | { retry: true; afterMs?: number }; + +const defaultSleep = (ms: number): Promise => + new Promise((resolve) => setTimeout(resolve, ms)); + +/** + * Compute the delay before the next retry attempt. + * + * - When the caller specifies `afterMs` (e.g., from `Retry-After`), use + * `min(afterMs, capDelayMs)` so a misbehaving server can't pin the + * client for an arbitrarily long wait. + * - Otherwise compute full-jitter exponential backoff: + * `random() * min(cap, base * 2^attempt)`. Full jitter (rather than + * "equal jitter") avoids retry-storm thundering herd, per AWS + * guidance on backoff strategies. + */ +export function computeBackoffMs( + attempt: number, + baseDelayMs: number, + capDelayMs: number, + afterMs: number | undefined, + random: () => number, +): number { + if (afterMs !== undefined) { + return Math.min(Math.max(0, afterMs), capDelayMs); + } + const exponential = baseDelayMs * Math.pow(2, attempt); + const upper = Math.min(capDelayMs, exponential); + return Math.floor(random() * upper); +} + +/** + * Execute `fn` with bounded retries. + * + * The classification of "retryable" is the caller's responsibility — see + * `resilient-fetch.ts` for the GitHub-dispatch-specific rules. This + * helper is the mechanical retry loop only. + */ +export async function withRetry( + fn: (attempt: number) => Promise, + opts: RetryOptions, +): Promise { + if (opts.maxAttempts < 1) { + throw new Error(`withRetry: maxAttempts must be >= 1, got ${opts.maxAttempts}`); + } + const sleep = opts.sleep ?? defaultSleep; + const random = opts.random ?? Math.random; + + let lastError: unknown; + for (let attempt = 0; attempt < opts.maxAttempts; attempt++) { + try { + return await fn(attempt); + } catch (err) { + lastError = err; + const decision = opts.isRetryable(err, attempt); + if (!decision.retry) throw err; + // Don't sleep after the final attempt. + if (attempt + 1 >= opts.maxAttempts) break; + const delayMs = computeBackoffMs( + attempt, + opts.baseDelayMs, + opts.capDelayMs, + decision.afterMs, + random, + ); + if (delayMs > 0) await sleep(delayMs); + } + } + throw lastError; +} diff --git a/gitnexus-shared/src/scope-resolution/finalize-algorithm.ts b/gitnexus-shared/src/scope-resolution/finalize-algorithm.ts index a94012a0b..f5d3dd0bf 100644 --- a/gitnexus-shared/src/scope-resolution/finalize-algorithm.ts +++ b/gitnexus-shared/src/scope-resolution/finalize-algorithm.ts @@ -833,7 +833,16 @@ function expandWildcard( if (target === undefined) return [edge]; const names = hooks.expandsWildcardTo(edge.targetModuleScope, workspace); - if (names.length === 0) return []; + if (names.length === 0) { + // Resolved wildcard with zero propagating names is still a real file- + // level dependency (e.g. a C++ header that only declares classes — + // `#include` is a valid IMPORTS edge, but unqualified-binding names + // are correctly empty since class methods require `Class::method`). + // Preserve the original wildcard edge so the file→file IMPORTS edge + // survives; downstream binding materialization sees no propagated + // names because the edge has no `targetExportedName`/`localName`. + return [edge]; + } const expanded: ImportEdge[] = []; for (const name of names) { diff --git a/gitnexus-shared/src/scope-resolution/method-dispatch-index.ts b/gitnexus-shared/src/scope-resolution/method-dispatch-index.ts index d09e8fa89..dcaa45055 100644 --- a/gitnexus-shared/src/scope-resolution/method-dispatch-index.ts +++ b/gitnexus-shared/src/scope-resolution/method-dispatch-index.ts @@ -40,11 +40,27 @@ export interface MethodDispatchIndex { readonly mroByOwnerDefId: ReadonlyMap; /** Interfaces / traits → classes that implement them. */ readonly implsByInterfaceDefId: ReadonlyMap; + /** + * Optional parallel MRO view that EXCLUDES mixin-like augmentation + * (e.g., PHP traits). Populated only when the input supplies + * `computeExtendsOnlyMro`. Used by the super-branch dispatch in + * `receiver-bound-calls` so that `parent::method()` walks the + * inheritance chain only, not the trait-augmented one. Undefined for + * languages without mixin-like semantics — callers should fall back + * to `mroFor` when this is missing. + */ + readonly extendsOnlyMroByOwnerDefId?: ReadonlyMap; /** `mroByOwnerDefId.get`, with an empty frozen array on miss. */ mroFor(ownerDefId: DefId): readonly DefId[]; /** `implsByInterfaceDefId.get`, with an empty frozen array on miss. */ implementorsOf(interfaceDefId: DefId): readonly DefId[]; + /** + * `extendsOnlyMroByOwnerDefId.get`, with an empty frozen array on miss. + * Undefined when `extendsOnlyMroByOwnerDefId` was not populated; callers + * should treat this as equivalent to `mroFor` for non-mixin languages. + */ + readonly extendsOnlyMroFor?: (ownerDefId: DefId) => readonly DefId[]; } export interface MethodDispatchInput { @@ -81,12 +97,25 @@ export interface MethodDispatchInput { * write-wins policy and fires at most once per unique owner. */ readonly implementsOf: (ownerDefId: DefId) => readonly DefId[]; + /** + * Optional: return the EXTENDS-only ancestor chain for `ownerDefId`, + * excluding the owner itself AND any mixin-like augmentation (e.g., + * PHP traits). Languages without mixin semantics leave this undefined + * and the index's `extendsOnlyMroByOwnerDefId` stays unpopulated. + * + * Same contract as `computeMro`: pure, deterministic, `[]` on no parents. + * Called at most once per unique owner (first-write-wins). + */ + readonly computeExtendsOnlyMro?: (ownerDefId: DefId) => readonly DefId[]; } // ─── Builder ──────────────────────────────────────────────────────────────── export function buildMethodDispatchIndex(input: MethodDispatchInput): MethodDispatchIndex { const mroByOwnerDefId = new Map(); + const extendsOnlyByOwnerDefId = input.computeExtendsOnlyMro + ? new Map() + : undefined; const implsBuilding = new Map(); const implsSeen = new Map>(); @@ -97,6 +126,14 @@ export function buildMethodDispatchIndex(input: MethodDispatchInput): MethodDisp const chain = input.computeMro(ownerId); mroByOwnerDefId.set(ownerId, Object.freeze(chain.slice())); } + if ( + input.computeExtendsOnlyMro !== undefined && + extendsOnlyByOwnerDefId !== undefined && + !extendsOnlyByOwnerDefId.has(ownerId) + ) { + const extOnly = input.computeExtendsOnlyMro(ownerId); + extendsOnlyByOwnerDefId.set(ownerId, Object.freeze(extOnly.slice())); + } for (const ifaceId of input.implementsOf(ownerId)) { let seen = implsSeen.get(ifaceId); @@ -121,7 +158,7 @@ export function buildMethodDispatchIndex(input: MethodDispatchInput): MethodDisp implsByInterfaceDefId.set(ifaceId, Object.freeze(owners.slice())); } - return wrapIndex(mroByOwnerDefId, implsByInterfaceDefId); + return wrapIndex(mroByOwnerDefId, implsByInterfaceDefId, extendsOnlyByOwnerDefId); } // ─── Internal ─────────────────────────────────────────────────────────────── @@ -131,8 +168,9 @@ const EMPTY: readonly DefId[] = Object.freeze([]); function wrapIndex( mroByOwnerDefId: Map, implsByInterfaceDefId: Map, + extendsOnlyMroByOwnerDefId: Map | undefined, ): MethodDispatchIndex { - return { + const base: MethodDispatchIndex = { mroByOwnerDefId, implsByInterfaceDefId, mroFor(ownerDefId: DefId): readonly DefId[] { @@ -142,4 +180,14 @@ function wrapIndex( return implsByInterfaceDefId.get(interfaceDefId) ?? EMPTY; }, }; + if (extendsOnlyMroByOwnerDefId !== undefined) { + return { + ...base, + extendsOnlyMroByOwnerDefId, + extendsOnlyMroFor(ownerDefId: DefId): readonly DefId[] { + return extendsOnlyMroByOwnerDefId.get(ownerDefId) ?? EMPTY; + }, + }; + } + return base; } diff --git a/gitnexus-shared/src/scope-resolution/registries/lookup-core.ts b/gitnexus-shared/src/scope-resolution/registries/lookup-core.ts index a18ad4930..fff3e7adb 100644 --- a/gitnexus-shared/src/scope-resolution/registries/lookup-core.ts +++ b/gitnexus-shared/src/scope-resolution/registries/lookup-core.ts @@ -423,13 +423,30 @@ function applyArityFilter( } let anyCompatible = false; + let anyUnknown = false; for (const state of perCandidate.values()) { const verdict = arityFn(callsite, state.def); state.signals.arityVerdict = verdict; if (verdict === 'compatible') anyCompatible = true; + else if (verdict === 'unknown') anyUnknown = true; } - if (!anyCompatible) return; + // When ALL candidates are 'incompatible' (none compatible, none unknown), + // the call is genuinely arity-broken — drop every candidate so the + // registry returns no resolution. This matches the PHP variadic case + // f(int $req, ...$rest) called with zero args: every candidate definitively + // rejects, and emitting an edge to a definitively-rejected callable is + // a false positive. When some candidates are 'unknown' (missing metadata), + // keep the set so downstream evidence can break the tie — that's the + // original safety-fallback behavior. + if (!anyCompatible) { + if (!anyUnknown) { + for (const defId of perCandidate.keys()) { + perCandidate.delete(defId); + } + } + return; + } // Filter: when at least one compatible candidate exists, drop incompatibles. for (const [defId, state] of perCandidate) { diff --git a/gitnexus-shared/src/scope-resolution/symbol-definition.ts b/gitnexus-shared/src/scope-resolution/symbol-definition.ts index d07dbf38b..7f9840f5c 100644 --- a/gitnexus-shared/src/scope-resolution/symbol-definition.ts +++ b/gitnexus-shared/src/scope-resolution/symbol-definition.ts @@ -30,6 +30,8 @@ export interface SymbolDefinition { returnType?: string; /** Declared type for non-callable symbols — fields/properties (e.g. 'Address', 'List') */ declaredType?: string; + /** Generic/template specialization arguments for class-like symbols (e.g. ['User'], ['T*']). */ + templateArguments?: string[]; /** Links Method/Constructor/Property to owning Class/Struct/Trait nodeId */ ownerId?: string; } diff --git a/gitnexus-shared/src/test-helpers.ts b/gitnexus-shared/src/test-helpers.ts new file mode 100644 index 000000000..a92441878 --- /dev/null +++ b/gitnexus-shared/src/test-helpers.ts @@ -0,0 +1,13 @@ +/** + * Test-only helpers. + * + * Symbols here are reachable from `gitnexus-shared/test-helpers` so test + * suites can reset shared registries or exercise internal classifiers, + * but they are deliberately NOT re-exported from the main `gitnexus-shared` + * barrel. Production consumers should never import this module — calling + * `__resetBreakerRegistry__()` from a tool implementation would silently + * nuke every circuit breaker process-wide. + */ + +export { __resetBreakerRegistry__ } from './integrations/circuit-breaker.js'; +export { classifyOutcome } from './integrations/resilient-fetch.js'; diff --git a/gitnexus-web/package-lock.json b/gitnexus-web/package-lock.json index 7fcc0d299..cf69e1083 100644 --- a/gitnexus-web/package-lock.json +++ b/gitnexus-web/package-lock.json @@ -8,9 +8,9 @@ "name": "gitnexus", "version": "0.0.0", "dependencies": { - "@langchain/anthropic": "^1.3.28", + "@langchain/anthropic": "^1.3.29", "@langchain/core": "^1.1.44", - "@langchain/google-genai": "^2.1.28", + "@langchain/google-genai": "^2.1.30", "@langchain/langgraph": "^1.2.9", "@langchain/ollama": "^1.2.6", "@langchain/openai": "^1.4.5", @@ -26,10 +26,10 @@ "graphology-layout-forceatlas2": "^0.10.1", "graphology-layout-noverlap": "^0.4.2", "graphology-utils": "^2.3.0", - "langchain": "^1.3.4", + "langchain": "^1.3.5", "lru-cache": "^11.2.4", - "lucide-react": "^1.11.0", - "mermaid": "^11.14.0", + "lucide-react": "^1.14.0", + "mermaid": "^11.15.0", "mnemonist": "^0.39.0", "pandemonium": "^2.4.0", "react": "^19.2.5", @@ -49,7 +49,7 @@ "@testing-library/jest-dom": "^6.9.1", "@testing-library/react": "^16.3.2", "@testing-library/user-event": "^14.6.1", - "@types/dompurify": "^3.0.5", + "@types/dompurify": "^3.2.0", "@types/node": "^25.6.0", "@types/react": "^19.2.14", "@types/react-dom": "^19.2.3", @@ -60,7 +60,7 @@ "jsdom": "^29.1.1", "tree-sitter-wasms": "^0.1.13", "typescript": "^5.4.5", - "vite": "^8.0.10", + "vite": "^8.0.11", "vitest": "^4.1.5", "wait-on": "^9.0.5" }, @@ -95,9 +95,9 @@ } }, "node_modules/@anthropic-ai/sdk": { - "version": "0.90.0", - "resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.90.0.tgz", - "integrity": "sha512-MzZtPabJF1b0FTDl6Z6H5ljphPwACLGP13lu8MTiB8jXaW/YXlpOp+Po2cVou3MPM5+f5toyLnul9whKCy7fBg==", + "version": "0.91.1", + "resolved": "https://registry.npmjs.org/@anthropic-ai/sdk/-/sdk-0.91.1.tgz", + "integrity": "sha512-LAmu761tSN9r66ixvmciswUj/ZC+1Q4iAfpedTfSVLeswRwnY3n2Nb6Tsk+cLPP28aLOPWeMgIuTuCcMC6W/iw==", "license": "MIT", "dependencies": { "json-schema-to-ts": "^3.1.1" @@ -528,41 +528,10 @@ "integrity": "sha512-gAmrUZSGtKc3AiBL71iNWxDsyUC5uMaKKGdvzYsBoTW/xi42JQHl7eKV2OYzCUqvc+D2RCcf7EXY2iCyFIk6og==", "license": "MIT" }, - "node_modules/@chevrotain/cst-dts-gen": { - "version": "12.0.0", - "resolved": "https://registry.npmjs.org/@chevrotain/cst-dts-gen/-/cst-dts-gen-12.0.0.tgz", - "integrity": "sha512-fSL4KXjTl7cDgf0B5Rip9Q05BOrYvkJV/RrBTE/bKDN096E4hN/ySpcBK5B24T76dlQ2i32Zc3PAE27jFnFrKg==", - "license": "Apache-2.0", - "dependencies": { - "@chevrotain/gast": "12.0.0", - "@chevrotain/types": "12.0.0" - } - }, - "node_modules/@chevrotain/gast": { - "version": "12.0.0", - "resolved": "https://registry.npmjs.org/@chevrotain/gast/-/gast-12.0.0.tgz", - "integrity": "sha512-1ne/m3XsIT8aEdrvT33so0GUC+wkctpUPK6zU9IlOyJLUbR0rg4G7ZiApiJbggpgPir9ERy3FRjT6T7lpgetnQ==", - "license": "Apache-2.0", - "dependencies": { - "@chevrotain/types": "12.0.0" - } - }, - "node_modules/@chevrotain/regexp-to-ast": { - "version": "12.0.0", - "resolved": "https://registry.npmjs.org/@chevrotain/regexp-to-ast/-/regexp-to-ast-12.0.0.tgz", - "integrity": "sha512-p+EW9MaJwgaHguhoqwOtx/FwuGr+DnNn857sXWOi/mClXIkPGl3rn7hGNWvo31HA3vyeQxjqe+H36yZJwYU8cA==", - "license": "Apache-2.0" - }, "node_modules/@chevrotain/types": { - "version": "12.0.0", - "resolved": "https://registry.npmjs.org/@chevrotain/types/-/types-12.0.0.tgz", - "integrity": "sha512-S+04vjFQKeuYw0/eW3U52LkAHQsB1ASxsPGsLPUyQgrZ2iNNibQrsidruDzjEX2JYfespXMG0eZmXlhA6z7nWA==", - "license": "Apache-2.0" - }, - "node_modules/@chevrotain/utils": { - "version": "12.0.0", - "resolved": "https://registry.npmjs.org/@chevrotain/utils/-/utils-12.0.0.tgz", - "integrity": "sha512-lB59uJoaGIfOOL9knQqQRfhl9g7x8/wqFkp13zTdkRu1huG9kg6IJs1O8hqj9rs6h7orGxHJUKb+mX3rPbWGhA==", + "version": "11.1.2", + "resolved": "https://registry.npmjs.org/@chevrotain/types/-/types-11.1.2.tgz", + "integrity": "sha512-U+HFai5+zmJCkK86QsaJtoITlboZHBqrVketcO2ROv865xfCMSFpELQoz1GkX5GzME8pTa+3kbKrZHQtI0gdbw==", "license": "Apache-2.0" }, "node_modules/@cspotcode/source-map-support": { @@ -1396,25 +1365,25 @@ } }, "node_modules/@langchain/anthropic": { - "version": "1.3.28", - "resolved": "https://registry.npmjs.org/@langchain/anthropic/-/anthropic-1.3.28.tgz", - "integrity": "sha512-gOF8oXJL8xDdYes2KXNI9vFm/9TldBBBHOjuCdt27kganVaQKzLvTw5kV6R4mjbnFagV5CWteNH7APLZYCpdwg==", + "version": "1.3.29", + "resolved": "https://registry.npmjs.org/@langchain/anthropic/-/anthropic-1.3.29.tgz", + "integrity": "sha512-ep1qBIcV07bajsg3fDqMd39rYwoRLOEK/6lk+MCxlm1YB5SRoKKJAZANrblQ/4RYhZJnxf95c6BSQu8VoNbVAQ==", "license": "MIT", "dependencies": { - "@anthropic-ai/sdk": "^0.90.0", + "@anthropic-ai/sdk": "^0.91.1", "zod": "^3.25.76 || ^4" }, "engines": { "node": ">=20" }, "peerDependencies": { - "@langchain/core": "^1.1.42" + "@langchain/core": "^1.1.45" } }, "node_modules/@langchain/core": { - "version": "1.1.44", - "resolved": "https://registry.npmjs.org/@langchain/core/-/core-1.1.44.tgz", - "integrity": "sha512-RePW1IjGCHr9ua2vcby3aE8mOOz3EnwDZxMEGbNDT91kf14eqkJqxDXvaZFviGdcN9DTrxM5RPQNAHmwSm4tbg==", + "version": "1.1.45", + "resolved": "https://registry.npmjs.org/@langchain/core/-/core-1.1.45.tgz", + "integrity": "sha512-Y/wvuglLTMKJahkl4QD9dBIdF/z/CxZJWdTfHJF/q2jtlJtoFf6Mb5JpGxZfsi3mBY6NSG941FSLTcqhCKrhBA==", "license": "MIT", "dependencies": { "@cfworker/json-schema": "^4.0.2", @@ -1433,32 +1402,18 @@ } }, "node_modules/@langchain/google-genai": { - "version": "2.1.28", - "resolved": "https://registry.npmjs.org/@langchain/google-genai/-/google-genai-2.1.28.tgz", - "integrity": "sha512-iTzNYWST8hTRqOXZdme18tq5GnCUwtrrJECE51ZCjg6Vg0mPsV44amdC+/bc+UK0+uphKWESGWs277aAyM2MlA==", + "version": "2.1.30", + "resolved": "https://registry.npmjs.org/@langchain/google-genai/-/google-genai-2.1.30.tgz", + "integrity": "sha512-0wKgy1NvV89fw5MwYiOOhh18SnUEH20z6MZrPV6Tj2hMAA3jAHVSLlIcCQ2mDRJo2r1aHLV8MDXhzkvD1tEHoQ==", "license": "MIT", "dependencies": { - "@google/generative-ai": "^0.24.0", - "uuid": "^11.1.0" + "@google/generative-ai": "^0.24.0" }, "engines": { "node": ">=20" }, "peerDependencies": { - "@langchain/core": "^1.1.41" - } - }, - "node_modules/@langchain/google-genai/node_modules/uuid": { - "version": "11.1.0", - "resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.0.tgz", - "integrity": "sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A==", - "funding": [ - "https://github.com/sponsors/broofa", - "https://github.com/sponsors/ctavan" - ], - "license": "MIT", - "bin": { - "uuid": "dist/esm/bin/uuid" + "@langchain/core": "^1.1.43" } }, "node_modules/@langchain/langgraph": { @@ -1679,12 +1634,12 @@ } }, "node_modules/@mermaid-js/parser": { - "version": "1.1.0", - "resolved": "https://registry.npmjs.org/@mermaid-js/parser/-/parser-1.1.0.tgz", - "integrity": "sha512-gxK9ZX2+Fex5zu8LhRQoMeMPEHbc73UKZ0FQ54YrQtUxE1VVhMwzeNtKRPAu5aXks4FasbMe4xB4bWrmq6Jlxw==", + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/@mermaid-js/parser/-/parser-1.1.1.tgz", + "integrity": "sha512-VuHdsYMK1bT6X2JbcAaWAhugTRvRBRyuZgd+c22swUeI9g/ntaxF7CY7dYarhZovofCbUNO0G7JesfmNtjYOCw==", "license": "MIT", "dependencies": { - "langium": "^4.0.0" + "@chevrotain/types": "~11.1.1" } }, "node_modules/@napi-rs/wasm-runtime": { @@ -1744,9 +1699,9 @@ } }, "node_modules/@oxc-project/types": { - "version": "0.127.0", - "resolved": "https://registry.npmjs.org/@oxc-project/types/-/types-0.127.0.tgz", - "integrity": "sha512-aIYXQBo4lCbO4z0R3FHeucQHpF46l2LbMdxRvqvuRuW2OxdnSkcng5B8+K12spgLDj93rtN3+J2Vac/TIO+ciQ==", + "version": "0.128.0", + "resolved": "https://registry.npmjs.org/@oxc-project/types/-/types-0.128.0.tgz", + "integrity": "sha512-huv1Y/LzBJkBVHt3OlC7u0zHBW9qXf1FdD7sGmc1rXc2P1mTwHssYv7jyGx5KAACSCH+9B3Bhn6Z9luHRvf7pQ==", "license": "MIT", "funding": { "url": "https://github.com/sponsors/Boshen" @@ -1769,9 +1724,9 @@ } }, "node_modules/@rolldown/binding-android-arm64": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-android-arm64/-/binding-android-arm64-1.0.0-rc.17.tgz", - "integrity": "sha512-s70pVGhw4zqGeFnXWvAzJDlvxhlRollagdCCKRgOsgUOH3N1l0LIxf83AtGzmb5SiVM4Hjl5HyarMRfdfj3DaQ==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-android-arm64/-/binding-android-arm64-1.0.0-rc.18.tgz", + "integrity": "sha512-lIDyUAfD7U3+BWKzdxMbJcsYHuqXqmGz40aeRqvuAm3y5TkJSYTBW2RDrn65DJFPQqVjUAUqq5uz8urzQ8aBdQ==", "cpu": [ "arm64" ], @@ -1785,9 +1740,9 @@ } }, "node_modules/@rolldown/binding-darwin-arm64": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-arm64/-/binding-darwin-arm64-1.0.0-rc.17.tgz", - "integrity": "sha512-4ksWc9n0mhlZpZ9PMZgTGjeOPRu8MB1Z3Tz0Mo02eWfWCHMW1zN82Qz/pL/rC+yQa+8ZnutMF0JjJe7PjwasYw==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-arm64/-/binding-darwin-arm64-1.0.0-rc.18.tgz", + "integrity": "sha512-apJq2ktnGp27nSInMR5Vcj8kY6xJzDAvfdIFlpDcAK/w4cDO58qVoi1YQsES/SKiFNge/6e4CUzgjfHduYqWpQ==", "cpu": [ "arm64" ], @@ -1801,9 +1756,9 @@ } }, "node_modules/@rolldown/binding-darwin-x64": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-x64/-/binding-darwin-x64-1.0.0-rc.17.tgz", - "integrity": "sha512-SUSDOI6WwUVNcWxd02QEBjLdY1VPHvlEkw6T/8nYG322iYWCTxRb1vzk4E+mWWYehTp7ERibq54LSJGjmouOsw==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-x64/-/binding-darwin-x64-1.0.0-rc.18.tgz", + "integrity": "sha512-5Ofot8xbs+pxRHJqm9/9N/4sTQOvdrwEsmPE9pdLEEoAbdZtG6F2LMDfO1sp6ZAtXJuJV/21ew2srq3W8NXB5g==", "cpu": [ "x64" ], @@ -1817,9 +1772,9 @@ } }, "node_modules/@rolldown/binding-freebsd-x64": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-freebsd-x64/-/binding-freebsd-x64-1.0.0-rc.17.tgz", - "integrity": "sha512-hwnz3nw9dbJ05EDO/PvcjaaewqqDy7Y1rn1UO81l8iIK1GjenME75dl16ajbvSSMfv66WXSRCYKIqfgq2KCfxw==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-freebsd-x64/-/binding-freebsd-x64-1.0.0-rc.18.tgz", + "integrity": "sha512-7h8eeOTT1eyqJyx64BFCnWZpNm486hGWt2sqeLLgDxA0xI1oGZ9H7gK1S85uNGmBhkdPwa/6reTxfFFKvIsebw==", "cpu": [ "x64" ], @@ -1833,9 +1788,9 @@ } }, "node_modules/@rolldown/binding-linux-arm-gnueabihf": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm-gnueabihf/-/binding-linux-arm-gnueabihf-1.0.0-rc.17.tgz", - "integrity": "sha512-IS+W7epTcwANmFSQFrS1SivEXHtl1JtuQA9wlxrZTcNi6mx+FDOYrakGevvvTwgj2JvWiK8B29/qD9BELZPyXQ==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm-gnueabihf/-/binding-linux-arm-gnueabihf-1.0.0-rc.18.tgz", + "integrity": "sha512-eRcm/HVt9U/JFu5RKAEKwGQYtDCKWLiaH6wOnsSEp6NMBb/3Os8LgHZlNyzMpFVNmiiMFlfb2zEnebfzJrHFmg==", "cpu": [ "arm" ], @@ -1849,9 +1804,9 @@ } }, "node_modules/@rolldown/binding-linux-arm64-gnu": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-gnu/-/binding-linux-arm64-gnu-1.0.0-rc.17.tgz", - "integrity": "sha512-e6usGaHKW5BMNZOymS1UcEYGowQMWcgZ71Z17Sl/h2+ZziNJ1a9n3Zvcz6LdRyIW5572wBCTH/Z+bKuZouGk9Q==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-gnu/-/binding-linux-arm64-gnu-1.0.0-rc.18.tgz", + "integrity": "sha512-SOrT/cT4ukTmgnrEz/Hg3m7LBnuCLW9psDeMKrimRWY4I8DmnO7Lco8W2vtqPmMkbVu8iJ+g4GFLVLLOVjJ9DQ==", "cpu": [ "arm64" ], @@ -1865,9 +1820,9 @@ } }, "node_modules/@rolldown/binding-linux-arm64-musl": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-musl/-/binding-linux-arm64-musl-1.0.0-rc.17.tgz", - "integrity": "sha512-b/CgbwAJpmrRLp02RPfhbudf5tZnN9nsPWK82znefso832etkem8H7FSZwxrOI9djcdTP7U6YfNhbRnh7djErg==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-musl/-/binding-linux-arm64-musl-1.0.0-rc.18.tgz", + "integrity": "sha512-QWjdxN1HJCpBTAcZ5N5F7wju3gVPzRzSpmGzx7na0c/1qpN9CFil+xt+l9lV/1M6/gqHSNXCiqPfwhVJPeLnug==", "cpu": [ "arm64" ], @@ -1881,9 +1836,9 @@ } }, "node_modules/@rolldown/binding-linux-ppc64-gnu": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-ppc64-gnu/-/binding-linux-ppc64-gnu-1.0.0-rc.17.tgz", - "integrity": "sha512-4EII1iNGRUN5WwGbF/kOh/EIkoDN9HsupgLQoXfY+D1oyJm7/F4t5PYU5n8SWZgG0FEwakyM8pGgwcBYruGTlA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-ppc64-gnu/-/binding-linux-ppc64-gnu-1.0.0-rc.18.tgz", + "integrity": "sha512-ugCOyj7a4d9h3q9B+wXmf6g3a68UsjGh6dob5DHevHGMwDUbhsYNbSPxJsENcIttJZ9jv7qGM2UesLw5jqIhdg==", "cpu": [ "ppc64" ], @@ -1897,9 +1852,9 @@ } }, "node_modules/@rolldown/binding-linux-s390x-gnu": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-s390x-gnu/-/binding-linux-s390x-gnu-1.0.0-rc.17.tgz", - "integrity": "sha512-AH8oq3XqQo4IibpVXvPeLDI5pzkpYn0WiZAfT05kFzoJ6tQNzwRdDYQ45M8I/gslbodRZwW8uxLhbSBbkv96rA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-s390x-gnu/-/binding-linux-s390x-gnu-1.0.0-rc.18.tgz", + "integrity": "sha512-kKWRhbsotpXkGbcd5dllUWg5gEXcDAa8u5YnP9AV5DYNbvJHGzzuwv7dpmhc8NqKMJldl0a+x76IHbspEpEmdA==", "cpu": [ "s390x" ], @@ -1913,9 +1868,9 @@ } }, "node_modules/@rolldown/binding-linux-x64-gnu": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-gnu/-/binding-linux-x64-gnu-1.0.0-rc.17.tgz", - "integrity": "sha512-cLnjV3xfo7KslbU41Z7z8BH/E1y5mzUYzAqih1d1MDaIGZRCMqTijqLv76/P7fyHuvUcfGsIpqCdddbxLLK9rA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-gnu/-/binding-linux-x64-gnu-1.0.0-rc.18.tgz", + "integrity": "sha512-uCo8ElcCIAMyYAZyuIZ81oFkhTSIllNvUCHCAlbhlN4ji3uC28h7IIdlXyIvGO7HsuqnV9p3rD/bpH7XhIyhRw==", "cpu": [ "x64" ], @@ -1929,9 +1884,9 @@ } }, "node_modules/@rolldown/binding-linux-x64-musl": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-musl/-/binding-linux-x64-musl-1.0.0-rc.17.tgz", - "integrity": "sha512-0phclDw1spsL7dUB37sIARuis2tAgomCJXAHZlpt8PXZ4Ba0dRP1e+66lsRqrfhISeN9bEGNjQs+T/Fbd7oYGw==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-musl/-/binding-linux-x64-musl-1.0.0-rc.18.tgz", + "integrity": "sha512-XNOQZtuE6yUIvx4rwGemwh8kpL1xvU41FXy/s9K7T/3JVcqGzo3NfKM2HrbrGgfPYGFW42f07Wk++aOC6B9NWA==", "cpu": [ "x64" ], @@ -1945,9 +1900,9 @@ } }, "node_modules/@rolldown/binding-openharmony-arm64": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-openharmony-arm64/-/binding-openharmony-arm64-1.0.0-rc.17.tgz", - "integrity": "sha512-0ag/hEgXOwgw4t8QyQvUCxvEg+V0KBcA6YuOx9g0r02MprutRF5dyljgm3EmR02O292UX7UeS6HzWHAl6KgyhA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-openharmony-arm64/-/binding-openharmony-arm64-1.0.0-rc.18.tgz", + "integrity": "sha512-tSn/kzrfa7tNOXr7sEacDBN4YsIqTyLqh45IO0nHDwtpKIDNDJr+VFojt+4klSpChxB29JLyduSsE0MKEwa65A==", "cpu": [ "arm64" ], @@ -1961,9 +1916,9 @@ } }, "node_modules/@rolldown/binding-wasm32-wasi": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-wasm32-wasi/-/binding-wasm32-wasi-1.0.0-rc.17.tgz", - "integrity": "sha512-LEXei6vo0E5wTGwpkJ4KoT3OZJRnglwldt5ziLzOlc6qqb55z4tWNq2A+PFqCJuvWWdP53CVhG1Z9NtToDPJrA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-wasm32-wasi/-/binding-wasm32-wasi-1.0.0-rc.18.tgz", + "integrity": "sha512-+J9YGmc+czgqlhYmwun3S3O0FIZhsH8ep2456xwjAdIOmuJxM7xz4P4PtrxU+Bz17a/5bqPA8o3HAAoX0teUdg==", "cpu": [ "wasm32" ], @@ -1979,9 +1934,9 @@ } }, "node_modules/@rolldown/binding-win32-arm64-msvc": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-arm64-msvc/-/binding-win32-arm64-msvc-1.0.0-rc.17.tgz", - "integrity": "sha512-gUmyzBl3SPMa6hrqFUth9sVfcLBlYsbMzBx5PlexMroZStgzGqlZ26pYG89rBb45Mnia+oil6YAIFeEWGWhoZA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-arm64-msvc/-/binding-win32-arm64-msvc-1.0.0-rc.18.tgz", + "integrity": "sha512-zsu47DgU0FQzSwi6sU9dZoEdUv7pc1AptSEz/Z8HBg54sV0Pbs3N0+CrIbTsgiu6EyoaNN9CHboqbLaz9lhOyQ==", "cpu": [ "arm64" ], @@ -1995,9 +1950,9 @@ } }, "node_modules/@rolldown/binding-win32-x64-msvc": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-x64-msvc/-/binding-win32-x64-msvc-1.0.0-rc.17.tgz", - "integrity": "sha512-3hkiolcUAvPB9FLb3UZdfjVVNWherN1f/skkGWJP/fgSQhYUZpSIRr0/I8ZK9TkF3F7kxvJAk0+IcKvPHk9qQg==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-x64-msvc/-/binding-win32-x64-msvc-1.0.0-rc.18.tgz", + "integrity": "sha512-7H+3yqGgmnlDTRRhw/xpYY9J1kf4GC681nVc4GqKhExZTDrVVrV2tsOR9kso0fvgBdcTCcQShx4SLLoHgaLwhg==", "cpu": [ "x64" ], @@ -2800,13 +2755,14 @@ "license": "MIT" }, "node_modules/@types/dompurify": { - "version": "3.0.5", - "resolved": "https://registry.npmjs.org/@types/dompurify/-/dompurify-3.0.5.tgz", - "integrity": "sha512-1Wg0g3BtQF7sSb27fJQAKck1HECM6zV1EB66j8JH9i3LCjYabJa0FSdiSgsD5K/RbrsR0SiraKacLB+T8ZVYAg==", + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/@types/dompurify/-/dompurify-3.2.0.tgz", + "integrity": "sha512-Fgg31wv9QbLDA0SpTOXO3MaxySc4DKGLi8sna4/Utjo4r3ZRPdCt4UQee8BWr+Q5z21yifghREPJGYaEOEIACg==", + "deprecated": "This is a stub types definition. dompurify provides its own type definitions, so you do not need this installed.", "dev": true, "license": "MIT", "dependencies": { - "@types/trusted-types": "*" + "dompurify": "*" } }, "node_modules/@types/estree": { @@ -2909,8 +2865,8 @@ "version": "2.0.7", "resolved": "https://registry.npmjs.org/@types/trusted-types/-/trusted-types-2.0.7.tgz", "integrity": "sha512-ScaPdn1dQczgbl0QFTeTOmVHFULt394XJgOQNoyVhZ6r2vLnMLJfBPd53SB52T/3G36VI1/g2MZaX0cwDuXsfw==", - "devOptional": true, - "license": "MIT" + "license": "MIT", + "optional": true }, "node_modules/@types/unist": { "version": "3.0.3", @@ -3642,34 +3598,6 @@ "url": "https://github.com/sponsors/wooorm" } }, - "node_modules/chevrotain": { - "version": "12.0.0", - "resolved": "https://registry.npmjs.org/chevrotain/-/chevrotain-12.0.0.tgz", - "integrity": "sha512-csJvb+6kEiQaqo1woTdSAuOWdN0WTLIydkKrBnS+V5gZz0oqBrp4kQ35519QgK6TpBThiG3V1vNSHlIkv4AglQ==", - "license": "Apache-2.0", - "dependencies": { - "@chevrotain/cst-dts-gen": "12.0.0", - "@chevrotain/gast": "12.0.0", - "@chevrotain/regexp-to-ast": "12.0.0", - "@chevrotain/types": "12.0.0", - "@chevrotain/utils": "12.0.0" - }, - "engines": { - "node": ">=22.0.0" - } - }, - "node_modules/chevrotain-allstar": { - "version": "0.4.1", - "resolved": "https://registry.npmjs.org/chevrotain-allstar/-/chevrotain-allstar-0.4.1.tgz", - "integrity": "sha512-PvVJm3oGqrveUVW2Vt/eZGeiAIsJszYweUcYwcskg9e+IubNYKKD+rHHem7A6XVO22eDAL+inxNIGAzZ/VIWlA==", - "license": "MIT", - "dependencies": { - "lodash-es": "^4.17.21" - }, - "peerDependencies": { - "chevrotain": "^12.0.0" - } - }, "node_modules/chownr": { "version": "3.0.0", "resolved": "https://registry.npmjs.org/chownr/-/chownr-3.0.0.tgz", @@ -4627,6 +4555,16 @@ "node": ">= 0.4" } }, + "node_modules/es-toolkit": { + "version": "1.46.1", + "resolved": "https://registry.npmjs.org/es-toolkit/-/es-toolkit-1.46.1.tgz", + "integrity": "sha512-5eNtXOs3tbfxXOj04tjjseeWkRWaoCjdEI+96DgwzZoe6c9juL49pXlzAFTI72aWC9Y8p7168g6XIKjh7k6pyQ==", + "license": "MIT", + "workspaces": [ + "docs", + "benchmarks" + ] + }, "node_modules/esbuild": { "version": "0.27.0", "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.27.0.tgz", @@ -5643,53 +5581,21 @@ "integrity": "sha512-Ls993zuzfayK269Svk9hzpeGUKob/sIgZzyHYdjQoAdQetRKpOLj+k/QQQ/6Qi0Yz65mlROrfd+Ev+1+7dz9Kw==" }, "node_modules/langchain": { - "version": "1.3.4", - "resolved": "https://registry.npmjs.org/langchain/-/langchain-1.3.4.tgz", - "integrity": "sha512-umrD+ZC6vr0Q0U1lC5PoIMMQqgnP+7QhaIdAXCeZiSX2GPVBiVR7Ed2ZR+3MPvz1yWrRtIm17wPaovkND+wOXg==", + "version": "1.3.5", + "resolved": "https://registry.npmjs.org/langchain/-/langchain-1.3.5.tgz", + "integrity": "sha512-QSB8TEo6G1tWupgNt1Osm8ylLLoOMq1lLw5NeijnIwRPI5BqdBjUn4/U8usbjEJJcQnbXSK2qTKgTx7zvblnBw==", "license": "MIT", "dependencies": { "@langchain/langgraph": "^1.2.9", "@langchain/langgraph-checkpoint": "^1.0.1", "langsmith": ">=0.5.0 <1.0.0", - "uuid": "^11.1.0", "zod": "^3.25.76 || ^4" }, "engines": { "node": ">=20" }, "peerDependencies": { - "@langchain/core": "^1.1.41" - } - }, - "node_modules/langchain/node_modules/uuid": { - "version": "11.1.0", - "resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.0.tgz", - "integrity": "sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A==", - "funding": [ - "https://github.com/sponsors/broofa", - "https://github.com/sponsors/ctavan" - ], - "license": "MIT", - "bin": { - "uuid": "dist/esm/bin/uuid" - } - }, - "node_modules/langium": { - "version": "4.2.2", - "resolved": "https://registry.npmjs.org/langium/-/langium-4.2.2.tgz", - "integrity": "sha512-JUshTRAfHI4/MF9dH2WupvjSXyn8JBuUEWazB8ZVJUtXutT0doDlAv1XKbZ1Pb5sMexa8FF4CFBc0iiul7gbUQ==", - "license": "MIT", - "dependencies": { - "@chevrotain/regexp-to-ast": "~12.0.0", - "chevrotain": "~12.0.0", - "chevrotain-allstar": "~0.4.1", - "vscode-languageserver": "~9.0.1", - "vscode-languageserver-textdocument": "~1.0.11", - "vscode-uri": "~3.1.0" - }, - "engines": { - "node": ">=20.10.0", - "npm": ">=10.2.3" + "@langchain/core": "^1.1.42" } }, "node_modules/langsmith": { @@ -6041,9 +5947,9 @@ } }, "node_modules/lucide-react": { - "version": "1.11.0", - "resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-1.11.0.tgz", - "integrity": "sha512-UOhjdztXCgdBReRcIhsvz2siIBogfv/lhJEIViCpLt924dO+GDms9T7DNoucI23s6kEPpe988m5N0D2ajnzb2g==", + "version": "1.14.0", + "resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-1.14.0.tgz", + "integrity": "sha512-+1mdWcfSJVUsaTIjN9zoezmUhfXo5l0vP7ekBMPo3jcS/aIkxHnXqAPsByszMZx/Y8oQBRJxJx5xg+RH3urzxA==", "license": "ISC", "peerDependencies": { "react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0" @@ -6435,14 +6341,14 @@ } }, "node_modules/mermaid": { - "version": "11.14.0", - "resolved": "https://registry.npmjs.org/mermaid/-/mermaid-11.14.0.tgz", - "integrity": "sha512-GSGloRsBs+JINmmhl0JDwjpuezCsHB4WGI4NASHxL3fHo3o/BRXTxhDLKnln8/Q0lRFRyDdEjmk1/d5Sn1Xz8g==", + "version": "11.15.0", + "resolved": "https://registry.npmjs.org/mermaid/-/mermaid-11.15.0.tgz", + "integrity": "sha512-pTMbcf3rWdtLiYGpmoTjHEpeY8seiy6sR+9nD7LOs8KfUbHE4lOUAprTRqRAcWSQ6MQpdX+YEsxShtGsINtPtw==", "license": "MIT", "dependencies": { "@braintree/sanitize-url": "^7.1.1", "@iconify/utils": "^3.0.2", - "@mermaid-js/parser": "^1.1.0", + "@mermaid-js/parser": "^1.1.1", "@types/d3": "^7.4.3", "@upsetjs/venn.js": "^2.0.0", "cytoscape": "^3.33.1", @@ -6453,27 +6359,14 @@ "dagre-d3-es": "7.0.14", "dayjs": "^1.11.19", "dompurify": "^3.3.1", + "es-toolkit": "^1.45.1", "katex": "^0.16.25", "khroma": "^2.1.0", - "lodash-es": "^4.17.23", "marked": "^16.3.0", "roughjs": "^4.6.6", "stylis": "^4.3.6", "ts-dedent": "^2.2.0", - "uuid": "^11.1.0" - } - }, - "node_modules/mermaid/node_modules/uuid": { - "version": "11.1.0", - "resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.0.tgz", - "integrity": "sha512-0/A9rDy9P7cJ+8w1c9WD9V//9Wj15Ce2MPz8Ri6032usz+NfePxx5AcN3bN+r6ZL6jEo066/yNYB3tn4pQEx+A==", - "funding": [ - "https://github.com/sponsors/broofa", - "https://github.com/sponsors/ctavan" - ], - "license": "MIT", - "bin": { - "uuid": "dist/esm/bin/uuid" + "uuid": "^11.1.0 || ^12 || ^13 || ^14.0.0" } }, "node_modules/micromark": { @@ -7229,9 +7122,9 @@ } }, "node_modules/nanoid": { - "version": "3.3.11", - "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz", - "integrity": "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==", + "version": "3.3.12", + "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.12.tgz", + "integrity": "sha512-ZB9RH/39qpq5Vu6Y+NmUaFhQR6pp+M2Xt76XBnEwDaGcVAqhlvxrl3B2bKS5D3NH3QR76v3aSrKaF/Kiy7lEtQ==", "funding": [ { "type": "github", @@ -7608,9 +7501,9 @@ } }, "node_modules/postcss": { - "version": "8.5.10", - "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.10.tgz", - "integrity": "sha512-pMMHxBOZKFU6HgAZ4eyGnwXF/EvPGGqUr0MnZ5+99485wwW41kW91A4LOGxSHhgugZmSChL5AlElNdwlNgcnLQ==", + "version": "8.5.14", + "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.14.tgz", + "integrity": "sha512-SoSL4+OSEtR99LHFZQiJLkT59C5B1amGO1NzTwj7TT1qCUgUO6hxOvzkOYxD+vMrXBM3XJIKzokoERdqQq/Zmg==", "funding": [ { "type": "opencollective", @@ -7960,13 +7853,13 @@ "license": "Unlicense" }, "node_modules/rolldown": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/rolldown/-/rolldown-1.0.0-rc.17.tgz", - "integrity": "sha512-ZrT53oAKrtA4+YtBWPQbtPOxIbVDbxT0orcYERKd63VJTF13zPcgXTvD4843L8pcsI7M6MErt8QtON6lrB9tyA==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/rolldown/-/rolldown-1.0.0-rc.18.tgz", + "integrity": "sha512-phmyKBpuBdRYDf4hgyynGAYn/rDDe+iZXKVJ7WX5b1zQzpLkP5oJRPGsfJuHdzPMlyyEO/4sPW6yfSx2gf7lVg==", "license": "MIT", "dependencies": { - "@oxc-project/types": "=0.127.0", - "@rolldown/pluginutils": "1.0.0-rc.17" + "@oxc-project/types": "=0.128.0", + "@rolldown/pluginutils": "1.0.0-rc.18" }, "bin": { "rolldown": "bin/cli.mjs" @@ -7975,27 +7868,27 @@ "node": "^20.19.0 || >=22.12.0" }, "optionalDependencies": { - "@rolldown/binding-android-arm64": "1.0.0-rc.17", - "@rolldown/binding-darwin-arm64": "1.0.0-rc.17", - "@rolldown/binding-darwin-x64": "1.0.0-rc.17", - "@rolldown/binding-freebsd-x64": "1.0.0-rc.17", - "@rolldown/binding-linux-arm-gnueabihf": "1.0.0-rc.17", - "@rolldown/binding-linux-arm64-gnu": "1.0.0-rc.17", - "@rolldown/binding-linux-arm64-musl": "1.0.0-rc.17", - "@rolldown/binding-linux-ppc64-gnu": "1.0.0-rc.17", - "@rolldown/binding-linux-s390x-gnu": "1.0.0-rc.17", - "@rolldown/binding-linux-x64-gnu": "1.0.0-rc.17", - "@rolldown/binding-linux-x64-musl": "1.0.0-rc.17", - "@rolldown/binding-openharmony-arm64": "1.0.0-rc.17", - "@rolldown/binding-wasm32-wasi": "1.0.0-rc.17", - "@rolldown/binding-win32-arm64-msvc": "1.0.0-rc.17", - "@rolldown/binding-win32-x64-msvc": "1.0.0-rc.17" + "@rolldown/binding-android-arm64": "1.0.0-rc.18", + "@rolldown/binding-darwin-arm64": "1.0.0-rc.18", + "@rolldown/binding-darwin-x64": "1.0.0-rc.18", + "@rolldown/binding-freebsd-x64": "1.0.0-rc.18", + "@rolldown/binding-linux-arm-gnueabihf": "1.0.0-rc.18", + "@rolldown/binding-linux-arm64-gnu": "1.0.0-rc.18", + "@rolldown/binding-linux-arm64-musl": "1.0.0-rc.18", + "@rolldown/binding-linux-ppc64-gnu": "1.0.0-rc.18", + "@rolldown/binding-linux-s390x-gnu": "1.0.0-rc.18", + "@rolldown/binding-linux-x64-gnu": "1.0.0-rc.18", + "@rolldown/binding-linux-x64-musl": "1.0.0-rc.18", + "@rolldown/binding-openharmony-arm64": "1.0.0-rc.18", + "@rolldown/binding-wasm32-wasi": "1.0.0-rc.18", + "@rolldown/binding-win32-arm64-msvc": "1.0.0-rc.18", + "@rolldown/binding-win32-x64-msvc": "1.0.0-rc.18" } }, "node_modules/rolldown/node_modules/@rolldown/pluginutils": { - "version": "1.0.0-rc.17", - "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-rc.17.tgz", - "integrity": "sha512-n8iosDOt6Ig1UhJ2AYqoIhHWh/isz0xpicHTzpKBeotdVsTEcxsSA/i3EVM7gQAj0rU27OLAxCjzlj15IWY7bg==", + "version": "1.0.0-rc.18", + "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-rc.18.tgz", + "integrity": "sha512-CUY5Mnhe64xQBGZEEXQ5WyZwsc1JU3vAZLIxtrsBt3LO6UOb+C8GunVKqe9sT8NeWb4lqSaoJtp2xo6GxT1MNw==", "license": "MIT" }, "node_modules/roughjs": { @@ -8715,15 +8608,15 @@ } }, "node_modules/vite": { - "version": "8.0.10", - "resolved": "https://registry.npmjs.org/vite/-/vite-8.0.10.tgz", - "integrity": "sha512-rZuUu9j6J5uotLDs+cAA4O5H4K1SfPliUlQwqa6YEwSrWDZzP4rhm00oJR5snMewjxF5V/K3D4kctsUTsIU9Mw==", + "version": "8.0.11", + "resolved": "https://registry.npmjs.org/vite/-/vite-8.0.11.tgz", + "integrity": "sha512-Jz1mxtUBR5xTT65VOdJZUUeoyLtqljmFkiUXhPTLZka3RDc9vpi/xXkyrnsdRcm2lIi3l3GPMnAidTsEGIj3Ow==", "license": "MIT", "dependencies": { "lightningcss": "^1.32.0", "picomatch": "^4.0.4", - "postcss": "^8.5.10", - "rolldown": "1.0.0-rc.17", + "postcss": "^8.5.14", + "rolldown": "1.0.0-rc.18", "tinyglobby": "^0.2.16" }, "bin": { @@ -8740,7 +8633,7 @@ }, "peerDependencies": { "@types/node": "^20.19.0 || >=22.12.0", - "@vitejs/devtools": "^0.1.0", + "@vitejs/devtools": "^0.1.18", "esbuild": "^0.27.0 || ^0.28.0", "jiti": ">=1.21.0", "less": "^4.0.0", @@ -8888,55 +8781,6 @@ "dev": true, "license": "MIT" }, - "node_modules/vscode-jsonrpc": { - "version": "8.2.0", - "resolved": "https://registry.npmjs.org/vscode-jsonrpc/-/vscode-jsonrpc-8.2.0.tgz", - "integrity": "sha512-C+r0eKJUIfiDIfwJhria30+TYWPtuHJXHtI7J0YlOmKAo7ogxP20T0zxB7HZQIFhIyvoBPwWskjxrvAtfjyZfA==", - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, - "node_modules/vscode-languageserver": { - "version": "9.0.1", - "resolved": "https://registry.npmjs.org/vscode-languageserver/-/vscode-languageserver-9.0.1.tgz", - "integrity": "sha512-woByF3PDpkHFUreUa7Hos7+pUWdeWMXRd26+ZX2A8cFx6v/JPTtd4/uN0/jB6XQHYaOlHbio03NTHCqrgG5n7g==", - "license": "MIT", - "dependencies": { - "vscode-languageserver-protocol": "3.17.5" - }, - "bin": { - "installServerIntoExtension": "bin/installServerIntoExtension" - } - }, - "node_modules/vscode-languageserver-protocol": { - "version": "3.17.5", - "resolved": "https://registry.npmjs.org/vscode-languageserver-protocol/-/vscode-languageserver-protocol-3.17.5.tgz", - "integrity": "sha512-mb1bvRJN8SVznADSGWM9u/b07H7Ecg0I3OgXDuLdn307rl/J3A9YD6/eYOssqhecL27hK1IPZAsaqh00i/Jljg==", - "license": "MIT", - "dependencies": { - "vscode-jsonrpc": "8.2.0", - "vscode-languageserver-types": "3.17.5" - } - }, - "node_modules/vscode-languageserver-textdocument": { - "version": "1.0.12", - "resolved": "https://registry.npmjs.org/vscode-languageserver-textdocument/-/vscode-languageserver-textdocument-1.0.12.tgz", - "integrity": "sha512-cxWNPesCnQCcMPeenjKKsOCKQZ/L6Tv19DTRIGuLWe32lyzWhihGVJ/rcckZXJxfdKCFvRLS3fpBIsV/ZGX4zA==", - "license": "MIT" - }, - "node_modules/vscode-languageserver-types": { - "version": "3.17.5", - "resolved": "https://registry.npmjs.org/vscode-languageserver-types/-/vscode-languageserver-types-3.17.5.tgz", - "integrity": "sha512-Ld1VelNuX9pdF39h2Hgaeb5hEZM2Z3jUrrMgWQAu82jMtZp7p3vJT3BzToKtZI7NgQssZje5o0zryOrhQvzQAg==", - "license": "MIT" - }, - "node_modules/vscode-uri": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/vscode-uri/-/vscode-uri-3.1.0.tgz", - "integrity": "sha512-/BpdSx+yCQGnCvecbyXdxHDkuk55/G3xwnC0GqY4gmQ3j+A+g8kzzgB4Nk/SINjqn6+waqw3EgbVF2QKExkRxQ==", - "license": "MIT" - }, "node_modules/w3c-xmlserializer": { "version": "5.0.0", "resolved": "https://registry.npmjs.org/w3c-xmlserializer/-/w3c-xmlserializer-5.0.0.tgz", diff --git a/gitnexus-web/package.json b/gitnexus-web/package.json index 81d7fc5fa..211bb65c7 100644 --- a/gitnexus-web/package.json +++ b/gitnexus-web/package.json @@ -19,9 +19,9 @@ }, "dependencies": { "gitnexus-shared": "file:../gitnexus-shared", - "@langchain/anthropic": "^1.3.28", + "@langchain/anthropic": "^1.3.29", "@langchain/core": "^1.1.44", - "@langchain/google-genai": "^2.1.28", + "@langchain/google-genai": "^2.1.30", "@langchain/langgraph": "^1.2.9", "@langchain/ollama": "^1.2.6", "@langchain/openai": "^1.4.5", @@ -36,10 +36,10 @@ "graphology-layout-forceatlas2": "^0.10.1", "graphology-layout-noverlap": "^0.4.2", "graphology-utils": "^2.3.0", - "langchain": "^1.3.4", + "langchain": "^1.3.5", "lru-cache": "^11.2.4", - "lucide-react": "^1.11.0", - "mermaid": "^11.14.0", + "lucide-react": "^1.14.0", + "mermaid": "^11.15.0", "mnemonist": "^0.39.0", "pandemonium": "^2.4.0", "react": "^19.2.5", @@ -59,7 +59,7 @@ "@testing-library/jest-dom": "^6.9.1", "@testing-library/react": "^16.3.2", "@testing-library/user-event": "^14.6.1", - "@types/dompurify": "^3.0.5", + "@types/dompurify": "^3.2.0", "@types/node": "^25.6.0", "@types/react": "^19.2.14", "@types/react-dom": "^19.2.3", @@ -70,7 +70,7 @@ "jsdom": "^29.1.1", "tree-sitter-wasms": "^0.1.13", "typescript": "^5.4.5", - "vite": "^8.0.10", + "vite": "^8.0.11", "vitest": "^4.1.5", "wait-on": "^9.0.5" } diff --git a/gitnexus-web/src/core/llm/settings-service.ts b/gitnexus-web/src/core/llm/settings-service.ts index 5e49cb7af..86330d2a5 100644 --- a/gitnexus-web/src/core/llm/settings-service.ts +++ b/gitnexus-web/src/core/llm/settings-service.ts @@ -20,6 +20,7 @@ import { ProviderConfig, } from './types'; import { DEFAULT_OPENROUTER_BASE_URL, DEFAULT_OLLAMA_BASE_URL } from '../../config/ui-constants'; +import { resilientFetch } from 'gitnexus-shared'; const STORAGE_KEY = 'gitnexus-llm-settings'; @@ -407,7 +408,10 @@ export const getAvailableModels = (provider: LLMProvider): string[] => { */ export const fetchOpenRouterModels = async (): Promise> => { try { - const response = await fetch(`${DEFAULT_OPENROUTER_BASE_URL}/models`); + const response = await resilientFetch(`${DEFAULT_OPENROUTER_BASE_URL}/models`, undefined, { + breakerKey: 'openrouter-models', + retry: { maxAttempts: 2, baseDelayMs: 500, capDelayMs: 2_000 }, + }); if (!response.ok) throw new Error('Failed to fetch models'); const data = await response.json(); return data.data.map((model: any) => ({ diff --git a/gitnexus-web/src/services/backend-client.ts b/gitnexus-web/src/services/backend-client.ts index ec8c1a964..e887e3901 100644 --- a/gitnexus-web/src/services/backend-client.ts +++ b/gitnexus-web/src/services/backend-client.ts @@ -7,6 +7,7 @@ */ import type { GraphNode, GraphRelationship } from 'gitnexus-shared'; +import { CircuitOpenError, ResilientFetchExhaustedError, resilientFetch } from 'gitnexus-shared'; // ── Types ────────────────────────────────────────────────────────────────── @@ -204,8 +205,32 @@ export function streamSSE(url: string, handlers: SSEHandlers): A let _backendUrl = 'http://localhost:4747'; +/** + * Validate that a backend URL is a safe http:// or https:// origin before + * storing it as the fetch target base (CodeQL js/client-side-request-forgery). + * + * Throws if the URL uses a non-HTTP scheme (e.g. javascript:, data:, file://). + * All other well-formed http/https URLs are accepted — the client intentionally + * supports connecting to remote GitNexus servers, not just localhost. + */ +export function validateBackendUrl(url: string): void { + let parsed: URL; + try { + parsed = new URL(url); + } catch { + // Do not echo raw input — it may contain credentials. + throw new Error('Invalid backend URL: must be a well-formed http:// or https:// URL'); + } + if (parsed.protocol !== 'http:' && parsed.protocol !== 'https:') { + // Use parsed.protocol only (scheme), not the full URL, to avoid leaking credentials. + throw new Error(`Backend URL must use http:// or https:// (got ${parsed.protocol})`); + } +} + export const setBackendUrl = (url: string): void => { - _backendUrl = url.replace(/\/$/, ''); + const trimmed = url.replace(/\/$/, ''); + validateBackendUrl(trimmed); + _backendUrl = trimmed; }; export const getBackendUrl = (): string => _backendUrl; @@ -237,29 +262,91 @@ export function normalizeServerUrl(input: string): string { const DEFAULT_TIMEOUT_MS = 30_000; const PROBE_TIMEOUT_MS = 2_000; +/** Idempotent HTTP methods. Other verbs (POST, PATCH, PUT, DELETE) get + * a single-attempt retry budget by default to avoid duplicate side + * effects on retry — a POST that 5xx'd may have already executed + * server-side. Callers that have idempotency keys or otherwise know + * their mutation is safe to retry can opt in via `forceRetry`. */ +const IDEMPOTENT_METHODS = new Set(['GET', 'HEAD', 'OPTIONS']); + const fetchWithTimeout = async ( url: string, init: RequestInit = {}, timeoutMs: number = DEFAULT_TIMEOUT_MS, + /** + * Force a retry budget on non-idempotent methods. Default false. + * Pass true only when the endpoint is known-idempotent (e.g. DELETE + * of a known-deleted resource — second call is a 404 / no-op) AND + * the duplicate-side-effect window is acceptable. + */ + forceRetry = false, ): Promise => { - const controller = new AbortController(); - // Merge external signal if provided + // Merge the external caller signal (if any) with an + // `AbortSignal.timeout()` so a timer-fired abort produces a + // `DOMException` with `name === 'TimeoutError'` — which + // `resilientFetch` correctly classifies as terminal-network (no + // retry, no breaker hit). A manual `AbortController.abort()` would + // produce `name === 'AbortError'` and route through the + // retryable-network branch, which mis-penalizes the breaker for + // user-side network slowness. + const timeoutSignal = AbortSignal.timeout(timeoutMs); const externalSignal = init.signal; - if (externalSignal) { - externalSignal.addEventListener('abort', () => controller.abort()); + const signal = externalSignal ? AbortSignal.any([timeoutSignal, externalSignal]) : timeoutSignal; + + const method = (init.method ?? 'GET').toUpperCase(); + const isIdempotent = IDEMPOTENT_METHODS.has(method); + const maxAttempts = isIdempotent || forceRetry ? 2 : 1; + + // Key the breaker by the current backend origin so switching backend + // URLs (e.g. recovering from a flapping local server by pointing at + // a different host) gives the new origin a fresh breaker state. A + // single shared `'web-backend'` key would otherwise leave a user + // locked out for the full cooldown after one bad host trips the + // circuit. The malformed-URL fallback is defensive — `setBackendUrl` + // normalizes input, so this branch shouldn't fire in practice. + let breakerKey: string; + try { + breakerKey = `web-backend:${new URL(_backendUrl).origin}`; + } catch { + breakerKey = 'web-backend:invalid'; } - const timer = setTimeout(() => controller.abort(), timeoutMs); try { - const response = await fetch(url, { ...init, signal: controller.signal }); + // Bounded retries + 5xx/429 handling are delegated to resilientFetch. + // Method-aware budget: idempotent verbs retry once on transient + // backend failures; mutations (POST/PATCH/PUT/DELETE) default to + // single-attempt to avoid duplicate side effects. + const response = await resilientFetch( + url, + { ...init, signal }, + { + breakerKey, + retry: { maxAttempts, baseDelayMs: 250, capDelayMs: 1500 }, + }, + ); return response; } catch (error: unknown) { - if (error instanceof DOMException && error.name === 'AbortError') { - if (externalSignal?.aborted) { - throw new BackendError('Request aborted', 0, 'network'); - } + if (error instanceof CircuitOpenError) { + throw new BackendError( + `GitNexus backend at ${_backendUrl} is unhealthy; retry in ${Math.ceil(error.retryAfterMs / 1000)}s`, + 0, + 'network', + ); + } + if (error instanceof ResilientFetchExhaustedError) { + // Fall through to caller — surface the raw response so assertOk + // can craft the BackendError with the right code. + return error.response; + } + if (error instanceof DOMException && error.name === 'TimeoutError') { throw new BackendError(`Request to ${url} timed out after ${timeoutMs}ms`, 0, 'timeout'); } + if (error instanceof DOMException && error.name === 'AbortError') { + // External caller-driven cancellation — `timeoutSignal` would + // have surfaced as TimeoutError above, so this branch covers + // only the externally-aborted case. + throw new BackendError('Request aborted', 0, 'network'); + } if (error instanceof TypeError) { throw new BackendError( `Network error reaching GitNexus backend at ${_backendUrl}: ${error.message}`, @@ -268,8 +355,6 @@ const fetchWithTimeout = async ( ); } throw error; - } finally { - clearTimeout(timer); } }; diff --git a/gitnexus-web/test/unit/backend-client-retry.test.ts b/gitnexus-web/test/unit/backend-client-retry.test.ts new file mode 100644 index 000000000..ea0fcf3a7 --- /dev/null +++ b/gitnexus-web/test/unit/backend-client-retry.test.ts @@ -0,0 +1,110 @@ +/** + * Method-aware retry budget + timeout-as-TimeoutError verification for + * backend-client's `fetchWithTimeout`. + * + * Closes review findings on PR #1448: + * - Non-idempotent POST/DELETE must NOT be retried by default — + * a 5xx on `startAnalyze` could otherwise start a duplicate job. + * - Timer-fired timeout must surface as `DOMException(name='TimeoutError')`, + * not `AbortError`, so resilientFetch routes it through the + * terminal-network branch (no retry, no breaker hit). + */ + +import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'; +import { getBreaker } from 'gitnexus-shared'; +import { __resetBreakerRegistry__ } from 'gitnexus-shared/test-helpers'; +import { fetchRepos, setBackendUrl, startAnalyze } from '../../src/services/backend-client'; + +const BASE = 'http://localhost:4747'; + +describe('backend-client retry budget (method-aware)', () => { + beforeEach(() => { + __resetBreakerRegistry__(); + setBackendUrl(BASE); + }); + + afterEach(() => { + vi.unstubAllGlobals(); + }); + + it('GET retries once on transient 503 (idempotent verb)', async () => { + let n = 0; + const fetchMock = vi.fn(async () => { + n += 1; + if (n === 1) return new Response('boom', { status: 503 }); + return new Response('[]', { + status: 200, + headers: { 'Content-Type': 'application/json' }, + }); + }); + vi.stubGlobal('fetch', fetchMock); + + const repos = await fetchRepos(); + expect(repos).toEqual([]); + // 1 retry budget on idempotent GET → 2 total fetch calls. + expect(fetchMock).toHaveBeenCalledTimes(2); + }); + + it('POST does NOT retry on 503 by default (non-idempotent verb)', async () => { + const fetchMock = vi.fn(async () => new Response('boom', { status: 503 })); + vi.stubGlobal('fetch', fetchMock); + + await expect(startAnalyze({ path: '/tmp/repo' })).rejects.toBeTruthy(); + // Single attempt — never duplicates a job-start POST. + expect(fetchMock).toHaveBeenCalledTimes(1); + }); + + it('switching backend URL after a circuit opens reaches a fresh breaker (U3)', async () => { + // Pre-open the breaker for host-A by directly recording 3 failures. + setBackendUrl('http://host-a.test:4747'); + const aKey = 'web-backend:http://host-a.test:4747'; + const breakerA = getBreaker(aKey); + breakerA.recordFailure(); + breakerA.recordFailure(); + breakerA.recordFailure(); + expect(breakerA.getState()).toBe('open'); + + // Switch to host-B and make a request — must succeed against the + // new origin without tripping the host-A circuit. Under the old + // single-key behaviour the call would throw CircuitOpenError. + setBackendUrl('http://host-b.test:4747'); + const fetchMock = vi.fn( + async () => + new Response('[]', { + status: 200, + headers: { 'Content-Type': 'application/json' }, + }), + ); + vi.stubGlobal('fetch', fetchMock); + + const repos = await fetchRepos(); + expect(repos).toEqual([]); + expect(fetchMock).toHaveBeenCalledTimes(1); + + // Host-A's breaker is still open in cooldown. + expect(breakerA.getState()).toBe('open'); + // Host-B has its own (fresh) breaker. + const bKey = 'web-backend:http://host-b.test:4747'; + expect(getBreaker(bKey).getState()).toBe('closed'); + expect(getBreaker(bKey).getConsecutiveFailures()).toBe(0); + }); + + it('breaker not incremented when timeout fires (TimeoutError, not AbortError)', async () => { + // Reject directly with a TimeoutError DOMException, mimicking what + // `fetch` produces when its `AbortSignal.timeout()`-wired signal + // fires. The real-fetch path goes signal.reason → reject(reason); + // we shortcut that here so the test doesn't have to wait the + // 30-second default timeout. + const fetchMock = vi.fn(async () => { + throw new DOMException('aborted by timeout', 'TimeoutError'); + }); + vi.stubGlobal('fetch', fetchMock); + + await expect(fetchRepos()).rejects.toMatchObject({ code: 'timeout' }); + + // The breaker must not have been penalized for a local timeout. + expect(getBreaker(`web-backend:${BASE}`).getConsecutiveFailures()).toBe(0); + // Timeout is terminal — no retry attempted. + expect(fetchMock).toHaveBeenCalledTimes(1); + }); +}); diff --git a/gitnexus-web/test/unit/server-connection.test.ts b/gitnexus-web/test/unit/server-connection.test.ts index f5ee43c53..e39b829a1 100644 --- a/gitnexus-web/test/unit/server-connection.test.ts +++ b/gitnexus-web/test/unit/server-connection.test.ts @@ -1,5 +1,11 @@ import { afterEach, describe, expect, it, vi } from 'vitest'; -import { fetchGraph, normalizeServerUrl, setBackendUrl } from '../../src/services/backend-client'; +import { + fetchGraph, + getBackendUrl, + normalizeServerUrl, + setBackendUrl, + validateBackendUrl, +} from '../../src/services/backend-client'; describe('normalizeServerUrl', () => { it('adds http:// to localhost', () => { @@ -165,3 +171,61 @@ describe('fetchGraph', () => { }); }); }); + +describe('validateBackendUrl', () => { + it('allows http:// URLs', () => { + expect(() => validateBackendUrl('http://localhost:4747')).not.toThrow(); + expect(() => validateBackendUrl('http://127.0.0.1:4747')).not.toThrow(); + }); + + it('allows https:// URLs', () => { + expect(() => validateBackendUrl('https://gitnexus.example.com')).not.toThrow(); + expect(() => validateBackendUrl('https://my-server.internal:4747')).not.toThrow(); + }); + + it('rejects non-http schemes', () => { + expect(() => validateBackendUrl('javascript:alert(1)')).toThrow('must use http:// or https://'); + expect(() => validateBackendUrl('file:///etc/passwd')).toThrow('must use http:// or https://'); + expect(() => validateBackendUrl('data:text/plain,evil')).toThrow( + 'must use http:// or https://', + ); + }); + + it('rejects malformed URLs', () => { + expect(() => validateBackendUrl('not-a-url')).toThrow('Invalid backend URL'); + }); + + it('does not include the raw URL in error messages (credential hygiene)', () => { + const urlWithCreds = 'javascript:alert("sk-secret")'; + let msg = ''; + try { + validateBackendUrl(urlWithCreds); + } catch (e) { + msg = (e as Error).message; + } + expect(msg).not.toContain('sk-secret'); + expect(msg).not.toContain(urlWithCreds); + }); +}); + +describe('setBackendUrl', () => { + it('accepts valid http URLs', () => { + expect(() => setBackendUrl('http://localhost:4747')).not.toThrow(); + }); + + it('accepts valid https URLs', () => { + expect(() => setBackendUrl('https://my-server.example.com')).not.toThrow(); + }); + + it('rejects non-http/https schemes', () => { + expect(() => setBackendUrl('javascript:alert(1)')).toThrow('must use http:// or https://'); + expect(() => setBackendUrl('file:///etc/passwd')).toThrow('must use http:// or https://'); + }); + + it('does not mutate _backendUrl when validation fails', () => { + setBackendUrl('http://localhost:4747'); + expect(() => setBackendUrl('javascript:alert(1)')).toThrow(); + // State must be preserved — validation must happen before the assignment + expect(getBackendUrl()).toBe('http://localhost:4747'); + }); +}); diff --git a/gitnexus/CHANGELOG.md b/gitnexus/CHANGELOG.md index ca51f0493..583ed97b3 100644 --- a/gitnexus/CHANGELOG.md +++ b/gitnexus/CHANGELOG.md @@ -4,6 +4,73 @@ All notable changes to GitNexus will be documented in this file. ## [Unreleased] +## [1.6.4] - 2026-05-10 + +### Added + +- **`gitnexus publish`** — opt-in command to push your indexed graph to the understand-quickly registry for shareable browsing (#1425) +- **`IncludeExtractor` for C++** — cross-repo include tracking joins the group contract pipeline (#1156) +- **Unreal Engine C++ support** — strips reflection macros (`UCLASS`, `UFUNCTION`, `UPROPERTY`, etc.) before tree-sitter parses, so UE projects index cleanly (#1439) +- **Thrift contracts extractor** — group-mode contract detection for Apache Thrift IDL (#1234) +- **Workspace extractors for Node, Python, Go, Java, Elixir** — group-mode auto-discovery of cross-package boundaries (#1260) +- **Rust workspace cross-crate contracts** — auto-discovery of `[workspace]` member crates and their cross-crate links (#1256) +- **Go scope-resolution hooks** — Go joins Python / C# / TypeScript on the registry-primary RFC #909 path (#1302) +- **TypeScript registry-primary scope resolution (Ring 3)** — TypeScript fully migrated to scope-based resolution (#1050) +- **Configurable group cross-link path exclusions** — reduces false-positive contract links in vendored / monorepo trees (#1093) +- **MCP tool safety annotations** — every MCP tool advertises read-only / mutating semantics so hosts can prompt appropriately (#1127) +- **`--embeddings ` opt-in cap** — bound the embeddings pass on huge graphs (closes #382, #1375) +- **Pino structured logger** — replaces ad-hoc console output across the core with structured JSON logs (with pretty-print for TTY) (#1336) +- **Shared resilient-fetch helper** — single retries + circuit breaker module reused by HF / Docker / publish flows (#1448) +- **`/autofix` ChatOps button** — fork-safe PR autofix pipeline replaces the inline reviewdog flow (#1446, #1458) +- **Automated security & vulnerability scans** in CI (#1297, #1455) + +### Fixed + +- **FTS read-only DB cluster** — hook resolves canonical repo root and guards read-only FTS ensure; missing-FTS warning is now surfaced. Closes #1255, #1287, #1170, #1449, #1440, #1216, #1438 (#1226, #1418, #1107, #1123) +- **WAL corruption recovery** — quarantine corrupted `.wal` files instead of failing analyze; CHECKPOINT before close prevents recurrence; `safeClose` consolidates flush. Closes #1402, #1236, #1273, #1361 (#1417, #1314, #1377) +- **Embedding download failures** — actionable HF_ENDPOINT guidance, retries, timeout, and circuit breaker; bridge `HF_ENDPOINT` to transformers.js; iterative DFS; HF cache via `os.homedir()`. Closes #1378, #1437, #1205 (#1419, #1252, #1078) +- **Windows reliability** — pin tree-sitter-c/cpp to fix segfault, prefer `.cmd`/`.bat` from `where` output, robust LadybugDB lock acquisition for CI integration tests, surface silent finalize-skips so analyze cannot exit 0 without persisting. Closes #1242, #1427, #1447, #1468, #1400; partial #1218 (#1243, #1299, #1430, #1237, #1226, #1235) +- **DuckDB / LadybugDB native** — bumped to 0.16.0 then 0.16.1; prevent extension install hangs; CHECKPOINT before close; WAL quarantine on corruption. Closes #1162, #1160, #273 (#1235, #1326, #1129, #1314, #1417) +- **C# scope-resolution "Cannot add property" crashes** — generic typed properties included in context and impact, fixing crashes on Unity ECS partial structs and on properties whose name matches the class name. Closes #1426, #1465 (#1399) +- **C# frozen-bucket regression** + scope-resolution I8 hardening — closes #1066 (#1082, #1085) +- **Scope resolution** — same-range Module-as-parent for top-level scopes (closes #1086) (#1087); avoid variadic reference-site aggregation (#1112); skip empty scope extraction (#1100); classify Python class methods as Method (#1102) +- **Python** — index repos with empty `__init__.py` and >32 KB files (#1163); walk ancestors for multi-segment dotted imports (#1241); deterministic multi-segment suffix fallback (#1253) +- **TypeScript** — capture missed CALLS edges from HOF callbacks and JSX (#1175); name HOC-wrapped const declarations (`forwardRef` / `memo` / `useCallback` / `useMemo` / `observer`) (#1261); pair-with-arrow `@declaration.function` anchored on inner arrow +- **Go** — loose equality for `Array.find()` null checks (#1384) +- **Swift** — switched to the official prebuilt parser runtime (#1130) +- **Server hardening cluster (U2–U8)** — JS path-injection on `/api/file` + docker-server (U2, #1322); git-clone path/CLI-injection / ReDoS hardening (U3, #1325); per-route rate limiting on FS-touching endpoints (U4, #1327); URL/regex/tag-filter sanitization (U7, #1330); ReDoS in cobol-preprocessor + rust-workspace + cross-impact resource exhaustion (U8, #1331); critical type-confusion + validation helper (#1317); rate-limit `/api/analyze` and `/api/embed` (closes #1328, #1339); IPv6 ipKeyGenerator (closes #1360, #1374); IPv4-compatible IPv6 / NAT64 SSRF bypasses in `validateGitUrl` (closes #1148, 95814847); predictable tempfile names → `crypto.randomBytes` (#1387); log-injection / http-to-file-access / client-side request forgery (#1456); pin Docker Node base images + Trivy verification + Dependabot policy (#1455) +- **Group / contracts** — `runExactMatch` honours `.gitnexusignore` via shared `IgnoreService` (closes #1185, #1247); custom manifest links resolved against graph symbols (#1254); `IgnoreService` EACCES test under uid=0 (#1108) +- **MCP** — close MCP server timeout via stdout discipline + cold-start friction (#1383); avoid `git` from non-repo cwd in sibling-cwd match (closes #1138, #1293); start MCP bridge correctly when using `npx` (#1114); project `tool_map` flows from handlers (#1113); parallelize staleness checks in `list_repos` (#1416) +- **Storage / CLI** — derive registry name from canonical repo root, not worktree slug (closes #1259, #1296); `--skip-git` treats cwd as index root (#1245); keep GitNexus ignores inside `.gitnexus/` (#1248); surface silent finalize-skips so `analyze` cannot exit 0 without persisting (closes #1169, #1237); ignore global registry during staleness checks (#1141); use `os.homedir()` instead of `process.env.HOME` for HF cache dir (#1078); correct OpenCode skills install path in status message (#1386) +- **Docker / server** — dedicated health endpoint for container healthcheck (closes #1147, #1355); HEAD probe so SSE heartbeat doesn't time out healthcheck (#1182); flush WAL after `/api/embed` so search sees new embeddings (closes #1149, #1359); platform-aware semantic fallback (#1150); skip vector index query on unsupported platforms (closes #1178, #1181); serve web UI at root path instead of 404 (#1048) +- **Worker pool** — wait for replacement worker online before dispatch (#1324); prevent premature pool resolution in worker split-and-retry path (#1321); recover worker parse stalls (#1121); widened CI flake-tolerant timeouts (#1323, #1347, #1354) +- **Embeddings storage** — CHECKPOINT before closing DB to prevent WAL corruption (#1314) +- **Performance** — replace O(n³) C3 merge loop with O(n²) head-pointer algorithm (#1316) +- **Install** — vendor tree-sitter-dart source (#1125) +- **Git utils** — suppress stderr leak in `getCurrentCommit` and `getGitRoot` (closes #1172, #1341) +- **Search** — load FTS during core DB init (#1123); create FTS indexes during `analyze` (#1107); surface warning when FTS indexes are missing (#1418) +- **Hooks** — clarify `PostToolUse` hook is notification-only, not auto-reindex (#1070) +- **Docs** — README Web UI section corrected (closes #1110, #1159, #2ff3e64f); Goliath capitalisation typo (#1126) +- **CI** — fork-safe PR autofix pipeline (#1446); consolidated Claude review workflow (#1258); fine-grained PAT for RC tag push (#1407); handle expired artifacts in base coverage fetch (#1410, #1412); allow expected legacy parity failures (#1099); avoid duplicate main push checks; isolate native LadybugDB / CLI e2e flakes; seed e2e with a small fixture repo (#1249); configure e2e GitNexus home at runtime; widen rate-limit test window for Windows CI (#1347) + +### Changed + +- **`gitnexus publish` artefact contract** — universal opt-in publish format introduced (#1425, #1458) +- **Refactor: per-language patterns consolidated into `LanguageProvider`** (#1279) +- **Refactor: `safeClose` helper** consolidates WAL flush across LadybugDB call sites (#1377) +- **Quality: exclude `test/fixtures` from CodeQL, ESLint, and Prettier** (#1313) +- **Regression coverage** for `.gitnexusignore` behaviour with `--skip-git` (#1450) + +### Chore / Dependencies + +- `@ladybugdb/core` 0.16.0 → 0.16.1 (#1235, #1326) +- `@anthropic-ai/sdk` (#1442), `@langchain/anthropic` (#1389), `@langchain/core` (#1394), `@langchain/openai` (#1215) +- `hono` 4.12.9 → 4.12.18 + `@hono/node-server` (#1310, #1311, #1443) +- `axios` (#1345), `fast-uri` 3.1.0 → 3.1.2 (#1441), `lru-cache` 11.3.5 → 11.3.6 (#1344), `mnemonist` 0.40.3 → 0.40.4 (#1239), `express-rate-limit` (#1343, #1397), `onnxruntime-node` (#1213, #1435), `uuid` 13 → 14 in /gitnexus-web (#1211, after revert #1222 / re-land #1250 + #1208) +- `react`/`@types/react` (#1210), `react-dom` 19.2.5 → 19.2.6 (#1396), `react-zoom-pan-pinch` (#1214), `jsdom` 29.0.2 → 29.1.1 (#1395) +- npm_and_yarn group bump (#1312), uv group bump (#1315), `python-dotenv` (#1320), `@types/node` (#1212, #1421, #1436) +- GitHub Actions: `docker/build-push-action` 6.19.2 → 7.1.0 (#1391), `github/codeql-action` 3.35.3 → 4.35.3 (#1390) + ## [1.6.3] - 2026-04-24 ### Added diff --git a/gitnexus/Dockerfile.test b/gitnexus/Dockerfile.test index 0282129ff..37374a5f5 100644 --- a/gitnexus/Dockerfile.test +++ b/gitnexus/Dockerfile.test @@ -1,6 +1,15 @@ -FROM node:20-bookworm +# Pinned npm version — keep in sync with the root Dockerfile.cli and +# Dockerfile.web. +ARG NPM_VERSION=11.14.1 + +# node:22-bookworm-slim +FROM node:22-bookworm-slim@sha256:9f6d5975c7dca860947d3915877f85607946403fc55349f39b4bc3688448bb6e +ARG NPM_VERSION WORKDIR /app -RUN apt-get -o Acquire::Check-Valid-Until=false -o Acquire::Check-Date=false update && apt-get install -y python3 make g++ && rm -rf /var/lib/apt/lists/* +RUN npx --yes npm@${NPM_VERSION} install -g npm@${NPM_VERSION} \ + && apt-get -o Acquire::Check-Valid-Until=false -o Acquire::Check-Date=false update \ + && apt-get install -y python3 make g++ \ + && rm -rf /var/lib/apt/lists/* COPY . . RUN npm ci --ignore-scripts \ && npm rebuild tree-sitter-swift 2>&1 \ diff --git a/gitnexus/README.md b/gitnexus/README.md index 8a5144598..55cdc12f7 100644 --- a/gitnexus/README.md +++ b/gitnexus/README.md @@ -33,7 +33,7 @@ To configure MCP for your editor, run `npx gitnexus setup` once — or set it up | Editor | MCP | Skills | Hooks (auto-augment) | Support | |--------|-----|--------|---------------------|---------| | **Claude Code** | Yes | Yes | Yes (PreToolUse) | **Full** | -| **Cursor** | Yes | Yes | — | MCP + Skills | +| **Cursor** | Yes | Yes | Yes (postToolUse, [manual install](../gitnexus-cursor-integration/README.md#hook-install)) | **Full** | | **Codex** | Yes | Yes | — | MCP + Skills | | **Windsurf** | Yes | — | — | MCP | | **OpenCode** | Yes | Yes | — | MCP + Skills | diff --git a/gitnexus/hooks/claude/gitnexus-hook.cjs b/gitnexus/hooks/claude/gitnexus-hook.cjs index 7bfa150cd..e39fcf8e1 100755 --- a/gitnexus/hooks/claude/gitnexus-hook.cjs +++ b/gitnexus/hooks/claude/gitnexus-hook.cjs @@ -14,6 +14,8 @@ const fs = require('fs'); const path = require('path'); const { spawnSync } = require('child_process'); +const { acquireHookSlot } = require('./hook-lock.cjs'); +const { hasGitNexusDbLockedByGitNexusServer } = require('./hook-db-lock-probe.cjs'); /** * Read JSON input from stdin synchronously. @@ -102,6 +104,28 @@ function findGitNexusDir(startDir) { return null; } +function hasGitNexusServerOwner(gitNexusDir) { + return hasGitNexusDbLockedByGitNexusServer(path.join(gitNexusDir, 'lbug'), process.pid); +} + +function extractAugmentContext(stderr) { + const output = (stderr || '').trim(); + const marker = output.indexOf('[GitNexus]'); + const debug = process.env.GITNEXUS_DEBUG === '1' || process.env.GITNEXUS_DEBUG === 'true'; + if (debug && output.length > 0) { + // Emit the FULL discarded prefix (everything before the marker, or all of + // it when no marker is present) so suppressed diagnostics — KuzuDB lock + // warnings, parser errors, etc. — remain recoverable on the hook's own + // stderr. The untruncated payload lets operators see exactly what was + // filtered out instead of a 180-char JSON-quoted preview. + const discarded = marker === -1 ? output : output.slice(0, marker).trim(); + if (discarded.length > 0) { + process.stderr.write(`[GitNexus hook] augment stderr discarded prefix:\n${discarded}\n`); + } + } + return marker === -1 ? '' : output.slice(marker).trim(); +} + /** * Extract search pattern from tool input. */ @@ -167,6 +191,10 @@ function extractPattern(toolName, toolInput) { * 3. Fall back to npx (returns empty string) */ function resolveCliPath() { + const fromEnv = process.env.GITNEXUS_HOOK_CLI_PATH; + if (fromEnv !== undefined && String(fromEnv).trim() && fs.existsSync(String(fromEnv))) { + return String(fromEnv); + } let cliPath = path.resolve(__dirname, '..', '..', 'dist', 'cli', 'index.js'); if (!fs.existsSync(cliPath)) { try { @@ -207,7 +235,8 @@ function runGitNexusCli(cliPath, args, cwd, timeout) { function handlePreToolUse(input) { const cwd = input.cwd || process.cwd(); if (!path.isAbsolute(cwd)) return; - if (!findGitNexusDir(cwd)) return; + const gitNexusDir = findGitNexusDir(cwd); + if (!gitNexusDir) return; const toolName = input.tool_name || ''; const toolInput = input.tool_input || {}; @@ -216,20 +245,29 @@ function handlePreToolUse(input) { const pattern = extractPattern(toolName, toolInput); if (!pattern || pattern.length < 3) return; + if (hasGitNexusServerOwner(gitNexusDir)) { + process.stderr.write('[GitNexus] augment skipped: MCP server owns DB\n'); + return; + } + + const release = acquireHookSlot(gitNexusDir); + if (!release) return; const cliPath = resolveCliPath(); let result = ''; try { const child = runGitNexusCli(cliPath, ['augment', '--', pattern], cwd, 7000); if (!child.error && child.status === 0) { - result = child.stderr || ''; + result = extractAugmentContext(child.stderr || ''); } } catch { /* graceful failure */ + } finally { + release(); } - if (result && result.trim()) { - sendHookResponse('PreToolUse', result.trim()); + if (result) { + sendHookResponse('PreToolUse', result); } } diff --git a/gitnexus/hooks/claude/hook-db-lock-probe.cjs b/gitnexus/hooks/claude/hook-db-lock-probe.cjs new file mode 100644 index 000000000..783cd0804 --- /dev/null +++ b/gitnexus/hooks/claude/hook-db-lock-probe.cjs @@ -0,0 +1,238 @@ +/** + * Cross-platform best-effort probe: does another process hold dbPath open + * with a command line that looks like a GitNexus MCP/serve server? + * + * Backends (no user-installed Sysinternals): + * - Linux: scan procfs under /proc (per-PID fd entries) via stat(2) (dev+inode); works without lsof; + * optional lsof fallback when proc scan finds nothing. + * - macOS / *BSD / etc.: trusted lsof + ps (absolute paths first). + * - Windows: Restart Manager (rstrtmgr) via bundled PowerShell script + + * Win32_Process for command lines; trusted powershell.exe under %SystemRoot%. + * + * Fail-open on most errors; fail-closed only on lsof ETIMEDOUT (Unix) or + * PowerShell ETIMEDOUT (Windows), matching the hook contract. + */ + +const fs = require('fs'); +const path = require('path'); +const { spawnSync } = require('child_process'); + +function isGitNexusServerCommand(command) { + const hasServerMode = /(?:^|\s)(mcp|serve)(?:\s|$)/.test(command); + const hasGitNexus = + /(?:^|[/\\\s])gitnexus(?:\.cmd)?(?:\s|$)/.test(command) || + /node_modules[/\\]gitnexus[/\\]/.test(command); + return hasServerMode && hasGitNexus; +} + +function resolveHookBinary(tool) { + const envKey = tool === 'lsof' ? 'GITNEXUS_HOOK_LSOF_PATH' : 'GITNEXUS_HOOK_PS_PATH'; + const fromEnv = process.env[envKey]; + if (fromEnv && String(fromEnv).trim() && fs.existsSync(String(fromEnv))) { + return String(fromEnv); + } + const candidates = + tool === 'lsof' + ? ['/usr/bin/lsof', '/usr/sbin/lsof', '/sbin/lsof', tool] + : ['/bin/ps', '/usr/bin/ps', tool]; + for (const candidate of candidates) { + if (candidate === tool) return tool; + try { + if (fs.existsSync(candidate)) return candidate; + } catch { + /* ignore */ + } + } + return tool; +} + +function resolveWindowsPowerShellPath() { + const fromEnv = process.env.GITNEXUS_HOOK_POWERSHELL_PATH; + if (fromEnv && String(fromEnv).trim() && fs.existsSync(String(fromEnv).trim())) { + return String(fromEnv).trim(); + } + const root = process.env.SystemRoot || 'C:\\Windows'; + const ps = path.join(root, 'System32', 'WindowsPowerShell', 'v1.0', 'powershell.exe'); + if (fs.existsSync(ps)) return ps; + const psWow = path.join(root, 'SysWOW64', 'WindowsPowerShell', 'v1.0', 'powershell.exe'); + if (fs.existsSync(psWow)) return psWow; + return 'powershell.exe'; +} + +// Sentinel: +// undefined = not loaded yet (try the read) +// string = encoded PowerShell command (successful load) +// null = load attempted and failed (do not retry; warning already emitted) +let windowsRmListPsEncodedCommandCache; +let windowsRmListPsLoadFailureWarned = false; +function getWindowsRmListEncodedCommand() { + if (windowsRmListPsEncodedCommandCache !== undefined) { + return windowsRmListPsEncodedCommandCache; + } + try { + const ps1Path = path.join(__dirname, 'win-rm-list-json.ps1'); + const src = fs + .readFileSync(ps1Path, 'utf8') + .replace(/^\uFEFF/, '') + .replace(/\r\n/g, '\n'); + windowsRmListPsEncodedCommandCache = Buffer.from(src, 'utf16le').toString('base64'); + } catch (err) { + windowsRmListPsEncodedCommandCache = null; + if ( + !windowsRmListPsLoadFailureWarned && + (process.env.GITNEXUS_DEBUG === '1' || process.env.GITNEXUS_DEBUG === 'true') + ) { + windowsRmListPsLoadFailureWarned = true; + const msg = err && err.message ? String(err.message).slice(0, 200) : 'unknown'; + process.stderr.write(`[GitNexus hook] win-rm-list-json.ps1 load failed: ${msg}\n`); + } + } + return windowsRmListPsEncodedCommandCache; +} + +function hasGitNexusServerOwnerWindows(dbPathAbs, myPid) { + const encoded = getWindowsRmListEncodedCommand(); + if (!encoded) return false; + const psExe = resolveWindowsPowerShellPath(); + const r = spawnSync( + psExe, + [ + '-NoProfile', + '-NonInteractive', + '-ExecutionPolicy', + 'Bypass', + '-STA', + '-EncodedCommand', + encoded, + ], + { + encoding: 'utf-8', + timeout: 6000, + stdio: ['ignore', 'pipe', 'ignore'], + env: { ...process.env, GITNEXUS_HOOK_RM_TARGET: dbPathAbs }, + }, + ); + // ETIMEDOUT means the PowerShell probe didn't return in time; treat as 'unresponsive process holds DB' → fail-closed (skip augment). + if (r.error) return r.error.code === 'ETIMEDOUT'; + if (r.status !== 0) return false; + let rows; + try { + rows = JSON.parse(String(r.stdout || '').trim() || '[]'); + } catch { + return false; + } + if (!Array.isArray(rows)) return false; + for (const row of rows) { + const procId = Number(row.pid); + const cmd = String(row.cmd || ''); + if (!Number.isFinite(procId) || procId === myPid) continue; + if (isGitNexusServerCommand(cmd)) return true; + } + return false; +} + +function readLinuxCmdline(pidStr) { + try { + return fs.readFileSync(`/proc/${pidStr}/cmdline`, 'utf8').replace(/\0+/g, ' ').trim(); + } catch { + return ''; + } +} + +function linuxProcScanFindGitNexusServer(dbPathAbs, myPid) { + const raw = process.env.GITNEXUS_HOOK_LINUX_PROC_BUDGET_MS; + const budget = Number(raw && String(raw).trim()) ? Number.parseInt(String(raw), 10) : 1200; + const start = Date.now(); + let targetStat; + try { + targetStat = fs.statSync(dbPathAbs); + } catch { + return false; + } + let procEntries; + try { + procEntries = fs.readdirSync('/proc', { withFileTypes: true }); + } catch { + return false; + } + for (const ent of procEntries) { + if (Date.now() - start > budget) return false; + if (!ent.isDirectory() || !/^\d+$/.test(ent.name)) continue; + const pid = Number.parseInt(ent.name, 10); + if (!Number.isFinite(pid) || pid === myPid) continue; + const fdDir = path.join('/proc', ent.name, 'fd'); + let fds; + try { + fds = fs.readdirSync(fdDir); + } catch { + continue; + } + let holds = false; + for (const fd of fds) { + if (Date.now() - start > budget) return false; + try { + const st = fs.statSync(path.join(fdDir, fd)); + if (st.dev === targetStat.dev && st.ino === targetStat.ino) { + holds = true; + break; + } + } catch { + /* ignore */ + } + } + if (!holds) continue; + if (isGitNexusServerCommand(readLinuxCmdline(ent.name))) return true; + } + return false; +} + +function unixLsofPsFindGitNexusServer(dbPathAbs, myPid) { + const lsofPath = resolveHookBinary('lsof'); + const lsof = spawnSync(lsofPath, ['-nP', '-t', '--', dbPathAbs], { + encoding: 'utf-8', + timeout: 1000, + stdio: ['ignore', 'pipe', 'ignore'], + }); + if (lsof.error) return lsof.error.code === 'ETIMEDOUT'; + + const pids = (lsof.stdout || '').split(/\s+/).filter(Boolean); + const psPath = resolveHookBinary('ps'); + for (const pid of pids) { + if (Number(pid) === myPid) continue; + const ps = spawnSync(psPath, ['-p', pid, '-o', 'command='], { + encoding: 'utf-8', + timeout: 500, + stdio: ['ignore', 'pipe', 'ignore'], + }); + if (ps.error) { + if (ps.error.code === 'ETIMEDOUT') return true; + continue; + } + if (isGitNexusServerCommand(ps.stdout || '')) return true; + } + return false; +} + +/** + * @param {string} dbPath Absolute or relative path to the DB file (e.g. .../lbug). + * @param {number} myPid Current process PID (hook runner), excluded from matches. + */ +function hasGitNexusDbLockedByGitNexusServer(dbPath, myPid) { + if (!fs.existsSync(dbPath)) return false; + const dbPathAbs = path.resolve(dbPath); + + if (process.platform === 'win32') { + return hasGitNexusServerOwnerWindows(dbPathAbs, myPid); + } + + if (process.platform === 'linux') { + if (linuxProcScanFindGitNexusServer(dbPathAbs, myPid)) return true; + return unixLsofPsFindGitNexusServer(dbPathAbs, myPid); + } + + return unixLsofPsFindGitNexusServer(dbPathAbs, myPid); +} + +module.exports = { + hasGitNexusDbLockedByGitNexusServer, +}; diff --git a/gitnexus/hooks/claude/hook-lock.cjs b/gitnexus/hooks/claude/hook-lock.cjs new file mode 100644 index 000000000..759856384 --- /dev/null +++ b/gitnexus/hooks/claude/hook-lock.cjs @@ -0,0 +1,119 @@ +const fs = require('fs'); +const path = require('path'); + +const HOOK_LOCK_SUBDIR = '.hook-locks'; +const HOOK_LOCK_MAX_INFLIGHT = 3; +const HOOK_LOCK_STALE_MS = 30000; + +function acquireHookSlot(gitNexusDir) { + const lockDir = path.join(gitNexusDir, HOOK_LOCK_SUBDIR); + try { + fs.mkdirSync(lockDir, { recursive: true }); + } catch { + // Cannot create lock dir (read-only fs, cross-user perm denial, out of + // inodes, etc.) — fail closed by returning null. Caller skips augment. + // Fail-open here would let N concurrent hooks all proceed unguarded and + // reintroduce the #1486 fan-out the guard exists to prevent. + return null; + } + + const myPidStr = String(process.pid); + + for (let slot = 0; slot < HOOK_LOCK_MAX_INFLIGHT; slot++) { + const slotPath = path.join(lockDir, `slot-${slot}.lock`); + for (let attempt = 0; attempt < 2; attempt++) { + try { + fs.writeFileSync(slotPath, myPidStr, { flag: 'wx' }); + let released = false; + const release = () => { + if (released) return; + released = true; + try { + // Only unlink if we still own the slot. If we appeared stale and + // another hook took over, the file now belongs to it — leave alone. + const content = fs.readFileSync(slotPath, 'utf-8').trim(); + if (content === myPidStr) fs.unlinkSync(slotPath); + } catch { + /* already removed or unreadable */ + } + }; + process.on('exit', release); + return release; + } catch { + // Slot exists. Decide whether to take it over. + // Open once and inspect mtime + content via the same fd so there's + // no TOCTOU between the metadata check and the content read + // (codeql js/file-system-race). + let fd; + try { + fd = fs.openSync(slotPath, 'r'); + } catch { + continue; // Vanished between EEXIST and open — retry this slot. + } + let isLive = false; + let mtimeMs = Date.now(); + try { + mtimeMs = fs.fstatSync(fd).mtimeMs; + const buf = Buffer.alloc(32); + const n = fs.readSync(fd, buf, 0, 32, 0); + const ownerStr = buf.slice(0, n).toString('utf-8').trim(); + if (ownerStr === '') { + // Owner created the file but hasn't written its PID yet. The + // wx open+write window is microseconds; give it the benefit + // of the doubt and treat as live. + isLive = true; + } else { + const owner = Number.parseInt(ownerStr, 10); + if (Number.isFinite(owner) && owner > 0) { + try { + process.kill(owner, 0); + isLive = true; + } catch (e) { + // ESRCH = process gone → treat as dead. EPERM = process exists + // but owned by another user (cross-user lock dir) → still alive, + // keep the slot. Anything else: be conservative, assume alive. + if (e && e.code === 'ESRCH') { + isLive = false; + } else { + isLive = true; + } + } + } + } + } catch { + /* unreadable — treat as dead */ + } finally { + try { + fs.closeSync(fd); + } catch { + /* already closed */ + } + } + // For slots younger than HOOK_LOCK_STALE_MS, PID-liveness wins — + // a slow-but-alive hook is never wrongly evicted. For older slots, + // age is the final arbiter as a defense against PID reuse on long- + // abandoned slots. 30s >> the 7s augment timeout, so a healthy run + // never crosses this threshold. + if (isLive && Date.now() - mtimeMs > HOOK_LOCK_STALE_MS) { + isLive = false; + } + if (isLive) break; // Try the next slot. + try { + fs.unlinkSync(slotPath); + } catch { + /* another hook beat us to it — retry will hit EEXIST */ + } + // Loop and retry this slot. + } + } + } + + return null; +} + +module.exports = { + HOOK_LOCK_SUBDIR, + HOOK_LOCK_MAX_INFLIGHT, + HOOK_LOCK_STALE_MS, + acquireHookSlot, +}; diff --git a/gitnexus/hooks/claude/win-rm-list-json.ps1 b/gitnexus/hooks/claude/win-rm-list-json.ps1 new file mode 100644 index 000000000..5c1564e30 --- /dev/null +++ b/gitnexus/hooks/claude/win-rm-list-json.ps1 @@ -0,0 +1,76 @@ +$ErrorActionPreference = 'Stop' +$target = $env:GITNEXUS_HOOK_RM_TARGET +if ([string]::IsNullOrWhiteSpace($target)) { Write-Output '[]'; exit 0 } +$target = (Resolve-Path -LiteralPath $target).ProviderPath + +if (-not ([Management.Automation.PSTypeName]'GitNexusHookRm.Native').Type) { +Add-Type @' +using System; +using System.Runtime.InteropServices; +namespace GitNexusHookRm { + public static class Native { + public const int ErrorMoreData = 234; + [StructLayout(LayoutKind.Sequential, Pack = 4)] + public struct RM_UNIQUE_PROCESS { + public int dwProcessId; + public long ProcessStartTime; + } + [StructLayout(LayoutKind.Sequential, CharSet = CharSet.Unicode)] + public struct RM_PROCESS_INFO { + public RM_UNIQUE_PROCESS Process; + [MarshalAs(UnmanagedType.ByValTStr, SizeConst = 256)] + public string strAppName; + [MarshalAs(UnmanagedType.ByValTStr, SizeConst = 64)] + public string strServiceShortName; + public uint ApplicationType; + public uint AppStatus; + public uint TSSessionId; + public uint bRestartable; + } + [DllImport("rstrtmgr.dll", CharSet = CharSet.Unicode)] + public static extern int RmStartSession(out uint pSessionHandle, uint dwSessionFlags, string strSessionKey); + [DllImport("rstrtmgr.dll", CharSet = CharSet.Unicode)] + public static extern int RmRegisterResources(uint pSessionHandle, uint nFiles, string[] rgsFileNames, uint nApplications, IntPtr rgApplications, uint nServices, string[] rgsServiceNames); + [DllImport("rstrtmgr.dll")] + public static extern int RmGetList(uint dwSessionHandle, out uint pnProcInfoNeeded, ref uint pnProcInfo, [In, Out] RM_PROCESS_INFO[] rgAffectedApps, ref uint lpdwRebootReasons); + [DllImport("rstrtmgr.dll")] + public static extern int RmEndSession(uint pSessionHandle); + } +} +'@ +} + +$h = [uint32]0 +$key = [guid]::NewGuid().ToString('N') +$rmErr = [GitNexusHookRm.Native]::RmStartSession([ref]$h, 0, $key) +if ($rmErr -ne 0) { Write-Output '[]'; exit 0 } +$files = @($target) +$err = [GitNexusHookRm.Native]::RmRegisterResources($h, 1, $files, 0, [IntPtr]::Zero, 0, $null) +if ($err -ne 0) { + [void][GitNexusHookRm.Native]::RmEndSession($h) + Write-Output '[]' + exit 0 +} +$need = [uint32]0 +$n = [uint32]0 +$reboot = [uint32]0 +$err = [GitNexusHookRm.Native]::RmGetList($h, [ref]$need, [ref]$n, $null, [ref]$reboot) +if ($err -ne [GitNexusHookRm.Native]::ErrorMoreData) { + [void][GitNexusHookRm.Native]::RmEndSession($h) + Write-Output '[]' + exit 0 +} +$n = $need +$buf = New-Object GitNexusHookRm.Native+RM_PROCESS_INFO[] ([int]$n) +$err = [GitNexusHookRm.Native]::RmGetList($h, [ref]$need, [ref]$n, $buf, [ref]$reboot) +[void][GitNexusHookRm.Native]::RmEndSession($h) +if ($err -ne 0) { Write-Output '[]'; exit 0 } + +$out = @() +for ($i = 0; $i -lt [int]$n; $i++) { + $procId = $buf[$i].Process.dwProcessId + $p = Get-CimInstance -ClassName Win32_Process -Filter "ProcessId=$procId" -ErrorAction SilentlyContinue + $cmd = if ($p) { $p.CommandLine } else { '' } + $out += [PSCustomObject]@{ pid = [int]$procId; cmd = $cmd } +} +ConvertTo-Json -InputObject @($out) -Compress diff --git a/gitnexus/package-lock.json b/gitnexus/package-lock.json index 04233b1a1..b367a3251 100644 --- a/gitnexus/package-lock.json +++ b/gitnexus/package-lock.json @@ -1,12 +1,12 @@ { "name": "gitnexus", - "version": "1.6.3", + "version": "1.6.4", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "gitnexus", - "version": "1.6.3", + "version": "1.6.4", "hasInstallScript": true, "license": "PolyForm-Noncommercial-1.0.0", "dependencies": { @@ -63,7 +63,7 @@ "vitest": "^4.0.18" }, "engines": { - "node": ">=20.0.0" + "node": ">=22.0.0" }, "optionalDependencies": { "node-addon-api": "^8.0.0", @@ -142,9 +142,9 @@ } }, "node_modules/@emnapi/core": { - "version": "1.9.2", - "resolved": "https://registry.npmjs.org/@emnapi/core/-/core-1.9.2.tgz", - "integrity": "sha512-UC+ZhH3XtczQYfOlu3lNEkdW/p4dsJ1r/bP7H8+rhao3TTTMO1ATq/4DdIi23XuGoFY+Cz0JmCbdVl0hz9jZcA==", + "version": "1.10.0", + "resolved": "https://registry.npmjs.org/@emnapi/core/-/core-1.10.0.tgz", + "integrity": "sha512-yq6OkJ4p82CAfPl0u9mQebQHKPJkY7WrIuk205cTYnYe+k2Z8YBh11FrbRG/H6ihirqcacOgl2BIO8oyMQLeXw==", "dev": true, "license": "MIT", "optional": true, @@ -1572,9 +1572,9 @@ } }, "node_modules/@oxc-project/types": { - "version": "0.126.0", - "resolved": "https://registry.npmjs.org/@oxc-project/types/-/types-0.126.0.tgz", - "integrity": "sha512-oGfVtjAgwQVVpfBrbtk4e1XDyWHRFta6BS3GWVzrF8xYBT2VGQAk39yJS/wFSMrZqoiCU4oghT3Ch0HaHGIHcQ==", + "version": "0.130.0", + "resolved": "https://registry.npmjs.org/@oxc-project/types/-/types-0.130.0.tgz", + "integrity": "sha512-ibD2usx9JRu7f5pu2tMKMI4cpA4NgXJQoYRP4pQ7Pxmn1l6k/53qWtQWZayhYy3X4QZkt90Ot+mJEaeXouio6Q==", "dev": true, "license": "MIT", "funding": { @@ -1600,9 +1600,9 @@ "license": "BSD-3-Clause" }, "node_modules/@protobufjs/codegen": { - "version": "2.0.4", - "resolved": "https://registry.npmjs.org/@protobufjs/codegen/-/codegen-2.0.4.tgz", - "integrity": "sha512-YyFaikqM5sH0ziFZCN3xDC7zeGaB/d0IUb9CATugHWbd1FRFwWwt4ld4OYMPWu5a3Xe01mGAULCdqhMlPl29Jg==", + "version": "2.0.5", + "resolved": "https://registry.npmjs.org/@protobufjs/codegen/-/codegen-2.0.5.tgz", + "integrity": "sha512-zgXFLzW3Ap33e6d0Wlj4MGIm6Ce8O89n/apUaGNB/jx+hw+ruWEp7EwGUshdLKVRCxZW12fp9r40E1mQrf/34g==", "license": "BSD-3-Clause" }, "node_modules/@protobufjs/eventemitter": { @@ -1628,9 +1628,9 @@ "license": "BSD-3-Clause" }, "node_modules/@protobufjs/inquire": { - "version": "1.1.0", - "resolved": "https://registry.npmjs.org/@protobufjs/inquire/-/inquire-1.1.0.tgz", - "integrity": "sha512-kdSefcPdruJiFMVSbn801t4vFK7KB/5gd2fYvrxhuJYg8ILrmn9SKSX2tZdV6V+ksulWqS7aXjBcRXl3wHoD9Q==", + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/@protobufjs/inquire/-/inquire-1.1.1.tgz", + "integrity": "sha512-mnzgDV26ueAvk7rsbt9L7bE0SuAoqyuys/sMMrmVcN5x9VsxpcG3rqAUSgDyLp0UZlmNfIbQ4fHfCtreVBk8Ew==", "license": "BSD-3-Clause" }, "node_modules/@protobufjs/path": { @@ -1646,15 +1646,15 @@ "license": "BSD-3-Clause" }, "node_modules/@protobufjs/utf8": { - "version": "1.1.0", - "resolved": "https://registry.npmjs.org/@protobufjs/utf8/-/utf8-1.1.0.tgz", - "integrity": "sha512-Vvn3zZrhQZkkBE8LSuW3em98c0FwgO4nxzv6OdSxPKJIEKY2bGbHn+mhGIPerzI4twdxaP8/0+06HBpwf345Lw==", + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/@protobufjs/utf8/-/utf8-1.1.1.tgz", + "integrity": "sha512-oOAWABowe8EAbMyWKM0tYDKi8Yaox52D+HWZhAIJqQXbqe0xI/GV7FhLWqlEKreMkfDjshR5FKgi3mnle0h6Eg==", "license": "BSD-3-Clause" }, "node_modules/@rolldown/binding-android-arm64": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-android-arm64/-/binding-android-arm64-1.0.0-rc.16.tgz", - "integrity": "sha512-rhY3k7Bsae9qQfOtph2Pm2jZEA+s8Gmjoz4hhmx70K9iMQ/ddeae+xhRQcM5IuVx5ry1+bGfkvMn7D6MJggVSA==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-android-arm64/-/binding-android-arm64-1.0.1.tgz", + "integrity": "sha512-fJI3I0r3C3Oj/zdBCpaCmBRZYf07xpaq4yCfDDoSFm+beWNzbIl26puW8RraUdugoJw/95zerNOn6jasAhzSmg==", "cpu": [ "arm64" ], @@ -1669,9 +1669,9 @@ } }, "node_modules/@rolldown/binding-darwin-arm64": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-arm64/-/binding-darwin-arm64-1.0.0-rc.16.tgz", - "integrity": "sha512-rNz0yK078yrNn3DrdgN+PKiMOW8HfQ92jQiXxwX8yW899ayV00MLVdaCNeVBhG/TbH3ouYVObo8/yrkiectkcQ==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-arm64/-/binding-darwin-arm64-1.0.1.tgz", + "integrity": "sha512-cKnAhWEsV7TPcA/5EAteDp6KcJZBQ2G+BqE7zayMMi7kMvwRsbv7WT9aOnn0WNl4SKEIf43vjS31iUPu80nzXg==", "cpu": [ "arm64" ], @@ -1686,9 +1686,9 @@ } }, "node_modules/@rolldown/binding-darwin-x64": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-x64/-/binding-darwin-x64-1.0.0-rc.16.tgz", - "integrity": "sha512-r/OmdR00HmD4i79Z//xO06uEPOq5hRXdhw7nzkxQxwSavs3PSHa1ijntdpOiZ2mzOQ3fVVu8C1M19FoNM+dMUQ==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-darwin-x64/-/binding-darwin-x64-1.0.1.tgz", + "integrity": "sha512-YKrVwQjIRBPo+5G/u03wGjbdy4q7pyzCe93DK9VJ7zkVmeg8LJ7GbgsiHWdR4xSoe4CAXRD7Bcjgbtr64bkXNg==", "cpu": [ "x64" ], @@ -1703,9 +1703,9 @@ } }, "node_modules/@rolldown/binding-freebsd-x64": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-freebsd-x64/-/binding-freebsd-x64-1.0.0-rc.16.tgz", - "integrity": "sha512-KcRE5w8h0OnjUatG8pldyD14/CQ5Phs1oxfR+3pKDjboHRo9+MkqQaiIZlZRpsxC15paeXme/I127tUa9TXJ6g==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-freebsd-x64/-/binding-freebsd-x64-1.0.1.tgz", + "integrity": "sha512-z/oBsREo46SsFqBwYtFe0kpJeBijAT48O/WXLI4suiCLBkr03RTtTJMCzSdDd2znlh8VJizL09XVkQgk8IZonw==", "cpu": [ "x64" ], @@ -1720,9 +1720,9 @@ } }, "node_modules/@rolldown/binding-linux-arm-gnueabihf": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm-gnueabihf/-/binding-linux-arm-gnueabihf-1.0.0-rc.16.tgz", - "integrity": "sha512-bT0guA1bpxEJ/ZhTRniQf7rNF8ybvXOuWbNIeLABaV5NGjx4EtOWBTSRGWFU9ZWVkPOZ+HNFP8RMcBokBiZ0Kg==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm-gnueabihf/-/binding-linux-arm-gnueabihf-1.0.1.tgz", + "integrity": "sha512-ik8q7GM11zxvYxFc2PeDcT6TBvhCQMaUxfph/M5l9sKuTs/Sjg3L+Byw0F7w0ZVLBZmx30P+gG0ECzzN+MFcmQ==", "cpu": [ "arm" ], @@ -1737,9 +1737,9 @@ } }, "node_modules/@rolldown/binding-linux-arm64-gnu": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-gnu/-/binding-linux-arm64-gnu-1.0.0-rc.16.tgz", - "integrity": "sha512-+tHktCHWV8BDQSjemUqm/Jl/TPk3QObCTIjmdDy/nlupcujZghmKK2962LYrqFpWu+ai01AN/REOH3NEpqvYQg==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-gnu/-/binding-linux-arm64-gnu-1.0.1.tgz", + "integrity": "sha512-QoSx2EkyrrdZ6kcyE8stqZ62t0Yra8Fs5ia9lOxJrh6TMQJK7gQKmscdTHf7pOXKREKrVwOtJcQG3qVSfc866A==", "cpu": [ "arm64" ], @@ -1754,9 +1754,9 @@ } }, "node_modules/@rolldown/binding-linux-arm64-musl": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-musl/-/binding-linux-arm64-musl-1.0.0-rc.16.tgz", - "integrity": "sha512-3fPzdREH806oRLxpTWW1Gt4tQHs0TitZFOECB2xzCFLPKnSOy90gwA7P29cksYilFO6XVRY1kzga0cL2nRjKPg==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-arm64-musl/-/binding-linux-arm64-musl-1.0.1.tgz", + "integrity": "sha512-uwNwFpwKeNiZawfAWBgg0VIztPTV3ihhh1vV334h9ivnNLorxnQMU6Fz8wG1Zb4Qh9LC1/MkcyT3YlDXG3Rsgg==", "cpu": [ "arm64" ], @@ -1771,9 +1771,9 @@ } }, "node_modules/@rolldown/binding-linux-ppc64-gnu": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-ppc64-gnu/-/binding-linux-ppc64-gnu-1.0.0-rc.16.tgz", - "integrity": "sha512-EKwI1tSrLs7YVw+JPJT/G2dJQ1jl9qlTTTEG0V2Ok/RdOenRfBw2PQdLPyjhIu58ocdBfP7vIRN/pvMsPxs/AQ==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-ppc64-gnu/-/binding-linux-ppc64-gnu-1.0.1.tgz", + "integrity": "sha512-zY1bul7OWr7DFBiJ++wofXvnr8B45ce3QsQUhKrIhXsygAh7bTkwyeM1bi1a2g5C/yC/N8TZyGDEoMfm/l9mpg==", "cpu": [ "ppc64" ], @@ -1788,9 +1788,9 @@ } }, "node_modules/@rolldown/binding-linux-s390x-gnu": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-s390x-gnu/-/binding-linux-s390x-gnu-1.0.0-rc.16.tgz", - "integrity": "sha512-Uknladnb3Sxqu6SEcqBldQyJUpk8NleooZEc0MbRBJ4inEhRYWZX0NJu12vNf2mqAq7gsofAxHrGghiUYjhaLQ==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-s390x-gnu/-/binding-linux-s390x-gnu-1.0.1.tgz", + "integrity": "sha512-0frlsT/f4Ft6I7SMESTKnF3cZsdicQn1dCMkF/jT9wDLE+gGoiQfv1nmT9e+s7s/fekvvy6tZM2jHvI2tkbJDQ==", "cpu": [ "s390x" ], @@ -1805,9 +1805,9 @@ } }, "node_modules/@rolldown/binding-linux-x64-gnu": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-gnu/-/binding-linux-x64-gnu-1.0.0-rc.16.tgz", - "integrity": "sha512-FIb8+uG49sZBtLTn+zt1AJ20TqVcqWeSIyoVt0or7uAWesgKaHbiBh6OpA/k9v0LTt+PTrb1Lao133kP4uVxkg==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-gnu/-/binding-linux-x64-gnu-1.0.1.tgz", + "integrity": "sha512-XABVmGp9Tg0WspTVvwduTc4fpqy6JnAUrSQe6OuyqD/03nI7r0O9OWUkMIwFrjKAIqolvqoA4ZrJppgwE0Gxmw==", "cpu": [ "x64" ], @@ -1822,9 +1822,9 @@ } }, "node_modules/@rolldown/binding-linux-x64-musl": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-musl/-/binding-linux-x64-musl-1.0.0-rc.16.tgz", - "integrity": "sha512-RuERhF9/EgWxZEXYWCOaViUWHIboceK4/ivdtQ3R0T44NjLkIIlGIAVAuCddFxsZ7vnRHtNQUrt2vR2n2slB2w==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-linux-x64-musl/-/binding-linux-x64-musl-1.0.1.tgz", + "integrity": "sha512-bV4fzswuzVcKD90o/VM6QqKxnxlDq0g2BISDLNVmxrnhpv1DDbyPhCIjYfvzYLV+MvkKKnQt2Q6AO86SEBULUQ==", "cpu": [ "x64" ], @@ -1839,9 +1839,9 @@ } }, "node_modules/@rolldown/binding-openharmony-arm64": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-openharmony-arm64/-/binding-openharmony-arm64-1.0.0-rc.16.tgz", - "integrity": "sha512-mXcXnvd9GpazCxeUCCnZ2+YF7nut+ZOEbE4GtaiPtyY6AkhZWbK70y1KK3j+RDhjVq5+U8FySkKRb/+w0EeUwA==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-openharmony-arm64/-/binding-openharmony-arm64-1.0.1.tgz", + "integrity": "sha512-/Mh0Zhq3OP7fVs0kcQHZP6lZEthMGTaSf8UBQYSFEZDWGXXlEC+nJ6EqenaK2t4LBXMe3A+K/G2BVXXdtOr4PQ==", "cpu": [ "arm64" ], @@ -1856,9 +1856,9 @@ } }, "node_modules/@rolldown/binding-wasm32-wasi": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-wasm32-wasi/-/binding-wasm32-wasi-1.0.0-rc.16.tgz", - "integrity": "sha512-3Q2KQxnC8IJOLqXmUMoYwyIPZU9hzRbnHaoV3Euz+VVnjZKcY8ktnNP8T9R4/GGQtb27C/UYKABxesKWb8lsvQ==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-wasm32-wasi/-/binding-wasm32-wasi-1.0.1.tgz", + "integrity": "sha512-+1xc9X45l8ufsBAm6Gjvx2qDRIY9lTVt0cgWNcJ+1gdhXvkbxePA60yRTwSTuXL09CMhyJmjpV7E3NoyxbqFQQ==", "cpu": [ "wasm32" ], @@ -1866,8 +1866,8 @@ "license": "MIT", "optional": true, "dependencies": { - "@emnapi/core": "1.9.2", - "@emnapi/runtime": "1.9.2", + "@emnapi/core": "1.10.0", + "@emnapi/runtime": "1.10.0", "@napi-rs/wasm-runtime": "^1.1.4" }, "engines": { @@ -1875,9 +1875,9 @@ } }, "node_modules/@rolldown/binding-wasm32-wasi/node_modules/@emnapi/runtime": { - "version": "1.9.2", - "resolved": "https://registry.npmjs.org/@emnapi/runtime/-/runtime-1.9.2.tgz", - "integrity": "sha512-3U4+MIWHImeyu1wnmVygh5WlgfYDtyf0k8AbLhMFxOipihf6nrWC4syIm/SwEeec0mNSafiiNnMJwbza/Is6Lw==", + "version": "1.10.0", + "resolved": "https://registry.npmjs.org/@emnapi/runtime/-/runtime-1.10.0.tgz", + "integrity": "sha512-ewvYlk86xUoGI0zQRNq/mC+16R1QeDlKQy21Ki3oSYXNgLb45GV1P6A0M+/s6nyCuNDqe5VpaY84BzXGwVbwFA==", "dev": true, "license": "MIT", "optional": true, @@ -1886,9 +1886,9 @@ } }, "node_modules/@rolldown/binding-win32-arm64-msvc": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-arm64-msvc/-/binding-win32-arm64-msvc-1.0.0-rc.16.tgz", - "integrity": "sha512-tj7XRemQcOcFwv7qhpUxMTBbI5mWMlE4c1Omhg5+h8GuLXzyj8HviYgR+bB2DMDgRqUE+jiDleqSCRjx4aYk/Q==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-arm64-msvc/-/binding-win32-arm64-msvc-1.0.1.tgz", + "integrity": "sha512-1D+UqZdfnuR+Jy1GgMJwi85bD40H21uNmOPRWQhw4oRSuolZ/B5rixZ45DK2KXOTCvmVCecauWgEhbw8bI7tOw==", "cpu": [ "arm64" ], @@ -1903,9 +1903,9 @@ } }, "node_modules/@rolldown/binding-win32-x64-msvc": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-x64-msvc/-/binding-win32-x64-msvc-1.0.0-rc.16.tgz", - "integrity": "sha512-PH5DRZT+F4f2PTXRXR8uJxnBq2po/xFtddyabTJVJs/ZYVHqXPEgNIr35IHTEa6bpa0Q8Awg+ymkTaGnKITw4g==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/binding-win32-x64-msvc/-/binding-win32-x64-msvc-1.0.1.tgz", + "integrity": "sha512-INAycaWuhlOK3wk4mRHGsdgwYWmd9cChdPdE9bwWmy6rn9VqVNYNFGhOdXrofXUxwHIncSiPNb8tNm8knDVIeQ==", "cpu": [ "x64" ], @@ -1920,9 +1920,9 @@ } }, "node_modules/@rolldown/pluginutils": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-rc.16.tgz", - "integrity": "sha512-45+YtqxLYKDWQouLKCrpIZhke+nXxhsw+qAHVzHDVwttyBlHNBVs2K25rDXrZzhpTp9w1FlAlvweV1H++fdZoA==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.1.tgz", + "integrity": "sha512-2j9bGt5Jh8hj+vPtgzPtl72j0yRxHAyumoo6TNfAjsLB04UtpSvPbPcDcBMxz7n+9CYB0c1GxQFxYRg2jimqGw==", "dev": true, "license": "MIT" }, @@ -1941,9 +1941,9 @@ "license": "MIT" }, "node_modules/@tybys/wasm-util": { - "version": "0.10.1", - "resolved": "https://registry.npmjs.org/@tybys/wasm-util/-/wasm-util-0.10.1.tgz", - "integrity": "sha512-9tTaPJLSiejZKx+Bmog4uSubteqTvFrVrURwkmHixBo0G4seD0zUxp98E1DzUBJxLQ3NPwXrGKDiVjwx/DpPsg==", + "version": "0.10.2", + "resolved": "https://registry.npmjs.org/@tybys/wasm-util/-/wasm-util-0.10.2.tgz", + "integrity": "sha512-RoBvJ2X0wuKlWFIjrwffGw1IqZHKQqzIchKaadZZfnNpsAYp2mM0h36JtPCjNDAHGgYez/15uMBpfGwchhiMgg==", "dev": true, "license": "MIT", "optional": true, @@ -2132,14 +2132,14 @@ } }, "node_modules/@vitest/coverage-v8": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-4.1.5.tgz", - "integrity": "sha512-38C0/Ddb7HcRG0Z4/DUem8x57d2p9jYgp18mkaYswEOQBGsI1CG4f/hjm0ZCeaJfWhSZ4k7jgs29V1Zom7Ki9A==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-4.1.6.tgz", + "integrity": "sha512-36l628fQ/9a/8ihy97eOtEnvWQEdqULQOJtcaxtoNq0G1w3Mxd4szSahOaMM9/NGyZ+hyKcMtIW/WIxq0XQViQ==", "dev": true, "license": "MIT", "dependencies": { "@bcoe/v8-coverage": "^1.0.2", - "@vitest/utils": "4.1.5", + "@vitest/utils": "4.1.6", "ast-v8-to-istanbul": "^1.0.0", "istanbul-lib-coverage": "^3.2.2", "istanbul-lib-report": "^3.0.1", @@ -2153,8 +2153,8 @@ "url": "https://opencollective.com/vitest" }, "peerDependencies": { - "@vitest/browser": "4.1.5", - "vitest": "4.1.5" + "@vitest/browser": "4.1.6", + "vitest": "4.1.6" }, "peerDependenciesMeta": { "@vitest/browser": { @@ -2163,16 +2163,16 @@ } }, "node_modules/@vitest/expect": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-4.1.5.tgz", - "integrity": "sha512-PWBaRY5JoKuRnHlUHfpV/KohFylaDZTupcXN1H9vYryNLOnitSw60Mw9IAE2r67NbwwzBw/Cc/8q9BK3kIX8Kw==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-4.1.6.tgz", + "integrity": "sha512-7EHDquPthALSV0jhhjgEW8FXaviMx7rSqu8W6oqCoAuOhKov814P99QDV1pxMA3QPv21YudvJngIhjrNI4opLg==", "dev": true, "license": "MIT", "dependencies": { "@standard-schema/spec": "^1.1.0", "@types/chai": "^5.2.2", - "@vitest/spy": "4.1.5", - "@vitest/utils": "4.1.5", + "@vitest/spy": "4.1.6", + "@vitest/utils": "4.1.6", "chai": "^6.2.2", "tinyrainbow": "^3.1.0" }, @@ -2181,13 +2181,13 @@ } }, "node_modules/@vitest/mocker": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-4.1.5.tgz", - "integrity": "sha512-/x2EmFC4mT4NNzqvC3fmesuV97w5FC903KPmey4gsnJiMQ3Be1IlDKVaDaG8iqaLFHqJ2FVEkxZk5VmeLjIItw==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-4.1.6.tgz", + "integrity": "sha512-MCFc63czMjEInOlcY2cpQCvCN+KgbAn+60xu9cMgP4sKaLC5JNAKw7JH8QdAnoAC88hW1IiSNZ+GgVXlN1UcMQ==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/spy": "4.1.5", + "@vitest/spy": "4.1.6", "estree-walker": "^3.0.3", "magic-string": "^0.30.21" }, @@ -2208,9 +2208,9 @@ } }, "node_modules/@vitest/pretty-format": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.5.tgz", - "integrity": "sha512-7I3q6l5qr03dVfMX2wCo9FxwSJbPdwKjy2uu/YPpU3wfHvIL4QHwVRp57OfGrDFeUJ8/8QdfBKIV12FTtLn00g==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.6.tgz", + "integrity": "sha512-h5SxD/IzNhZYnrSZRsUZQIC+vD0GY8cUvq0iwsmkFKixRCKLLWqCXa/FIQ4S1R+sI+PGoojkHsdNrbZiM9Qpgw==", "dev": true, "license": "MIT", "dependencies": { @@ -2221,13 +2221,13 @@ } }, "node_modules/@vitest/runner": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-4.1.5.tgz", - "integrity": "sha512-2D+o7Pr82IEO46YPpoA/YU0neeyr6FTerQb5Ro7BUnBuv6NQtT/kmVnczngiMEBhzgqz2UZYl5gArejsyERDSQ==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-4.1.6.tgz", + "integrity": "sha512-nOPCmn2+yD0ZNmKdsXGv/UxMMWbMuKeD6GyYncNwdkYDxpQvrPSKYj2rWuDjC2Y4b6w6hjip5dBKFzEUuZe3vA==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/utils": "4.1.5", + "@vitest/utils": "4.1.6", "pathe": "^2.0.3" }, "funding": { @@ -2235,14 +2235,14 @@ } }, "node_modules/@vitest/snapshot": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-4.1.5.tgz", - "integrity": "sha512-zypXEt4KH/XgKGPUz4eC2AvErYx0My5hfL8oDb1HzGFpEk1P62bxSohdyOmvz+d9UJwanI68MKwr2EquOaOgMQ==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-4.1.6.tgz", + "integrity": "sha512-YhsdE6xAVfTDmzjxL2ZDUvjj+ZsgyOKe+TdQzqkD72wIOmHka8NuGQ6NpTNZv9D2Z63fbwWKJPeVpEw4EQgYxw==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/pretty-format": "4.1.5", - "@vitest/utils": "4.1.5", + "@vitest/pretty-format": "4.1.6", + "@vitest/utils": "4.1.6", "magic-string": "^0.30.21", "pathe": "^2.0.3" }, @@ -2251,9 +2251,9 @@ } }, "node_modules/@vitest/spy": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-4.1.5.tgz", - "integrity": "sha512-2lNOsh6+R2Idnf1TCZqSwYlKN2E/iDlD8sgU59kYVl+OMDmvldO1VDk39smRfpUNwYpNRVn3w4YfuC7KfbBnkQ==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-4.1.6.tgz", + "integrity": "sha512-JFKxMx6udhwKh/Ldo270e17QX710vgunMkuPAvXjHSvC6oqLWAHhVhjg/I71q0u0CBSErIODV1Kjv0FQNSWjdg==", "dev": true, "license": "MIT", "funding": { @@ -2261,13 +2261,13 @@ } }, "node_modules/@vitest/utils": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.5.tgz", - "integrity": "sha512-76wdkrmfXfqGjueGgnb45ITPyUi1ycZ4IHgC2bhPDUfWHklY/q3MdLOAB+TF1e6xfl8NxNY0ZYaPCFNWSsw3Ug==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.6.tgz", + "integrity": "sha512-FxIY+U81R3LGKCxaHHFRQ5+g6/iRgGLmeHWdp2Amj4ljQRrEIWHmZyDfDYBRZlpyqA7qKxtS9DD1dhk8RnRIVQ==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/pretty-format": "4.1.5", + "@vitest/pretty-format": "4.1.6", "convert-source-map": "^2.0.0", "tinyrainbow": "^3.1.0" }, @@ -4151,9 +4151,9 @@ "license": "MIT" }, "node_modules/nanoid": { - "version": "3.3.11", - "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz", - "integrity": "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w==", + "version": "3.3.12", + "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.12.tgz", + "integrity": "sha512-ZB9RH/39qpq5Vu6Y+NmUaFhQR6pp+M2Xt76XBnEwDaGcVAqhlvxrl3B2bKS5D3NH3QR76v3aSrKaF/Kiy7lEtQ==", "dev": true, "funding": [ { @@ -4498,9 +4498,9 @@ "license": "MIT" }, "node_modules/postcss": { - "version": "8.5.10", - "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.10.tgz", - "integrity": "sha512-pMMHxBOZKFU6HgAZ4eyGnwXF/EvPGGqUr0MnZ5+99485wwW41kW91A4LOGxSHhgugZmSChL5AlElNdwlNgcnLQ==", + "version": "8.5.14", + "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.14.tgz", + "integrity": "sha512-SoSL4+OSEtR99LHFZQiJLkT59C5B1amGO1NzTwj7TT1qCUgUO6hxOvzkOYxD+vMrXBM3XJIKzokoERdqQq/Zmg==", "dev": true, "funding": [ { @@ -4543,22 +4543,22 @@ "license": "MIT" }, "node_modules/protobufjs": { - "version": "7.5.5", - "resolved": "https://registry.npmjs.org/protobufjs/-/protobufjs-7.5.5.tgz", - "integrity": "sha512-3wY1AxV+VBNW8Yypfd1yQY9pXnqTAN+KwQxL8iYm3/BjKYMNg4i0owhEe26PWDOMaIrzeeF98Lqd5NGz4omiIg==", + "version": "7.5.8", + "resolved": "https://registry.npmjs.org/protobufjs/-/protobufjs-7.5.8.tgz", + "integrity": "sha512-dvpCIeLPbXZS/Ete7yLaO7RenOdken2NHKykBXbsaGxZT0UTltcarBciw+A78SRQs9iMAAVpsYA+l8b1hTePIA==", "hasInstallScript": true, "license": "BSD-3-Clause", "dependencies": { "@protobufjs/aspromise": "^1.1.2", "@protobufjs/base64": "^1.1.2", - "@protobufjs/codegen": "^2.0.4", + "@protobufjs/codegen": "^2.0.5", "@protobufjs/eventemitter": "^1.1.0", "@protobufjs/fetch": "^1.1.0", "@protobufjs/float": "^1.0.2", - "@protobufjs/inquire": "^1.1.0", + "@protobufjs/inquire": "^1.1.1", "@protobufjs/path": "^1.1.2", "@protobufjs/pool": "^1.1.0", - "@protobufjs/utf8": "^1.1.0", + "@protobufjs/utf8": "^1.1.1", "@types/node": ">=13.7.0", "long": "^5.0.0" }, @@ -4703,14 +4703,14 @@ } }, "node_modules/rolldown": { - "version": "1.0.0-rc.16", - "resolved": "https://registry.npmjs.org/rolldown/-/rolldown-1.0.0-rc.16.tgz", - "integrity": "sha512-rzi5WqKzEZw3SooTt7cgm4eqIoujPIyGcJNGFL7iPEuajQw7vxMHUkXylu4/vhCkJGXsgRmxqMKXUpT6FEgl0g==", + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/rolldown/-/rolldown-1.0.1.tgz", + "integrity": "sha512-X0KQHljNnEkWNqqiz9zJrGunh1B0HgOxLXvnFpCOcadzcy5qohZ3tqMEUg00vncoRovXuK3ZqCT9KnnKzoInFQ==", "dev": true, "license": "MIT", "dependencies": { - "@oxc-project/types": "=0.126.0", - "@rolldown/pluginutils": "1.0.0-rc.16" + "@oxc-project/types": "=0.130.0", + "@rolldown/pluginutils": "^1.0.0" }, "bin": { "rolldown": "bin/cli.mjs" @@ -4719,21 +4719,21 @@ "node": "^20.19.0 || >=22.12.0" }, "optionalDependencies": { - "@rolldown/binding-android-arm64": "1.0.0-rc.16", - "@rolldown/binding-darwin-arm64": "1.0.0-rc.16", - "@rolldown/binding-darwin-x64": "1.0.0-rc.16", - "@rolldown/binding-freebsd-x64": "1.0.0-rc.16", - "@rolldown/binding-linux-arm-gnueabihf": "1.0.0-rc.16", - "@rolldown/binding-linux-arm64-gnu": "1.0.0-rc.16", - "@rolldown/binding-linux-arm64-musl": "1.0.0-rc.16", - "@rolldown/binding-linux-ppc64-gnu": "1.0.0-rc.16", - "@rolldown/binding-linux-s390x-gnu": "1.0.0-rc.16", - "@rolldown/binding-linux-x64-gnu": "1.0.0-rc.16", - "@rolldown/binding-linux-x64-musl": "1.0.0-rc.16", - "@rolldown/binding-openharmony-arm64": "1.0.0-rc.16", - "@rolldown/binding-wasm32-wasi": "1.0.0-rc.16", - "@rolldown/binding-win32-arm64-msvc": "1.0.0-rc.16", - "@rolldown/binding-win32-x64-msvc": "1.0.0-rc.16" + "@rolldown/binding-android-arm64": "1.0.1", + "@rolldown/binding-darwin-arm64": "1.0.1", + "@rolldown/binding-darwin-x64": "1.0.1", + "@rolldown/binding-freebsd-x64": "1.0.1", + "@rolldown/binding-linux-arm-gnueabihf": "1.0.1", + "@rolldown/binding-linux-arm64-gnu": "1.0.1", + "@rolldown/binding-linux-arm64-musl": "1.0.1", + "@rolldown/binding-linux-ppc64-gnu": "1.0.1", + "@rolldown/binding-linux-s390x-gnu": "1.0.1", + "@rolldown/binding-linux-x64-gnu": "1.0.1", + "@rolldown/binding-linux-x64-musl": "1.0.1", + "@rolldown/binding-openharmony-arm64": "1.0.1", + "@rolldown/binding-wasm32-wasi": "1.0.1", + "@rolldown/binding-win32-arm64-msvc": "1.0.1", + "@rolldown/binding-win32-x64-msvc": "1.0.1" } }, "node_modules/router": { @@ -5612,16 +5612,16 @@ } }, "node_modules/vite": { - "version": "8.0.9", - "resolved": "https://registry.npmjs.org/vite/-/vite-8.0.9.tgz", - "integrity": "sha512-t7g7GVRpMXjNpa67HaVWI/8BWtdVIQPCL2WoozXXA7LBGEFK4AkkKkHx2hAQf5x1GZSlcmEDPkVLSGahxnEEZw==", + "version": "8.0.13", + "resolved": "https://registry.npmjs.org/vite/-/vite-8.0.13.tgz", + "integrity": "sha512-MFtjBYgzmSxmgA4RAfjIyXWpGe1oALnjgUTzzV7QLx/TKxCzjtMH6Fd9/eVK+5Fg1qNoz5VAwsmMs/NofrmJvw==", "dev": true, "license": "MIT", "dependencies": { "lightningcss": "^1.32.0", "picomatch": "^4.0.4", - "postcss": "^8.5.10", - "rolldown": "1.0.0-rc.16", + "postcss": "^8.5.14", + "rolldown": "1.0.1", "tinyglobby": "^0.2.16" }, "bin": { @@ -5638,7 +5638,7 @@ }, "peerDependencies": { "@types/node": "^20.19.0 || >=22.12.0", - "@vitejs/devtools": "^0.1.0", + "@vitejs/devtools": "^0.1.18", "esbuild": "^0.27.0 || ^0.28.0", "jiti": ">=1.21.0", "less": "^4.0.0", @@ -5690,19 +5690,19 @@ } }, "node_modules/vitest": { - "version": "4.1.5", - "resolved": "https://registry.npmjs.org/vitest/-/vitest-4.1.5.tgz", - "integrity": "sha512-9Xx1v3/ih3m9hN+SbfkUyy0JAs72ap3r7joc87XL6jwF0jGg6mFBvQ1SrwaX+h8BlkX6Hz9shdd1uo6AF+ZGpg==", + "version": "4.1.6", + "resolved": "https://registry.npmjs.org/vitest/-/vitest-4.1.6.tgz", + "integrity": "sha512-6lvjbS3p9b4CrdCmguzbh2/4uoXhGE2q71R4OX5sqF9R1bo9Xd6fGrMAfvp5wnCzlBnFVdCOp6onuTQVbo8iUQ==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/expect": "4.1.5", - "@vitest/mocker": "4.1.5", - "@vitest/pretty-format": "4.1.5", - "@vitest/runner": "4.1.5", - "@vitest/snapshot": "4.1.5", - "@vitest/spy": "4.1.5", - "@vitest/utils": "4.1.5", + "@vitest/expect": "4.1.6", + "@vitest/mocker": "4.1.6", + "@vitest/pretty-format": "4.1.6", + "@vitest/runner": "4.1.6", + "@vitest/snapshot": "4.1.6", + "@vitest/spy": "4.1.6", + "@vitest/utils": "4.1.6", "es-module-lexer": "^2.0.0", "expect-type": "^1.3.0", "magic-string": "^0.30.21", @@ -5730,12 +5730,12 @@ "@edge-runtime/vm": "*", "@opentelemetry/api": "^1.9.0", "@types/node": "^20.0.0 || ^22.0.0 || >=24.0.0", - "@vitest/browser-playwright": "4.1.5", - "@vitest/browser-preview": "4.1.5", - "@vitest/browser-webdriverio": "4.1.5", - "@vitest/coverage-istanbul": "4.1.5", - "@vitest/coverage-v8": "4.1.5", - "@vitest/ui": "4.1.5", + "@vitest/browser-playwright": "4.1.6", + "@vitest/browser-preview": "4.1.6", + "@vitest/browser-webdriverio": "4.1.6", + "@vitest/coverage-istanbul": "4.1.6", + "@vitest/coverage-v8": "4.1.6", + "@vitest/ui": "4.1.6", "happy-dom": "*", "jsdom": "*", "vite": "^6.0.0 || ^7.0.0 || ^8.0.0" diff --git a/gitnexus/package.json b/gitnexus/package.json index 84f702762..633c69f24 100644 --- a/gitnexus/package.json +++ b/gitnexus/package.json @@ -1,6 +1,6 @@ { "name": "gitnexus", - "version": "1.6.3", + "version": "1.6.4", "description": "Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.", "author": "Abhigyan Patwari", "license": "PolyForm-Noncommercial-1.0.0", @@ -116,6 +116,6 @@ } }, "engines": { - "node": ">=20.0.0" + "node": ">=22.0.0" } } diff --git a/gitnexus/scripts/build.js b/gitnexus/scripts/build.js index 84f43fc6b..ec7f67cf4 100644 --- a/gitnexus/scripts/build.js +++ b/gitnexus/scripts/build.js @@ -21,11 +21,15 @@ const SHARED_DEST = path.join(DIST, '_shared'); // ── 1. Build gitnexus-shared ─────────────────────────────────────── console.log('[build] compiling gitnexus-shared…'); -execSync('npx tsc', { cwd: SHARED_ROOT, stdio: 'inherit', timeout: 120_000 }); +const tscCmd = + process.platform === 'win32' + ? path.join('node_modules', '.bin', 'tsc.cmd') + : path.join('node_modules', '.bin', 'tsc'); +execSync(tscCmd, { cwd: SHARED_ROOT, stdio: 'inherit', timeout: 120_000 }); // ── 2. Build gitnexus ────────────────────────────────────────────── console.log('[build] compiling gitnexus…'); -execSync('npx tsc', { cwd: ROOT, stdio: 'inherit', timeout: 120_000 }); +execSync(tscCmd, { cwd: ROOT, stdio: 'inherit', timeout: 120_000 }); // ── 3. Copy shared dist ──────────────────────────────────────────── console.log('[build] copying shared module into dist/_shared…'); diff --git a/gitnexus/src/cli/ai-context.ts b/gitnexus/src/cli/ai-context.ts index 41ba6c73e..42dcb7aa7 100644 --- a/gitnexus/src/cli/ai-context.ts +++ b/gitnexus/src/cli/ai-context.ts @@ -28,6 +28,7 @@ interface RepoStats { export interface AIContextOptions { skipAgentsMd?: boolean; noStats?: boolean; + skipSkills?: boolean; } const GITNEXUS_START_MARKER = ''; @@ -94,6 +95,7 @@ function generateGitNexusContent( generatedSkills?: GeneratedSkillInfo[], groupNames?: string[], noStats?: boolean, + skipSkills?: boolean, ): string { const generatedRows = generatedSkills && generatedSkills.length > 0 @@ -105,14 +107,26 @@ function generateGitNexusContent( .join('\n') : ''; - const skillsTable = `| Task | Read this skill file | -|------|---------------------| -| Understand architecture / "How does X work?" | \`.claude/skills/gitnexus/gitnexus-exploring/SKILL.md\` | + // Standard skill rows reference files installed by installSkills(). When + // --skip-skills suppresses that install, these rows must be omitted — else + // AGENTS.md/CLAUDE.md would direct agents to read files that don't exist. + // Community skills (generatedRows) live in .claude/skills/generated/ and + // are independent of --skip-skills, so they remain when present. + const standardSkillsRows = skipSkills + ? '' + : `| Understand architecture / "How does X work?" | \`.claude/skills/gitnexus/gitnexus-exploring/SKILL.md\` | | Blast radius / "What breaks if I change X?" | \`.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md\` | | Trace bugs / "Why is X failing?" | \`.claude/skills/gitnexus/gitnexus-debugging/SKILL.md\` | | Rename / extract / split / refactor | \`.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md\` | | Tools, resources, schema reference | \`.claude/skills/gitnexus/gitnexus-guide/SKILL.md\` | -| Index, status, clean, wiki CLI commands | \`.claude/skills/gitnexus/gitnexus-cli/SKILL.md\` |${generatedRows ? '\n' + generatedRows : ''}`; +| Index, status, clean, wiki CLI commands | \`.claude/skills/gitnexus/gitnexus-cli/SKILL.md\` |`; + + const tableBody = [standardSkillsRows, generatedRows].filter(Boolean).join('\n'); + const skillsTable = tableBody + ? `| Task | Read this skill file | +|------|---------------------| +${tableBody}` + : ''; return `${GITNEXUS_START_MARKER} # GitNexus — Code Intelligence @@ -153,11 +167,15 @@ This repository is listed under GitNexus **group(s): ${groupNames.join(', ')}** ` : '' -}## CLI +}${ + skillsTable + ? `## CLI ${skillsTable} -${GITNEXUS_END_MARKER}`; +` + : '' + }${GITNEXUS_END_MARKER}`; } /** @@ -181,7 +199,9 @@ async function fileExists(filePath: string): Promise { async function upsertGitNexusSection( filePath: string, content: string, -): Promise<'created' | 'updated' | 'appended'> { + projectName: string, + stats: RepoStats, +): Promise<'created' | 'updated' | 'appended' | 'preserved'> { const exists = await fileExists(filePath); if (!exists) { @@ -205,7 +225,50 @@ async function upsertGitNexusSection( ); if (startIdx !== -1 && endIdx !== -1 && endIdx > startIdx) { - // Replace existing section + const existingSection = existingContent.substring( + startIdx, + endIdx + GITNEXUS_END_MARKER.length, + ); + + // If the existing section contains , preserve the user's + // custom layout and only update the stats line (node/edge/flow counts). + // This lets teams trim the verbose default template to a lean format without + // having it overwritten on every `gitnexus analyze`. + // + // Note: the keep-marker check operates on `existingSection` (the substring + // between valid section markers identified by findSectionMarkerIndex), so + // a keep marker in user prose OUTSIDE the GitNexus block has no effect. + if (existingSection.includes('')) { + // Build the new stats line from the caller-provided values directly. + // We do NOT re-extract from `content` because: + // (a) first-bold extraction is fragile if the template evolves + // (b) the parenthesized-text fallback can match unrelated tuples + // like `({target: "symbolName", direction: "upstream"})` + // when noStats is set + // Passing projectName + stats explicitly makes the contract obvious. + // noStats controls template generation, not keep-section stat updates — the user opted into a stats line by keeping it. + const newStatsInner = `${stats.nodes || 0} symbols, ${stats.edges || 0} relationships, ${stats.processes || 0} execution flows`; + const statsLine = `Indexed as **${projectName}** (${newStatsInner})`; + + // Match either canonical phrasing at line start (`^` with `m` flag) so we + // cannot replace prose embedded mid-paragraph. Deliberately no `$`: text + // after the closing `)` on the same line (e.g. ". MCP tools.") stays intact. + const statsPattern = /^(?:Indexed as|indexed by GitNexus as) \*\*[^*]+\*\* \([^)]+\)/m; + + if (statsPattern.test(existingSection)) { + const updatedSection = existingSection.replace(statsPattern, statsLine); + const before = existingContent.substring(0, startIdx); + const after = existingContent.substring(endIdx + GITNEXUS_END_MARKER.length); + await fs.writeFile(filePath, (before + updatedSection + after).trim() + '\n', 'utf-8'); + return 'updated'; + } + // Keep marker present but no stats line matched. Section is preserved + // unchanged on disk; return a distinct status so callers/CLI output + // don't mis-report this as 'updated' (which would imply a write). + return 'preserved'; + } + + // No keep marker — replace existing section with full verbose content const before = existingContent.substring(0, startIdx); const after = existingContent.substring(endIdx + GITNEXUS_END_MARKER.length); const newContent = before + content + after; @@ -319,28 +382,33 @@ export async function generateAIContextFiles( generatedSkills, groupNames, options?.noStats, + options?.skipSkills, ); const createdFiles: string[] = []; if (!options?.skipAgentsMd) { // Create AGENTS.md (standard for Cursor, Windsurf, OpenCode, Cline, etc.) const agentsPath = path.join(repoPath, 'AGENTS.md'); - const agentsResult = await upsertGitNexusSection(agentsPath, content); + const agentsResult = await upsertGitNexusSection(agentsPath, content, projectName, stats); createdFiles.push(`AGENTS.md (${agentsResult})`); // Create CLAUDE.md (for Claude Code) const claudePath = path.join(repoPath, 'CLAUDE.md'); - const claudeResult = await upsertGitNexusSection(claudePath, content); + const claudeResult = await upsertGitNexusSection(claudePath, content, projectName, stats); createdFiles.push(`CLAUDE.md (${claudeResult})`); } else { createdFiles.push('AGENTS.md (skipped via --skip-agents-md)'); createdFiles.push('CLAUDE.md (skipped via --skip-agents-md)'); } - // Install skills to .claude/skills/gitnexus/ - const installedSkills = await installSkills(repoPath); - if (installedSkills.length > 0) { - createdFiles.push(`.claude/skills/gitnexus/ (${installedSkills.length} skills)`); + // Install skills to .claude/skills/gitnexus/ (unless --skip-skills) + if (!options?.skipSkills) { + const installedSkills = await installSkills(repoPath); + if (installedSkills.length > 0) { + createdFiles.push(`.claude/skills/gitnexus/ (${installedSkills.length} skills)`); + } + } else { + createdFiles.push('.claude/skills/gitnexus/ (skipped via --skip-skills)'); } return { files: createdFiles }; diff --git a/gitnexus/src/cli/analyze.ts b/gitnexus/src/cli/analyze.ts index 47745c575..a20503bc4 100644 --- a/gitnexus/src/cli/analyze.ts +++ b/gitnexus/src/cli/analyze.ts @@ -117,8 +117,22 @@ export interface AnalyzeOptions { verbose?: boolean; /** Skip AGENTS.md and CLAUDE.md gitnexus block updates. */ skipAgentsMd?: boolean; - /** Omit volatile symbol/relationship counts from AGENTS.md and CLAUDE.md. */ - noStats?: boolean; + /** + * Stats inclusion in AGENTS.md and CLAUDE.md. + * + * Commander.js represents `--no-stats` as `stats: boolean` (default + * `true`; `false` when the user passes `--no-stats`), NOT as + * `noStats: boolean`. Reading the negated form would always be + * `undefined` and the flag would silently no-op (#1477). Consumers + * that want "did the user request --no-stats?" should compare with + * `=== false` to distinguish the explicit-off case from the + * default-on case. + */ + stats?: boolean; + /** Skip installing standard GitNexus skill files to .claude/skills/gitnexus/. */ + skipSkills?: boolean; + /** Pure index mode: skip all file injection (AGENTS.md, CLAUDE.md, skills). */ + indexOnly?: boolean; /** Index the folder even when no .git directory is present. */ skipGit?: boolean; /** @@ -150,6 +164,24 @@ export interface AnalyzeOptions { embeddingDevice?: string; } +/** + * Whether the post-index skill step should run. + * + * The gated block does two things in sequence: (1) generates the community + * skill files from `--skills`, and (2) re-runs `generateAIContextFiles` so + * AGENTS.md/CLAUDE.md can reference the freshly written skills. Both are + * suppressed together — `--index-only` drops the entire step, not just the + * community-skill write. Name retained for the test contract; see call site + * in `analyzeCommand` for the AGENTS.md/CLAUDE.md re-generation it also gates. + * + * Kept as a pure helper so the `--index-only --skills` contract is unit-tested + * without booting the full analyze pipeline (#742 review). + */ +export const shouldGenerateCommunitySkillFiles = ( + options: Pick | undefined, + pipelineResult: unknown, +): boolean => Boolean(options?.skills && pipelineResult && !options?.indexOnly); + export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOptions) => { if (ensureHeap()) return; @@ -245,6 +277,18 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption console.log('\n GitNexus Analyzer\n'); + // `--index-only` is the stronger contract — it suppresses every form of file + // injection, including community skill writes that `--skills` would normally + // produce. Surface the override explicitly so users don't wonder why a + // pipeline re-index ran but no skill files appeared. The pipeline still + // re-runs (see `force: options?.force || options?.skills` below); the warning + // is purely about the dropped post-index write step. + if (options?.indexOnly && options?.skills) { + console.log( + ' Note: --index-only overrides --skills; community skill files will not be written.\n', + ); + } + let repoPath: string; if (inputPath) { repoPath = path.resolve(inputPath); @@ -399,6 +443,9 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption // ── Run shared analysis orchestrator ─────────────────────────────── try { + const skipAll = options?.indexOnly; + const skipAgentsMd = skipAll || options?.skipAgentsMd; + const skipSkills = skipAll || options?.skipSkills; const result = await runFullAnalysis( repoPath, { @@ -410,8 +457,14 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption embeddingsNodeLimit, dropEmbeddings: options?.dropEmbeddings, skipGit: options?.skipGit, - skipAgentsMd: options?.skipAgentsMd, - noStats: options?.noStats, + skipAgentsMd, + skipSkills, + // commander.js `.option('--no-stats', …)` registers the flag as + // `options.stats` (boolean, default true; `false` when the user + // passed --no-stats). Reading `options?.noStats` here returns + // undefined every time, so the flag was a no-op on the markdown + // rewrite path before this fix. See #1477. + noStats: options?.stats === false, registryName: options?.name, // Registry-collision bypass — its own CLI flag, intentionally NOT // overloading --force. A user who hits the collision guard should @@ -456,8 +509,10 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption // a healthy index. await assertAnalysisFinalized(repoPath); - // Skill generation (CLI-only, uses pipeline result from analysis) - if (options?.skills && result.pipelineResult) { + // Skill generation (CLI-only, uses pipeline result from analysis). + // Gated so `--index-only --skills` skips community skill writes too + // (`shouldGenerateCommunitySkillFiles` — see unit test). + if (shouldGenerateCommunitySkillFiles(options, result.pipelineResult)) { updateBar(99, 'Generating skill files...'); try { const { generateSkillFiles } = await import('./skill-gen.js'); @@ -497,7 +552,13 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption processes: s.processes, }, skillResult.skills, - { skipAgentsMd: options?.skipAgentsMd, noStats: options?.noStats }, + { + skipAgentsMd, + skipSkills, + // Mirror runFullAnalysis `noStats` bridge (#1477) — same expression; + // exercised on the `--skills` path by analyze-no-stats-bridge.test.ts. + noStats: options?.stats === false, + }, ); } } catch { diff --git a/gitnexus/src/cli/augment.ts b/gitnexus/src/cli/augment.ts index 553e3f591..a97f6e23c 100644 --- a/gitnexus/src/cli/augment.ts +++ b/gitnexus/src/cli/augment.ts @@ -2,7 +2,7 @@ * Augment CLI Command * * Fast-path command for platform hooks. - * Shells out from Claude Code PreToolUse / Cursor beforeShellExecution hooks. + * Shells out from Claude Code PreToolUse / Cursor postToolUse hooks. * * Usage: gitnexus augment * Returns enriched text to stdout. diff --git a/gitnexus/src/cli/index.ts b/gitnexus/src/cli/index.ts index e4a455d40..4b009e4aa 100644 --- a/gitnexus/src/cli/index.ts +++ b/gitnexus/src/cli/index.ts @@ -33,9 +33,20 @@ program 'Drop existing embeddings on rebuild. By default, an `analyze` without `--embeddings` ' + 'preserves any embeddings already present in the index.', ) - .option('--skills', 'Generate repo-specific skill files from detected communities') + .option( + '--skills', + 'Generate repo-specific skill files from detected communities ' + + '(no-op when --index-only is also set).', + ) .option('--skip-agents-md', 'Skip updating the gitnexus section in AGENTS.md and CLAUDE.md') .option('--no-stats', 'Omit volatile file/symbol counts from AGENTS.md and CLAUDE.md') + .option( + '--skip-skills', + 'Skip installing standard GitNexus skill files under .claude/skills/gitnexus/. ' + + 'Does not suppress community skills from --skills (those use .claude/skills/generated/). ' + + 'Use --index-only to skip all AI-context file injection.', + ) + .option('--index-only', 'Pure index mode: skip all file injection (AGENTS.md, CLAUDE.md, skills)') .option( '--skip-git', 'Treat the provided path/cwd as the index root and skip parent git-root discovery', @@ -150,6 +161,8 @@ program ) .option('--no-reasoning-model', 'Disable reasoning model mode (overrides saved config)') .option('--concurrency ', 'Parallel LLM calls (default: 3)', '3') + .option('--timeout ', 'Per-attempt LLM request timeout in seconds (default: 60)') + .option('--retries ', 'Max LLM retry attempts per request (default: 3)') .option('--gist', 'Publish wiki as a public GitHub Gist after generation') .option('-v, --verbose', 'Enable verbose output (show LLM commands and responses)') .option('--review', 'Stop after grouping to review module structure before generating pages') diff --git a/gitnexus/src/cli/setup.ts b/gitnexus/src/cli/setup.ts index af3c4737a..3e7cbad8f 100644 --- a/gitnexus/src/cli/setup.ts +++ b/gitnexus/src/cli/setup.ts @@ -364,6 +364,33 @@ async function installClaudeCodeHooks(result: SetupResult): Promise { // Script not found in source — skip } + try { + await fs.copyFile( + path.join(pluginHooksPath, 'hook-lock.cjs'), + path.join(destHooksDir, 'hook-lock.cjs'), + ); + } catch { + // Helper not found in source — skip + } + + try { + await fs.copyFile( + path.join(pluginHooksPath, 'hook-db-lock-probe.cjs'), + path.join(destHooksDir, 'hook-db-lock-probe.cjs'), + ); + } catch { + // Helper not found in source — skip + } + + try { + await fs.copyFile( + path.join(pluginHooksPath, 'win-rm-list-json.ps1'), + path.join(destHooksDir, 'win-rm-list-json.ps1'), + ); + } catch { + // Helper not found in source — skip + } + const hookPath = path.join(destHooksDir, 'gitnexus-hook.cjs').replace(/\\/g, '/'); // Escape backslashes FIRST, then quotes (CodeQL js/incomplete-sanitization). // The previous shape `replace(/"/g, '\\"')` alone would let `path\with"quote` diff --git a/gitnexus/src/cli/wiki.ts b/gitnexus/src/cli/wiki.ts index 38a0f82a6..8d9da9572 100644 --- a/gitnexus/src/cli/wiki.ts +++ b/gitnexus/src/cli/wiki.ts @@ -33,6 +33,8 @@ export interface WikiCommandOptions { provider?: LLMProvider; verbose?: boolean; review?: boolean; + timeout?: string; + retries?: string; } /** @@ -347,6 +349,16 @@ export const wikiCommand = async (inputPath?: string, options?: WikiCommandOptio } } + // ── Apply per-run overrides not saved to config ──────────────────── + if (options?.timeout) { + const secs = parseInt(options.timeout, 10); + if (!isNaN(secs) && secs > 0) llmConfig.requestTimeoutMs = secs * 1000; + } + if (options?.retries) { + const n = parseInt(options.retries, 10); + if (!isNaN(n) && n > 0) llmConfig.maxAttempts = n; + } + // ── Setup progress bar with elapsed timer ────────────────────────── const bar = new cliProgress.SingleBar( { diff --git a/gitnexus/src/core/augmentation/engine.ts b/gitnexus/src/core/augmentation/engine.ts index f97415cc9..81e41077e 100644 --- a/gitnexus/src/core/augmentation/engine.ts +++ b/gitnexus/src/core/augmentation/engine.ts @@ -2,8 +2,8 @@ * Augmentation Engine * * Lightweight, fast-path enrichment of search patterns with knowledge graph context. - * Designed to be called from platform hooks (Claude Code PreToolUse, Cursor beforeShellExecution) - * when an agent runs grep/glob/search. + * Designed to be called from platform hooks (Claude Code PreToolUse, Cursor postToolUse) + * when an agent runs grep/glob/read/search. * * Performance target: <500ms cold start, <200ms warm. * @@ -86,6 +86,9 @@ async function findRepoForCwd(cwd: string): Promise<{ export async function augment(pattern: string, cwd?: string): Promise { if (!pattern || pattern.length < 3) return ''; + const patternFirstWord = pattern.trim().replace(/'/g, "''").split(/\s+/)[0]; + if (!patternFirstWord || patternFirstWord.length < 2) return ''; + const workDir = cwd || process.cwd(); try { @@ -104,9 +107,7 @@ export async function augment(pattern: string, cwd?: string): Promise { } // Step 1: BM25 search (fast, no embeddings) - const { results: bm25Results } = await searchFTSFromLbug(pattern, 10, repoId); - - if (bm25Results.length === 0) return ''; + const { results: bm25Results, ftsAvailable } = await searchFTSFromLbug(pattern, 10, repoId); // Step 2: Map BM25 file results to symbols const symbolMatches: Array<{ @@ -124,7 +125,7 @@ export async function augment(pattern: string, cwd?: string): Promise { repoId, ` MATCH (n) WHERE n.filePath = '${escaped}' - AND n.name CONTAINS '${pattern.replace(/'/g, "''").split(/\s+/)[0]}' + AND n.name CONTAINS '${patternFirstWord}' RETURN n.id AS id, n.name AS name, labels(n)[0] AS type, n.filePath AS filePath LIMIT 3 `, @@ -143,6 +144,29 @@ export async function augment(pattern: string, cwd?: string): Promise { } } + // When FTS indexes are unavailable (read-only DB, first run before indexes are built), + // fall back to a direct name CONTAINS query so enrichment still works. + if (symbolMatches.length === 0 && !ftsAvailable) { + const fallbackRows = await executeQuery( + repoId, + ` + MATCH (n) + WHERE n.name CONTAINS '${patternFirstWord}' + RETURN n.id AS id, n.name AS name, labels(n)[0] AS type, n.filePath AS filePath + LIMIT 5 + `, + ).catch(() => []); + for (const sym of fallbackRows) { + symbolMatches.push({ + nodeId: sym.id || sym[0], + name: sym.name || sym[1], + type: sym.type || sym[2], + filePath: sym.filePath || sym[3], + score: 1.0, + }); + } + } + if (symbolMatches.length === 0) return ''; // Step 3: Batch-fetch callers/callees/processes/cohesion for top matches diff --git a/gitnexus/src/core/embeddings/ast-utils.ts b/gitnexus/src/core/embeddings/ast-utils.ts index 8456b249e..e4976d71e 100644 --- a/gitnexus/src/core/embeddings/ast-utils.ts +++ b/gitnexus/src/core/embeddings/ast-utils.ts @@ -10,6 +10,7 @@ import { isLanguageAvailable, resolveLanguageKey, } from '../tree-sitter/parser-loader.js'; +import { parseSourceSafe } from '../tree-sitter/safe-parse.js'; const parserCache = new Map(); @@ -29,7 +30,7 @@ export const ensureAndParse = async (content: string, filePath: string): Promise parserCache.set(parserKey, parserInstance); } - return parserInstance.parse(content); + return parseSourceSafe(parserInstance, content); }; const FUNCTION_LIKE_TYPES = new Set([ diff --git a/gitnexus/src/core/embeddings/hf-env.ts b/gitnexus/src/core/embeddings/hf-env.ts index 95548fff2..5ae6d89ae 100644 --- a/gitnexus/src/core/embeddings/hf-env.ts +++ b/gitnexus/src/core/embeddings/hf-env.ts @@ -1,6 +1,8 @@ import os from 'node:os'; import { join } from 'node:path'; +import { CircuitBreaker, withRetry } from 'gitnexus-shared'; + // --------------------------------------------------------------------------- // Download resilience defaults // --------------------------------------------------------------------------- @@ -108,70 +110,19 @@ export function isNetworkFetchError(message: string): boolean { /** @internal Used by `withHfDownloadRetry` to mark a circuit-open rejection. */ export const CIRCUIT_OPEN_TAG = 'hf-circuit-open'; -/** Circuit-breaker states. */ -type CircuitState = 'closed' | 'open' | 'half-open'; - /** - * Circuit breaker for HuggingFace model downloads. - * - * After `failureThreshold` consecutive network failures the circuit opens and - * all subsequent calls to `withHfDownloadRetry` fail immediately without - * issuing any network requests. After `resetTimeoutMs` the circuit enters the - * half-open state and the next call is attempted — if it succeeds the circuit - * closes again; if it fails the circuit re-opens. - * - * Exported for unit-testing; production code should use the module-level - * `hfDownloadCircuit` singleton. + * Module-level singleton shared by both embedder entry points + * (`core/embeddings/embedder.ts` + `mcp/core/embedder.ts`). Per-process + * only — not persisted across restarts. Backed by the shared + * `CircuitBreaker` from `gitnexus-shared` (same state machine, same + * semantics, plus the single-permit half-open gate that prevents + * recovery-time stampedes). */ -export class HfDownloadCircuitBreaker { - private _state: CircuitState = 'closed'; - private _failures = 0; - /** Timestamp of the last recorded failure (ms since epoch). */ - lastFailureAt = 0; - - constructor( - readonly failureThreshold: number = CB_FAILURE_THRESHOLD, - readonly resetTimeoutMs: number = CB_RESET_TIMEOUT_MS, - ) {} - - /** Effective state, factoring in the reset-timeout transition. */ - get state(): CircuitState { - if (this._state === 'open' && Date.now() - this.lastFailureAt > this.resetTimeoutMs) { - this._state = 'half-open'; - } - return this._state; - } - - /** Returns true when the circuit is open and calls should be rejected. */ - isOpen(): boolean { - return this.state === 'open'; - } - - /** Record a successful call — resets the failure counter and closes the circuit. */ - recordSuccess(): void { - this._failures = 0; - this._state = 'closed'; - } - - /** Record a failed call — increments the counter and opens the circuit when the threshold is reached. */ - recordFailure(): void { - this._failures++; - this.lastFailureAt = Date.now(); - if (this._failures >= this.failureThreshold) { - this._state = 'open'; - } - } - - /** @internal Reset to initial state (used in tests). */ - reset(): void { - this._failures = 0; - this._state = 'closed'; - this.lastFailureAt = 0; - } -} - -/** Module-level singleton shared by both embedder entry points. */ -export const hfDownloadCircuit = new HfDownloadCircuitBreaker(); +export const hfDownloadCircuit = new CircuitBreaker({ + failureThreshold: CB_FAILURE_THRESHOLD, + cooldownMs: CB_RESET_TIMEOUT_MS, + key: 'hf-download', +}); // --------------------------------------------------------------------------- // Retry + timeout wrapper @@ -219,11 +170,6 @@ export function withDownloadTimeout(fn: () => Promise, timeoutMs: number): }); } -/** @internal Async sleep (exposed for testing). */ -export function sleep(ms: number): Promise { - return new Promise((resolve) => setTimeout(resolve, ms)); -} - export interface HfRetryOptions { /** Maximum total attempts including the initial one (default: `HF_MAX_ATTEMPTS`). */ maxAttempts?: number; @@ -235,7 +181,7 @@ export interface HfRetryOptions { * Circuit-breaker instance to use. Defaults to the module-level * `hfDownloadCircuit` singleton. Pass a fresh instance in tests. */ - circuit?: HfDownloadCircuitBreaker; + circuit?: CircuitBreaker; /** * Optional callback invoked before each retry (not the initial attempt). * @param attempt - 1-based retry number @@ -295,49 +241,74 @@ export async function withHfDownloadRetry( circuit = hfDownloadCircuit, onRetry, } = options; - if (circuit.isOpen()) { - const secsUntilReset = Math.ceil( - (circuit.resetTimeoutMs - (Date.now() - circuit.lastFailureAt)) / 1000, - ); + if (circuit.getState() === 'open') { + // Compute remaining cooldown without consuming a probe permit. + const openedAt = circuit.getOpenedAt(); + const secsUntilReset = + openedAt !== null ? Math.ceil((circuit.getCooldownMs() - (Date.now() - openedAt)) / 1000) : 0; throw new Error( `${CIRCUIT_OPEN_TAG}: HuggingFace download circuit is open after repeated network failures` + (secsUntilReset > 0 ? ` — will reset in ~${secsUntilReset}s` : ''), ); } - let lastError: Error = new Error('unknown error'); + // Retry budget delegated to `withRetry` from gitnexus-shared. The + // HF-specific bits — per-attempt timeout, network-vs-non-network + // classification, circuit-breaker recording, onRetry callback — wire + // through the `isRetryable` callback. `circuitTripped` is the + // sentinel that lets us replace the final thrown error with a + // CIRCUIT_OPEN_TAG message when the breaker tripped mid-loop. + let circuitTripped = false; - for (let attempt = 0; attempt < maxAttempts; attempt++) { - try { - const result = await withDownloadTimeout(fn, timeoutMs); - circuit.recordSuccess(); - return result; - } catch (err) { - lastError = err instanceof Error ? err : new Error(String(err)); - - if (!isNetworkFetchError(lastError.message)) { - // Non-network error (e.g. CUDA unavailable) — propagate without retry - throw lastError; - } - - circuit.recordFailure(); - - if (circuit.isOpen()) { - // Circuit just tripped — fail fast, no more retries - throw new Error( - `${CIRCUIT_OPEN_TAG}: HuggingFace download circuit opened after ${circuit.failureThreshold} consecutive failures`, - ); - } - - if (attempt < maxAttempts - 1) { - const delay = baseDelayMs * Math.pow(2, attempt); - onRetry?.(attempt + 1, maxAttempts, lastError); - await sleep(delay); - } + try { + return await withRetry( + async () => { + const result = await withDownloadTimeout(fn, timeoutMs); + circuit.recordSuccess(); + return result; + }, + { + maxAttempts, + baseDelayMs, + // Disable the cap to match the bespoke pure-exponential + // progression. With the default `HF_MAX_ATTEMPTS_CAP = 10` and + // `baseDelayMs = 2000`, the largest possible delay is + // `2000 * 2^9 = ~17 minutes` — bounded enough not to need a cap. + capDelayMs: Number.MAX_SAFE_INTEGER, + isRetryable: (err, attempt) => { + const error = err instanceof Error ? err : new Error(String(err)); + if (!isNetworkFetchError(error.message)) { + // Non-network error (e.g. CUDA unavailable) — propagate + // without retry. Use recordNeutral so the breaker's existing + // failure-count progress isn't reset by a non-network failure + // that says nothing about the CDN's health. + circuit.recordNeutral(); + return { retry: false }; + } + circuit.recordFailure(); + if (circuit.getState() === 'open') { + // Circuit just tripped — fail fast, no more retries. + circuitTripped = true; + return { retry: false }; + } + // Mirror the bespoke onRetry contract: fire only when there's + // actually a next attempt. + if (attempt + 1 < maxAttempts) { + onRetry?.(attempt + 1, maxAttempts, error); + } + return { retry: true }; + }, + }, + ); + } catch (err) { + if (circuitTripped) { + throw new Error( + `${CIRCUIT_OPEN_TAG}: HuggingFace download circuit opened after ${CB_FAILURE_THRESHOLD} consecutive failures`, + ); } + // All retries exhausted — rethrow the last network error so + // isNetworkFetchError patterns in the calling code still match and + // surface HF_ENDPOINT guidance. + throw err; } - - // All retries exhausted — throw the last network error so isNetworkFetchError - // patterns in the calling code still match and surface HF_ENDPOINT guidance. - throw lastError; } diff --git a/gitnexus/src/core/embeddings/http-client.ts b/gitnexus/src/core/embeddings/http-client.ts index 85ad79111..e8e9073ff 100644 --- a/gitnexus/src/core/embeddings/http-client.ts +++ b/gitnexus/src/core/embeddings/http-client.ts @@ -3,13 +3,22 @@ * * Shared fetch+retry logic for OpenAI-compatible /v1/embeddings endpoints. * Imported by both the core embedder (batch) and MCP embedder (query). + * + * Network resilience is delegated to `resilientFetch` from + * `gitnexus-shared` — bounded retries with exponential-backoff jitter, + * `Retry-After` honored on 429, and an in-process circuit breaker that + * fails fast on a flapping endpoint. Per-attempt timeout is enforced + * via `AbortSignal.timeout` on the underlying fetch. */ +import { CircuitOpenError, ResilientFetchExhaustedError, resilientFetch } from 'gitnexus-shared'; + const HTTP_TIMEOUT_MS = 30_000; const HTTP_MAX_RETRIES = 2; const HTTP_RETRY_BACKOFF_MS = 1_000; const HTTP_BATCH_SIZE = 64; const DEFAULT_DIMS = 384; +const HTTP_BREAKER_KEY = 'embeddings-http'; interface HttpConfig { baseUrl: string; @@ -31,8 +40,11 @@ const readConfig = (): HttpConfig | null => { const rawDims = process.env.GITNEXUS_EMBEDDING_DIMS; let dimensions: number | undefined; if (rawDims !== undefined) { + if (!/^\d+$/.test(rawDims)) { + throw new Error(`GITNEXUS_EMBEDDING_DIMS must be a positive integer, got "${rawDims}"`); + } const parsed = parseInt(rawDims, 10); - if (Number.isNaN(parsed) || parsed <= 0) { + if (parsed <= 0) { throw new Error(`GITNEXUS_EMBEDDING_DIMS must be a positive integer, got "${rawDims}"`); } dimensions = parsed; @@ -82,7 +94,13 @@ interface EmbeddingItem { * @param model - Model name for the request body * @param apiKey - Bearer token (only used in Authorization header) * @param batchIndex - Logical batch number (for error context) - * @param attempt - Current retry attempt (internal) + * @param dimensions - Optional output-vector size. When provided, sent as + * the `dimensions` field in the request body. Endpoints that implement + * Matryoshka truncation (OpenAI text-embedding-3-*, Cohere embed-v3, + * Voyage) return a truncated vector at that size; endpoints that do not + * recognise the field may ignore it or return 400. Leave + * `GITNEXUS_EMBEDDING_DIMS` unset for strict backends that reject + * unknown fields. */ const httpEmbedBatch = async ( url: string, @@ -90,46 +108,60 @@ const httpEmbedBatch = async ( model: string, apiKey: string, batchIndex = 0, - attempt = 0, + dimensions?: number, ): Promise => { + const requestBody: { input: string[]; model: string; dimensions?: number } = { + input: batch, + model, + }; + if (dimensions !== undefined) { + requestBody.dimensions = dimensions; + } + let resp: Response; try { - resp = await fetch(url, { - method: 'POST', - signal: AbortSignal.timeout(HTTP_TIMEOUT_MS), - headers: { - 'Content-Type': 'application/json', - Authorization: `Bearer ${apiKey}`, + resp = await resilientFetch( + url, + { + method: 'POST', + signal: AbortSignal.timeout(HTTP_TIMEOUT_MS), + headers: { + 'Content-Type': 'application/json', + Authorization: `Bearer ${apiKey}`, + }, + body: JSON.stringify(requestBody), }, - body: JSON.stringify({ input: batch, model }), - }); + { + breakerKey: HTTP_BREAKER_KEY, + retry: { maxAttempts: HTTP_MAX_RETRIES + 1, baseDelayMs: HTTP_RETRY_BACKOFF_MS }, + }, + ); } catch (err) { - // Timeouts should not be retried — the server is unresponsive. - // AbortSignal.timeout() throws DOMException with name 'TimeoutError'. - const isTimeout = err instanceof DOMException && err.name === 'TimeoutError'; - if (isTimeout) { + if (err instanceof CircuitOpenError) { + throw new Error( + `Embedding endpoint circuit open (${safeUrl(url)}, batch ${batchIndex}): retry in ${Math.ceil(err.retryAfterMs / 1000)}s`, + ); + } + if (err instanceof DOMException && err.name === 'TimeoutError') { throw new Error( `Embedding request timed out after ${HTTP_TIMEOUT_MS}ms (${safeUrl(url)}, batch ${batchIndex})`, ); } - // DNS, connection errors — retry with backoff - if (attempt < HTTP_MAX_RETRIES) { - const delay = HTTP_RETRY_BACKOFF_MS * (attempt + 1); - await new Promise((r) => setTimeout(r, delay)); - return httpEmbedBatch(url, batch, model, apiKey, batchIndex, attempt + 1); + if (err instanceof ResilientFetchExhaustedError) { + throw new Error( + `Embedding endpoint returned ${err.response.status} (${safeUrl(url)}, batch ${batchIndex})`, + ); } const reason = err instanceof Error ? err.message : String(err); throw new Error(`Embedding request failed (${safeUrl(url)}, batch ${batchIndex}): ${reason}`); } if (!resp.ok) { - const status = resp.status; - if ((status === 429 || status >= 500) && attempt < HTTP_MAX_RETRIES) { - const delay = HTTP_RETRY_BACKOFF_MS * (attempt + 1); - await new Promise((r) => setTimeout(r, delay)); - return httpEmbedBatch(url, batch, model, apiKey, batchIndex, attempt + 1); - } - throw new Error(`Embedding endpoint returned ${status} (${safeUrl(url)}, batch ${batchIndex})`); + // resilientFetch already retried 5xx/429; any non-OK response here is + // a terminal client error (4xx other than 429). + throw new Error( + `Embedding endpoint returned ${resp.status} (${safeUrl(url)}, batch ${batchIndex})`, + ); } const data = (await resp.json()) as { data: EmbeddingItem[] }; @@ -155,7 +187,14 @@ export const httpEmbed = async (texts: string[]): Promise => { for (let i = 0; i < texts.length; i += HTTP_BATCH_SIZE) { const batch = texts.slice(i, i + HTTP_BATCH_SIZE); const batchIndex = Math.floor(i / HTTP_BATCH_SIZE); - const items = await httpEmbedBatch(url, batch, config.model, config.apiKey, batchIndex); + const items = await httpEmbedBatch( + url, + batch, + config.model, + config.apiKey, + batchIndex, + config.dimensions, + ); if (items.length !== batch.length) { throw new Error( @@ -198,7 +237,14 @@ export const httpEmbedQuery = async (text: string): Promise => { if (!config) throw new Error('HTTP embedding not configured'); const url = `${config.baseUrl}/embeddings`; - const items = await httpEmbedBatch(url, [text], config.model, config.apiKey); + const items = await httpEmbedBatch( + url, + [text], + config.model, + config.apiKey, + 0, + config.dimensions, + ); if (!items.length) { throw new Error(`Embedding endpoint returned empty response (${safeUrl(url)})`); } diff --git a/gitnexus/src/core/group/bridge-db.ts b/gitnexus/src/core/group/bridge-db.ts index ef6244b22..7f44253bf 100644 --- a/gitnexus/src/core/group/bridge-db.ts +++ b/gitnexus/src/core/group/bridge-db.ts @@ -722,13 +722,15 @@ export async function openBridgeDbReadOnly(groupDir: string): Promise setTimeout(r, delay)); } } - // Pino's NDJSON serialization is structurally injection-resistant - // (CodeQL js/log-injection): groupDir and err.message are JSON-escaped - // by the serializer, so no manual CRLF / U+2028 / ANSI sanitization is - // needed. Demoted to debug — only fires when the bridge truly gave up - // after retries, and operators only need it at debug verbosity. + // Strip CRLF from user-controlled strings before logging to close + // CodeQL js/log-injection. Pino's NDJSON serialization already + // JSON-escapes all values, but we sanitize here as a defence-in-depth + // measure so CodeQL can see the taint flow is broken. + const safeGroupDir = String(groupDir).replace(/[\r\n]/g, ' '); + const safeErrMsg = + lastErr instanceof Error ? String(lastErr.message).replace(/[\r\n]/g, ' ') : undefined; bridgeLogger.debug( - { groupDir, err: lastErr, attempts: LBUG_OPEN_RETRY_ATTEMPTS }, + { groupDir: safeGroupDir, errMsg: safeErrMsg, attempts: LBUG_OPEN_RETRY_ATTEMPTS }, 'openBridgeDbReadOnly gave up', ); return null; diff --git a/gitnexus/src/core/group/extractors/grpc-extractor.ts b/gitnexus/src/core/group/extractors/grpc-extractor.ts index c08ba7c36..56107d8ee 100644 --- a/gitnexus/src/core/group/extractors/grpc-extractor.ts +++ b/gitnexus/src/core/group/extractors/grpc-extractor.ts @@ -5,6 +5,7 @@ import { createIgnoreFilter } from '../../../config/ignore-service.js'; import type { ContractExtractor, CypherExecutor } from '../contract-extractor.js'; import type { ExtractedContract, RepoHandle } from '../types.js'; import { readSafe } from './fs-utils.js'; +import { parseSourceSafe } from '../../tree-sitter/safe-parse.js'; import { logger } from '../../logger.js'; import { GRPC_SCAN_GLOB, @@ -428,7 +429,7 @@ export class GrpcExtractor implements ContractExtractor { let detections: GrpcDetection[] = []; try { parser.setLanguage(plugin.language); - const tree = parser.parse(content); + const tree = parseSourceSafe(parser, content); detections = plugin.scan(tree); } catch { continue; diff --git a/gitnexus/src/core/group/extractors/http-patterns/python.ts b/gitnexus/src/core/group/extractors/http-patterns/python.ts index 27ddf6633..0d3385247 100644 --- a/gitnexus/src/core/group/extractors/http-patterns/python.ts +++ b/gitnexus/src/core/group/extractors/http-patterns/python.ts @@ -1,3 +1,4 @@ +import type Parser from 'tree-sitter'; import Python from 'tree-sitter-python'; import { compilePatterns, @@ -12,6 +13,7 @@ import type { HttpDetection, HttpLanguagePlugin } from './types.js'; * - FastAPI `@app.get("/path")` provider decorators * - `requests.get/post/...("url")` consumer calls * - Generic `requests.request("METHOD", "url")` consumer calls + * - `httpx.AsyncClient` instances calling `.get/.post/...("url")` */ const FASTAPI_VERBS: Record = { @@ -77,11 +79,161 @@ const REQUESTS_GENERIC_PATTERNS = compilePatterns({ ], } satisfies LanguagePatterns>); +// ─── Consumer: httpx.AsyncClient assignments ──────────────────────── +// NOTE: This targeted detector only tracks explicit `httpx.AsyncClient(...)` +// construction. Direct imports (`from httpx import AsyncClient`) and module +// aliases (`import httpx as hx`) and annotated assignments (`client: httpx.AsyncClient = ...`) +// are intentionally left for a follow-up. Module-scope clients are only matched +// at module scope; calls inside functions require a function/class-local tracked +// client to avoid false positives from same-name local variables. +const HTTPX_ASYNC_CLIENT_ASSIGN_PATTERNS = compilePatterns({ + name: 'python-httpx-async-client-assign', + language: Python, + patterns: [ + { + meta: {}, + query: ` + (assignment + left: (_) @client + right: (call + function: (attribute + object: (identifier) @module (#eq? @module "httpx") + attribute: (identifier) @client_class (#eq? @client_class "AsyncClient")))) + `, + }, + ], +} satisfies LanguagePatterns>); + +// ─── Consumer: async with httpx.AsyncClient() as client ────────────── +const HTTPX_ASYNC_CLIENT_WITH_ALIAS_PATTERNS = compilePatterns({ + name: 'python-httpx-async-client-with-alias', + language: Python, + patterns: [ + { + meta: {}, + query: ` + (as_pattern + (call + function: (attribute + object: (identifier) @module (#eq? @module "httpx") + attribute: (identifier) @client_class (#eq? @client_class "AsyncClient"))) + (as_pattern_target (identifier) @client)) + `, + }, + ], +} satisfies LanguagePatterns>); + +function getScopeKey(node: Parser.SyntaxNode | null, preferClass = false): string { + if (preferClass) { + let current: Parser.SyntaxNode | null = node; + while (current) { + if (current.type === 'class_definition') { + return `class:${current.startIndex}:${current.endIndex}`; + } + current = current.parent; + } + } + + let current: Parser.SyntaxNode | null = node; + while (current) { + if (current.type === 'function_definition') { + return `function:${current.startIndex}:${current.endIndex}`; + } + current = current.parent; + } + + return 'module'; +} + +function trackedClientScopeKey(clientNode: Parser.SyntaxNode): string { + return getScopeKey(clientNode.parent, clientNode.text.includes('.')); +} + +function callScopeKeys(clientNode: Parser.SyntaxNode): string[] { + const keys = new Set(); + const preferClass = clientNode.text.includes('.'); + const nearestScope = getScopeKey(clientNode.parent, preferClass); + + keys.add(nearestScope); + + return [...keys]; +} + +function collectHttpxAsyncClients(tree: Parser.Tree): Map> { + const clients = new Map>(); + + const addClient = (clientNode: Parser.SyntaxNode | undefined) => { + if (!clientNode) return; + const scopeKey = trackedClientScopeKey(clientNode); + const clientText = clientNode.text; + const scopes = clients.get(clientText) ?? new Set(); + scopes.add(scopeKey); + clients.set(clientText, scopes); + }; + + for (const match of runCompiledPatterns(HTTPX_ASYNC_CLIENT_ASSIGN_PATTERNS, tree)) { + addClient(match.captures.client); + } + + for (const match of runCompiledPatterns(HTTPX_ASYNC_CLIENT_WITH_ALIAS_PATTERNS, tree)) { + addClient(match.captures.client); + } + + return clients; +} + +function hasTrackedHttpxAsyncClient( + clients: Map>, + clientNode: Parser.SyntaxNode, +): boolean { + const scopes = clients.get(clientNode.text); + if (!scopes) return false; + + return callScopeKeys(clientNode).some((scopeKey) => scopes.has(scopeKey)); +} + +// ─── Consumer: httpx AsyncClient .get/.post/...("url") ────────────── +const HTTPX_ASYNC_CLIENT_VERB_PATTERNS = compilePatterns({ + name: 'python-httpx-async-client-verb', + language: Python, + patterns: [ + { + meta: {}, + query: ` + (call + function: (attribute + object: (_) @client + attribute: (identifier) @method (#match? @method "^(get|post|put|delete|patch)$")) + arguments: (argument_list . (string) @path)) + `, + }, + ], +} satisfies LanguagePatterns>); + +// ─── Consumer: httpx AsyncClient .request("METHOD", "url") ───────── +const HTTPX_ASYNC_CLIENT_GENERIC_PATTERNS = compilePatterns({ + name: 'python-httpx-async-client-generic', + language: Python, + patterns: [ + { + meta: {}, + query: ` + (call + function: (attribute + object: (_) @client + attribute: (identifier) @method (#eq? @method "request")) + arguments: (argument_list . (string) @http_method (string) @path)) + `, + }, + ], +} satisfies LanguagePatterns>); + export const PYTHON_HTTP_PLUGIN: HttpLanguagePlugin = { name: 'python-http', language: Python, scan(tree) { const out: HttpDetection[] = []; + const httpxAsyncClients = collectHttpxAsyncClients(tree); // Providers: FastAPI for (const match of runCompiledPatterns(FASTAPI_PATTERNS, tree)) { @@ -137,6 +289,45 @@ export const PYTHON_HTTP_PLUGIN: HttpLanguagePlugin = { }); } + // Consumers: httpx.AsyncClient.("url") + for (const match of runCompiledPatterns(HTTPX_ASYNC_CLIENT_VERB_PATTERNS, tree)) { + const clientNode = match.captures.client; + const methodNode = match.captures.method; + const pathNode = match.captures.path; + if (!clientNode || !methodNode || !pathNode) continue; + if (!hasTrackedHttpxAsyncClient(httpxAsyncClients, clientNode)) continue; + const path = unquoteLiteral(pathNode.text); + if (path === null) continue; + out.push({ + role: 'consumer', + framework: 'python-httpx', + method: methodNode.text.toUpperCase(), + path, + name: null, + confidence: 0.7, + }); + } + + // Consumers: httpx.AsyncClient.request("METHOD", "url") + for (const match of runCompiledPatterns(HTTPX_ASYNC_CLIENT_GENERIC_PATTERNS, tree)) { + const clientNode = match.captures.client; + const methodNode = match.captures.http_method; + const pathNode = match.captures.path; + if (!clientNode || !methodNode || !pathNode) continue; + if (!hasTrackedHttpxAsyncClient(httpxAsyncClients, clientNode)) continue; + const methodRaw = unquoteLiteral(methodNode.text); + const path = unquoteLiteral(pathNode.text); + if (methodRaw === null || path === null) continue; + out.push({ + role: 'consumer', + framework: 'python-httpx', + method: methodRaw.toUpperCase(), + path, + name: null, + confidence: 0.7, + }); + } + return out; }, }; diff --git a/gitnexus/src/core/group/extractors/http-route-extractor.ts b/gitnexus/src/core/group/extractors/http-route-extractor.ts index d989876a8..898a22c38 100644 --- a/gitnexus/src/core/group/extractors/http-route-extractor.ts +++ b/gitnexus/src/core/group/extractors/http-route-extractor.ts @@ -5,6 +5,7 @@ import { createIgnoreFilter } from '../../../config/ignore-service.js'; import type { ContractExtractor, CypherExecutor } from '../contract-extractor.js'; import type { ExtractedContract, RepoHandle } from '../types.js'; import { readSafe } from './fs-utils.js'; +import { parseSourceSafe } from '../../tree-sitter/safe-parse.js'; import { getPluginForFile, HTTP_SCAN_GLOB, type HttpDetection } from './http-patterns/index.js'; /** @@ -172,7 +173,7 @@ export class HttpRouteExtractor implements ContractExtractor { } try { parser.setLanguage(plugin.language); - const tree = parser.parse(content); + const tree = parseSourceSafe(parser, content); const detections = plugin.scan(tree); cachedDetections.set(rel, detections); return detections; diff --git a/gitnexus/src/core/group/extractors/include-extractor.ts b/gitnexus/src/core/group/extractors/include-extractor.ts index 7bbfd61ed..98cbd371f 100644 --- a/gitnexus/src/core/group/extractors/include-extractor.ts +++ b/gitnexus/src/core/group/extractors/include-extractor.ts @@ -10,6 +10,7 @@ import { readSafe } from './fs-utils.js'; import { buildSuffixIndex, type SuffixIndex } from '../../ingestion/import-resolvers/utils.js'; import { createIgnoreFilter } from '../../../config/ignore-service.js'; import { getMaxFileSizeBytes } from '../../ingestion/utils/max-file-size.js'; +import { parseSourceSafe } from '../../tree-sitter/safe-parse.js'; import { logger } from '../../logger.js'; /** @@ -505,7 +506,7 @@ export class IncludeExtractor implements ContractExtractor { let extractionSource: 'tree_sitter' | 'regex_fallback'; try { parser.setLanguage(lang); - const tree = parser.parse(content); + const tree = parseSourceSafe(parser, content); let matches: Parser.QueryMatch[]; try { matches = query.matches(tree.rootNode); diff --git a/gitnexus/src/core/group/extractors/thrift-extractor.ts b/gitnexus/src/core/group/extractors/thrift-extractor.ts index 709968790..7d23e19cc 100644 --- a/gitnexus/src/core/group/extractors/thrift-extractor.ts +++ b/gitnexus/src/core/group/extractors/thrift-extractor.ts @@ -3,6 +3,7 @@ import Parser from 'tree-sitter'; import type { ContractExtractor, CypherExecutor } from '../contract-extractor.js'; import type { ExtractedContract, RepoHandle } from '../types.js'; import { readSafe } from './fs-utils.js'; +import { parseSourceSafe } from '../../tree-sitter/safe-parse.js'; import { getPluginForFile, THRIFT_SCAN_GLOB, @@ -311,7 +312,7 @@ export class ThriftExtractor implements ContractExtractor { let detections: ThriftDetection[] = []; try { parser.setLanguage(plugin.language); - const tree = parser.parse(content); + const tree = parseSourceSafe(parser, content); detections = plugin.scan(tree); } catch { continue; diff --git a/gitnexus/src/core/group/extractors/tree-sitter-scanner.ts b/gitnexus/src/core/group/extractors/tree-sitter-scanner.ts index cd50456aa..0463e8f0c 100644 --- a/gitnexus/src/core/group/extractors/tree-sitter-scanner.ts +++ b/gitnexus/src/core/group/extractors/tree-sitter-scanner.ts @@ -1,4 +1,5 @@ import Parser from 'tree-sitter'; +import { parseSourceSafe } from '../../tree-sitter/safe-parse.js'; /** * Shared, language-agnostic tree-sitter scanning utilities used by group @@ -155,7 +156,7 @@ export function scanFile( let tree: Parser.Tree; try { parser.setLanguage(plugin.language); - tree = parser.parse(content); + tree = parseSourceSafe(parser, content); } catch { return []; } diff --git a/gitnexus/src/core/incremental/shadow-candidates.ts b/gitnexus/src/core/incremental/shadow-candidates.ts new file mode 100644 index 000000000..415a6d9df --- /dev/null +++ b/gitnexus/src/core/incremental/shadow-candidates.ts @@ -0,0 +1,76 @@ +/** + * Shadow-candidate path derivation for incremental indexing. + * + * Background — Bugbot review on PR #1479: + * queryImporters() on a NEWLY ADDED file returns 0 importers in the + * pre-pipeline DB, because the new file's IMPORTS rows haven't been + * written yet. But pre-existing files may have IMPORTS edges that + * *resolved to a sibling path*, and the newcomer can now steal that + * resolution under standard JS/TS module-resolution rules. Without + * pulling those pre-existing files into the writable set, their + * stale CALLS edges remain pointing at the OLD resolution target. + * + * Given an added file path, this helper enumerates the pre-existing + * file paths whose import-resolution claim the newcomer can steal. + * Caller filters the candidates against the prior-run `fileHashes` + * map so we only query importers of paths that actually existed. + * + * Shadow patterns covered (resolution-priority-aware): + * + * (a) Same basename, different extension — + * added `foo/bar.ts` shadows `foo/bar.{tsx,js,jsx,mjs,cjs,d.ts}`. + * (b) Bare-file beats directory-style index — + * added `foo/bar.ts` shadows `foo/bar/index.{ts,tsx,...}`. + * (c) Directory-index beats bare-file — + * added `foo/index.ts` shadows `foo.{ts,tsx,...}` (rare but real, + * e.g. converting a single-file module into a directory module). + * + * Resolution-order priority is conservatively wide: we enumerate ALL + * common extensions because we don't know which the importer actually + * specified, and over-seeding is harmless (extra BFS work, but the + * subgraph extract still gates write-back by file membership). + * + * Cross-platform path separators: candidates are emitted with both `/` + * and `\` for shadow pattern (b), since the caller's prior fileHashes + * map may use either depending on the OS that wrote it. + */ + +const SHADOW_EXTS = ['.d.ts', '.tsx', '.ts', '.jsx', '.js', '.mjs', '.cjs']; + +/** + * Enumerate pre-existing paths whose import-resolution `added` can steal. + * + * @param added — repo-relative path of a newly-added file + * @returns deduplicated list of candidate paths (NOT filtered against + * any known-files set — caller does that) + */ +export const shadowCandidatesFor = (added: string): string[] => { + const ext = SHADOW_EXTS.find((e) => added.endsWith(e)); + if (!ext) return []; + + const noExt = added.slice(0, -ext.length); + const out = new Set(); + + // (a) Same basename, different extension. + for (const alt of SHADOW_EXTS) { + if (alt !== ext) out.add(noExt + alt); + } + + // (b) Bare file beats sibling directory-style index. + for (const idx of SHADOW_EXTS) { + out.add(`${noExt}/index${idx}`); + out.add(`${noExt}\\index${idx}`); + } + + // (c) New `foo/index.ext` shadows old `foo.ext`. + const idxSuffixSlash = '/index'; + const idxSuffixBack = '\\index'; + let dir: string | null = null; + if (noExt.endsWith(idxSuffixSlash)) dir = noExt.slice(0, -idxSuffixSlash.length); + else if (noExt.endsWith(idxSuffixBack)) dir = noExt.slice(0, -idxSuffixBack.length); + if (dir !== null) { + for (const alt of SHADOW_EXTS) out.add(dir + alt); + } + + return [...out]; +}; diff --git a/gitnexus/src/core/incremental/subgraph-extract.ts b/gitnexus/src/core/incremental/subgraph-extract.ts new file mode 100644 index 000000000..71fe656be --- /dev/null +++ b/gitnexus/src/core/incremental/subgraph-extract.ts @@ -0,0 +1,123 @@ +/** + * Subgraph extraction for incremental DB writeback. + * + * Given the FULL ctx.graph produced by the pipeline (all files parsed, + * all phases run) and the set of file paths whose DB rows must be + * replaced, produce a smaller KnowledgeGraph that contains: + * + * - Every node whose `properties.filePath` is in `toWriteSet`. + * - Every graph-wide node (Community, Process) — these are regenerated + * each run by the communities/processes phases and must be fully + * rewritten. + * - Every relationship where AT LEAST ONE endpoint is in the writable + * set above. Relationships entirely between unchanged-file nodes + * are skipped — their rows are still in the DB and re-inserting + * them would PK-conflict at COPY time. + * + * The resulting subgraph is what gets passed to `loadGraphToLbug` after + * the orchestrator has deleted the corresponding DB rows. Hydrated + * unchanged-file rows are never touched in the DB. + * + * # Cross-file edge consistency (Finding 1) + * + * `extractChangedSubgraph` intentionally does NOT expand the set it is + * given — expansion is the orchestrator's job, so the SAME expanded set + * can be fed to both `deleteNodesForFile` and this function (asymmetry + * between the delete set and the write set silently corrupts the DB). + * `computeEffectiveWriteSet` below performs the boundary-crossing 1-hop + * walk; the orchestrator composes it with its importer-BFS expansion and + * passes the result here. + * + * Why the 1-hop walk is needed: consider a barrel re-export change — + * file C (a barrel) shifts `export { foo } from './b'` to + * `export { foo } from './d'`. After scope resolution, file A's CALLS + * edge to `foo` resolves to D instead of B, even though A's content is + * byte-for-byte identical: + * + * - Old A→B edge survives in DB (neither A nor B is changed → not deleted) + * - New A→D edge is missing (neither A nor D in writable set → skipped) + * + * Pulling the unchanged-side file of every writable-boundary-crossing + * edge into the write set fixes both halves: the orchestrator's + * `DETACH DELETE` cleans up the stale unchanged-side rows, and the new + * cross-file edges land because at least one endpoint is now writable. + * + * Limitation (documented): if a file X *stopped* importing from a + * changed file C, X has no edge to C in the new graph, so this 1-hop + * walk doesn't catch it. The orchestrator's importer-BFS (which reads + * IMPORTS from the pre-pipeline DB) covers that case instead. + */ + +import type { GraphNode, GraphRelationship } from 'gitnexus-shared'; +import { createKnowledgeGraph } from '../graph/graph.js'; +import type { KnowledgeGraph } from '../graph/types.js'; + +const isGraphWide = (label: string): boolean => label === 'Community' || label === 'Process'; + +/** + * Build a Map for every File-bound node in the graph. + * Graph-wide nodes (Community/Process) have no filePath and are filtered. + */ +const indexNodeFilePaths = (fullGraph: KnowledgeGraph): Map => { + const idx = new Map(); + fullGraph.forEachNode((n: GraphNode) => { + const fp = n.properties?.filePath as string | undefined; + if (fp) idx.set(n.id, fp); + }); + return idx; +}; + +export const extractChangedSubgraph = ( + fullGraph: KnowledgeGraph, + toWriteSet: ReadonlySet, +): KnowledgeGraph => { + const sub = createKnowledgeGraph(); + const writableNodeIds = new Set(); + + fullGraph.forEachNode((n: GraphNode) => { + const filePath = n.properties?.filePath as string | undefined; + const include = (filePath && toWriteSet.has(filePath)) || isGraphWide(n.label); + if (include) { + sub.addNode(n); + writableNodeIds.add(n.id); + } + }); + + fullGraph.forEachRelationship((r: GraphRelationship) => { + if (writableNodeIds.has(r.sourceId) || writableNodeIds.has(r.targetId)) { + sub.addRelationship(r); + } + }); + + return sub; +}; + +/** + * Public — derive the EFFECTIVE write-set: `toWriteSet` expanded by one + * hop along every edge in the new graph that crosses the writable + * boundary (one endpoint in a writable file, the other in an unchanged + * file). The unchanged-side file is pulled in so its stale rows are + * deleted + rewritten in lockstep with the changed side. + * + * Single pass over the edge list. Does NOT mutate `toWriteSet`. The + * orchestrator MUST feed the returned set to both `deleteNodesForFile` + * and `extractChangedSubgraph` — feeding the unexpanded set to either + * one leaves stale rows or PK-conflicts at COPY time. + */ +export const computeEffectiveWriteSet = ( + fullGraph: KnowledgeGraph, + toWriteSet: ReadonlySet, +): Set => { + const nodeFilePaths = indexNodeFilePaths(fullGraph); + const expanded = new Set(toWriteSet); + fullGraph.forEachRelationship((r: GraphRelationship) => { + const sourcePath = nodeFilePaths.get(r.sourceId); + const targetPath = nodeFilePaths.get(r.targetId); + if (!sourcePath || !targetPath) return; // skip edges to graph-wide nodes + const sourceWritable = toWriteSet.has(sourcePath); + const targetWritable = toWriteSet.has(targetPath); + if (sourceWritable && !targetWritable) expanded.add(targetPath); + else if (targetWritable && !sourceWritable) expanded.add(sourcePath); + }); + return expanded; +}; diff --git a/gitnexus/src/core/ingestion/call-processor.ts b/gitnexus/src/core/ingestion/call-processor.ts index bf0206057..35a59dab4 100644 --- a/gitnexus/src/core/ingestion/call-processor.ts +++ b/gitnexus/src/core/ingestion/call-processor.ts @@ -40,13 +40,16 @@ import { getLanguageFromFilename, SupportedLanguages } from 'gitnexus-shared'; import { isRegistryPrimary } from './registry-primary-flag.js'; import { isVerboseIngestionEnabled } from './utils/verbose.js'; import { yieldToEventLoop } from './utils/event-loop.js'; +import { parseSourceSafe } from '../tree-sitter/safe-parse.js'; import { + CLASS_CONTAINER_TYPES, FUNCTION_NODE_TYPES, - findEnclosingClassId, findEnclosingClassInfo, genericFuncName, inferFunctionLabel, } from './utils/ast-helpers.js'; +import type { FieldInfo, FieldExtractorContext } from './field-types.js'; +import type { LanguageProvider } from './language-provider.js'; import { typeTagForId, constTagForId, buildCollisionGroups } from './utils/method-props.js'; import type { MethodInfo } from './method-types.js'; import { @@ -76,6 +79,62 @@ import type { LiteralTypeInferrer } from './type-extractors/types.js'; import type { SyntaxNode } from './utils/ast-helpers.js'; import { logger } from '../logger.js'; + +// ── Property-prepass helpers (parity with parse-worker.ts) ── +// These mirror the sequential-path equivalents in parse-worker.ts so the main- +// thread `processCalls` pre-pass produces byte-identical Property nodes/symbols +// to the worker pool. Drift between the two paths breaks the +// `incremental ≡ --force` invariant the moment a repo crosses the worker +// threshold between runs. + +/** Walk up to the nearest enclosing class/struct/interface AST node. */ +const findEnclosingClassNode = (node: SyntaxNode): SyntaxNode | null => { + let current = node.parent; + while (current) { + if (CLASS_CONTAINER_TYPES.has(current.type)) return current; + current = current.parent; + } + return null; +}; + +/** No-op SymbolTable stub for FieldExtractorContext — matches parse-worker. */ +const NOOP_SYMBOL_TABLE: SymbolTableReader = { + lookupExact: () => undefined, + lookupExactFull: () => undefined, + lookupExactAll: () => [], + lookupCallableByName: () => [], + getFiles: () => [][Symbol.iterator](), + getStats: () => ({ fileCount: 0 }), +}; + +/** + * Extract (and cache) field info for a class node. Cache is passed in so it + * stays scoped to a single `processCalls` invocation rather than leaking + * across analyze runs (worker uses module-level caching because each worker + * process is short-lived; the main thread is not). + * + * Cache key is `${filePath}:${classNode.startIndex}` — startIndex alone is a + * per-file byte offset, so almost every Ruby/Python file's leading class lands + * at byte 0 and would collide across files in the shared map. + */ +const getFieldInfo = ( + classNode: SyntaxNode, + provider: LanguageProvider, + context: FieldExtractorContext, + cache: Map>, +): Map | undefined => { + if (!provider.fieldExtractor) return undefined; + const cacheKey = `${context.filePath}:${classNode.startIndex}`; + const cached = cache.get(cacheKey); + if (cached) return cached; + const result = provider.fieldExtractor.extract(classNode, context); + if (!result?.fields?.length) return undefined; + const map = new Map(); + for (const field of result.fields) map.set(field.name, field); + cache.set(cacheKey, map); + return map; +}; + /** Per-file resolved type bindings for exported symbols. * Populated during call processing, consumed by Phase 14 re-resolution pass. */ export type ExportedTypeMap = Map>; @@ -715,6 +774,7 @@ export const processCalls = async ( propertyName: string; filePath: string; srcId: string; + line?: number; }[] = []; // Phase P cross-file: accumulate heritage across files for cross-file isSubclassOf. // Used as a secondary check when per-file parentMap lacks the relationship — helps @@ -771,7 +831,7 @@ export const processCalls = async ( if (!tree) { const parseContent = provider.preprocessSource?.(file.content, file.path) ?? file.content; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch (parseError) { @@ -859,6 +919,120 @@ export const processCalls = async ( prepared.push({ file, language, provider, tree, matches, parentMap, typeEnv }); } + // ── Property-registration pre-pass ── + // Register all routed properties (e.g. Ruby attr_accessor) BEFORE the + // resolution loop so cross-file field-type lookups (e.g. + // `user.address.save → Address#save`) succeed regardless of file + // processing order. This MUST stay in lockstep with the equivalent + // worker-path block in parse-worker.ts (kind === 'properties') — any + // divergence between the two paths breaks the `incremental ≡ --force` + // invariant once a repo crosses the worker threshold between runs. + const fieldInfoCache = new Map>(); + for (const { file, language, provider, matches, typeEnv } of prepared) { + const callRouter = provider.callRouter; + if (!callRouter) continue; + matches.forEach((match) => { + const captureMap: Record = {}; + match.captures.forEach((c) => (captureMap[c.name] = c.node)); + if (!captureMap['call']) return; + const callNameNode = captureMap['call.name']; + if (!callNameNode) return; + const routed = callRouter(callNameNode.text, captureMap['call']); + if (!routed || routed.kind !== 'properties') return; + + const propEnclosingInfo = findEnclosingClassInfo( + captureMap['call'], + file.path, + provider.resolveEnclosingOwner, + ); + const propEnclosingClassId = propEnclosingInfo?.classId ?? null; + + // Enrich routed properties with FieldExtractor metadata so types + // discovered from constructor assignments (e.g. `@address = Address.new`) + // are propagated even when the routing payload itself lacks declaredType. + let routedFieldMap: Map | undefined; + if (provider.fieldExtractor && typeEnv) { + const classNode = findEnclosingClassNode(captureMap['call']); + if (classNode) { + routedFieldMap = getFieldInfo( + classNode, + provider, + { + typeEnv, + symbolTable: NOOP_SYMBOL_TABLE, + filePath: file.path, + language, + }, + fieldInfoCache, + ); + } + } + + const fileId = generateId('File', file.path); + for (const item of routed.items) { + const routedFieldInfo = routedFieldMap?.get(item.propName); + const propQualifiedName = propEnclosingInfo + ? `${propEnclosingInfo.className}.${item.propName}` + : item.propName; + const nodeId = generateId('Property', `${file.path}:${propQualifiedName}`); + graph.addNode({ + id: nodeId, + label: 'Property', + properties: { + name: item.propName, + filePath: file.path, + startLine: item.startLine, + endLine: item.endLine, + language, + isExported: true, + description: item.accessorType, + ...(item.declaredType + ? { declaredType: item.declaredType } + : routedFieldInfo?.type + ? { declaredType: routedFieldInfo.type } + : {}), + ...(routedFieldInfo?.visibility !== undefined + ? { visibility: routedFieldInfo.visibility } + : {}), + ...(routedFieldInfo?.isStatic !== undefined + ? { isStatic: routedFieldInfo.isStatic } + : {}), + ...(routedFieldInfo?.isReadonly !== undefined + ? { isReadonly: routedFieldInfo.isReadonly } + : {}), + }, + }); + ctx.model.symbols.add(file.path, item.propName, nodeId, 'Property', { + ...(propEnclosingClassId ? { ownerId: propEnclosingClassId } : {}), + ...(item.declaredType + ? { declaredType: item.declaredType } + : routedFieldInfo?.type + ? { declaredType: routedFieldInfo.type } + : {}), + }); + const relId = generateId('DEFINES', `${fileId}->${nodeId}`); + graph.addRelationship({ + id: relId, + sourceId: fileId, + targetId: nodeId, + type: 'DEFINES', + confidence: 1.0, + reason: '', + }); + if (propEnclosingClassId) { + graph.addRelationship({ + id: generateId('HAS_PROPERTY', `${propEnclosingClassId}->${nodeId}`), + sourceId: propEnclosingClassId, + targetId: nodeId, + type: 'HAS_PROPERTY', + confidence: 1.0, + reason: '', + }); + } + } + }); + } + // ── Resolution loop: verify constructor bindings and resolve calls ── // The accumulator (if present) is now fully populated from the preparation // loop above, so verifyConstructorBindings sees all provider bindings @@ -932,7 +1106,13 @@ export const processCalls = async ( // Defer resolution: Ruby attr_accessor properties are registered during // this same loop, so cross-file lookups fail if the declaring file hasn't // been processed yet. Collect now, resolve after all files are done. - pendingWrites.push({ receiverTypeName, propertyName, filePath: file.path, srcId }); + pendingWrites.push({ + receiverTypeName, + propertyName, + filePath: file.path, + srcId, + line: captureMap['assignment'].startPosition.row + 1, + }); } // Assignment-only capture (no @call sibling): skip the rest of this // forEach iteration — this acts as a `continue` in the match loop. @@ -1052,47 +1232,8 @@ export const processCalls = async ( return; case 'properties': { - const fileId = generateId('File', file.path); - const propEnclosingClassId = findEnclosingClassId(captureMap['call'], file.path); - for (const item of routed.items) { - const nodeId = generateId('Property', `${file.path}:${item.propName}`); - graph.addNode({ - id: nodeId, - label: 'Property', - properties: { - name: item.propName, - filePath: file.path, - startLine: item.startLine, - endLine: item.endLine, - language, - isExported: true, - description: item.accessorType, - }, - }); - ctx.model.symbols.add(file.path, item.propName, nodeId, 'Property', { - ...(propEnclosingClassId ? { ownerId: propEnclosingClassId } : {}), - ...(item.declaredType ? { declaredType: item.declaredType } : {}), - }); - const relId = generateId('DEFINES', `${fileId}->${nodeId}`); - graph.addRelationship({ - id: relId, - sourceId: fileId, - targetId: nodeId, - type: 'DEFINES', - confidence: 1.0, - reason: '', - }); - if (propEnclosingClassId) { - graph.addRelationship({ - id: generateId('HAS_PROPERTY', `${propEnclosingClassId}->${nodeId}`), - sourceId: propEnclosingClassId, - targetId: nodeId, - type: 'HAS_PROPERTY', - confidence: 1.0, - reason: '', - }); - } - } + // Properties already registered in the pre-pass above. + // Skip to avoid duplicate nodes/edges. return; } @@ -1381,7 +1522,10 @@ export const processCalls = async ( ); if (fieldOwner) { graph.addRelationship({ - id: generateId('ACCESSES', `${pw.srcId}:${fieldOwner.nodeId}:write`), + id: generateId( + 'ACCESSES', + `${pw.srcId}:${fieldOwner.nodeId}:write${pw.line !== undefined ? `:${pw.line}` : ''}`, + ), sourceId: pw.srcId, targetId: fieldOwner.nodeId, type: 'ACCESSES', @@ -2978,7 +3122,10 @@ export const processAssignmentsFromExtracted = ( const fieldOwner = resolveFieldOwnership(receiverTypeName, asn.propertyName, asn.filePath, ctx); if (!fieldOwner) continue; graph.addRelationship({ - id: generateId('ACCESSES', `${asn.sourceId}:${fieldOwner.nodeId}:write`), + id: generateId( + 'ACCESSES', + `${asn.sourceId}:${fieldOwner.nodeId}:write${asn.line !== undefined ? `:${asn.line}` : ''}`, + ), sourceId: asn.sourceId, targetId: fieldOwner.nodeId, type: 'ACCESSES', @@ -3283,7 +3430,7 @@ export const extractFetchCallsFromFiles = async ( if (!tree) { const parseContent = provider.preprocessSource?.(file.content, file.path) ?? file.content; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch { diff --git a/gitnexus/src/core/ingestion/class-extractors/configs/c-cpp.ts b/gitnexus/src/core/ingestion/class-extractors/configs/c-cpp.ts index fcc1a22bf..fb5df99c3 100644 --- a/gitnexus/src/core/ingestion/class-extractors/configs/c-cpp.ts +++ b/gitnexus/src/core/ingestion/class-extractors/configs/c-cpp.ts @@ -2,6 +2,40 @@ import { SupportedLanguages } from 'gitnexus-shared'; import type { ClassExtractionConfig } from '../../class-types.js'; +import { + extractTemplateArguments, + stripTemplateArguments, +} from '../../utils/template-arguments.js'; + +function shouldSkipCppTemplateDuplicateCapture( + captureMap: Record, + definitionName: string | undefined, + capturedName: string | undefined, +): boolean { + if (captureMap['template-arguments'] !== undefined) return false; + if (!definitionName) return false; + const argsFromDefinitionName = extractTemplateArguments(definitionName); + if (argsFromDefinitionName === undefined) return false; + const argsFromCaptureName = capturedName ? extractTemplateArguments(capturedName) : undefined; + // Generic class capture emits only `List`, while the specialization-aware + // capture emits `List` + `@declaration.template-arguments`. Skip the former + // when the declaration name itself is templated to avoid duplicate class defs. + return argsFromCaptureName === undefined; +} + +function extractCppTemplateArgumentsWithFallback( + captureMap: Record, + definitionName: string | undefined, + capturedName: string | undefined, +): string[] | undefined { + return ( + (captureMap['template-arguments'] + ? extractTemplateArguments(captureMap['template-arguments'].text) + : undefined) ?? + (definitionName ? extractTemplateArguments(definitionName) : undefined) ?? + (capturedName ? extractTemplateArguments(capturedName) : undefined) + ); +} export const cClassConfig: ClassExtractionConfig = { language: SupportedLanguages.C, @@ -12,4 +46,27 @@ export const cppClassConfig: ClassExtractionConfig = { language: SupportedLanguages.CPlusPlus, typeDeclarationNodes: ['class_specifier', 'struct_specifier', 'enum_specifier'], ancestorScopeNodeTypes: ['namespace_definition', 'class_specifier', 'struct_specifier'], + extractName: (node) => { + const nameNode = node.childForFieldName?.('name'); + if (!nameNode) return undefined; + if (nameNode.type !== 'template_type') return undefined; + return stripTemplateArguments(nameNode.text); + }, + extractTemplateArguments: (node) => { + const nameNode = node.childForFieldName?.('name'); + if (!nameNode || nameNode.type !== 'template_type') return undefined; + return extractTemplateArguments(nameNode.text); + }, + shouldSkipClassCapture: ({ captureMap, definitionNode, nameNode }) => + shouldSkipCppTemplateDuplicateCapture( + captureMap, + definitionNode?.childForFieldName?.('name')?.text, + nameNode?.text, + ), + extractTemplateArgumentsFromCapture: ({ captureMap, definitionNode, nameNode }) => + extractCppTemplateArgumentsWithFallback( + captureMap, + definitionNode?.childForFieldName?.('name')?.text, + nameNode?.text, + ), }; diff --git a/gitnexus/src/core/ingestion/class-extractors/generic.ts b/gitnexus/src/core/ingestion/class-extractors/generic.ts index 303eb80c0..5f20d1dc2 100644 --- a/gitnexus/src/core/ingestion/class-extractors/generic.ts +++ b/gitnexus/src/core/ingestion/class-extractors/generic.ts @@ -154,10 +154,12 @@ export function createClassExtractor(config: ClassExtractionConfig): ClassExtrac if (!name || !type) return null; + const templateArguments = config.extractTemplateArguments?.(node); return { name, type, qualifiedName: buildQualifiedName(node, name) || name, + ...(templateArguments !== undefined ? { templateArguments } : {}), }; }; @@ -173,5 +175,13 @@ export function createClassExtractor(config: ClassExtractionConfig): ClassExtrac extractQualifiedName(node: SyntaxNode, simpleName: string): string | null { return extract(node, { name: simpleName })?.qualifiedName ?? null; }, + + shouldSkipClassCapture(context): boolean { + return config.shouldSkipClassCapture?.(context) ?? false; + }, + + extractTemplateArgumentsFromCapture(context): string[] | undefined { + return config.extractTemplateArgumentsFromCapture?.(context); + }, }; } diff --git a/gitnexus/src/core/ingestion/class-types.ts b/gitnexus/src/core/ingestion/class-types.ts index 858d4c2eb..9407d41fa 100644 --- a/gitnexus/src/core/ingestion/class-types.ts +++ b/gitnexus/src/core/ingestion/class-types.ts @@ -10,6 +10,13 @@ export interface ExtractedClassSymbol { name: string; type: ClassLikeNodeLabel; qualifiedName: string; + templateArguments?: string[]; +} + +export interface ClassCaptureContext { + captureMap: Record; + definitionNode: SyntaxNode | null; + nameNode: SyntaxNode | undefined; } /** @@ -30,6 +37,10 @@ export interface ClassExtractor { }, ): ExtractedClassSymbol | null; extractQualifiedName(node: SyntaxNode, simpleName: string): string | null; + shouldSkipClassCapture?( + context: ClassCaptureContext & { nodeLabel: ClassLikeNodeLabel }, + ): boolean; + extractTemplateArgumentsFromCapture?(context: ClassCaptureContext): string[] | undefined; } export interface ClassExtractionConfig { @@ -41,4 +52,9 @@ export interface ClassExtractionConfig { extractName?: (node: SyntaxNode) => string | undefined; extractType?: (node: SyntaxNode) => ClassLikeNodeLabel | undefined; extractScopeSegments?: (node: SyntaxNode) => string[] | null | undefined; + extractTemplateArguments?: (node: SyntaxNode) => string[] | undefined; + shouldSkipClassCapture?( + context: ClassCaptureContext & { nodeLabel: ClassLikeNodeLabel }, + ): boolean; + extractTemplateArgumentsFromCapture?(context: ClassCaptureContext): string[] | undefined; } diff --git a/gitnexus/src/core/ingestion/community-processor.ts b/gitnexus/src/core/ingestion/community-processor.ts index 9913e4a3f..ac8f068fa 100644 --- a/gitnexus/src/core/ingestion/community-processor.ts +++ b/gitnexus/src/core/ingestion/community-processor.ts @@ -41,6 +41,24 @@ interface LeidenDetailedResult { modularity: number; } +/** + * Deterministic PRNG (mulberry32) seed for the vendored Leiden algorithm. + * Vendored Leiden defaults `rng: Math.random`, which makes community + * assignment non-deterministic across runs. Passing a seeded RNG gives us + * reproducible community/modularity output, which is required for the + * incremental-indexing equivalence test (incremental ≡ full rebuild). + */ +const LEIDEN_SEED = 0xc0de; +function createSeededRng(seed: number): () => number { + let s = seed >>> 0; + return () => { + s = (s + 0x6d2b79f5) >>> 0; + let t = Math.imul(s ^ (s >>> 15), 1 | s); + t = (t + Math.imul(t ^ (t >>> 7), 61 | t)) ^ t; + return ((t ^ (t >>> 14)) >>> 0) / 4294967296; + }; +} + // ============================================================================ // TYPES // ============================================================================ @@ -150,6 +168,7 @@ export const processCommunities = async ( leiden.detailed(graph, { resolution: isLarge ? 2.0 : 1.0, maxIterations: isLarge ? 3 : 0, + rng: createSeededRng(LEIDEN_SEED), }), ), new Promise((_, reject) => diff --git a/gitnexus/src/core/ingestion/heritage-processor.ts b/gitnexus/src/core/ingestion/heritage-processor.ts index f8628e651..c223bd286 100644 --- a/gitnexus/src/core/ingestion/heritage-processor.ts +++ b/gitnexus/src/core/ingestion/heritage-processor.ts @@ -22,6 +22,7 @@ import { generateId } from '../../lib/utils.js'; import { getLanguageFromFilename, type NodeLabel, type SupportedLanguages } from 'gitnexus-shared'; import { isVerboseIngestionEnabled } from './utils/verbose.js'; import { yieldToEventLoop } from './utils/event-loop.js'; +import { parseSourceSafe } from '../tree-sitter/safe-parse.js'; import { getProvider } from './languages/index.js'; import { getTreeSitterBufferSize } from './constants.js'; import type { @@ -224,7 +225,7 @@ export const processHeritage = async ( // re-parses see the same input as the cached AST. const parseContent = provider.preprocessSource?.(file.content, file.path) ?? file.content; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch (parseError) { @@ -419,7 +420,7 @@ export async function extractExtractedHeritageFromFiles( if (!tree) { const parseContent = provider.preprocessSource?.(file.content, file.path) ?? file.content; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch { diff --git a/gitnexus/src/core/ingestion/import-processor.ts b/gitnexus/src/core/ingestion/import-processor.ts index 6f0b40b6f..f7742faa1 100644 --- a/gitnexus/src/core/ingestion/import-processor.ts +++ b/gitnexus/src/core/ingestion/import-processor.ts @@ -8,6 +8,7 @@ import { generateId } from '../../lib/utils.js'; import { getLanguageFromFilename } from 'gitnexus-shared'; import { isVerboseIngestionEnabled } from './utils/verbose.js'; import { yieldToEventLoop } from './utils/event-loop.js'; +import { parseSourceSafe } from '../tree-sitter/safe-parse.js'; import type { ExtractedImport } from './workers/parse-worker.js'; import { getTreeSitterBufferSize } from './constants.js'; import { loadImportConfigs } from './language-config.js'; @@ -307,7 +308,7 @@ export const processImports = async ( if (!tree) { const parseContent = provider.preprocessSource?.(file.content, file.path) ?? file.content; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch (parseError) { diff --git a/gitnexus/src/core/ingestion/import-resolvers/standard.ts b/gitnexus/src/core/ingestion/import-resolvers/standard.ts index f8aae9625..4ee6e1440 100644 --- a/gitnexus/src/core/ingestion/import-resolvers/standard.ts +++ b/gitnexus/src/core/ingestion/import-resolvers/standard.ts @@ -72,6 +72,13 @@ export const resolveImportPath = ( const resolved = tryResolveWithExtensions(rewritten, allFiles); if (resolved) return cache(resolved); + // ESM fallback: strip .js/.jsx/.mjs/.cjs and retry with TS equivalents + const strippedAlias = stripJsExtension(rewritten); + if (strippedAlias !== null) { + const esmResolved = tryResolveWithExtensions(strippedAlias, allFiles); + if (esmResolved) return cache(esmResolved); + } + // Try suffix matching as fallback const parts = rewritten.split('/').filter(Boolean); const suffixResult = suffixResolve(parts, normalizedFileList, allFileList, index); @@ -128,7 +135,18 @@ export const resolveImportPath = ( if (importPath.startsWith('.')) { const resolved = tryResolveWithExtensions(basePath, allFiles); - return cache(resolved); + if (resolved) return cache(resolved); + + // TypeScript ESM: imports use .js/.jsx/.mjs/.cjs but source files are + // .ts/.tsx/.mts/.cts. Strip the JS-family extension and re-resolve. + if (language === SupportedLanguages.TypeScript || language === SupportedLanguages.JavaScript) { + const stripped = stripJsExtension(basePath); + if (stripped !== null) { + return cache(tryResolveWithExtensions(stripped, allFiles)); + } + } + + return cache(null); } // ---- Generic package/absolute import resolution (suffix matching) ---- @@ -182,3 +200,19 @@ export function resolveStandard( export function createStandardStrategy(language: SupportedLanguages): ImportResolverStrategy { return (raw, fp, ctx) => resolveStandard(raw, fp, ctx, language); } + +// ============================================================================ +// ESM extension helpers +// ============================================================================ + +/** JS-family extensions that TypeScript ESM maps to TS equivalents. */ +const JS_EXTENSION_PATTERN = /\.(js|jsx|mjs|cjs)$/; + +/** + * Strip a JS-family extension from a path, returning the stem. + * Returns `null` if the path does not end with a JS-family extension. + */ +export function stripJsExtension(path: string): string | null { + const match = JS_EXTENSION_PATTERN.exec(path); + return match ? path.slice(0, -match[0].length) : null; +} diff --git a/gitnexus/src/core/ingestion/import-resolvers/utils.ts b/gitnexus/src/core/ingestion/import-resolvers/utils.ts index 8d915eb7f..c4d36556c 100644 --- a/gitnexus/src/core/ingestion/import-resolvers/utils.ts +++ b/gitnexus/src/core/ingestion/import-resolvers/utils.ts @@ -9,8 +9,12 @@ export const EXTENSIONS = [ // TypeScript/JavaScript '.tsx', '.ts', + '.mts', + '.cts', '.jsx', '.js', + '.mjs', + '.cjs', '.vue', '/index.tsx', '/index.ts', diff --git a/gitnexus/src/core/ingestion/languages/c-cpp.ts b/gitnexus/src/core/ingestion/languages/c-cpp.ts index 693e8cec2..c010e0e15 100644 --- a/gitnexus/src/core/ingestion/languages/c-cpp.ts +++ b/gitnexus/src/core/ingestion/languages/c-cpp.ts @@ -46,6 +46,24 @@ import { createCallExtractor } from '../call-extractors/generic.js'; import { cCallConfig, cppCallConfig } from '../call-extractors/configs/c-cpp.js'; import { createHeritageExtractor } from '../heritage-extractors/generic.js'; import { stripUeMacros } from '../cpp-ue-preprocessor.js'; +import { + emitCScopeCaptures, + interpretCImport, + interpretCTypeBinding, + cArityCompatibility, + cBindingScopeFor, + cImportOwningScope, + cReceiverBinding, +} from './c/index.js'; +import { + emitCppScopeCaptures, + interpretCppImport, + interpretCppTypeBinding, + cppArityCompatibility, + cppBindingScopeFor, + cppImportOwningScope, + cppReceiverBinding, +} from './cpp/index.js'; const C_BUILT_INS: ReadonlySet = new Set([ 'printf', @@ -294,12 +312,19 @@ const cCppExtractFunctionName = ( return { funcName, label }; }; -/** Check if a C/C++ function_definition is inside a class or struct body. +/** Check if a C/C++ function_definition is inside a class or struct body + * (and NOT a friend declaration). * Used by cppLabelOverride to skip duplicate function captures - * that are already covered by definition.method queries. */ + * that are already covered by definition.method queries. + * Friend functions are free functions defined inside class bodies — + * they must NOT be skipped (ISO C++ hidden-friend idiom). */ function isCppInsideClassOrStruct(functionNode: SyntaxNode): boolean { let ancestor: SyntaxNode | null = functionNode?.parent ?? null; while (ancestor) { + // Friend declarations: the function_definition is wrapped in + // `friend_declaration` → `field_declaration_list` → class_specifier. + // These are free functions, not methods — don't skip them. + if (ancestor.type === 'friend_declaration') return false; if (ancestor.type === 'class_specifier' || ancestor.type === 'struct_specifier') return true; ancestor = ancestor.parent; } @@ -367,6 +392,16 @@ export const cProvider = defineLanguage({ heritageExtractor: createHeritageExtractor(SupportedLanguages.C), labelOverride: cppLabelOverride, builtInNames: C_BUILT_INS, + + // ── RFC #909 Ring 3: scope-based resolution hooks (RFC §5) ────────── + emitScopeCaptures: emitCScopeCaptures, + interpretImport: interpretCImport, + interpretTypeBinding: interpretCTypeBinding, + bindingScopeFor: cBindingScopeFor, + importOwningScope: cImportOwningScope, + receiverBinding: cReceiverBinding, + arityCompatibility: cArityCompatibility, + // mergeBindings + resolveImportTarget live on ScopeResolver (see c/scope-resolver.ts). }); export const cppProvider = defineLanguage({ @@ -428,4 +463,14 @@ export const cppProvider = defineLanguage({ heritageExtractor: createHeritageExtractor(SupportedLanguages.CPlusPlus), labelOverride: cppLabelOverride, builtInNames: C_BUILT_INS, + + // ── RFC #909 Ring 3: scope-based resolution hooks (RFC §5) ────────── + emitScopeCaptures: emitCppScopeCaptures, + interpretImport: interpretCppImport, + interpretTypeBinding: interpretCppTypeBinding, + bindingScopeFor: cppBindingScopeFor, + importOwningScope: cppImportOwningScope, + receiverBinding: cppReceiverBinding, + arityCompatibility: cppArityCompatibility, + // mergeBindings + resolveImportTarget live on ScopeResolver (see cpp/scope-resolver.ts). }); diff --git a/gitnexus/src/core/ingestion/languages/c/arity-metadata.ts b/gitnexus/src/core/ingestion/languages/c/arity-metadata.ts new file mode 100644 index 000000000..013d78ea8 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/arity-metadata.ts @@ -0,0 +1,102 @@ +import type { SyntaxNode } from '../../utils/ast-helpers.js'; + +export interface CArityInfo { + parameterCount?: number; + requiredParameterCount?: number; + parameterTypes?: string[]; +} + +/** + * Compute declaration arity from a C function definition or declaration node. + */ +export function computeCDeclarationArity(node: SyntaxNode): CArityInfo { + // Find the function_declarator child (may be wrapped in pointer_declarator) + const funcDecl = findFuncDeclarator(node); + if (funcDecl === null) return {}; + + const paramList = funcDecl.childForFieldName('parameters'); + if (paramList === null) return {}; + + const params: SyntaxNode[] = []; + for (let i = 0; i < paramList.childCount; i++) { + const child = paramList.child(i); + if (child === null) continue; + if (child.type === 'parameter_declaration' || child.type === 'variadic_parameter') { + params.push(child); + } + } + + // K&R old-style declaration: `int foo()` has an empty parameter_list with + // no parameter_declaration or variadic_parameter children. Per C89/C99, + // this means the function accepts an unspecified number/types of arguments — + // NOT zero arguments. Return unknown arity to avoid false 'incompatible'. + // `int foo(void)` is the explicit zero-parameter form and is handled below. + if (params.length === 0) return {}; + + // (void) means zero parameters + if (params.length === 1 && params[0].type === 'parameter_declaration') { + const typeNode = params[0].childForFieldName('type'); + const hasDeclarator = params[0].childForFieldName('declarator') !== null; + if (typeNode !== null && typeNode.text === 'void' && !hasDeclarator) { + return { parameterCount: 0, requiredParameterCount: 0, parameterTypes: [] }; + } + } + + const isVariadic = params.some((p) => p.type === 'variadic_parameter'); + const nonVariadicCount = params.filter((p) => p.type !== 'variadic_parameter').length; + + const types: string[] = []; + for (const p of params) { + if (p.type === 'variadic_parameter') { + types.push('...'); + } else { + const typeNode = p.childForFieldName('type'); + types.push(typeNode?.text ?? 'unknown'); + } + } + + return { + parameterCount: isVariadic ? undefined : nonVariadicCount, + requiredParameterCount: nonVariadicCount, + parameterTypes: types, + }; +} + +/** + * Compute call-site arity from a call_expression node. + */ +export function computeCCallArity(node: SyntaxNode): number { + const argList = node.childForFieldName('arguments'); + if (argList === null) return 0; + + let count = 0; + for (let i = 0; i < argList.childCount; i++) { + const child = argList.child(i); + if (child === null) continue; + // Skip punctuation (commas, parens) + if (child.type !== ',' && child.type !== '(' && child.type !== ')') { + count++; + } + } + return count; +} + +function findFuncDeclarator(node: SyntaxNode): SyntaxNode | null { + // Direct child + let decl = node.childForFieldName('declarator'); + if (decl === null) { + for (let i = 0; i < node.childCount; i++) { + const c = node.child(i); + if (c?.type === 'function_declarator') return c; + } + return null; + } + // Unwrap pointer_declarator + while (decl.type === 'pointer_declarator') { + const next = decl.childForFieldName('declarator'); + if (next === null) break; + decl = next; + } + if (decl.type === 'function_declarator') return decl; + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/c/arity.ts b/gitnexus/src/core/ingestion/languages/c/arity.ts new file mode 100644 index 000000000..7bbfa9e57 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/arity.ts @@ -0,0 +1,20 @@ +import type { Callsite, SymbolDefinition } from 'gitnexus-shared'; + +/** + * C arity compatibility: no overloading. Variadic functions detected + * via '...' in parameterTypes. Otherwise exact match or unknown. + */ +export function cArityCompatibility( + def: SymbolDefinition, + callsite: Callsite, +): 'compatible' | 'unknown' | 'incompatible' { + const max = def.parameterCount; + const min = def.requiredParameterCount; + if (max === undefined && min === undefined) return 'unknown'; + if (!Number.isFinite(callsite.arity) || callsite.arity < 0) return 'unknown'; + + const variadic = def.parameterTypes?.some((t) => t === '...') ?? false; + if (min !== undefined && callsite.arity < min) return 'incompatible'; + if (max !== undefined && callsite.arity > max && !variadic) return 'incompatible'; + return 'compatible'; +} diff --git a/gitnexus/src/core/ingestion/languages/c/captures.ts b/gitnexus/src/core/ingestion/languages/c/captures.ts new file mode 100644 index 000000000..836eb3eac --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/captures.ts @@ -0,0 +1,142 @@ +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { + findNodeAtRange, + nodeToCapture, + syntheticCapture, + type SyntaxNode, +} from '../../utils/ast-helpers.js'; +import { getCParser, getCScopeQuery } from './query.js'; +import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; +import { splitCInclude } from './import-decomposer.js'; +import { computeCDeclarationArity, computeCCallArity } from './arity-metadata.js'; +import { markStaticName } from './static-linkage.js'; + +export function emitCScopeCaptures( + sourceText: string, + filePath: string, + cachedTree?: unknown, +): readonly CaptureMatch[] { + let tree = cachedTree as ReturnType['parse']> | undefined; + if (tree === undefined) { + tree = parseSourceSafe(getCParser(), sourceText, undefined, { + bufferSize: getTreeSitterBufferSize(sourceText), + }); + } + + const rawMatches = getCScopeQuery().matches(tree.rootNode); + const out: CaptureMatch[] = []; + + // Track ranges where typedef-struct/union was captured as @declaration.struct/union + // so we can suppress the duplicate @declaration.typedef match at the same range. + const structTypedefRanges = new Set(); + + for (const m of rawMatches) { + const grouped: Record = {}; + for (const c of m.captures) { + const tag = '@' + c.name; + if (tag.startsWith('@_')) continue; + grouped[tag] = nodeToCapture(tag, c.node); + } + if (Object.keys(grouped).length === 0) continue; + + // Handle #include statements + if (grouped['@import.statement'] !== undefined) { + const anchor = grouped['@import.statement']!; + const includeNode = findNodeAtRange(tree.rootNode, anchor.range, 'preproc_include'); + if (includeNode !== null) { + const split = splitCInclude(includeNode); + if (split !== null) { + out.push(split); + continue; + } + } + } + + // Track typedef-struct ranges to suppress duplicate typedef declarations + const structAnchor = grouped['@declaration.struct'] ?? grouped['@declaration.union']; + if (structAnchor !== undefined) { + const r = structAnchor.range; + structTypedefRanges.add(`${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`); + } + + // Suppress @declaration.typedef if the same range was already captured as struct/union + const typedefAnchor = grouped['@declaration.typedef']; + if (typedefAnchor !== undefined) { + const r = typedefAnchor.range; + const key = `${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`; + if (structTypedefRanges.has(key)) continue; + } + + // Enrich function declarations with arity metadata and detect static linkage + const declAnchor = grouped['@declaration.function']; + if (declAnchor !== undefined) { + const fnNode = + findNodeAtRange(tree.rootNode, declAnchor.range, 'function_definition') ?? + findNodeAtRange(tree.rootNode, declAnchor.range, 'declaration'); + if (fnNode !== null) { + const arity = computeCDeclarationArity(fnNode); + if (arity.parameterCount !== undefined) { + grouped['@declaration.parameter-count'] = syntheticCapture( + '@declaration.parameter-count', + fnNode, + String(arity.parameterCount), + ); + } + if (arity.requiredParameterCount !== undefined) { + grouped['@declaration.required-parameter-count'] = syntheticCapture( + '@declaration.required-parameter-count', + fnNode, + String(arity.requiredParameterCount), + ); + } + if (arity.parameterTypes !== undefined) { + grouped['@declaration.parameter-types'] = syntheticCapture( + '@declaration.parameter-types', + fnNode, + JSON.stringify(arity.parameterTypes), + ); + } + + // Detect static storage class (file-local linkage) + if (hasStaticStorageClass(fnNode)) { + const nameText = grouped['@declaration.name']?.text; + if (nameText !== undefined) { + markStaticName(filePath, nameText); + } + } + } + } + + // Enrich call references with arity + const callAnchor = grouped['@reference.call.free'] ?? grouped['@reference.call.member']; + if (callAnchor !== undefined && grouped['@reference.arity'] === undefined) { + const callNode = findNodeAtRange(tree.rootNode, callAnchor.range, 'call_expression'); + if (callNode !== null) { + grouped['@reference.arity'] = syntheticCapture( + '@reference.arity', + callNode, + String(computeCCallArity(callNode)), + ); + } + } + + out.push(grouped); + } + + return out; +} + +/** + * Check if a C function_definition or declaration has `static` storage class. + * Walks direct children for a `storage_class_specifier` node with text `static`. + */ +function hasStaticStorageClass(node: SyntaxNode): boolean { + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null && child.type === 'storage_class_specifier' && child.text === 'static') { + return true; + } + } + return false; +} diff --git a/gitnexus/src/core/ingestion/languages/c/header-scan.ts b/gitnexus/src/core/ingestion/languages/c/header-scan.ts new file mode 100644 index 000000000..034e27f4d --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/header-scan.ts @@ -0,0 +1,58 @@ +import { readdirSync, type Dirent } from 'fs'; +import { join, relative } from 'path'; + +/** C header extensions to scan for in the workspace. */ +const HEADER_EXTENSIONS = new Set(['.h']); + +/** + * Walk `repoPath` recursively and return relative paths of all `.h` files. + * Used by `loadResolutionConfig` so the C resolver can resolve `#include` + * targets that live in `.h` files (classified as C++ by language detection + * but importable from `.c` files). + */ +export function scanHeaderFiles(repoPath: string): ReadonlySet { + const headers = new Set(); + walk(repoPath, repoPath, headers); + return headers; +} + +function walk(dir: string, root: string, out: Set): void { + let entries: Dirent[]; + try { + entries = readdirSync(dir, { withFileTypes: true, encoding: 'utf8' }); + } catch { + return; // permission denied, etc. + } + for (const entry of entries) { + const name = entry.name; + const full = join(dir, name); + if (entry.isDirectory()) { + // Skip common non-source directories and build output dirs. + // Build dirs (dist, build, out, target, _build, .next, cmake-build-*) + // may contain generated headers that shadow source headers. + if ( + name === 'node_modules' || + name === '.git' || + name === 'vendor' || + name === 'dist' || + name === 'build' || + name === 'out' || + name === 'target' || + name === '_build' || + name === '.next' || + name.startsWith('cmake-build') + ) { + continue; + } + walk(full, root, out); + } else if (entry.isFile()) { + const ext = name.slice(name.lastIndexOf('.')); + if (HEADER_EXTENSIONS.has(ext)) { + // Normalize to forward slashes for cross-platform consistency. + // path.relative() returns backslash-separated paths on Windows, + // but the scope-resolution pipeline uses forward slashes uniformly. + out.add(relative(root, full).replace(/\\/g, '/')); + } + } + } +} diff --git a/gitnexus/src/core/ingestion/languages/c/import-decomposer.ts b/gitnexus/src/core/ingestion/languages/c/import-decomposer.ts new file mode 100644 index 000000000..5cef27430 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/import-decomposer.ts @@ -0,0 +1,55 @@ +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js'; + +/** + * Decompose a `preproc_include` node into a CaptureMatch with structured + * import captures. C #include maps to a wildcard import (all symbols + * from the header are visible). + */ +export function splitCInclude(node: SyntaxNode): CaptureMatch | null { + // node.type === 'preproc_include' + // path field: (string_literal (string_content)) | (system_lib_string) + const pathNode = node.childForFieldName?.('path') ?? null; + if (pathNode === null) { + // Fallback: scan children + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child === null) continue; + if (child.type === 'string_literal' || child.type === 'system_lib_string') { + return buildIncludeCapture(node, child); + } + } + return null; + } + return buildIncludeCapture(node, pathNode); +} + +function buildIncludeCapture(node: SyntaxNode, pathNode: SyntaxNode): CaptureMatch { + let raw: string; + if (pathNode.type === 'string_literal') { + // string_literal has children: `"`, string_content, `"` + // Use namedChildren to find the string_content node + const content = pathNode.namedChildren.find((c) => c.type === 'string_content'); + raw = content?.text ?? pathNode.text.replace(/^"|"$/g, ''); + } else { + // system_lib_string: → strip angle brackets + raw = pathNode.text; + if (raw.startsWith('<') && raw.endsWith('>')) { + raw = raw.slice(1, -1); + } + } + + const isSystem = pathNode.type === 'system_lib_string'; + + const result: Record = { + '@import.statement': nodeToCapture('@import.statement', node), + '@import.kind': syntheticCapture('@import.kind', node, 'wildcard'), + '@import.source': syntheticCapture('@import.source', node, raw), + }; + + if (isSystem) { + result['@import.system'] = syntheticCapture('@import.system', node, 'true'); + } + + return result; +} diff --git a/gitnexus/src/core/ingestion/languages/c/import-target.ts b/gitnexus/src/core/ingestion/languages/c/import-target.ts new file mode 100644 index 000000000..0cb9c2fb4 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/import-target.ts @@ -0,0 +1,64 @@ +import { dirname, join } from 'path'; + +/** + * Resolve a C #include path to a file in the workspace. + * + * Strategy: + * 1. Check for a same-directory sibling relative to the including file + * (matches C compiler `#include "…"` relative-lookup semantics). + * 2. Check for an exact match (path as-is in the workspace). + * 3. Fall back to suffix matching against all workspace file paths. + * Tie-breaking: prefer the match with the fewest path components + * (closest to root). On equal depth, break ties lexicographically + * by normalized path to ensure deterministic resolution regardless + * of filesystem iteration order. + */ +export function resolveCImportTarget( + targetRaw: string, + fromFile: string, + allFilePaths: ReadonlySet, +): string | null { + if (!targetRaw) return null; + + const normalizedTarget = targetRaw.replace(/\\/g, '/'); + + // Same-directory sibling first: mirrors the C compiler's #include "…" + // relative-lookup semantics where the directory of the including + // file is searched before the include-path list. + if (fromFile) { + const siblingRaw = join(dirname(fromFile), targetRaw); + const sibling = siblingRaw.replace(/\\/g, '/'); + if (allFilePaths.has(sibling)) return sibling; + // When targetRaw contains backslashes, the normalized form may + // resolve to a different sibling path — try it as well. + if (targetRaw !== normalizedTarget) { + const siblingAlt = join(dirname(fromFile), normalizedTarget); + const siblingAltNorm = siblingAlt.replace(/\\/g, '/'); + if (allFilePaths.has(siblingAltNorm)) return siblingAltNorm; + } + } + + // Exact match (path as-is in the workspace) + if (allFilePaths.has(normalizedTarget)) return normalizedTarget; + + // Suffix match: find files ending with /targetRaw or equal to targetRaw + const suffix = '/' + normalizedTarget; + let bestMatch: string | null = null; + let bestDepth = Infinity; + let bestNormalized = ''; + + for (const filePath of allFilePaths) { + const normalized = filePath.replace(/\\/g, '/'); + if (normalized === normalizedTarget || normalized.endsWith(suffix)) { + // Prefer shortest path (closest match) + const depth = normalized.split('/').length; + if (depth < bestDepth || (depth === bestDepth && normalized < bestNormalized)) { + bestDepth = depth; + bestMatch = filePath; + bestNormalized = normalized; + } + } + } + + return bestMatch; +} diff --git a/gitnexus/src/core/ingestion/languages/c/index.ts b/gitnexus/src/core/ingestion/languages/c/index.ts new file mode 100644 index 000000000..c6900ecba --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/index.ts @@ -0,0 +1,16 @@ +/** + * C scope-resolution hooks (RFC #909 Ring 3). + */ +export { emitCScopeCaptures } from './captures.js'; +export { interpretCImport, interpretCTypeBinding, normalizeCTypeName } from './interpret.js'; +export { splitCInclude } from './import-decomposer.js'; +export { cArityCompatibility } from './arity.js'; +export { cMergeBindings } from './merge-bindings.js'; +export { cBindingScopeFor, cImportOwningScope, cReceiverBinding } from './simple-hooks.js'; +export { resolveCImportTarget } from './import-target.js'; +export { + markStaticName, + isStaticName, + clearStaticNames, + expandCWildcardNames, +} from './static-linkage.js'; diff --git a/gitnexus/src/core/ingestion/languages/c/interpret.ts b/gitnexus/src/core/ingestion/languages/c/interpret.ts new file mode 100644 index 000000000..e5a15f2fe --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/interpret.ts @@ -0,0 +1,51 @@ +import type { CaptureMatch, ParsedImport, ParsedTypeBinding, TypeRef } from 'gitnexus-shared'; + +/** + * Interpret a C #include capture into a ParsedImport. + * C includes are always wildcard imports (all symbols from the header). + */ +export function interpretCImport(captures: CaptureMatch): ParsedImport | null { + const source = captures['@import.source']?.text; + if (source === undefined) return null; + + // System headers (e.g. ) are not resolved to local files + if (captures['@import.system'] !== undefined) return null; + + return { kind: 'wildcard', targetRaw: source }; +} + +/** + * Interpret a C type-binding capture into a ParsedTypeBinding. + */ +export function interpretCTypeBinding(captures: CaptureMatch): ParsedTypeBinding | null { + const name = captures['@type-binding.name']?.text; + const type = captures['@type-binding.type']?.text; + if (name === undefined || type === undefined) return null; + + let source: TypeRef['source'] = 'annotation'; + + if (captures['@type-binding.parameter'] !== undefined) { + source = 'parameter-annotation'; + } else if (captures['@type-binding.assignment'] !== undefined) { + source = 'assignment-inferred'; + } + + return { boundName: name, rawTypeName: normalizeCTypeName(type), source }; +} + +/** + * Normalize a C type name: strip pointer/array syntax, qualifiers. + */ +export function normalizeCTypeName(text: string): string { + let t = text.trim(); + // Strip const, volatile, restrict qualifiers + t = t.replace(/\b(const|volatile|restrict|static|extern|inline)\b/g, '').trim(); + // Strip pointer stars + while (t.endsWith('*')) t = t.slice(0, -1).trim(); + while (t.startsWith('*')) t = t.slice(1).trim(); + // Strip array brackets + t = t.replace(/\[.*?\]/g, '').trim(); + // Strip struct/union/enum prefixes + t = t.replace(/^(struct|union|enum)\s+/, ''); + return t; +} diff --git a/gitnexus/src/core/ingestion/languages/c/merge-bindings.ts b/gitnexus/src/core/ingestion/languages/c/merge-bindings.ts new file mode 100644 index 000000000..b8bd20c6f --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/merge-bindings.ts @@ -0,0 +1,32 @@ +import type { BindingRef } from 'gitnexus-shared'; + +const TIER: Record = { + local: 0, + namespace: 1, + import: 2, + reexport: 3, + wildcard: 4, +}; + +/** + * C merge bindings: simple first-wins by tier (local > import > wildcard). + * C has no namespaces or reexports, but the tiers are defined for + * compatibility with the shared infrastructure. + */ +export function cMergeBindings( + existing: readonly BindingRef[], + incoming: readonly BindingRef[], + _scopeId: string, +): BindingRef[] { + const seen = new Set(); + return [...existing, ...incoming] + .sort( + (a, b) => + (TIER[a.origin] ?? 99) - (TIER[b.origin] ?? 99) || a.def.nodeId.localeCompare(b.def.nodeId), + ) + .filter((binding) => { + if (seen.has(binding.def.nodeId)) return false; + seen.add(binding.def.nodeId); + return true; + }); +} diff --git a/gitnexus/src/core/ingestion/languages/c/query.ts b/gitnexus/src/core/ingestion/languages/c/query.ts new file mode 100644 index 000000000..da49a1a6a --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/query.ts @@ -0,0 +1,165 @@ +import Parser from 'tree-sitter'; +import C from 'tree-sitter-c'; + +const C_SCOPE_QUERY = ` +;; Scopes +(translation_unit) @scope.module +(struct_specifier) @scope.class +(union_specifier) @scope.class +(function_definition) @scope.function +(compound_statement) @scope.block +(if_statement) @scope.block +(for_statement) @scope.block +(while_statement) @scope.block +(do_statement) @scope.block +(switch_statement) @scope.block +(case_statement) @scope.block + +;; Declarations — struct (named) +(struct_specifier + name: (type_identifier) @declaration.name + body: (field_declaration_list)) @declaration.struct + +;; Declarations — struct (typedef struct { ... } Name) +(type_definition + type: (struct_specifier + body: (field_declaration_list)) + declarator: (type_identifier) @declaration.name) @declaration.struct + +;; Declarations — union (named) +(union_specifier + name: (type_identifier) @declaration.name + body: (field_declaration_list)) @declaration.union + +;; Declarations — union (typedef union { ... } Name) +(type_definition + type: (union_specifier + body: (field_declaration_list)) + declarator: (type_identifier) @declaration.name) @declaration.union + +;; Declarations — enum +(enum_specifier + name: (type_identifier) @declaration.name) @declaration.enum + +;; Declarations — function definition +(function_definition + declarator: (function_declarator + declarator: (identifier) @declaration.name)) @declaration.function + +;; Declarations — function definition with pointer return +(function_definition + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (identifier) @declaration.name))) @declaration.function + +;; Declarations — function declaration (prototype) +;; Note: Both prototypes and definitions are captured as @declaration.function. +;; This may produce duplicate Function nodes in the knowledge graph when a +;; function is declared in a header and defined in a .c file. CALLS edges +;; resolve correctly through scope-based wildcard import chains; the +;; duplication is a graph-quality concern only (no false edges). +(declaration + declarator: (function_declarator + declarator: (identifier) @declaration.name)) @declaration.function + +;; Declarations — function declaration with pointer return (prototype) +(declaration + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (identifier) @declaration.name))) @declaration.function + +;; Declarations — typedef +(type_definition + declarator: (type_identifier) @declaration.name) @declaration.typedef + +;; Declarations — typedef for function pointers: typedef void (*callback)(int, int) +(type_definition + declarator: (function_declarator + declarator: (parenthesized_declarator + (pointer_declarator + declarator: (type_identifier) @declaration.name)))) @declaration.typedef + +;; Declarations — struct fields +(field_declaration + declarator: (field_identifier) @declaration.name) @declaration.field + +;; Declarations — struct fields (pointer) +(field_declaration + declarator: (pointer_declarator + declarator: (field_identifier) @declaration.name)) @declaration.field + +;; Declarations — variables (with initializer) +(declaration + declarator: (init_declarator + declarator: (identifier) @declaration.name)) @declaration.variable + +;; Declarations — macro definitions +(preproc_def + name: (identifier) @declaration.name) @declaration.macro + +(preproc_function_def + name: (identifier) @declaration.name) @declaration.macro + +;; Declarations — enum constants +(enumerator + name: (identifier) @declaration.name) @declaration.const + +;; Imports +(preproc_include) @import.statement + +;; Type bindings — parameter annotations +(parameter_declaration + type: (_) @type-binding.type + declarator: (identifier) @type-binding.name) @type-binding.parameter + +;; Type bindings — variable with type (init_declarator) +(declaration + type: (_) @type-binding.type + declarator: (init_declarator + declarator: (identifier) @type-binding.name)) @type-binding.assignment + +;; References — free calls +;; Note: This also captures calls through function pointer variables (e.g. fp(x)) +;; since tree-sitter-c produces structurally identical AST nodes for both direct +;; function calls and function-pointer-variable calls. A type-based guard to +;; distinguish variable-calls from function-calls is not implemented — this is a +;; known architectural trade-off shared with the Go resolver. The uniqueness +;; constraint in pickUniqueGlobalCallable limits false edge exposure. +(call_expression + function: (identifier) @reference.name) @reference.call.free + +;; References — member calls via pointer (ptr->func()) +(call_expression + function: (field_expression + argument: (_) @reference.receiver + field: (field_identifier) @reference.name)) @reference.call.member + +;; References — field reads +(field_expression + argument: (_) @reference.receiver + field: (field_identifier) @reference.name) @reference.read + +;; References — field writes (assignment) +(assignment_expression + left: (field_expression + argument: (_) @reference.receiver + field: (field_identifier) @reference.name)) @reference.write +`; + +let _parser: Parser | null = null; +let _query: Parser.Query | null = null; + +export function getCParser(): Parser { + if (_parser === null) { + _parser = new Parser(); + _parser.setLanguage(C as Parameters[0]); + } + return _parser; +} + +export function getCScopeQuery(): Parser.Query { + if (_query === null) { + _query = new Parser.Query(C as Parameters[0], C_SCOPE_QUERY); + } + return _query; +} diff --git a/gitnexus/src/core/ingestion/languages/c/scope-resolver.ts b/gitnexus/src/core/ingestion/languages/c/scope-resolver.ts new file mode 100644 index 000000000..90d54e072 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/scope-resolver.ts @@ -0,0 +1,73 @@ +import type { ParsedFile, SymbolDefinition } from 'gitnexus-shared'; +import { SupportedLanguages } from 'gitnexus-shared'; +import { buildMro, defaultLinearize } from '../../scope-resolution/passes/mro.js'; +import { populateClassOwnedMembers } from '../../scope-resolution/scope/walkers.js'; +import type { ScopeResolver } from '../../scope-resolution/contract/scope-resolver.js'; +import { cProvider } from '../c-cpp.js'; +import { cArityCompatibility, cMergeBindings, resolveCImportTarget } from './index.js'; +import { scanHeaderFiles } from './header-scan.js'; +import { expandCWildcardNames, isStaticName, clearStaticNames } from './static-linkage.js'; + +/** + * C `ScopeResolver` registered in `SCOPE_RESOLVERS` and consumed by + * the generic `runScopeResolution` orchestrator (RFC #909 Ring 3). + * + * C is a structurally simple language for scope resolution: + * - No classes (structs are value types, no method dispatch) + * - No inheritance (no MRO needed beyond the shared first-wins default) + * - No overloading (arity check is simple: variadic detection only) + * - `#include` is wildcard import (all symbols from header are visible) + * - `static` functions are file-local (not exported) + */ +export const cScopeResolver: ScopeResolver = { + language: SupportedLanguages.C, + languageProvider: cProvider, + importEdgeReason: 'c-scope: include', + + loadResolutionConfig: (repoPath: string) => { + // Clear stale static-linkage data from any previous invocation to + // prevent cross-repo contamination in server-mode scenarios. + clearStaticNames(); + return scanHeaderFiles(repoPath); + }, + + resolveImportTarget: (targetRaw, fromFile, allFilePaths, resolutionConfig) => { + // Augment allFilePaths with .h files discovered via loadResolutionConfig + // since the phase only passes .c files to the C resolver but #include + // targets .h files classified as C++ in language detection. + const headerPaths = resolutionConfig as ReadonlySet | undefined; + if (headerPaths !== undefined && headerPaths.size > 0) { + const augmented = new Set(allFilePaths); + for (const h of headerPaths) augmented.add(h); + return resolveCImportTarget(targetRaw, fromFile, augmented); + } + return resolveCImportTarget(targetRaw, fromFile, allFilePaths); + }, + + expandsWildcardTo: (targetModuleScope, parsedFiles) => + expandCWildcardNames(targetModuleScope, parsedFiles), + + mergeBindings: (existing, incoming, scopeId) => cMergeBindings(existing, incoming, scopeId), + + arityCompatibility: (callsite, def) => cArityCompatibility(def, callsite), + + buildMro: (graph, parsedFiles, nodeLookup) => + buildMro(graph, parsedFiles, nodeLookup, defaultLinearize), + + populateOwners: (parsed: ParsedFile) => populateClassOwnedMembers(parsed), + + isSuperReceiver: () => false, + + // C is statically typed — disable field fallback heuristic + fieldFallbackOnMethodLookup: false, + // C has no method return types to propagate + propagatesReturnTypesAcrossImports: false, + // C #include brings in all symbols — enable global free call fallback + allowGlobalFreeCallFallback: true, + // C `static` functions have file-local (translation-unit) linkage — + // exclude them from global free-call fallback cross-file resolution. + isFileLocalDef: (def: SymbolDefinition) => { + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + return isStaticName(def.filePath, simple); + }, +}; diff --git a/gitnexus/src/core/ingestion/languages/c/simple-hooks.ts b/gitnexus/src/core/ingestion/languages/c/simple-hooks.ts new file mode 100644 index 000000000..537ea07c5 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/simple-hooks.ts @@ -0,0 +1,38 @@ +import type { + CaptureMatch, + ParsedImport, + Scope, + ScopeId, + ScopeTree, + TypeRef, +} from 'gitnexus-shared'; + +/** + * C binding scope: always use default auto-hoist (null). + * C has no self/receiver bindings that need special scoping. + */ +export function cBindingScopeFor( + _decl: CaptureMatch, + _innermost: Scope, + _tree: ScopeTree, +): ScopeId | null { + return null; +} + +/** + * C import owning scope: always use default (null). + */ +export function cImportOwningScope( + _imp: ParsedImport, + _innermost: Scope, + _tree: ScopeTree, +): ScopeId | null { + return null; +} + +/** + * C receiver binding: always null. C has no methods or receivers. + */ +export function cReceiverBinding(_functionScope: Scope): TypeRef | null { + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/c/static-linkage.ts b/gitnexus/src/core/ingestion/languages/c/static-linkage.ts new file mode 100644 index 000000000..5cfd166b1 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/c/static-linkage.ts @@ -0,0 +1,64 @@ +import type { ParsedFile, ScopeId, SymbolDefinition } from 'gitnexus-shared'; + +/** + * Per-file set of function names declared with `static` storage class. + * Populated during `emitCScopeCaptures` and consumed by `expandCWildcardNames` + * to exclude file-local symbols from cross-file wildcard import visibility. + * + * NOTE: module-level state, single-process-single-repo use only. + * For server-mode or multi-repo-in-one-process use cases, call + * `clearStaticNames()` at the start of each resolution pass to avoid + * stale static-linkage data from a previous invocation. + * + * Key: filePath, Value: Set of static function names. + */ +const staticNames = new Map>(); + +/** Record a symbol name as `static` (file-local linkage) for the given file. */ +export function markStaticName(filePath: string, name: string): void { + let names = staticNames.get(filePath); + if (names === undefined) { + names = new Set(); + staticNames.set(filePath, names); + } + names.add(name); +} + +/** Check whether a symbol name has `static` linkage in the given file. */ +export function isStaticName(filePath: string, name: string): boolean { + return staticNames.get(filePath)?.has(name) ?? false; +} + +/** Clear tracked static names (for testing). */ +export function clearStaticNames(): void { + staticNames.clear(); +} + +/** + * Return the names visible through a C wildcard import (`#include`). + * All module-scope defs from the target file are visible EXCEPT those + * declared with `static` storage class (file-local linkage in C). + */ +export function expandCWildcardNames( + targetModuleScope: ScopeId, + parsedFiles: readonly ParsedFile[], +): readonly string[] { + const target = parsedFiles.find((p) => p.moduleScope === targetModuleScope); + if (target === undefined) return []; + + const seen = new Set(); + const names: string[] = []; + for (const def of target.localDefs) { + const name = simpleName(def); + if (name === '') continue; + if (isStaticName(target.filePath, name)) continue; + if (seen.has(name)) continue; + seen.add(name); + names.push(name); + } + return names; +} + +function simpleName(def: SymbolDefinition): string { + return def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/adl.ts b/gitnexus/src/core/ingestion/languages/cpp/adl.ts new file mode 100644 index 000000000..0bcda9322 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/adl.ts @@ -0,0 +1,540 @@ +/** + * C++ argument-dependent lookup (ADL / Koenig lookup). + * + * When ordinary unqualified lookup fails for a free-call site, ADL also + * considers candidates declared in the **associated namespaces** of the + * call's argument types (ISO C++ `[basic.lookup.argdep]`). The canonical + * pattern V1 unlocks: + * + * namespace audit { struct Event; void record(Event); } + * namespace app { void run() { audit::Event e; record(e); } } + * + * Without ADL: `record(e)` is unresolved because `app::run` doesn't + * `using` anything. With V1 ADL: `audit::record` is discovered via + * `audit::Event`'s associated namespace. + * + * ## Current boundary + * + * The current implementation covers class-typed arguments (value, pointer, + * and reference) and template specializations with explicit type arguments: + * - `audit::Event e`, `audit::Event* p`, `audit::Event** pp` + * - `audit::Event& r`, `audit::Event&& rr` + * - `std::vector` (template namespace + template-arg namespaces) + * + * V2 additionally walks class ancestors (via MRO), so base-class enclosing + * namespaces also contribute associated namespaces. + * + * **GitNexus approximation (not strict ISO C++ ADL):** passing a qualified + * function reference like `utils::worker` contributes `utils` to the associated + * set, enabling resolution of unqualified calls like `with_callback(utils::worker)` + * to `utils::with_callback`. Under ISO C++ `[basic.lookup.argdep]`, associated + * entities for function-type arguments come from the **parameter types and return + * type** of each function in the overload set — NOT the function's enclosing + * namespace. For `void worker()`, the standard-compliant associated set is empty. + * GitNexus instead contributes the enclosing namespace of any Function/Method + * def whose simple name matches, because it enables the dominant real-world ADL + * pattern at reasonable precision cost. + * + * For qualified refs (e.g. `utils::worker`) the namespace is confirmed via a + * workspace lookup (only contributed when a Function/Method named `worker` exists + * in `utils`). For unqualified refs the workspace is searched for any Function + * def with that simple name. Locally-declared function-pointer variables + * (e.g. `void (*g)()`) and function parameters are excluded from this path. + * + * ADL candidates are merged with ordinary unqualified-lookup candidates + * in the free-call fallback before overload narrowing. + * + * ## Parenthesized-name suppression + * + * `(f)(s)` MUST NOT trigger ADL — the parenthesized name forces ordinary + * lookup only. `captures.ts` records sites whose `function` child is a + * `parenthesized_expression` into `noAdlSites`; `pickCppAdlCandidates` + * short-circuits when the site key is present. + * + * ## State lifecycle + * + * Three module-level maps populated per pipeline invocation, cleared via + * `clearCppAdlState()` (called from `clearFileLocalNames`): + * + * - `argInfoBySite` — per-call-site argument shape (capture-time) + * - `noAdlSites` — call sites with parenthesized function (capture-time) + * - `classToNamespaceQualifiedName` — class def → its enclosing namespace + * qualified name (`populateCppAssociatedNamespaces` time) + * + * The class→namespace map uses qualified names (not scope IDs) because + * C++ namespaces are open: `namespace N { ... }` in file A and + * `namespace N { ... }` in file B produce two distinct Namespace scopes + * but logically share the same namespace. ADL must consider candidates + * declared in either file. + */ + +import type { ParsedFile, ScopeId, SymbolDefinition } from 'gitnexus-shared'; +import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; +import { isCppInlineNamespaceScope } from './inline-namespaces.js'; + +/** + * Per-argument shape information collected at capture time. ADL fires for + * arguments where `simpleClassName !== ''`, including class pointers and + * references whose declarator chain resolves to a named class type. + * Free-function reference arguments use `functionRefText`. + */ +export interface CppAdlArgInfo { + /** Simple class-like type name (last segment of qualified name); empty + * for primitives, literals, function pointers, etc. */ + readonly simpleClassName: string; + /** Template's own simple class-like name (e.g. `vector` for + * `std::vector`), empty when arg type is not a template spec. */ + readonly templateSimpleClassName: string; + /** Template's own enclosing namespace (dot-qualified, e.g. `std`), empty + * when unavailable / unqualified. */ + readonly templateNamespace: string; + /** Class-like names extracted from explicit type template arguments, + * recursively bounded. */ + readonly templateArgClassNames: readonly string[]; + /** Enclosing namespaces extracted from explicit type template arguments, + * recursively bounded. */ + readonly templateArgNamespaces: readonly string[]; + /** When set, the arg is a potential free-function reference (not a locally- + * declared function-pointer variable or function parameter). Contains the + * identifier text as written in source (e.g. `"utils::worker"` or + * `"worker"`). GitNexus approximation: the function's enclosing namespace + * is contributed to the ADL associated set. For qualified refs a workspace + * lookup confirms a Function/Method with that simple name exists in the + * namespace before contributing; for unqualified refs every namespace + * containing a matching Function/Method def is contributed. */ + readonly functionRefText?: string; +} + +const argInfoBySite = new Map(); +const noAdlSites = new Set(); +const classToNamespaceQualifiedName = new Map(); + +function siteKey(filePath: string, line: number, col: number): string { + return `${filePath}:${line}:${col}`; +} + +/** Record per-call-site argument info. Called once per call site from + * `emitCppScopeCaptures`. */ +export function markCppAdlSiteArgs( + filePath: string, + line: number, + col: number, + args: readonly CppAdlArgInfo[], +): void { + argInfoBySite.set(siteKey(filePath, line, col), args); +} + +/** Mark a call site as ADL-suppressed (function child wrapped in + * `parenthesized_expression`, e.g. `(f)(s)`). */ +export function markCppAdlSiteNoAdl(filePath: string, line: number, col: number): void { + noAdlSites.add(siteKey(filePath, line, col)); +} + +/** Clear ADL state. Called from `clearFileLocalNames` so all C++ resolver + * per-pipeline state is reset together. */ +export function clearCppAdlState(): void { + argInfoBySite.clear(); + noAdlSites.clear(); + classToNamespaceQualifiedName.clear(); +} + +/** + * Walk `parsed.scopes` to record each Class def's enclosing namespace + * qualified name. Run from the cpp resolver's `populateOwners` hook so + * the index is available before any resolution pass consults it. + * + * Computes the namespace's qualified name by walking parent scope chain + * and looking up Namespace defs in each parent's `ownedDefs`. The + * resulting name is dot-joined (matching `populateClassOwnedMembers`'s + * dotted convention; conversion to `::` is consumer-internal). + */ +export function populateCppAssociatedNamespaces(parsed: ParsedFile): void { + const scopesById = new Map(); + for (const scope of parsed.scopes) scopesById.set(scope.id, scope); + + for (const scope of parsed.scopes) { + if (scope.kind !== 'Class') continue; + const nsQName = computeEnclosingNamespaceQName(scope, scopesById); + if (nsQName === '') continue; + for (const def of scope.ownedDefs) { + if (def.type !== 'Class' && def.type !== 'Struct' && def.type !== 'Interface') continue; + classToNamespaceQualifiedName.set(def.nodeId, nsQName); + } + } + + // Enum defs live in Namespace scopes directly (not inside Class scopes). + // Map each Enum def to its enclosing namespace so ADL on enum-typed + // arguments contributes the correct associated namespace. + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + const nsQName = computeNamespaceQName(scope, scopesById); + if (nsQName === '') continue; + for (const def of scope.ownedDefs) { + if (def.type !== 'Enum') continue; + classToNamespaceQualifiedName.set(def.nodeId, nsQName); + } + } +} + +/** + * ADL candidate collector. Returns: + * - `readonly SymbolDefinition[]` — ADL candidates to merge with + * ordinary unqualified lookup candidates. + * - `undefined` — no ADL candidates. + * + * Fires only when: + * - the call site is not in `noAdlSites` (parenthesized form), AND + * - at least one argument resolves to a named class type (value, + * pointer, or reference; but not function pointer, literal, or primitive). + */ +export function pickCppAdlCandidates( + site: { + readonly name: string; + readonly atRange: { startLine: number; startCol: number }; + }, + callerParsed: ParsedFile, + scopes: ScopeResolutionIndexes, + parsedFiles: readonly ParsedFile[], +): readonly SymbolDefinition[] | undefined { + const key = siteKey(callerParsed.filePath, site.atRange.startLine, site.atRange.startCol); + if (noAdlSites.has(key)) return undefined; + const args = argInfoBySite.get(key); + if (args === undefined || args.length === 0) return undefined; + + // Collect associated namespace QNames from every participating class-typed arg + // and from function-reference args. + const associatedNamespaces = new Set(); + for (const arg of args) { + collectAssociatedNamespacesForAdlArg(arg, scopes, associatedNamespaces); + if (arg.functionRefText !== undefined) { + collectFunctionRefNamespaces(arg.functionRefText, parsedFiles, associatedNamespaces); + } + } + if (associatedNamespaces.size === 0) return undefined; + + // Walk every namespace scope in every parsed file; collect callable + // ownedDefs whose enclosing namespace matches one of the associated + // QNames AND whose simple name matches the call's name. + // ISO C++: inline namespaces are transparent — candidates in inline + // children of an associated namespace are also ADL-reachable. + const candidates: SymbolDefinition[] = []; + const seenKey = new Set(); + for (const parsed of parsedFiles) { + const scopesById = new Map(); + for (const sc of parsed.scopes) scopesById.set(sc.id, sc); + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + const qName = computeNamespaceQName(scope, scopesById); + if (!associatedNamespaces.has(qName)) { + // Check if this is an inline-namespace child of an associated NS. + // ISO C++ inline namespaces are transparent for ADL: if the outer + // namespace is in the associated set, candidates in the inline child + // are also reachable. + if (!isCppInlineNamespaceScope(scope.id)) continue; + const parentScope = scope.parent !== null ? scopesById.get(scope.parent) : undefined; + if (parentScope === undefined || parentScope.kind !== 'Namespace') continue; + const parentQName = computeNamespaceQName(parentScope, scopesById); + if (!associatedNamespaces.has(parentQName)) continue; + } + for (const def of scope.ownedDefs) { + if (def.type !== 'Function' && def.type !== 'Method' && def.type !== 'Constructor') { + continue; + } + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple !== site.name) continue; + // Dedup by nodeId — using normalized parameter-types as the key + // would collapse `process(int)`/`process(long)`-style overloads + // (both normalize to `['int']`) before + // `isOverloadAmbiguousAfterNormalization` can detect them. + if (seenKey.has(def.nodeId)) continue; + seenKey.add(def.nodeId); + candidates.push(def); + } + } + // ISO C++ `[basic.lookup.argdep]` §2: hidden friend functions declared + // inside a class body are visible via ADL when the class is an associated + // class. Scan Class scopes whose enclosing namespace is in the associated + // set for callable ownedDefs matching the call name. This enables the + // canonical "hidden friend" idiom: + // struct Foo { friend void swap(Foo&, Foo&) {} }; + for (const scope of parsed.scopes) { + if (scope.kind !== 'Class') continue; + // Check if ANY class def in this scope has an associated namespace. + let isAssociatedClass = false; + for (const def of scope.ownedDefs) { + if (def.type !== 'Class' && def.type !== 'Struct' && def.type !== 'Interface') continue; + const nsQName = classToNamespaceQualifiedName.get(def.nodeId); + if (nsQName !== undefined && associatedNamespaces.has(nsQName)) { + isAssociatedClass = true; + break; + } + } + if (!isAssociatedClass) continue; + // Also scan Function scopes that are direct children of this class + // scope — friend function definitions create their own Function scope + // underneath the Class scope. + for (const childScope of parsed.scopes) { + if (childScope.parent !== scope.id) continue; + if (childScope.kind !== 'Function') continue; + for (const def of childScope.ownedDefs) { + if (def.type !== 'Function' && def.type !== 'Method' && def.type !== 'Constructor') { + continue; + } + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple !== site.name) continue; + if (seenKey.has(def.nodeId)) continue; + seenKey.add(def.nodeId); + candidates.push(def); + } + } + for (const def of scope.ownedDefs) { + if (def.type !== 'Function' && def.type !== 'Method' && def.type !== 'Constructor') { + continue; + } + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple !== site.name) continue; + if (seenKey.has(def.nodeId)) continue; + seenKey.add(def.nodeId); + candidates.push(def); + } + } + } + if (candidates.length === 0) return undefined; + return candidates; +} + +function collectAssociatedNamespacesForAdlArg( + arg: CppAdlArgInfo, + scopes: ScopeResolutionIndexes, + associatedNamespaces: Set, +): void { + // For template args this may be the template name itself (e.g. `vector`); + // simple-name lookup can match project classes with the same name (known + // V1/V2 simplification). + addAssociatedNamespaceForClassName(arg.simpleClassName, scopes, associatedNamespaces); + + // Includes template-owner namespaces (e.g. `std` in std::vector). If + // that surfaces extra candidates, merged-candidate overload narrowing in + // free-call-fallback suppresses arbitrary edge emission. + if (arg.templateNamespace.length > 0) associatedNamespaces.add(arg.templateNamespace); + + for (const ns of arg.templateArgNamespaces) { + if (ns.length > 0) associatedNamespaces.add(ns); + } + for (const className of arg.templateArgClassNames) { + addAssociatedNamespaceForClassName(className, scopes, associatedNamespaces); + } +} + +function addAssociatedNamespaceForClassName( + simpleClassName: string, + scopes: ScopeResolutionIndexes, + associatedNamespaces: Set, +): void { + if (simpleClassName.length === 0) return; + const classLookup = findCppClassDefBySimpleName(simpleClassName, scopes); + if (classLookup === undefined) return; + const { classDef, ambiguous } = classLookup; + const nsQName = classToNamespaceQualifiedName.get(classDef.nodeId); + if (nsQName !== undefined) associatedNamespaces.add(nsQName); + // Preserve V1 collision behavior for the direct class namespace, but avoid + // amplifying a same-simple-name collision by walking an arbitrary class's + // full MRO chain. + if (ambiguous) return; + for (const ancestorDefId of scopes.methodDispatch.mroFor(classDef.nodeId)) { + const ancestorNsQName = classToNamespaceQualifiedName.get(ancestorDefId); + if (ancestorNsQName !== undefined) associatedNamespaces.add(ancestorNsQName); + } +} + +/** Walk upward from a Class scope, finding the innermost enclosing + * Namespace scope, and return that namespace's qualified name (dot- + * joined, outermost-first). Returns '' when the class has no enclosing + * namespace (e.g., declared at translation-unit scope). */ +function computeEnclosingNamespaceQName( + classScope: { readonly parent: ScopeId | null }, + scopesById: ReadonlyMap< + ScopeId, + { + readonly parent: ScopeId | null; + readonly kind: string; + readonly ownedDefs: readonly SymbolDefinition[]; + } + >, +): string { + let parentId: ScopeId | null = classScope.parent; + while (parentId !== null) { + const parent = scopesById.get(parentId); + if (parent === undefined) return ''; + if (parent.kind === 'Namespace') { + return computeNamespaceQName(parent, scopesById); + } + parentId = parent.parent; + } + return ''; +} + +/** Walk upward from a Namespace scope collecting each enclosing + * Namespace's simple name (innermost last). Returns the dot-joined + * qualified name (e.g., `outer.inner`). The namespace's own def lives + * in its OWN scope's `ownedDefs` (the C++ extractor stamps the + * namespace-decl def into the namespace scope itself, not the parent + * module scope). */ +function computeNamespaceQName( + nsScope: { readonly parent: ScopeId | null; readonly ownedDefs: readonly SymbolDefinition[] }, + scopesById: ReadonlyMap< + ScopeId, + { + readonly parent: ScopeId | null; + readonly kind: string; + readonly ownedDefs: readonly SymbolDefinition[]; + } + >, +): string { + const segments: string[] = []; + let currentId: ScopeId | null = nsScope.parent; + let current: + | { readonly parent: ScopeId | null; readonly ownedDefs: readonly SymbolDefinition[] } + | undefined = nsScope; + // Outer guard against pathological cycles in malformed scope trees. + let safety = 64; + while (current !== undefined && safety-- > 0) { + const nsDef = findNamespaceDefInScope(current); + if (nsDef === undefined) { + // No name found — bail out. Returning a partial QName would risk + // false ADL associations. + return ''; + } + const simple = nsDef.qualifiedName?.split('.').pop() ?? nsDef.qualifiedName ?? ''; + segments.unshift(simple); + // Walk up to next enclosing namespace (skipping non-namespace parents). + let nextId: ScopeId | null = currentId; + let nextNs: typeof current | undefined; + while (nextId !== null) { + const nx = scopesById.get(nextId); + if (nx === undefined) break; + if (nx.kind === 'Namespace') { + nextNs = nx; + currentId = nx.parent; + break; + } + nextId = nx.parent; + } + current = nextNs; + } + return segments.join('.'); +} + +/** Find the Namespace def attached to this scope (the namespace's own + * decl, stamped into its own `ownedDefs` by the C++ extractor). Returns + * the first Namespace-type def encountered — for normal C++ the scope + * carries exactly one Namespace-typed self def. */ +function findNamespaceDefInScope(scope: { + readonly ownedDefs: readonly SymbolDefinition[]; +}): SymbolDefinition | undefined { + for (const def of scope.ownedDefs) { + if (def.type === 'Namespace') return def; + } + return undefined; +} + +/** Find a class-like or enum def by simple name across the workspace. + * V1 still arbitrary-picks the first match on collisions (multiple defs + * share the simple name), but reports the collision so callers can avoid + * amplifying that uncertainty (for example by skipping MRO expansion). + * C++ ADL strictness would require full type-driven lookup. + * + * ISO C++ `[basic.lookup.argdep]` §2: enumerations contribute their + * enclosing namespace to the associated set, just like class types. */ +function findCppClassDefBySimpleName( + simpleName: string, + scopes: ScopeResolutionIndexes, +): { classDef: SymbolDefinition; ambiguous: boolean } | undefined { + let firstMatch: SymbolDefinition | undefined; + for (const def of scopes.defs.byId.values()) { + if ( + def.type !== 'Class' && + def.type !== 'Struct' && + def.type !== 'Interface' && + def.type !== 'Enum' + ) + continue; + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple !== simpleName) continue; + if (firstMatch === undefined) { + firstMatch = def; + continue; + } + return { classDef: firstMatch, ambiguous: true }; + } + if (firstMatch === undefined) return undefined; + return { classDef: firstMatch, ambiguous: false }; +} + +/** + * Contribute associated namespaces for a function-reference argument. + * + * - **Qualified refs** (`utils::worker`, `outer::inner::fn`): the namespace + * is extracted from the qualifier text (converting `::` to `.` for dot-joined + * QName matching). A workspace lookup then **verifies** that a Function or + * Method def named `worker` (the simple name after the last `::`) actually + * exists in the extracted namespace. This prevents false positives from + * namespace-qualified variables, enum values, and static data members, which + * also produce `qualified_identifier` AST nodes in tree-sitter-cpp (the + * AST node type alone does not distinguish functions from non-function names). + * - **Unqualified refs** (`worker`): the workspace is searched for any + * Function/Method def whose simple name matches. Every distinct enclosing + * namespace found is added — overloads across the same namespace produce + * a single entry; GitNexus does not select a specific overload at this stage. + */ +function collectFunctionRefNamespaces( + refText: string, + parsedFiles: readonly ParsedFile[], + out: Set, +): void { + const colonIdx = refText.lastIndexOf('::'); + if (colonIdx !== -1) { + // Qualified ref: extract namespace prefix and normalise :: → dot notation. + const nsText = refText.slice(0, colonIdx).replace(/::/g, '.'); + if (nsText === '') return; + const simpleName = refText.slice(colonIdx + 2); + // Verify that a Function/Method named `simpleName` exists in `nsText`. + // Without this guard every `a::b` qualified_identifier arg (variable, + // enum value, static member, type alias) would blindly contribute `a` + // to the associated set and risk a false-positive CALLS edge. + for (const parsed of parsedFiles) { + const scopesById = new Map(); + for (const sc of parsed.scopes) scopesById.set(sc.id, sc); + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + if (computeNamespaceQName(scope, scopesById) !== nsText) continue; + for (const def of scope.ownedDefs) { + if (def.type !== 'Function' && def.type !== 'Method') continue; + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple === simpleName) { + out.add(nsText); + return; // Namespace confirmed; no need to scan further files. + } + } + } + } + return; + } + + // Unqualified: search all namespace scopes for a Function def with this + // simple name and contribute its enclosing namespace. + for (const parsed of parsedFiles) { + const scopesById = new Map(); + for (const sc of parsed.scopes) scopesById.set(sc.id, sc); + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + for (const def of scope.ownedDefs) { + if (def.type !== 'Function' && def.type !== 'Method') continue; + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple !== refText) continue; + const nsQName = computeNamespaceQName(scope, scopesById); + if (nsQName !== '') out.add(nsQName); + } + } + } +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/arity-metadata.ts b/gitnexus/src/core/ingestion/languages/cpp/arity-metadata.ts new file mode 100644 index 000000000..fb47d3122 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/arity-metadata.ts @@ -0,0 +1,185 @@ +import type { SyntaxNode } from '../../utils/ast-helpers.js'; + +export interface CppArityInfo { + parameterCount?: number; + requiredParameterCount?: number; + parameterTypes?: string[]; +} + +/** + * Compute declaration arity from a C++ function definition or declaration node. + * Extends the C arity computation with support for: + * - optional_parameter_declaration (default parameters) + * - variadic_parameter_declaration / parameter packs + * - (void) explicit zero-parameter form + */ +export function computeCppDeclarationArity(node: SyntaxNode): CppArityInfo { + const funcDecl = findFuncDeclarator(node); + if (funcDecl === null) return {}; + + const paramList = funcDecl.childForFieldName('parameters'); + if (paramList === null) return {}; + + const params: SyntaxNode[] = []; + // Track whether a C-style variadic `...` anonymous token appears. + // tree-sitter-cpp emits `...` as an anonymous (non-named) child of + // parameter_list, not as `variadic_parameter`. + let hasEllipsis = false; + for (let i = 0; i < paramList.childCount; i++) { + const child = paramList.child(i); + if (child === null) continue; + if ( + child.type === 'parameter_declaration' || + child.type === 'optional_parameter_declaration' || + child.type === 'variadic_parameter' || + child.type === 'variadic_parameter_declaration' + ) { + params.push(child); + } else if (child.type === '...' || (!child.isNamed && child.text === '...')) { + hasEllipsis = true; + } + } + + // Empty parameter list: C++ `void foo()` means zero params (unlike C) + if (params.length === 0 && !hasEllipsis) { + return { parameterCount: 0, requiredParameterCount: 0, parameterTypes: [] }; + } + + // (void) means zero parameters + if (params.length === 1 && params[0].type === 'parameter_declaration') { + const typeNode = params[0].childForFieldName('type'); + const hasDeclarator = params[0].childForFieldName('declarator') !== null; + if (typeNode !== null && typeNode.text === 'void' && !hasDeclarator) { + return { parameterCount: 0, requiredParameterCount: 0, parameterTypes: [] }; + } + } + + // C-style variadic: `void foo(int x, ...)` — the `...` is an anonymous + // token in tree-sitter-cpp, detected via `hasEllipsis` above. + // C++ parameter packs: `template void foo(Ts... args)` — + // detected as `variadic_parameter_declaration`. + const isVariadic = + hasEllipsis || + params.some( + (p) => p.type === 'variadic_parameter' || p.type === 'variadic_parameter_declaration', + ); + const optionalCount = params.filter((p) => p.type === 'optional_parameter_declaration').length; + const requiredCount = params.filter( + (p) => + p.type === 'parameter_declaration' || + // variadic_parameter_declaration with a name is a parameter pack — counts as one + p.type === 'variadic_parameter_declaration', + ).length; + const totalNonVariadic = requiredCount + optionalCount; + + const types: string[] = []; + for (const p of params) { + if (p.type === 'variadic_parameter') { + types.push('...'); + } else if (p.type === 'variadic_parameter_declaration') { + // Parameter pack: treated as variadic + types.push('...'); + } else { + const typeNode = p.childForFieldName('type'); + types.push(normalizeCppParamType(typeNode?.text ?? 'unknown')); + } + } + // Append '...' for C-style variadic if not already in types + if (hasEllipsis && !types.includes('...')) { + types.push('...'); + } + + return { + parameterCount: isVariadic ? undefined : totalNonVariadic, + requiredParameterCount: requiredCount, + parameterTypes: types, + }; +} + +/** + * Compute call-site arity from a call_expression node. + */ +export function computeCppCallArity(node: SyntaxNode): number { + const argList = node.childForFieldName('arguments'); + if (argList === null) return 0; + + let count = 0; + for (let i = 0; i < argList.childCount; i++) { + const child = argList.child(i); + if (child === null) continue; + if (child.type !== ',' && child.type !== '(' && child.type !== ')') { + count++; + } + } + return count; +} + +/** + * Normalize a C++ parameter type for overload disambiguation. + * Maps common qualified/aliased types to their canonical short forms + * so that `narrowOverloadCandidates` can match against literal-inferred + * argument types (e.g. `inferCppLiteralType` returns `'string'` for + * string literals, not `'std::string'`). + */ +function normalizeCppParamType(raw: string): string { + let t = raw.trim(); + // Strip const, volatile, etc. + t = t.replace(/\b(const|volatile|restrict|mutable|constexpr)\b/g, '').trim(); + // Strip reference/pointer markers + t = t.replace(/[&*]+\s*$/, '').trim(); + // Strip template parameters (loop handles nested: Map> → Map) + while (t.includes('<')) { + const stripped = t.replace(/<[^<>]*>/g, ''); + if (stripped === t) break; // avoid infinite loop on malformed input + t = stripped; + } + t = t.trim(); + // Map std:: types to canonical short forms + const STD_MAP: Record = { + 'std::string': 'string', + 'std::wstring': 'string', + 'std::string_view': 'string', + string: 'string', + char: 'char', + int: 'int', + long: 'int', + short: 'int', + unsigned: 'int', + 'unsigned int': 'int', + 'long long': 'int', + size_t: 'int', + 'std::size_t': 'int', + float: 'double', + double: 'double', + bool: 'bool', + nullptr_t: 'null', + 'std::nullptr_t': 'null', + }; + return STD_MAP[t] ?? t; +} + +function findFuncDeclarator(node: SyntaxNode): SyntaxNode | null { + let decl = node.childForFieldName('declarator'); + if (decl === null) { + for (let i = 0; i < node.childCount; i++) { + const c = node.child(i); + if (c?.type === 'function_declarator') return c; + } + return null; + } + // Unwrap pointer_declarator / reference_declarator + while (decl.type === 'pointer_declarator' || decl.type === 'reference_declarator') { + const next = decl.childForFieldName('declarator'); + if (next === null) { + // reference_declarator may not use field name + for (let i = 0; i < decl.childCount; i++) { + const c = decl.child(i); + if (c?.type === 'function_declarator') return c; + } + break; + } + decl = next; + } + if (decl.type === 'function_declarator') return decl; + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/arity.ts b/gitnexus/src/core/ingestion/languages/cpp/arity.ts new file mode 100644 index 000000000..e13fa6a3a --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/arity.ts @@ -0,0 +1,35 @@ +import type { Callsite, SymbolDefinition } from 'gitnexus-shared'; + +/** + * C++ arity compatibility: supports overloading and default parameters. + * + * Unlike C (no overloading, exact match only), C++ has: + * - Overloaded functions (same name, different signatures) + * - Default parameters (requiredParameterCount < parameterCount) + * - Variadic functions (C-style `...`) + * - Parameter packs (V1: treated as variadic) + * - Templates (V1: generic-ignored, arity check on non-template params) + * + * Verdict: + * - 'compatible': callsite.arity fits within [required, total] range + * - 'incompatible': callsite.arity is outside the valid range + * - 'unknown': insufficient metadata to determine + */ +export function cppArityCompatibility( + def: SymbolDefinition, + callsite: Callsite, +): 'compatible' | 'unknown' | 'incompatible' { + const max = def.parameterCount; + const min = def.requiredParameterCount; + if (max === undefined && min === undefined) return 'unknown'; + if (!Number.isFinite(callsite.arity) || callsite.arity < 0) return 'unknown'; + + const variadic = def.parameterTypes?.some((t) => t === '...') ?? false; + + // Too few arguments: less than the minimum required + if (min !== undefined && callsite.arity < min) return 'incompatible'; + // Too many arguments: more than the maximum and not variadic + if (max !== undefined && callsite.arity > max && !variadic) return 'incompatible'; + + return 'compatible'; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/captures.ts b/gitnexus/src/core/ingestion/languages/cpp/captures.ts new file mode 100644 index 000000000..5c74950bb --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/captures.ts @@ -0,0 +1,1204 @@ +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { + findNodeAtRange, + nodeToCapture, + syntheticCapture, + type SyntaxNode, +} from '../../utils/ast-helpers.js'; +import { getCppParser, getCppScopeQuery } from './query.js'; +import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; +import { splitCppInclude, splitCppUsingDecl } from './import-decomposer.js'; +import { computeCppDeclarationArity, computeCppCallArity } from './arity-metadata.js'; +import { markCppAnonymousNamespaceRange, markFileLocal } from './file-local-linkage.js'; +import { markCppDependentBase } from './two-phase-lookup.js'; +import { markCppAdlSiteArgs, markCppAdlSiteNoAdl, type CppAdlArgInfo } from './adl.js'; +import { markCppInlineNamespaceRange } from './inline-namespaces.js'; + +export function emitCppScopeCaptures( + sourceText: string, + filePath: string, + cachedTree?: unknown, +): readonly CaptureMatch[] { + let tree = cachedTree as ReturnType['parse']> | undefined; + if (tree === undefined) { + tree = parseSourceSafe(getCppParser(), sourceText, undefined, { + bufferSize: getTreeSitterBufferSize(sourceText), + }); + } + + const rawMatches = getCppScopeQuery().matches(tree.rootNode); + const out: CaptureMatch[] = []; + + // Track ranges where typedef-struct was captured as @declaration.struct + // so we can suppress the duplicate @declaration.typedef match. + const structTypedefRanges = new Set(); + + for (const m of rawMatches) { + const grouped: Record = {}; + for (const c of m.captures) { + const tag = '@' + c.name; + if (tag.startsWith('@_')) continue; + grouped[tag] = nodeToCapture(tag, c.node); + } + if (Object.keys(grouped).length === 0) continue; + + // ── Handle #include statements ────────────────────────────────── + if (grouped['@import.statement'] !== undefined) { + const anchor = grouped['@import.statement']!; + const includeNode = findNodeAtRange(tree.rootNode, anchor.range, 'preproc_include'); + if (includeNode !== null) { + const split = splitCppInclude(includeNode); + if (split !== null) { + out.push(split); + continue; + } + } + } + + // ── Handle using declarations (using namespace / using name) ──── + if (grouped['@import.using-decl'] !== undefined) { + const anchor = grouped['@import.using-decl']!; + const usingNode = findNodeAtRange(tree.rootNode, anchor.range, 'using_declaration'); + if (usingNode !== null) { + const split = splitCppUsingDecl(usingNode); + if (split !== null) { + out.push(split); + continue; + } + } + } + + // ── Track typedef-struct ranges ───────────────────────────────── + const structAnchor = grouped['@declaration.struct'] ?? grouped['@declaration.class']; + if (structAnchor !== undefined) { + const r = structAnchor.range; + structTypedefRanges.add(`${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`); + } + + // Suppress @declaration.typedef if the same range was already captured + const typedefAnchor = grouped['@declaration.typedef']; + if (typedefAnchor !== undefined) { + const r = typedefAnchor.range; + const key = `${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`; + if (structTypedefRanges.has(key)) continue; + } + + // ── Enrich function/method declarations with arity metadata ───── + const declAnchor = grouped['@declaration.function'] ?? grouped['@declaration.method']; + if (declAnchor !== undefined) { + const fnNode = + findNodeAtRange(tree.rootNode, declAnchor.range, 'function_definition') ?? + findNodeAtRange(tree.rootNode, declAnchor.range, 'declaration') ?? + findNodeAtRange(tree.rootNode, declAnchor.range, 'field_declaration'); + if (fnNode !== null) { + const arity = computeCppDeclarationArity(fnNode); + if (arity.parameterCount !== undefined) { + grouped['@declaration.parameter-count'] = syntheticCapture( + '@declaration.parameter-count', + fnNode, + String(arity.parameterCount), + ); + } + if (arity.requiredParameterCount !== undefined) { + grouped['@declaration.required-parameter-count'] = syntheticCapture( + '@declaration.required-parameter-count', + fnNode, + String(arity.requiredParameterCount), + ); + } + if (arity.parameterTypes !== undefined) { + grouped['@declaration.parameter-types'] = syntheticCapture( + '@declaration.parameter-types', + fnNode, + JSON.stringify(arity.parameterTypes), + ); + } + + // Detect static storage class (file-local linkage) + if (hasStaticStorageClass(fnNode)) { + const nameText = grouped['@declaration.name']?.text; + if (nameText !== undefined) { + markFileLocal(filePath, nameText); + } + } + + // Detect anonymous namespace (file-local linkage) + if (isInsideAnonymousNamespace(fnNode)) { + const nameText = grouped['@declaration.name']?.text; + if (nameText !== undefined) { + markFileLocal(filePath, nameText); + } + } + } + } + + // ── Detect static variables (file-local linkage) ──────────────── + const varDeclAnchor = grouped['@declaration.variable']; + if (varDeclAnchor !== undefined) { + const varNode = findNodeAtRange(tree.rootNode, varDeclAnchor.range, 'declaration'); + if (varNode !== null) { + if (hasStaticStorageClass(varNode) || isInsideAnonymousNamespace(varNode)) { + const nameText = grouped['@declaration.name']?.text; + if (nameText !== undefined) { + markFileLocal(filePath, nameText); + } + } + } + } + + // ── Enrich call references with arity ─────────────────────────── + const callAnchor = + grouped['@reference.call.free'] ?? + grouped['@reference.call.member'] ?? + grouped['@reference.call.qualified']; + if (callAnchor !== undefined && grouped['@reference.arity'] === undefined) { + const callNode = findNodeAtRange(tree.rootNode, callAnchor.range, 'call_expression'); + if (callNode !== null) { + grouped['@reference.arity'] = syntheticCapture( + '@reference.arity', + callNode, + String(computeCppCallArity(callNode)), + ); + } + } + + // ── Enrich constructor calls (new Foo()) with arity ───────────── + const ctorCallAnchor = grouped['@reference.call.constructor']; + if (ctorCallAnchor !== undefined && grouped['@reference.arity'] === undefined) { + const newNode = findNodeAtRange(tree.rootNode, ctorCallAnchor.range, 'new_expression'); + if (newNode !== null) { + grouped['@reference.arity'] = syntheticCapture( + '@reference.arity', + newNode, + String(computeCppCallArity(newNode)), + ); + } + } + + // ── Synthesize argument types for overload narrowing ──────────── + const anyCallAnchor = callAnchor ?? ctorCallAnchor; + if (anyCallAnchor !== undefined && grouped['@reference.parameter-types'] === undefined) { + const cNode = + findNodeAtRange(tree.rootNode, anyCallAnchor.range, 'call_expression') ?? + findNodeAtRange(tree.rootNode, anyCallAnchor.range, 'new_expression'); + if (cNode !== null) { + const argTypes = inferCppCallArgTypes(cNode); + if (argTypes !== undefined && argTypes.length > 0) { + grouped['@reference.parameter-types'] = syntheticCapture( + '@reference.parameter-types', + cNode, + JSON.stringify(argTypes), + ); + } + } + } + + // ── Inline namespace detection ────────────────────────────────── + // `inline namespace v1 { ... }` — tree-sitter-cpp exposes the + // `inline` keyword as a child of `namespace_definition`. Record the + // namespace's source range so `populateCppInlineNamespaceScopes` + // (during populateOwners) can match it back to the corresponding + // Namespace scope. + // `@declaration.namespace` fires only for NAMED namespaces (the query + // requires a `name: (namespace_identifier)` child). Use the unconditional + // `@scope.namespace` capture so the anonymous-namespace branch also runs. + const namespaceScopeAnchor = grouped['@declaration.namespace'] ?? grouped['@scope.namespace']; + if (namespaceScopeAnchor !== undefined) { + const nsNode = findNodeAtRange( + tree.rootNode, + namespaceScopeAnchor.range, + 'namespace_definition', + ); + if (nsNode !== null) { + // Range coords stored in the shared Range shape use 1-based + // line numbers (see `ast-helpers.ts` rangeForNode where + // `startPosition.row + 1` is applied). Match that convention so + // the populators can join against `Scope.range`. + const nsRange = { + startLine: nsNode.startPosition.row + 1, + startCol: nsNode.startPosition.column, + endLine: nsNode.endPosition.row + 1, + endCol: nsNode.endPosition.column, + }; + if (isInlineNamespace(nsNode)) { + markCppInlineNamespaceRange(filePath, nsRange); + } + // Anonymous namespace: `namespace_definition` with no `name` field. + // Recorded so `expandCppWildcardNames` can propagate its members + // to including TUs even though their names are also `markFileLocal`'d + // (which blocks the global free-call fallback's cross-file path). + if ((nsNode.childForFieldName?.('name') ?? null) === null) { + markCppAnonymousNamespaceRange(filePath, nsRange); + } + } + } + + // ── ADL (Koenig lookup) per-site recording ────────────────────── + // Only free-call sites (no explicit receiver) participate in ADL — + // qualified `Ns::f(s)` and member `obj.f(s)` calls bypass the + // free-call fallback entirely (handled by receiver-bound-calls). + if (grouped['@reference.call.free'] !== undefined) { + const freeCallNode = findNodeAtRange( + tree.rootNode, + grouped['@reference.call.free']!.range, + 'call_expression', + ); + if (freeCallNode !== null) { + const adlAnchorRange = grouped['@reference.call.free']!.range; + if (isParenthesizedFunctionCall(freeCallNode)) { + markCppAdlSiteNoAdl(filePath, adlAnchorRange.startLine, adlAnchorRange.startCol); + } + const adlArgs = inferCppCallAdlArgs(freeCallNode); + if (adlArgs.length > 0) { + markCppAdlSiteArgs(filePath, adlAnchorRange.startLine, adlAnchorRange.startCol, adlArgs); + } + } + } + + // ── Post-process @type-binding.assignment for auto declarations ── + // The wildcard `type: (_)` in the @type-binding.assignment query + // pattern matches before the more specific @type-binding.alias and + // @type-binding.member-access patterns. When the type is `auto` + // (placeholder_type_specifier), we re-inspect the AST to synthesize + // the correct capture tags so interpret.ts can produce the right + // rawTypeName for compound-receiver chain resolution. + if ( + grouped['@type-binding.assignment'] !== undefined && + grouped['@type-binding.type']?.text === 'auto' + ) { + const anchor = grouped['@type-binding.assignment']!; + const declNode = findNodeAtRange(tree.rootNode, anchor.range, 'declaration'); + if (declNode !== null) { + const declarator = declNode.childForFieldName('declarator'); + if (declarator?.type === 'init_declarator') { + const valueNode = declarator.childForFieldName('value'); + if (valueNode !== null) { + if (valueNode.type === 'identifier') { + // auto alias = existingVar → promote to @type-binding.alias + grouped['@type-binding.alias'] = anchor; + grouped['@type-binding.type'] = nodeToCapture('@type-binding.type', valueNode); + delete grouped['@type-binding.assignment']; + } else if (valueNode.type === 'field_expression') { + // auto addr = user.address → promote to @type-binding.member-access + const argNode = valueNode.childForFieldName('argument'); + const fieldNode = valueNode.childForFieldName('field'); + if (argNode !== null && fieldNode !== null) { + grouped['@type-binding.member-access'] = anchor; + grouped['@type-binding.member-access-receiver'] = nodeToCapture( + '@type-binding.member-access-receiver', + argNode, + ); + grouped['@type-binding.type'] = nodeToCapture('@type-binding.type', fieldNode); + delete grouped['@type-binding.assignment']; + } + } else if (valueNode.type === 'call_expression') { + const fnNode = valueNode.childForFieldName('function'); + if (fnNode?.type === 'field_expression') { + // auto city = addr.getCity() → promote to @type-binding.alias + // with dotted rawName "addr.getCity" for compound-receiver + const argNode = fnNode.childForFieldName('argument'); + const fieldNode = fnNode.childForFieldName('field'); + if (argNode !== null && fieldNode !== null) { + grouped['@type-binding.member-access'] = anchor; + grouped['@type-binding.member-access-receiver'] = nodeToCapture( + '@type-binding.member-access-receiver', + argNode, + ); + grouped['@type-binding.type'] = nodeToCapture('@type-binding.type', fieldNode); + delete grouped['@type-binding.assignment']; + } + } + } + } + } + } + } + + out.push(grouped); + } + + // ── Emit inheritance references for scope-resolution MRO / EXTENDS ── + // Walk every class/struct base list and synthesize `@reference.inherits` + // captures consumed by the registry-primary graph bridge. The lookup name + // is normalized to the bare class name so `Base` / `outer::v1::Base` + // resolve through V1's simple-name `findClassBindingInScope('Base')`. + emitCppInheritanceCaptures(tree.rootNode, out); + + // ── Detect dependent-base relationships for two-phase template lookup ── + // Walk the tree once, finding every `template_declaration` whose + // child is a class/struct definition with a `base_class_clause` whose + // base names reference an in-scope template parameter. Record the + // (className, dependentBaseName) pair so `populateCppDependentBases` + // (called from the `populateOwners` hook) can resolve names to nodeIds + // and the resolver can suppress unqualified-call binding to those + // bases per ISO C++ two-phase lookup. + detectCppDependentBases(tree.rootNode, filePath); + + return out; +} + +/** + * Walk every C++ class/struct base clause and emit `@reference.inherits` + * captures for each base so scope resolution can resolve them into EXTENDS + * edges. Lookup names are normalized to bare class names (`Base` → `Base`, + * `outer::v1::Base` → `Base`) to match the V1 simple-name + * `findClassBindingInScope` contract. This intentionally preserves the + * existing scope-chain tradeoff: qualified namespace context is discarded + * here instead of introducing a C++-only name-resolution lane in shared + * ingestion infrastructure. + */ +function emitCppInheritanceCaptures(root: SyntaxNode, out: CaptureMatch[]): void { + const stack: SyntaxNode[] = [root]; + while (stack.length > 0) { + const node = stack.pop()!; + if (node.type === 'class_specifier' || node.type === 'struct_specifier') { + const baseClause = findChildOfType(node, ['base_class_clause']); + if (baseClause !== null) { + for (const base of iterBaseClasses(baseClause)) { + const baseName = extractBaseLookupName(base); + if (baseName.length === 0) continue; + out.push({ + '@reference.inherits': nodeToCapture('@reference.inherits', base), + '@reference.name': syntheticCapture('@reference.name', base, baseName), + }); + } + } + } + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null) stack.push(child); + } + } +} + +/** + * Walk the AST finding every template_declaration containing a class or + * struct definition with a dependent base. Records (className, baseName) + * pairs into the module-level state via `markCppDependentBase`. + * + * A base is "dependent" when its name (typically a template_type like + * `Base`) uses a template parameter of the enclosing template_declaration. + * Conservative bias: `typename T::U`, `decltype(...)` and template-template + * parameter shapes are also treated as dependent. + */ +function detectCppDependentBases(root: SyntaxNode, filePath: string): void { + const stack: SyntaxNode[] = [root]; + while (stack.length > 0) { + const node = stack.pop()!; + if (node.type === 'template_declaration') { + // Collect template-parameter names declared by this declaration. + // Inner template_declarations shadow outer ones — handled by the + // recursive descent below (each template_declaration creates its + // own parameter scope). + const params = collectTemplateParameterNames(node); + + // Find the class/struct definition inside this template_declaration. + const classNode = findChildOfType(node, ['class_specifier', 'struct_specifier']); + if (classNode !== null) { + const className = getTypeIdentifierName(classNode); + if (className !== '') { + const baseClause = findChildOfType(classNode, ['base_class_clause']); + if (baseClause !== null) { + for (const base of iterBaseClasses(baseClause)) { + if (isBaseDependent(base, params)) { + const baseName = extractBaseLookupName(base); + if (baseName !== '') { + markCppDependentBase(filePath, className, baseName); + } + } + } + } + } + } + } + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null) stack.push(child); + } + } +} + +/** Collect simple template parameter names from a template_declaration. */ +function collectTemplateParameterNames(templateDecl: SyntaxNode): Set { + const names = new Set(); + const paramList = findChildOfType(templateDecl, ['template_parameter_list']); + if (paramList === null) return names; + for (let i = 0; i < paramList.childCount; i++) { + const param = paramList.child(i); + if (param === null) continue; + if ( + param.type === 'type_parameter_declaration' || + param.type === 'optional_type_parameter_declaration' || + param.type === 'variadic_type_parameter_declaration' + ) { + const idNode = findFirstDescendantOfType(param, 'type_identifier'); + if (idNode !== null) names.add(idNode.text); + } else if ( + param.type === 'parameter_declaration' || + param.type === 'optional_parameter_declaration' || + param.type === 'variadic_parameter_declaration' + ) { + // Non-type template parameter (e.g. `template`). + const idNode = findFirstDescendantOfType(param, 'identifier'); + if (idNode !== null) names.add(idNode.text); + } else if (param.type === 'template_template_parameter_declaration') { + // template-template parameter (e.g. `template class TT>`) + const idNode = findFirstDescendantOfType(param, 'type_identifier'); + if (idNode !== null) names.add(idNode.text); + } + } + return names; +} + +/** Yield each base-class entry from a `base_class_clause`. */ +function* iterBaseClasses(baseClause: SyntaxNode): IterableIterator { + for (let i = 0; i < baseClause.childCount; i++) { + const child = baseClause.child(i); + if (child === null) continue; + // Skip ':', ',', and access_specifier nodes — the base names are + // type_identifier, template_type, or qualified_identifier. + if ( + child.type === 'type_identifier' || + child.type === 'template_type' || + child.type === 'qualified_identifier' + ) { + yield child; + } + } +} + +/** + * A base is dependent when: + * - it's a `template_type` and its argument list contains a + * `type_identifier` matching one of the enclosing template's params + * (e.g., `Base` where `T` is a template parameter), OR + * - it contains a `typename`, `decltype`, or `template_template_parameter` + * shape (conservatively treated as dependent). + * + * Non-dependent: `Base`, `ConcreteBase`, `Base` where + * `MyConcrete` is not a template parameter. + */ +function isBaseDependent(baseNode: SyntaxNode, templateParams: Set): boolean { + if (baseNode.type !== 'template_type') { + // Bare `type_identifier` or `qualified_identifier` bases — not + // dependent (the base name itself doesn't reference a template + // parameter at this level). + return false; + } + // Walk all descendants of the template_argument_list looking for any + // type_identifier matching a template parameter, or any conservative- + // dependent shape. + const stack: SyntaxNode[] = [baseNode]; + while (stack.length > 0) { + const node = stack.pop()!; + if (node.type === 'type_identifier' && templateParams.has(node.text)) { + return true; + } + if ( + node.type === 'decltype' || + node.type === 'dependent_type' || + node.type === 'template_template_parameter_declaration' + ) { + return true; + } + if (node.type === 'qualified_identifier') { + // `typename T::U` or `T::nested` — if any inner identifier matches + // a template parameter, dependent. + for (let i = 0; i < node.childCount; i++) { + const c = node.child(i); + if (c !== null) stack.push(c); + } + continue; + } + for (let i = 0; i < node.childCount; i++) { + const c = node.child(i); + if (c !== null) stack.push(c); + } + } + return false; +} + +/** + * Recursively extract the bare lookup name of a base class node. + * Examples: `Base` → `Base`, `Base` → `Base`, + * `outer::v1::Base` → `Base`. Namespace qualifiers are intentionally + * dropped to align with V1 scope-chain lookup everywhere else in the + * registry-primary pipeline. + */ +function extractBaseLookupName(baseNode: SyntaxNode): string { + if (baseNode.type === 'type_identifier' || baseNode.type === 'identifier') return baseNode.text; + if (baseNode.type === 'template_type') { + const nameNode = baseNode.childForFieldName('name'); + if (nameNode !== null) return extractBaseLookupName(nameNode); + const id = + findFirstDescendantOfType(baseNode, 'type_identifier') ?? + findFirstDescendantOfType(baseNode, 'identifier'); + if (id !== null) return id.text; + } + if (baseNode.type === 'qualified_identifier') { + const nameNode = baseNode.childForFieldName('name'); + if (nameNode !== null) { + const nested = extractBaseLookupName(nameNode); + if (nested.length > 0) return nested; + } + for (let i = baseNode.childCount - 1; i >= 0; i--) { + const child = baseNode.child(i); + if (child === null) continue; + const nested = extractBaseLookupName(child); + if (nested.length > 0) return nested; + } + } + return ''; +} + +/** Find the first direct child matching one of the given types. */ +function findChildOfType(node: SyntaxNode, types: readonly string[]): SyntaxNode | null { + for (let i = 0; i < node.childCount; i++) { + const c = node.child(i); + if (c !== null && types.includes(c.type)) return c; + } + return null; +} + +/** Recursive search for the first descendant of a given type. */ +function findFirstDescendantOfType(node: SyntaxNode, type: string): SyntaxNode | null { + if (node.type === type) return node; + for (let i = 0; i < node.childCount; i++) { + const c = node.child(i); + if (c === null) continue; + const hit = findFirstDescendantOfType(c, type); + if (hit !== null) return hit; + } + return null; +} + +/** Get the name of a class/struct/template_type node via its `name` field. */ +function getTypeIdentifierName(node: SyntaxNode): string { + const nameNode = node.childForFieldName('name'); + if (nameNode !== null) return nameNode.text; + const id = findFirstDescendantOfType(node, 'type_identifier'); + return id !== null ? id.text : ''; +} + +/** + * Infer argument types from a call_expression or new_expression node. + * Used for overload disambiguation by parameter types. + * + * Only literal types are inferred — identifiers and complex expressions + * return empty string (unknown) so narrowOverloadCandidates treats them + * as any-match. + */ +function inferCppCallArgTypes(node: SyntaxNode): string[] | undefined { + const argList = node.childForFieldName('arguments'); + if (argList === null) return undefined; + + const types: string[] = []; + for (let i = 0; i < argList.childCount; i++) { + const child = argList.child(i); + if (child === null) continue; + if (child.type === ',' || child.type === '(' || child.type === ')') continue; + const litType = inferCppLiteralType(child); + if (litType !== '') { + types.push(litType); + } else if (child.type === 'identifier') { + // Variable reference — look up declared type in enclosing scope + types.push(lookupDeclaredTypeForIdentifier(child)); + } else { + types.push(''); + } + } + return types.length > 0 ? types : undefined; +} + +/** + * Infer the canonical type name of a C++ literal AST node. + * Returns empty string for non-literal / unknown nodes. + */ +function inferCppLiteralType(node: SyntaxNode): string { + switch (node.type) { + case 'number_literal': { + const text = node.text; + // Floating-point literals contain '.', 'e', 'E', or end with 'f'/'F' + if ( + text.includes('.') || + text.includes('e') || + text.includes('E') || + text.endsWith('f') || + text.endsWith('F') + ) { + return 'double'; + } + return 'int'; + } + case 'string_literal': + case 'raw_string_literal': + case 'concatenated_string': + return 'string'; + case 'char_literal': + return 'char'; + case 'true': + case 'false': + return 'bool'; + case 'null': + case 'nullptr': + return 'null'; + default: + return ''; + } +} + +/** + * Look up the declared type of a variable by scanning sibling declarations + * in the enclosing compound_statement (function body). Handles: + * - `std::string result = ...` → 'string' + * - `int n = ...` → 'int' + * - `const int n = ...` → 'int' + * Returns empty string if no declaration found or type is auto/placeholder. + */ +function lookupDeclaredTypeForIdentifier(identNode: SyntaxNode): string { + const varName = identNode.text; + // Walk up to the enclosing compound_statement (function body) + let scope: SyntaxNode | null = identNode.parent; + while ( + scope !== null && + scope.type !== 'compound_statement' && + scope.type !== 'translation_unit' + ) { + scope = scope.parent; + } + if (scope === null) return ''; + + // Scan declarations in the scope for a matching variable name + for (let i = 0; i < scope.childCount; i++) { + const stmt = scope.child(i); + if (stmt === null || stmt.type !== 'declaration') continue; + + const typeNode = stmt.childForFieldName('type'); + if (typeNode === null) continue; + // Skip auto/placeholder types — those need chain-follow, not literal + if (typeNode.type === 'placeholder_type_specifier') continue; + + // Check init_declarator children for the variable name + const declarator = stmt.childForFieldName('declarator'); + if (declarator === null) continue; + if (declarator.type === 'init_declarator') { + const nameChild = declarator.childForFieldName('declarator'); + if (nameChild !== null && nameChild.text === varName) { + return normalizeCppTypeText(typeNode.text); + } + } else if (declarator.text === varName) { + return normalizeCppTypeText(typeNode.text); + } + } + return ''; +} + +/** Normalize a type-specifier text for argument type matching. + * Strips qualifiers (const, volatile), namespace prefixes (std::), + * and pointer/reference markers. */ +function normalizeCppTypeText(text: string): string { + let t = text.trim(); + t = t.replace(/\b(const|volatile|static|extern|mutable)\b/g, '').trim(); + t = t.replace(/^.*::/, ''); // strip namespace prefix + t = t.replace(/[*&]/g, '').trim(); + return t; +} + +/** + * Detect whether a `namespace_definition` AST node is inline. + * Tree-sitter-cpp exposes the `inline` keyword as an anonymous child + * node — we scan direct children for that keyword. + */ +function isInlineNamespace(nsNode: SyntaxNode): boolean { + for (let i = 0; i < nsNode.childCount; i++) { + const c = nsNode.child(i); + if (c === null) continue; + if (c.type === 'inline') return true; + // Some grammar variants surface keywords by their text rather than + // by a dedicated node type; check both for resilience. + if (c.text === 'inline' && (c.type === 'storage_class_specifier' || c.type === 'inline')) { + return true; + } + } + return false; +} + +/** + * Detect `(f)(args)` shape — the call-expression's `function` field is a + * `parenthesized_expression`. ISO C++ specifies that this form suppresses + * ADL (`[basic.lookup.argdep]/3.1`): the parenthesized name is treated as + * an ordinary unqualified-lookup-only callee. + */ +function isParenthesizedFunctionCall(callNode: SyntaxNode): boolean { + const fn = callNode.childForFieldName('function'); + return fn !== null && fn.type === 'parenthesized_expression'; +} + +/** + * Per-argument ADL classification: walk each argument of a free call and + * classify its declared type for associated-namespace lookup. + * + * Value/pointer/reference class-typed args and template specializations + * with explicit type arguments contribute; function pointers, primitives, + * literals, and other unsupported shapes produce an empty result. + * + * Class-typed values/pointers/references (`N::S`, `N::S*`, `N::S&`) all + * preserve the class name for associated-namespace lookup. + * Function pointers remain excluded even when their return type names a + * class, because the associated entity is the pointed-to function type, + * not the return type. + */ +function inferCppCallAdlArgs(callNode: SyntaxNode): CppAdlArgInfo[] { + const argList = callNode.childForFieldName('arguments'); + if (argList === null) return []; + const out: CppAdlArgInfo[] = []; + for (let i = 0; i < argList.childCount; i++) { + const child = argList.child(i); + if (child === null) continue; + if (child.type === ',' || child.type === '(' || child.type === ')') continue; + out.push(classifyAdlArg(child)); + } + return out; +} + +const ADL_TEMPLATE_RECURSION_MAX_DEPTH = 8; +const EMPTY_ADL_ARG: CppAdlArgInfo = { + simpleClassName: '', + templateSimpleClassName: '', + templateNamespace: '', + templateArgClassNames: [], + templateArgNamespaces: [], +}; + +function classifyAdlArg(argNode: SyntaxNode): CppAdlArgInfo { + // Literals and primitive-shaped expressions never have associated namespaces. + if ( + argNode.type === 'number_literal' || + argNode.type === 'string_literal' || + argNode.type === 'raw_string_literal' || + argNode.type === 'char_literal' || + argNode.type === 'true' || + argNode.type === 'false' || + argNode.type === 'null' || + argNode.type === 'nullptr' + ) { + return EMPTY_ADL_ARG; + } + // Qualified expression (a::b) — may be a function, variable, enum value, + // or static member. Record as a potential function reference; resolution + // time verifies via workspace lookup that a Function/Method with this simple + // name exists in the extracted namespace before contributing to the set. + if (argNode.type === 'qualified_identifier') { + return { + simpleClassName: '', + templateSimpleClassName: '', + templateNamespace: '', + templateArgClassNames: [], + templateArgNamespaces: [], + functionRefText: argNode.text, + }; + } + // Variable reference — look up its declared type (preserving pointer / + // reference / qualified-name shape; the existing arity-narrowing helper + // strips this info). + if (argNode.type === 'identifier') { + const result = lookupAdlIdentifierType(argNode); + if (result === null) { + // Not found in the local compound_statement scope — could be a + // free-function reference (unqualified name, namespace scope). + return { + simpleClassName: '', + templateSimpleClassName: '', + templateNamespace: '', + templateArgClassNames: [], + templateArgNamespaces: [], + functionRefText: argNode.text, + }; + } + return result; + } + // Other shapes (calls, member access, operators) — V1 unsupported. + return EMPTY_ADL_ARG; +} + +/** + * Returns `true` when `varName` appears as a parameter name in the nearest + * enclosing `function_definition` or `function_declarator` that contains + * `identNode`. Parameters live in `parameter_list` (a sibling of the + * `compound_statement`), so the `compound_statement`-local declaration scan + * in `lookupAdlIdentifierType` would not find them — causing them to be + * mistakenly classified as potential free-function references. + * + * In tree-sitter-cpp a `function_definition` does NOT expose `parameters` + * as a direct named field; parameters live inside the nested + * `function_declarator`. For `function_declarator` nodes the `parameters` + * field IS direct. Both cases are handled below. + */ +function isIdentifierAFunctionParameter(identNode: SyntaxNode, varName: string): boolean { + let node: SyntaxNode | null = identNode.parent; + let safety = 64; + while (node !== null && safety-- > 0) { + let params: SyntaxNode | null = null; + if (node.type === 'function_declarator') { + // parameters is a direct field on function_declarator. + params = node.childForFieldName('parameters'); + } else if (node.type === 'function_definition') { + // function_definition carries parameters inside its `declarator` field + // (which is a function_declarator). Walk through it. + const decl = node.childForFieldName('declarator'); + if (decl !== null && decl.type === 'function_declarator') { + params = decl.childForFieldName('parameters'); + } + } + if (params !== null) { + for (let i = 0; i < params.namedChildCount; i++) { + const param = params.namedChild(i); + if (param === null) continue; + const declNode = param.childForFieldName('declarator'); + if (declNode === null) continue; + const leafName = extractDeclaratorLeafName(declNode); + if (leafName === varName) return true; + } + // Only check the immediately enclosing function — do not climb further. + break; + } + if (node.type === 'translation_unit') break; + node = node.parent; + } + return false; +} + +function lookupAdlIdentifierType(identNode: SyntaxNode): CppAdlArgInfo | null { + const varName = identNode.text; + let scope: SyntaxNode | null = identNode.parent; + while ( + scope !== null && + scope.type !== 'compound_statement' && + scope.type !== 'translation_unit' + ) { + scope = scope.parent; + } + if (scope === null) return null; + + // Function parameters live in the enclosing function's `parameter_list`, + // NOT inside the `compound_statement`, so the declaration scan below would + // never find them and would return `null` — incorrectly triggering the + // free-function-reference path. Check the parameter_list first. + if (isIdentifierAFunctionParameter(identNode, varName)) { + return EMPTY_ADL_ARG; + } + + let foundAsLocalFunctionPointer = false; + for (let i = 0; i < scope.childCount; i++) { + const stmt = scope.child(i); + if (stmt === null || stmt.type !== 'declaration') continue; + const typeNode = stmt.childForFieldName('type'); + if (typeNode === null) continue; + if (typeNode.type === 'placeholder_type_specifier') continue; + + const declarator = stmt.childForFieldName('declarator'); + if (declarator === null) continue; + + // Unwrap declarator chain to find pointer/reference markers and the + // variable name. `init_declarator > pointer_declarator > identifier` + // means pointer-typed; repeated pointer wrappers still count as pointer + // typed; `init_declarator > reference_declarator > ...` (or + // `rvalue_reference_declarator`) means reference-typed; bare + // `init_declarator > identifier` is value. + // Function-pointer wrappers (`pointer_declarator > function_declarator`) + // must not contribute ADL associated namespaces. + let isFunctionPointer = false; + let inner: SyntaxNode = declarator; + let nameText: string | null = null; + let safety = 16; // bound walk depth defensively + while (safety-- > 0) { + if (inner.type === 'pointer_declarator') { + if (findFirstDescendantOfType(inner, 'function_declarator') !== null) { + isFunctionPointer = true; + // Extract the name from within the function-pointer declarator chain + // so `foundAsLocalFunctionPointer` can detect a matching declaration. + nameText = extractDeclaratorLeafName(inner); + break; + } + const next = inner.childForFieldName('declarator'); + if (next === null) break; + inner = next; + continue; + } + if (inner.type === 'reference_declarator' || inner.type === 'rvalue_reference_declarator') { + // reference_declarator has a single child (the inner declarator). + let next: SyntaxNode | null = null; + for (let j = 0; j < inner.namedChildCount; j++) { + const c = inner.namedChild(j); + if (c !== null) { + next = c; + break; + } + } + if (next === null) break; + inner = next; + continue; + } + if (inner.type === 'init_declarator') { + const next = inner.childForFieldName('declarator'); + if (next === null) break; + inner = next; + continue; + } + if (inner.type === 'function_declarator') { + isFunctionPointer = true; + // Extract the name from the inner declarator (e.g. `(*g)` in `void (*g)()`). + const innerDecl = inner.childForFieldName('declarator'); + if (innerDecl !== null) nameText = extractDeclaratorLeafName(innerDecl); + break; + } + // Reached the leaf — usually `identifier`. Take its text. + nameText = inner.text; + break; + } + if (nameText === varName && isFunctionPointer) { + // Explicitly declared as a function-pointer variable — must not be + // treated as a free-function reference by the caller. + foundAsLocalFunctionPointer = true; + continue; + } + if (isFunctionPointer || nameText !== varName) continue; + + const simpleClassName = extractAdlSimpleTypeName(typeNode); + const { + templateSimpleClassName, + templateNamespace, + templateArgClassNames, + templateArgNamespaces, + } = extractAdlTemplateInfo(typeNode); + return { + simpleClassName, + templateSimpleClassName, + templateNamespace, + templateArgClassNames, + templateArgNamespaces, + }; + } + // If the identifier was found in local scope as a function-pointer variable, + // return EMPTY_ADL_ARG so the caller does NOT treat it as a free-function + // reference. Otherwise return null to indicate "not in local scope". + // + // Known limitation (Finding 4): variables whose type is a typedef/using alias + // for a function-pointer type are NOT detected here. For example: + // using Callback = void (*)(); + // Callback g; + // foo(g); // `g`'s declarator is `identifier` with type `Callback` + // The declarator has no `pointer_declarator` wrapper, so `isFunctionPointer` + // stays false and `extractAdlSimpleTypeName` returns `"Callback"`. ADL then + // looks for a class named `Callback`; if none exists, this degrades to + // EMPTY_ADL_ARG (class not found → no namespace contributed). If a class + // named `Callback` does exist, a spurious namespace contribution could occur. + // Risk is low in practice; a future fix should resolve the typedef/alias chain. + return foundAsLocalFunctionPointer ? EMPTY_ADL_ARG : null; +} + +/** Extract the simple class-like type name from a `type:` field node. + * Returns '' for primitives and any other + * unsupported type-only shape. Function pointers are filtered at the + * declarator level in `lookupAdlIdentifierType`. */ +function extractAdlSimpleTypeName(typeNode: SyntaxNode): string { + if (typeNode.type === 'type_descriptor') { + const innerType = typeNode.childForFieldName('type'); + if (innerType !== null) return extractAdlSimpleTypeName(innerType); + for (let i = 0; i < typeNode.childCount; i++) { + const child = typeNode.child(i); + if (child === null) continue; + if ( + child.type === 'type_identifier' || + child.type === 'qualified_identifier' || + child.type === 'template_type' + ) { + return extractAdlSimpleTypeName(child); + } + } + return ''; + } + if (typeNode.type === 'primitive_type') return ''; + if (typeNode.type === 'sized_type_specifier') return ''; + if (typeNode.type === 'type_identifier') return typeNode.text; + if (typeNode.type === 'template_type') { + const nameNode = typeNode.childForFieldName('name'); + if (nameNode !== null) return extractAdlSimpleTypeName(nameNode); + const id = findFirstDescendantOfType(typeNode, 'type_identifier'); + return id !== null ? id.text : ''; + } + if (typeNode.type === 'qualified_identifier') { + const nameNode = typeNode.childForFieldName('name'); + if (nameNode !== null) return extractAdlSimpleTypeName(nameNode); + const id = findFirstDescendantOfType(typeNode, 'type_identifier'); + return id !== null ? id.text : ''; + } + // Function pointers, decltype, etc — unsupported for ADL participation. + return ''; +} + +function extractAdlTypeNamespace(typeNode: SyntaxNode): string { + if (typeNode.type === 'type_descriptor') { + const innerType = typeNode.childForFieldName('type'); + if (innerType !== null) return extractAdlTypeNamespace(innerType); + for (let i = 0; i < typeNode.childCount; i++) { + const child = typeNode.child(i); + if (child === null) continue; + if ( + child.type === 'qualified_identifier' || + child.type === 'template_type' || + child.type === 'type_identifier' + ) { + return extractAdlTypeNamespace(child); + } + } + return ''; + } + if (typeNode.type === 'template_type') { + const nameNode = typeNode.childForFieldName('name'); + return nameNode !== null ? extractAdlTypeNamespace(nameNode) : ''; + } + if (typeNode.type === 'qualified_identifier') { + const scope = typeNode.childForFieldName('scope'); + if (scope !== null) return normalizeCppNamespaceQName(scope.text); + return extractNamespaceFromQualifiedText(typeNode.text); + } + return ''; +} + +function extractAdlTemplateInfo(typeNode: SyntaxNode): { + templateSimpleClassName: string; + templateNamespace: string; + templateArgClassNames: string[]; + templateArgNamespaces: string[]; +} { + const templateTypeNode = findTemplateTypeNode(typeNode); + if (templateTypeNode === null) { + return { + templateSimpleClassName: '', + templateNamespace: '', + templateArgClassNames: [], + templateArgNamespaces: [], + }; + } + const templateArgClassNames: string[] = []; + const templateArgNamespaces: string[] = []; + collectAdlTemplateArgs(templateTypeNode, 0, templateArgClassNames, templateArgNamespaces); + return { + templateSimpleClassName: extractAdlSimpleTypeName(templateTypeNode), + templateNamespace: extractAdlTypeNamespace(typeNode), + templateArgClassNames, + templateArgNamespaces, + }; +} + +function collectAdlTemplateArgs( + templateTypeNode: SyntaxNode, + depth: number, + outClassNames: string[], + outNamespaces: string[], +): void { + if (depth >= ADL_TEMPLATE_RECURSION_MAX_DEPTH) return; + if (templateTypeNode.type !== 'template_type') return; + + const argList = + templateTypeNode.childForFieldName('arguments') ?? + findChildOfType(templateTypeNode, ['template_argument_list']); + if (argList === null) return; + + for (let i = 0; i < argList.namedChildCount; i++) { + const arg = argList.namedChild(i); + if (arg === null || arg.type !== 'type_descriptor') continue; + const simpleClassName = extractAdlSimpleTypeName(arg); + if (simpleClassName.length > 0) outClassNames.push(simpleClassName); + const ns = extractAdlTypeNamespace(arg); + if (ns.length > 0) outNamespaces.push(ns); + + const nestedType = arg.childForFieldName('type'); + const nestedTemplate = nestedType !== null ? findTemplateTypeNode(nestedType) : null; + if (nestedTemplate !== null) { + collectAdlTemplateArgs(nestedTemplate, depth + 1, outClassNames, outNamespaces); + } + } +} + +function findTemplateTypeNode(typeNode: SyntaxNode): SyntaxNode | null { + if (typeNode.type === 'template_type') return typeNode; + if (typeNode.type === 'type_descriptor') { + const innerType = typeNode.childForFieldName('type'); + if (innerType !== null) return findTemplateTypeNode(innerType); + return null; + } + if (typeNode.type === 'qualified_identifier') { + const nameNode = typeNode.childForFieldName('name'); + if (nameNode !== null) return findTemplateTypeNode(nameNode); + return null; + } + return null; +} + +function normalizeCppNamespaceQName(text: string): string { + const normalized = text.replace(/^::/, '').replace(/::$/, '').replace(/::/g, '.'); + return normalized; +} + +function extractNamespaceFromQualifiedText(text: string): string { + const cleaned = text.replace(/\s+/g, ''); + const idx = cleaned.lastIndexOf('::'); + if (idx <= 0) return ''; + return normalizeCppNamespaceQName(cleaned.slice(0, idx)); +} + +/** + * Walk a declarator node chain, unwrapping pointer/reference/function/ + * parenthesized wrappers, and return the text of the innermost identifier. + * Returns `null` when no identifier is found within `safety` steps. + * Used by `lookupAdlIdentifierType` to extract the variable name from + * function-pointer declarator trees such as `(*g)()` in `void (*g)()`. + */ +function extractDeclaratorLeafName(node: SyntaxNode): string | null { + let cur: SyntaxNode = node; + let safety = 16; + while (safety-- > 0) { + if (cur.type === 'identifier' || cur.type === 'type_identifier') return cur.text; + // Common wrapper nodes — follow the 'declarator' field when present. + const next = + cur.childForFieldName('declarator') ?? + // parenthesized_declarator: single named child + (cur.type === 'parenthesized_declarator' ? cur.namedChild(0) : null); + if (next === null) return null; + cur = next; + } + return null; +} + +/** + * Check if a C++ function_definition or declaration has `static` storage class. + */ +function hasStaticStorageClass(node: SyntaxNode): boolean { + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null && child.type === 'storage_class_specifier' && child.text === 'static') { + return true; + } + } + return false; +} + +/** + * Check if a node is inside an anonymous namespace (file-local linkage in C++). + * Anonymous namespaces have no `name` field in tree-sitter-cpp. + */ +function isInsideAnonymousNamespace(node: SyntaxNode): boolean { + let ancestor: SyntaxNode | null = node.parent ?? null; + while (ancestor !== null) { + if (ancestor.type === 'namespace_definition') { + // Anonymous namespace: has declaration_list but no name child + const nameChild = ancestor.childForFieldName?.('name') ?? null; + if (nameChild === null) return true; + } + ancestor = ancestor.parent; + } + return false; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/file-local-linkage.ts b/gitnexus/src/core/ingestion/languages/cpp/file-local-linkage.ts new file mode 100644 index 000000000..dd5fc8c0a --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/file-local-linkage.ts @@ -0,0 +1,302 @@ +import type { ParsedFile, Scope, ScopeId, SymbolDefinition } from 'gitnexus-shared'; +import { isCppInlineNamespaceScope } from './inline-namespaces.js'; + +/** + * Per-file set of symbol names with file-local linkage. + * In C++ there are two sources of file-local linkage: + * 1. `static` storage class (same as C) + * 2. Anonymous namespace (`namespace { ... }`) + * + * Populated during `emitCppScopeCaptures` and consumed by + * `expandCppWildcardNames` to exclude file-local symbols from + * cross-file wildcard import visibility. + * + * NOTE: module-level state, single-process-single-repo use only. + * Call `clearFileLocalNames()` at the start of each resolution pass. + * + * Key: filePath, Value: Set of file-local symbol names. + */ +const fileLocalNames = new Map>(); + +/** + * Per-file set of `SymbolDefinition.nodeId`s that are NOT visible by + * unqualified lookup from outside the file — class-owned methods/fields + * and namespace-nested symbols. Populated by `populateCppNonGloballyVisible` + * during the per-file `populateOwners` hook; consumed by + * `isCppDefGloballyVisible` from both `expandCppWildcardNames` (wildcard + * propagation) and the global free-call fallback's `isFileLocalDef` hook. + * + * Tracked per filePath rather than as a single global set so cross-file + * lookup correctly compares the candidate's owning file's non-visible + * set without leaking across pipeline invocations (the global free-call + * fallback checks `def.filePath !== callerFilePath` and then asks "is + * this def visible from outside its own file?" — that's exactly what + * this set encodes). + */ +const nonGloballyVisibleNodeIds = new Map>(); + +/** + * Per-file set of source-range keys identifying `namespace { ... }` blocks. + * Resolved to `ScopeId`s in `populateCppAnonymousNamespaceScopes` and + * consumed via `isCppAnonymousNamespaceScope`. + * + * Anonymous namespaces have file-local linkage but, unlike `static`, their + * members propagate to any TU that `#include`s the declaring file — each + * including TU gets its own internal-linkage copy. So for wildcard import + * expansion (`expandCppWildcardNames`) we treat anonymous-namespace owned + * defs as if declared at the enclosing scope. Cross-file unqualified + * lookup that does NOT go through `#include` is still blocked by the + * `isFileLocal` mark recorded on the def's name. + */ +const anonymousNamespaceRangesByFile = new Map>(); +const anonymousNamespaceScopeIds = new Set(); + +interface RangeKeyShape { + readonly startLine: number; + readonly startCol: number; + readonly endLine: number; + readonly endCol: number; +} + +function rangeKey(r: RangeKeyShape): string { + return `${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`; +} + +/** Record a symbol name as file-local (static or anonymous namespace). */ +export function markFileLocal(filePath: string, name: string): void { + let names = fileLocalNames.get(filePath); + if (names === undefined) { + names = new Set(); + fileLocalNames.set(filePath, names); + } + names.add(name); +} + +/** Check whether a symbol name has file-local linkage in the given file. */ +export function isFileLocal(filePath: string, name: string): boolean { + return fileLocalNames.get(filePath)?.has(name) ?? false; +} + +/** Capture-time: record an anonymous `namespace_definition` source range. */ +export function markCppAnonymousNamespaceRange(filePath: string, range: RangeKeyShape): void { + let set = anonymousNamespaceRangesByFile.get(filePath); + if (set === undefined) { + set = new Set(); + anonymousNamespaceRangesByFile.set(filePath, set); + } + set.add(rangeKey(range)); +} + +/** Predicate consumed by `populateCppNonGloballyVisible` and + * `expandCppWildcardNames` to exempt anonymous-namespace scopes from + * the cross-file unqualified-lookup exclusion that applies to ordinary + * named namespaces. */ +export function isCppAnonymousNamespaceScope(scopeId: ScopeId): boolean { + return anonymousNamespaceScopeIds.has(scopeId); +} + +/** Clear tracked file-local names (call at start of each resolution pass). */ +export function clearFileLocalNames(): void { + fileLocalNames.clear(); + nonGloballyVisibleNodeIds.clear(); + anonymousNamespaceRangesByFile.clear(); + anonymousNamespaceScopeIds.clear(); +} + +/** Resolve recorded anonymous-namespace source ranges to `ScopeId`s. + * Must run inside `populateOwners` BEFORE `populateCppNonGloballyVisible` + * consults the resolved set. */ +export function populateCppAnonymousNamespaceScopes(parsed: { + readonly filePath: string; + readonly scopes: readonly { + readonly id: ScopeId; + readonly kind: string; + readonly range: RangeKeyShape; + }[]; +}): void { + const ranges = anonymousNamespaceRangesByFile.get(parsed.filePath); + if (ranges === undefined || ranges.size === 0) return; + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + if (ranges.has(rangeKey(scope.range))) { + anonymousNamespaceScopeIds.add(scope.id); + } + } +} + +/** + * Populate per-file "not globally visible" nodeIds by walking the parsed + * file's scopes. Run as part of the `populateOwners` hook so every C++ + * scope is reflected before any cross-file resolution pass consults the + * set. + * + * A def is "not globally visible" when its nearest structurally enclosing + * scope is a `Namespace` or `Class` — those require qualification + * (`ns::name`, `Class::method`) for cross-file unqualified lookup. + * Module-scoped defs remain globally visible. + */ +export function populateCppNonGloballyVisible(parsed: { + readonly filePath: string; + readonly scopes: readonly { + readonly id: ScopeId; + readonly kind: string; + readonly ownedDefs: readonly { readonly nodeId: string }[]; + }[]; +}): void { + let set = nonGloballyVisibleNodeIds.get(parsed.filePath); + if (set === undefined) { + set = new Set(); + nonGloballyVisibleNodeIds.set(parsed.filePath, set); + } + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace' && scope.kind !== 'Class') continue; + // Inline namespaces (`inline namespace v1 { ... }`) propagate their + // members to the enclosing namespace's unqualified-lookup scope per + // ISO C++ `[namespace.def]/p4`. Skip them here so cross-file + // unqualified lookup can still see their callable defs. + if (scope.kind === 'Namespace' && isCppInlineNamespaceScope(scope.id)) continue; + // Anonymous namespaces give internal linkage but their contents are + // visible at the enclosing scope within the same TU and propagate to + // any TU that `#include`s the declaring file. The `isFileLocal` mark + // (recorded on the def's name in this file) still blocks cross-file + // unqualified lookup that does not go through #include, so dropping + // the structural visibility exclusion here is safe. + if (scope.kind === 'Namespace' && anonymousNamespaceScopeIds.has(scope.id)) continue; + for (const def of scope.ownedDefs) { + set.add(def.nodeId); + } + } +} + +/** + * Check whether a def is visible by unqualified lookup from outside its + * own file. Returns `false` for class-owned and namespace-nested defs. + * + * Used by the global free-call fallback's `isFileLocalDef` hook (which + * historically meant "static / anonymous-namespace" but semantically + * stands for "logically invisible cross-file"). Including class methods + * and namespace members under the same negative answer fixes the leak + * where unqualified `save()` resolved to `User::save` through a shared + * workspace registry walk. + */ +export function isCppDefGloballyVisible(filePath: string, nodeId: string): boolean { + return nonGloballyVisibleNodeIds.get(filePath)?.has(nodeId) !== true; +} + +/** + * Return the names visible through a C++ wildcard import (`#include` or + * `using namespace`). + * + * ## Contract + * + * C++ unqualified name lookup only sees names at the importer's enclosing + * scope. Class members and namespace-nested symbols are NOT visible by + * unqualified lookup from a free function in an including TU — they must + * be reached via `Class::method`, `ns::name`, or a working `using` + * declaration. The filter below enforces that contract for header + * propagation: only defs whose nearest enclosing scope is the header's + * `Module` scope are emitted as wildcard-binding names. + * + * ## Why scope-aware and not predicate-on-qualifiedName + * + * A naive `def.qualifiedName.indexOf('.') === -1` check is unreliable + * because `populateClassOwnedMembers` + * (`gitnexus/src/core/ingestion/scope-resolution/scope/walkers.ts`) + * only dot-qualifies `qualifiedName` for `Class` scopes. Namespace-nested + * defs (`namespace ns { void foo(); }`) arrive in `localDefs` with + * `qualifiedName === 'foo'` and `ownerId === undefined`, indistinguishable + * from a top-level free function. The structural truth lives in + * `Scope.ownedDefs`: each scope lists what it structurally owns; the + * Module scope owns only top-level symbols. We look the def up by + * `nodeId` against the scope tree to identify its owning kind. + * + * ## `localDefs` consumer survey (recorded for future maintainers) + * + * Other consumers of `ParsedFile.localDefs` were audited at the time + * this filter was introduced (see PR #1520 / plan + * `docs/plans/2026-05-12-002-fix-cpp-resolver-followups-plan.md`): + * + * - `finalize-orchestrator.ts:113,163` — flattens defs into a workspace + * registry keyed by `ownerId` + `qualifiedName`; class-owned and + * namespace-owned symbols are registered under their owner, not as + * unqualified names. Not a leak surface. + * - `csharp/namespace-siblings.ts:307`, `go/expand-wildcards.ts:86`, + * `php/scope-resolver.ts:141,151`, `c/static-linkage.ts:51` — other + * languages' own wildcard / sibling expansions. Each owns its own + * visibility contract. + * - `receiver-bound-calls.ts:99`, `reconcile-ownership.ts:66,119`, + * `mro.ts:61` — keyed by `ownerId` for member lookup, never used + * as unqualified bindings. + * - `go/interface-impls.ts:40,53`, `go/package-siblings.ts:41` — Go- + * specific, sibling-package scoped. + * + * No other consumer treats `localDefs` as a flat unqualified-binding + * set the way this function did before the fix. If a future consumer + * does, mirror this filter or harden registration so class/namespace + * members never enter `localDefs` unqualified. + */ +export function expandCppWildcardNames( + targetModuleScope: ScopeId, + parsedFiles: readonly ParsedFile[], +): readonly string[] { + const target = parsedFiles.find((p) => p.moduleScope === targetModuleScope); + if (target === undefined) return []; + + // Build nodeId → owning Scope map from the structural scope tree. + // `Scope.ownedDefs` is the canonical source of structural ownership; + // `localDefs` is its flattened union, which is why the original code + // leaked: walking only `localDefs` discards the owning-scope context. + const ownerScopeByNodeId = new Map(); + for (const scope of target.scopes) { + for (const ownedDef of scope.ownedDefs) { + ownerScopeByNodeId.set(ownedDef.nodeId, scope); + } + } + + const seen = new Set(); + const names: string[] = []; + for (const def of target.localDefs) { + // Defense-in-depth: class methods carry a non-undefined ownerId after + // `populateClassOwnedMembers` runs. Skip them outright. + if (def.ownerId !== undefined) continue; + + // Structural visibility check: exclude defs whose owning scope is a + // Namespace or Class — these require qualification (`ns::name`, + // `Class::method`) and are NOT reachable by unqualified lookup in an + // including TU. When the owning scope is unknown we default to + // include (preserves prior behavior for any def whose structural + // ownership wasn't recorded in `Scope.ownedDefs`). + // + // Anonymous namespaces are exempt: their members propagate to the + // enclosing scope of any TU that #includes the declaring file (each + // including TU gets its own internal-linkage copy per ISO C++). + const ownerScope = ownerScopeByNodeId.get(def.nodeId); + const ownerIsAnonymousNamespace = + ownerScope !== undefined && + ownerScope.kind === 'Namespace' && + anonymousNamespaceScopeIds.has(ownerScope.id); + if ( + ownerScope !== undefined && + !ownerIsAnonymousNamespace && + (ownerScope.kind === 'Namespace' || ownerScope.kind === 'Class') + ) { + continue; + } + + const name = simpleName(def); + if (name === '') continue; + // Same exemption for the `isFileLocal` mark — anonymous-namespace + // names are recorded as file-local to suppress the global free-call + // fallback's cross-file leak, but they MUST still propagate through + // wildcard import expansion to including TUs. + if (!ownerIsAnonymousNamespace && isFileLocal(target.filePath, name)) continue; + if (seen.has(name)) continue; + seen.add(name); + names.push(name); + } + return names; +} + +function simpleName(def: SymbolDefinition): string { + return def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/header-scan.ts b/gitnexus/src/core/ingestion/languages/cpp/header-scan.ts new file mode 100644 index 000000000..39ef608b3 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/header-scan.ts @@ -0,0 +1,53 @@ +import { readdirSync, type Dirent } from 'fs'; +import { join, relative } from 'path'; + +/** C++ header extensions to scan for in the workspace. */ +const HEADER_EXTENSIONS = new Set(['.h', '.hpp', '.hxx', '.hh']); + +/** + * Walk `repoPath` recursively and return relative paths of all C++ header files. + * Used by `loadResolutionConfig` so the C++ resolver can resolve `#include` + * targets that live in header files. + * + * Scans for: .h, .hpp, .hxx, .hh + */ +export function scanCppHeaderFiles(repoPath: string): ReadonlySet { + const headers = new Set(); + walk(repoPath, repoPath, headers); + return headers; +} + +function walk(dir: string, root: string, out: Set): void { + let entries: Dirent[]; + try { + entries = readdirSync(dir, { withFileTypes: true, encoding: 'utf8' }); + } catch { + return; // permission denied, etc. + } + for (const entry of entries) { + const name = entry.name; + const full = join(dir, name); + if (entry.isDirectory()) { + if ( + name === 'node_modules' || + name === '.git' || + name === 'vendor' || + name === 'dist' || + name === 'build' || + name === 'out' || + name === 'target' || + name === '_build' || + name === '.next' || + name.startsWith('cmake-build') + ) { + continue; + } + walk(full, root, out); + } else if (entry.isFile()) { + const ext = name.slice(name.lastIndexOf('.')); + if (HEADER_EXTENSIONS.has(ext)) { + out.add(relative(root, full).replace(/\\/g, '/')); + } + } + } +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/import-decomposer.ts b/gitnexus/src/core/ingestion/languages/cpp/import-decomposer.ts new file mode 100644 index 000000000..eb6b252ce --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/import-decomposer.ts @@ -0,0 +1,120 @@ +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js'; + +/** + * Decompose a `preproc_include` node into a CaptureMatch with structured + * import captures. C++ #include maps to a wildcard import (all symbols + * from the header are visible). Identical to C's splitCInclude. + */ +export function splitCppInclude(node: SyntaxNode): CaptureMatch | null { + const pathNode = node.childForFieldName?.('path') ?? null; + if (pathNode === null) { + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child === null) continue; + if (child.type === 'string_literal' || child.type === 'system_lib_string') { + return buildIncludeCapture(node, child); + } + } + return null; + } + return buildIncludeCapture(node, pathNode); +} + +function buildIncludeCapture(node: SyntaxNode, pathNode: SyntaxNode): CaptureMatch { + let raw: string; + if (pathNode.type === 'string_literal') { + const content = pathNode.namedChildren.find((c) => c.type === 'string_content'); + raw = content?.text ?? pathNode.text.replace(/^"|"$/g, ''); + } else { + raw = pathNode.text; + if (raw.startsWith('<') && raw.endsWith('>')) { + raw = raw.slice(1, -1); + } + } + + const isSystem = pathNode.type === 'system_lib_string'; + + const result: Record = { + '@import.statement': nodeToCapture('@import.statement', node), + '@import.kind': syntheticCapture('@import.kind', node, 'wildcard'), + '@import.source': syntheticCapture('@import.source', node, raw), + }; + + if (isSystem) { + result['@import.system'] = syntheticCapture('@import.system', node, 'true'); + } + + return result; +} + +/** + * Decompose a `using_declaration` node into a CaptureMatch. + * + * tree-sitter-cpp produces: + * using namespace std; → using_declaration { "using", "namespace", identifier("std"), ";" } + * using std::vector; → using_declaration { "using", qualified_identifier("std::vector"), ";" } + * + * The first form is a wildcard import (all names from namespace). + * The second form is a named import (single symbol). + */ +export function splitCppUsingDecl(node: SyntaxNode): CaptureMatch | null { + if (node.type !== 'using_declaration') return null; + + // Check for "namespace" keyword among anonymous children + let hasNamespaceKeyword = false; + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null && !child.isNamed && child.text === 'namespace') { + hasNamespaceKeyword = true; + break; + } + } + + if (hasNamespaceKeyword) { + // using namespace ; + // The namespace name can be an identifier or qualified_identifier + let namespaceName: string | null = null; + for (let i = 0; i < node.namedChildCount; i++) { + const child = node.namedChild(i); + if (child === null) continue; + if (child.type === 'identifier' || child.type === 'qualified_identifier') { + namespaceName = child.text; + break; + } + } + if (namespaceName === null) return null; + + return { + '@import.statement': nodeToCapture('@import.statement', node), + '@import.kind': syntheticCapture('@import.kind', node, 'wildcard'), + '@import.source': syntheticCapture('@import.source', node, namespaceName), + '@import.using-namespace': syntheticCapture('@import.using-namespace', node, 'true'), + }; + } + + // using ; (e.g. using std::vector) + let qualId: SyntaxNode | null = null; + for (let i = 0; i < node.namedChildCount; i++) { + const child = node.namedChild(i); + if (child !== null && child.type === 'qualified_identifier') { + qualId = child; + break; + } + } + if (qualId === null) return null; + + // Extract the imported name (last identifier) and source (namespace part) + const nameNode = qualId.childForFieldName?.('name') ?? null; + const scopeNode = qualId.childForFieldName?.('scope') ?? null; + + const importedName = nameNode?.text ?? qualId.text.split('::').pop() ?? ''; + const source = scopeNode?.text ?? qualId.text.replace(new RegExp('::' + importedName + '$'), ''); + + return { + '@import.statement': nodeToCapture('@import.statement', node), + '@import.kind': syntheticCapture('@import.kind', node, 'named'), + '@import.source': syntheticCapture('@import.source', node, source), + '@import.name': syntheticCapture('@import.name', node, importedName), + }; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/import-target.ts b/gitnexus/src/core/ingestion/languages/cpp/import-target.ts new file mode 100644 index 000000000..26e317c6e --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/import-target.ts @@ -0,0 +1,18 @@ +import { resolveCImportTarget } from '../c/import-target.js'; + +/** + * Resolve a C++ #include path to a file in the workspace. + * C++ #include path resolution is identical to C: + * 1. Same-directory sibling (relative lookup) + * 2. Exact match + * 3. Suffix match with depth + lexicographic tiebreak + * + * Re-exports the C implementation since the #include semantics are shared. + */ +export function resolveCppImportTarget( + targetRaw: string, + fromFile: string, + allFilePaths: ReadonlySet, +): string | null { + return resolveCImportTarget(targetRaw, fromFile, allFilePaths); +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/index.ts b/gitnexus/src/core/ingestion/languages/cpp/index.ts new file mode 100644 index 000000000..c4d208d76 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/index.ts @@ -0,0 +1,16 @@ +/** + * C++ scope-resolution hooks (RFC #909 Ring 3). + */ +export { emitCppScopeCaptures } from './captures.js'; +export { interpretCppImport, interpretCppTypeBinding, normalizeCppTypeName } from './interpret.js'; +export { splitCppInclude, splitCppUsingDecl } from './import-decomposer.js'; +export { cppArityCompatibility } from './arity.js'; +export { cppMergeBindings } from './merge-bindings.js'; +export { cppBindingScopeFor, cppImportOwningScope, cppReceiverBinding } from './simple-hooks.js'; +export { resolveCppImportTarget } from './import-target.js'; +export { + markFileLocal, + isFileLocal, + clearFileLocalNames, + expandCppWildcardNames, +} from './file-local-linkage.js'; diff --git a/gitnexus/src/core/ingestion/languages/cpp/inline-namespaces.ts b/gitnexus/src/core/ingestion/languages/cpp/inline-namespaces.ts new file mode 100644 index 000000000..604c50c0b --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/inline-namespaces.ts @@ -0,0 +1,203 @@ +/** + * C++ inline namespace support (U5 of plan 2026-05-13-001). + * + * `inline namespace v1 { void foo(); }` has two ISO C++ semantics that + * GitNexus must model: + * + * 1. **Transitive unqualified visibility.** Names declared in an inline + * namespace are reachable by unqualified lookup from the enclosing + * namespace's scope, as if they were declared directly there. + * `populateCppNonGloballyVisible` (file-local-linkage.ts) treats + * inline-namespace members as globally visible for cross-file + * unqualified lookup. + * + * 2. **Transitive qualified visibility.** `outer::foo()` resolves to + * `outer::v1::foo()` when `v1` is inline. The qualified-namespace + * receiver resolver (`resolveCppQualifiedNamespaceMember`) walks + * inline-namespace children transitively when collecting candidates. + * + * State lifecycle: capture-time `markCppInlineNamespaceRange` records each + * inline namespace's source range; `populateCppInlineNamespaceScopes` + * resolves ranges to `ScopeId`s during `populateOwners`. Cleared via + * `clearCppInlineNamespaces`, called from `clearFileLocalNames`. + * + * STL idiom this enables: `std::__1::vector` (libc++) and `std::__cxx11` + * (libstdc++) are inline namespaces of `std`. With this support, + * `std::vector` qualified calls resolve to the inline-namespace + * declaration transparently. + */ + +import type { ParsedFile, ScopeId, SymbolDefinition } from 'gitnexus-shared'; +import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; +import { + isOverloadAmbiguousAfterNormalization, + narrowOverloadCandidates, +} from '../../scope-resolution/passes/overload-narrowing.js'; + +interface RangeKey { + readonly startLine: number; + readonly startCol: number; + readonly endLine: number; + readonly endCol: number; +} + +const inlineNamespaceRangesByFile = new Map>(); +const inlineNamespaceScopeIds = new Set(); + +function rangeKey(r: RangeKey): string { + return `${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`; +} + +/** Capture-time: record a namespace_definition's range as inline. + * Called from `emitCppScopeCaptures` when the tree-sitter AST shows an + * `inline` keyword child on `namespace_definition`. */ +export function markCppInlineNamespaceRange(filePath: string, range: RangeKey): void { + let set = inlineNamespaceRangesByFile.get(filePath); + if (set === undefined) { + set = new Set(); + inlineNamespaceRangesByFile.set(filePath, set); + } + set.add(rangeKey(range)); +} + +/** Clear all inline-namespace state. Called from `clearFileLocalNames`. */ +export function clearCppInlineNamespaces(): void { + inlineNamespaceRangesByFile.clear(); + inlineNamespaceScopeIds.clear(); +} + +/** Resolve captured ranges to actual ScopeIds by matching scope ranges + * against the inline-namespace ranges recorded for this file. Run from + * the cpp resolver's `populateOwners` hook so the per-pipeline Set is + * populated before any resolution pass consults it. */ +export function populateCppInlineNamespaceScopes(parsed: ParsedFile): void { + const ranges = inlineNamespaceRangesByFile.get(parsed.filePath); + if (ranges === undefined || ranges.size === 0) return; + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + if (ranges.has(rangeKey(scope.range))) { + inlineNamespaceScopeIds.add(scope.id); + } + } +} + +/** Predicate consumed by `populateCppNonGloballyVisible` to exempt + * inline-namespace members from cross-file unqualified-lookup + * exclusion (they remain reachable as if declared at the enclosing + * namespace's level). */ +export function isCppInlineNamespaceScope(scopeId: ScopeId): boolean { + return inlineNamespaceScopeIds.has(scopeId); +} + +/** + * Walk every parsed file looking for a Namespace scope whose qualified + * name matches `receiverName`, collect its callable ownedDefs matching + * `memberName`, transitively descending into any inline-namespace + * children (since they're members of the enclosing namespace under ISO + * C++). + * + * Returns the most specific (innermost) match — for `outer::foo()` + * where `inline namespace v1` declares `foo`, returns `v1::foo`. When + * multiple inline-namespace children declare the same name, ISO C++ + * leaves the call ambiguous; returns `'ambiguous'` so the caller + * suppresses edge emission rather than picking arbitrarily (#1564). + */ +export function resolveCppQualifiedNamespaceMember( + receiverName: string, + memberName: string, + parsedFiles: readonly ParsedFile[], + _scopes: ScopeResolutionIndexes, +): SymbolDefinition | 'ambiguous' | undefined { + const allHits: SymbolDefinition[] = []; + const seenNodeId = new Set(); + for (const parsed of parsedFiles) { + const scopesById = new Map(); + for (const sc of parsed.scopes) scopesById.set(sc.id, sc); + for (const scope of parsed.scopes) { + if (scope.kind !== 'Namespace') continue; + const nsDef = findNamespaceDefInScope(scope); + if (nsDef === undefined) continue; + const nsName = nsDef.qualifiedName?.split('.').pop() ?? nsDef.qualifiedName ?? ''; + if (nsName !== receiverName) continue; + // Found a matching namespace scope in this file. Collect ALL + // members transitively through any inline-namespace children. + const hits = findMemberInNamespaceTransitive(scope, scopesById, memberName); + for (const hit of hits) { + if (seenNodeId.has(hit.nodeId)) continue; + seenNodeId.add(hit.nodeId); + allHits.push(hit); + } + } + } + if (allHits.length === 0) return undefined; + if (allHits.length === 1) return allHits[0]; + + // Multi-candidate: the `resolveQualifiedReceiverMember` hook has no + // access to call-site arity or argument types, so + // `narrowOverloadCandidates` cannot actually narrow here — the call + // with `(allHits, undefined, undefined)` is effectively a pass-through. + // We retain it so that `isOverloadAmbiguousAfterNormalization` can + // still detect int/long-style normalization collisions on this path, + // but for any multi-hit case where candidates have genuinely distinct + // signatures (e.g. `foo(int)` vs `foo(double)` in different inline + // children), we conservatively suppress rather than pick arbitrarily. + // A future enhancement could thread call-site argument info through + // the `resolveQualifiedReceiverMember` contract to enable real + // narrowing here. + const narrowed = narrowOverloadCandidates(allHits, undefined, undefined); + if (narrowed.length === 1) return narrowed[0]; + if (narrowed.length === 0) return undefined; + if (isOverloadAmbiguousAfterNormalization(narrowed, undefined)) return 'ambiguous'; + // Multiple surviving candidates (distinct signatures) — conservative + // suppress because we lack call-site info to disambiguate. + return 'ambiguous'; +} + +/** Recursively search a namespace scope and any inline-namespace + * descendants for callable defs with the given simple name. Non-inline + * nested namespaces are NOT traversed — they require explicit + * qualification (`outer::nested::foo`). Returns ALL matches so the + * caller can detect same-name ambiguity across inline children (#1564). */ +function findMemberInNamespaceTransitive( + scope: { + readonly id: ScopeId; + readonly ownedDefs: readonly SymbolDefinition[]; + readonly parent: ScopeId | null; + }, + scopesById: ReadonlyMap< + ScopeId, + { + readonly id: ScopeId; + readonly kind: string; + readonly parent: ScopeId | null; + readonly ownedDefs: readonly SymbolDefinition[]; + } + >, + memberName: string, +): SymbolDefinition[] { + const results: SymbolDefinition[] = []; + // Check this scope's own ownedDefs first. + for (const def of scope.ownedDefs) { + if (def.type !== 'Function' && def.type !== 'Method' && def.type !== 'Constructor') continue; + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (simple === memberName) results.push(def); + } + // Descend into inline-namespace children. + for (const childScope of scopesById.values()) { + if (childScope.parent !== scope.id) continue; + if (childScope.kind !== 'Namespace') continue; + if (!inlineNamespaceScopeIds.has(childScope.id)) continue; + const childHits = findMemberInNamespaceTransitive(childScope, scopesById, memberName); + for (const hit of childHits) results.push(hit); + } + return results; +} + +function findNamespaceDefInScope(scope: { + readonly ownedDefs: readonly SymbolDefinition[]; +}): SymbolDefinition | undefined { + for (const def of scope.ownedDefs) { + if (def.type === 'Namespace') return def; + } + return undefined; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/interpret.ts b/gitnexus/src/core/ingestion/languages/cpp/interpret.ts new file mode 100644 index 000000000..b330a3fc0 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/interpret.ts @@ -0,0 +1,110 @@ +import type { CaptureMatch, ParsedImport, ParsedTypeBinding, TypeRef } from 'gitnexus-shared'; + +/** + * Interpret a C++ import capture into a ParsedImport. + * + * C++ has three import forms: + * 1. #include "file.h" → wildcard import (all symbols from header) + * 2. using namespace X; → wildcard import (all symbols from namespace X) + * 3. using X::name; → named import (single symbol from namespace X) + * + * System headers (#include <...>) are not resolved to local files. + */ +export function interpretCppImport(captures: CaptureMatch): ParsedImport | null { + const source = captures['@import.source']?.text; + if (source === undefined) return null; + + // System headers are not resolved to local files + if (captures['@import.system'] !== undefined) return null; + + const kind = captures['@import.kind']?.text; + + if (kind === 'named') { + // using X::name — named import + const importedName = captures['@import.name']?.text; + if (importedName === undefined) return null; + return { kind: 'named', targetRaw: source, localName: importedName, importedName }; + } + + // #include or using namespace — wildcard import + return { kind: 'wildcard', targetRaw: source }; +} + +/** + * Interpret a C++ type-binding capture into a ParsedTypeBinding. + * + * Source classification (strongest → weakest): + * - `'parameter-annotation'` — function parameter type + * - `'annotation'` — explicit type declaration (`User user;`) + * - `'assignment-inferred'` — typed init (`User user = ...`) + * - `'constructor'` — constructor call (`auto u = User(...)` / `User{}`) + * - `'return'` — function return type + * - `'field'` — class field type + * - `'alias'` — `auto x = existingVar` + */ +export function interpretCppTypeBinding(captures: CaptureMatch): ParsedTypeBinding | null { + const name = captures['@type-binding.name']?.text; + const type = captures['@type-binding.type']?.text; + if (name === undefined || type === undefined) return null; + + let source: TypeRef['source'] = 'annotation'; + + if (captures['@type-binding.parameter'] !== undefined) { + source = 'parameter-annotation'; + } else if (captures['@type-binding.constructor'] !== undefined) { + source = 'constructor-inferred'; + } else if (captures['@type-binding.return'] !== undefined) { + source = 'return-annotation'; + } else if (captures['@type-binding.field'] !== undefined) { + // Field types are structurally equivalent to annotations — the type + // is explicitly written, not inferred. + source = 'annotation'; + } else if (captures['@type-binding.member-access'] !== undefined) { + // auto addr = user.address — the type is inferred from the member access. + // Synthesize a dotted rawName ("receiver.field") so compound-receiver + // can resolve the chain: look up receiver's class, then field's type. + const receiver = captures['@type-binding.member-access-receiver']?.text; + if (receiver !== undefined) { + return { boundName: name, rawTypeName: `${receiver}.${type}`, source: 'assignment-inferred' }; + } + source = 'assignment-inferred'; + } else if (captures['@type-binding.alias'] !== undefined) { + // auto alias = existingVar — the type is inferred from the RHS variable. + source = 'assignment-inferred'; + } else if (captures['@type-binding.assignment'] !== undefined) { + source = 'assignment-inferred'; + } else if (captures['@type-binding.annotation'] !== undefined) { + source = 'annotation'; + } + + return { boundName: name, rawTypeName: normalizeCppTypeName(type), source }; +} + +/** + * Normalize a C++ type name: strip pointer/array/reference syntax, + * qualifiers, while preserving template arguments for specialization-aware + * receiver binding (`List` vs `List`). + * + * Keeping template arguments here allows receiver-bound fallback to match + * specialization-specific class defs first; non-template behavior is preserved + * by base-name fallback in resolveClassBindingForName. + */ +export function normalizeCppTypeName(text: string): string { + let t = text.trim(); + // Strip const, volatile, restrict, static, extern, inline, mutable, constexpr + t = t + .replace(/\b(const|volatile|restrict|static|extern|inline|mutable|constexpr|consteval)\b/g, '') + .trim(); + // Strip pointer stars + while (t.endsWith('*')) t = t.slice(0, -1).trim(); + while (t.startsWith('*')) t = t.slice(1).trim(); + // Strip reference markers + while (t.endsWith('&')) t = t.slice(0, -1).trim(); + // Strip array brackets + t = t.replace(/\[.*?\]/g, '').trim(); + // Strip struct/union/enum/class prefixes + t = t.replace(/^(struct|union|enum|class)\s+/, ''); + // Strip leading :: (global namespace qualifier) + t = t.replace(/^::/, ''); + return t; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/merge-bindings.ts b/gitnexus/src/core/ingestion/languages/cpp/merge-bindings.ts new file mode 100644 index 000000000..6409cef46 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/merge-bindings.ts @@ -0,0 +1,38 @@ +import type { BindingRef } from 'gitnexus-shared'; + +const TIER: Record = { + local: 0, + namespace: 1, + import: 2, + reexport: 3, + wildcard: 4, +}; + +/** + * C++ merge bindings: first-wins by tier. + * + * C++ tier precedence: + * local(0) > namespace(1) > import(2) > reexport(3) > wildcard(4) + * + * Unlike C (no namespaces), C++ uses the `namespace` tier for symbols + * brought in via `using namespace X;` that are then locally referenced. + * The tier ordering ensures local definitions shadow namespace imports, + * which in turn shadow wildcard #include imports. + */ +export function cppMergeBindings( + existing: readonly BindingRef[], + incoming: readonly BindingRef[], + _scopeId: string, +): BindingRef[] { + const seen = new Set(); + return [...existing, ...incoming] + .sort( + (a, b) => + (TIER[a.origin] ?? 99) - (TIER[b.origin] ?? 99) || a.def.nodeId.localeCompare(b.def.nodeId), + ) + .filter((binding) => { + if (seen.has(binding.def.nodeId)) return false; + seen.add(binding.def.nodeId); + return true; + }); +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/query.ts b/gitnexus/src/core/ingestion/languages/cpp/query.ts new file mode 100644 index 000000000..70d544e3d --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/query.ts @@ -0,0 +1,512 @@ +import Parser from 'tree-sitter'; +import CPP from 'tree-sitter-cpp'; + +const CPP_SCOPE_QUERY = ` +;; ─── Scopes ────────────────────────────────────────────────────────── +(translation_unit) @scope.module +(namespace_definition) @scope.namespace +(class_specifier) @scope.class +(struct_specifier) @scope.class +(function_definition) @scope.function +(lambda_expression) @scope.function +(compound_statement) @scope.block +(if_statement) @scope.block +(for_statement) @scope.block +(for_range_loop) @scope.block +(while_statement) @scope.block +(do_statement) @scope.block +(switch_statement) @scope.block +(case_statement) @scope.block +(try_statement) @scope.block +(catch_clause) @scope.block + +;; ─── Declarations — namespace ──────────────────────────────────────── +(namespace_definition + name: (namespace_identifier) @declaration.name) @declaration.namespace + +;; Anonymous namespace (no name child) — captured as scope only, names +;; inside are marked file-local by captures.ts. + +;; ─── Declarations — class / struct (named) ─────────────────────────── +(class_specifier + name: (type_identifier) @declaration.name + body: (field_declaration_list)) @declaration.class + +(class_specifier + name: (template_type + (type_identifier) @declaration.name + (template_argument_list) @declaration.template-arguments) + body: (field_declaration_list)) @declaration.class + +(struct_specifier + name: (type_identifier) @declaration.name + body: (field_declaration_list)) @declaration.struct + +(struct_specifier + name: (template_type + (type_identifier) @declaration.name + (template_argument_list) @declaration.template-arguments) + body: (field_declaration_list)) @declaration.struct + +;; ─── Declarations — class / struct inside template_declaration ─────── +(template_declaration + (class_specifier + name: (type_identifier) @declaration.name + body: (field_declaration_list)) @declaration.class) + +(template_declaration + (class_specifier + name: (template_type + (type_identifier) @declaration.name + (template_argument_list) @declaration.template-arguments) + body: (field_declaration_list)) @declaration.class) + +(template_declaration + (struct_specifier + name: (type_identifier) @declaration.name + body: (field_declaration_list)) @declaration.struct) + +(template_declaration + (struct_specifier + name: (template_type + (type_identifier) @declaration.name + (template_argument_list) @declaration.template-arguments) + body: (field_declaration_list)) @declaration.struct) + +;; ─── Declarations — enum ───────────────────────────────────────────── +(enum_specifier + name: (type_identifier) @declaration.name) @declaration.enum + +;; ─── Declarations — enum constants ─────────────────────────────────── +(enumerator + name: (identifier) @declaration.name) @declaration.const + +;; ─── Declarations — function definition (plain identifier) ────────── +(function_definition + declarator: (function_declarator + declarator: (identifier) @declaration.name)) @declaration.function + +;; ─── Declarations — function definition with pointer return ───────── +(function_definition + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (identifier) @declaration.name))) @declaration.function + +;; ─── Declarations — out-of-class method (qualified_identifier) ────── +(function_definition + declarator: (function_declarator + declarator: (qualified_identifier + name: (identifier) @declaration.name))) @declaration.method + +;; ─── Declarations — out-of-class method with pointer return ───────── +(function_definition + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (qualified_identifier + name: (identifier) @declaration.name)))) @declaration.method + +;; ─── Declarations — out-of-class method (destructor_name) ─────────── +(function_definition + declarator: (function_declarator + declarator: (qualified_identifier + name: (destructor_name) @declaration.name))) @declaration.method + +;; ─── Declarations — template function definition ──────────────────── +(template_declaration + (function_definition + declarator: (function_declarator + declarator: (identifier) @declaration.name)) @declaration.function) + +;; ─── Declarations — template method (qualified) ───────────────────── +(template_declaration + (function_definition + declarator: (function_declarator + declarator: (qualified_identifier + name: (identifier) @declaration.name))) @declaration.method) + +;; ─── Declarations — inline method in class body (field_identifier) ── +;; tree-sitter-cpp uses field_identifier for names inside class bodies +(function_definition + declarator: (function_declarator + declarator: (field_identifier) @declaration.name)) @declaration.method + +;; ─── Declarations — inline method with pointer return (field_identifier) ── +;; Covers: User* lookup(int id) { ... } inside a class body +;; AST: function_definition > pointer_declarator > function_declarator > field_identifier +(function_definition + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (field_identifier) @declaration.name))) @declaration.method + +;; ─── Declarations — inline method with reference return (field_identifier) ── +;; Covers: User& getRef() { ... } inside a class body +(function_definition + declarator: (reference_declarator + (function_declarator + declarator: (field_identifier) @declaration.name))) @declaration.method + +;; ─── Declarations — function prototype (forward declaration) ──────── +(declaration + declarator: (function_declarator + declarator: (identifier) @declaration.name)) @declaration.function + +;; ─── Declarations — function prototype with pointer return ────────── +(declaration + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (identifier) @declaration.name))) @declaration.function + +;; ─── Declarations — typedef ───────────────────────────────────────── +(type_definition + declarator: (type_identifier) @declaration.name) @declaration.typedef + +;; ─── Declarations — type alias (using Name = Type) ────────────────── +(alias_declaration + name: (type_identifier) @declaration.name) @declaration.typedef + +;; ─── Declarations — method prototype in class body (forward decl) ──── +;; Covers: class User { void save(); std::string getName(); }; +;; AST: field_declaration > function_declarator > field_identifier +(field_declaration + declarator: (function_declarator + declarator: (field_identifier) @declaration.name)) @declaration.method + +;; Method prototype with pointer return: User* lookup(int id); +(field_declaration + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (field_identifier) @declaration.name))) @declaration.method + +;; Method prototype with reference return: User& getRef(); +(field_declaration + declarator: (reference_declarator + (function_declarator + declarator: (field_identifier) @declaration.name))) @declaration.method + +;; ─── Declarations — fields ────────────────────────────────────────── +(field_declaration + declarator: (field_identifier) @declaration.name) @declaration.field + +;; Declarations — fields (pointer) +(field_declaration + declarator: (pointer_declarator + declarator: (field_identifier) @declaration.name)) @declaration.field + +;; Declarations — fields (reference) +(field_declaration + declarator: (reference_declarator + (field_identifier) @declaration.name)) @declaration.field + +;; ─── Declarations — variables (with initializer) ──────────────────── +(declaration + declarator: (init_declarator + declarator: (identifier) @declaration.name)) @declaration.variable + +;; ─── Declarations — macro definitions ─────────────────────────────── +(preproc_def + name: (identifier) @declaration.name) @declaration.macro + +(preproc_function_def + name: (identifier) @declaration.name) @declaration.macro + +;; ─── Imports — #include ───────────────────────────────────────────── +(preproc_include) @import.statement + +;; ─── Imports — using declaration ───────────────────────────────────── +;; Both "using namespace std;" and "using std::vector;" are +;; using_declaration nodes in tree-sitter-cpp. The captures.ts +;; differentiates between them by checking for a "namespace" anonymous +;; child token. +(using_declaration) @import.using-decl + +;; ─── Type bindings — parameter annotations ────────────────────────── +(parameter_declaration + type: (_) @type-binding.type + declarator: (identifier) @type-binding.name) @type-binding.parameter + +;; Type bindings — reference parameter (const std::string& name) +(parameter_declaration + type: (_) @type-binding.type + declarator: (reference_declarator + (identifier) @type-binding.name)) @type-binding.parameter + +;; Type bindings — pointer parameter (User* ptr) +(parameter_declaration + type: (_) @type-binding.type + declarator: (pointer_declarator + declarator: (identifier) @type-binding.name)) @type-binding.parameter + +;; ─── Type bindings — variable with type (init_declarator) ─────────── +;; Covers: User user("alice"), User user = ..., int x = 0 +(declaration + type: (_) @type-binding.type + declarator: (init_declarator + declarator: (identifier) @type-binding.name)) @type-binding.assignment + +;; ─── Type bindings — plain declaration (no initializer) ───────────── +;; Covers: User user; +(declaration + type: (type_identifier) @type-binding.type + declarator: (identifier) @type-binding.name) @type-binding.annotation + +;; Covers: List users; +(declaration + type: (template_type) @type-binding.type + declarator: (identifier) @type-binding.name) @type-binding.annotation + +;; ─── Type bindings — pointer variable declaration ─────────────────── +;; Covers: User* ptr = new User() +(declaration + type: (type_identifier) @type-binding.type + declarator: (init_declarator + declarator: (pointer_declarator + declarator: (identifier) @type-binding.name))) @type-binding.annotation + +;; ─── Type bindings — auto + constructor call ──────────────────────── +;; Covers: auto user = User("alice") +;; AST: declaration > placeholder_type_specifier/auto > init_declarator > identifier + call_expression > identifier +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (call_expression + function: (identifier) @type-binding.type))) @type-binding.constructor + +;; ─── Type bindings — auto + brace-init (compound_literal_expression) ─ +;; Covers: auto user = User{}, auto user = User{args} +;; AST: declaration > placeholder_type_specifier/auto > init_declarator > identifier + compound_literal_expression > type_identifier +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (compound_literal_expression + type: (type_identifier) @type-binding.type))) @type-binding.constructor + +;; ─── Type bindings — auto + scoped brace-init (qualified) ─────────── +;; Covers: auto client = ns::HttpClient{} +;; AST: compound_literal_expression > qualified_identifier > type_identifier +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (compound_literal_expression + type: (qualified_identifier + name: (type_identifier) @type-binding.type)))) @type-binding.constructor + +;; ─── Type bindings — auto + new expression ────────────────────────── +;; Covers: auto user = new User(name) +;; AST: declaration > placeholder_type_specifier/auto > init_declarator > identifier + new_expression > type_identifier +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (new_expression + type: (type_identifier) @type-binding.type))) @type-binding.constructor + +;; ─── Type bindings — auto + qualified template factory (std::make_shared()) ─ +;; AST: declaration(1 > placeholder_type_specifier(2)2 > init_declarator(3 > +;; identifier(4)4 > call_expression(5 > qualified_identifier(6 > +;; template_function(7 > template_argument_list(8 > type_descriptor(9 > +;; type_identifier(10)10 )9 )8 )7 )6 )5 )3 )1 +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (call_expression + function: (qualified_identifier + name: (template_function + arguments: (template_argument_list + (type_descriptor + type: (type_identifier) @type-binding.type))))))) @type-binding.constructor + +;; ─── Type bindings — auto + bare template factory (make_shared()) ─────── +;; Same but without qualified_identifier wrapper — one fewer nesting level +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (call_expression + function: (template_function + arguments: (template_argument_list + (type_descriptor + type: (type_identifier) @type-binding.type)))))) @type-binding.constructor + +;; ─── Type bindings — auto alias assignment ────────────────────────── +;; Covers: auto alias = existingVar (RHS is a plain identifier) +;; AST: declaration > placeholder_type_specifier/auto > init_declarator > identifier + identifier +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (identifier) @type-binding.type)) @type-binding.alias + +;; ─── Type bindings — auto + member access (field_expression) ──────── +;; Covers: auto addr = user.address (RHS is obj.field) +;; AST: declaration > placeholder_type_specifier > init_declarator > identifier + field_expression +;; We capture the field name as @type-binding.type so the compound-receiver +;; chain resolver can look it up on the receiver class scope. +;; The full obj.field text is synthesized by interpret.ts into a dotted +;; rawName for chain-follow resolution. +(declaration + type: (placeholder_type_specifier) + declarator: (init_declarator + declarator: (identifier) @type-binding.name + value: (field_expression + argument: (_) @type-binding.member-access-receiver + field: (field_identifier) @type-binding.type))) @type-binding.member-access + +;; ─── Type bindings — function return type ─────────────────────────── +;; Covers: User getUser() { ... } +;; AST: function_definition > type_identifier + function_declarator > identifier +(function_definition + type: (type_identifier) @type-binding.type + declarator: (function_declarator + declarator: (identifier) @type-binding.name)) @type-binding.return + +;; Return type — out-of-class method: User Class::getUser() { ... } +(function_definition + type: (type_identifier) @type-binding.type + declarator: (function_declarator + declarator: (qualified_identifier + name: (identifier) @type-binding.name))) @type-binding.return + +;; Return type — pointer return: User* getUser() { ... } +(function_definition + type: (type_identifier) @type-binding.type + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (identifier) @type-binding.name))) @type-binding.return + +;; ─── Type bindings — inline method return type ────────────────────── +;; Covers: class Foo { User getUser() { ... } }; +(function_definition + type: (type_identifier) @type-binding.type + declarator: (function_declarator + declarator: (field_identifier) @type-binding.name)) @type-binding.return + +;; Inline method pointer return type: class Foo { User* lookup(int) { ... } }; +(function_definition + type: (type_identifier) @type-binding.type + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (field_identifier) @type-binding.name))) @type-binding.return + +;; ─── Type bindings — method prototype return type in class body ────── +;; Covers: class User { User* lookup(int); std::string getName(); }; +;; AST: field_declaration > function_declarator > field_identifier +(field_declaration + type: (type_identifier) @type-binding.type + declarator: (function_declarator + declarator: (field_identifier) @type-binding.name)) @type-binding.return + +;; Method prototype pointer return type: User* lookup(int id); +(field_declaration + type: (type_identifier) @type-binding.type + declarator: (pointer_declarator + declarator: (function_declarator + declarator: (field_identifier) @type-binding.name))) @type-binding.return + +;; ─── Type bindings — field type declarations (class members) ──────── +;; Covers: class User { Address address; }; +(field_declaration + type: (type_identifier) @type-binding.type + declarator: (field_identifier) @type-binding.name) @type-binding.field + +;; Field pointer type: Address* address; +(field_declaration + type: (type_identifier) @type-binding.type + declarator: (pointer_declarator + declarator: (field_identifier) @type-binding.name)) @type-binding.field + +;; Field reference type: Address& address; +(field_declaration + type: (type_identifier) @type-binding.type + declarator: (reference_declarator + (field_identifier) @type-binding.name)) @type-binding.field + +;; ─── References — constructor calls (new Foo()) ───────────────────── +(new_expression + type: (type_identifier) @reference.name) @reference.call.constructor + +;; Constructor call with qualified type: new ns::Foo() +(new_expression + type: (qualified_identifier + name: (type_identifier) @reference.name)) @reference.call.constructor + +;; ─── References — free calls ──────────────────────────────────────── +(call_expression + function: (identifier) @reference.name) @reference.call.free + +;; ─── References — qualified calls (Namespace func or Class method) ─── +;; Capture the LHS of scope-resolution as the explicit receiver so +;; qualified static member calls route through receiver-bound-calls +;; Case 2 (class-name receiver) path. Without the receiver capture, +;; qualified calls have no explicit receiver and class methods cannot +;; resolve through receiver-bound paths. +(call_expression + function: (qualified_identifier + scope: (_) @reference.receiver + name: (identifier) @reference.name)) @reference.call.qualified + +;; Nested qualified receiver: outer::v1::Base::f() +;; tree-sitter-cpp nests this as qualified_identifier(name: +;; qualified_identifier(scope: qualified_identifier(...), name: identifier)). +;; Capturing the innermost receiver still gives isSuperReceiverInContext +;; enough text to strip qualifiers/template args down to Base. +(call_expression + function: (qualified_identifier + name: (qualified_identifier + scope: (_) @reference.receiver + name: (identifier) @reference.name))) @reference.call.qualified + +;; Double-nested qualified receiver: outer::v1::Base::f() +(call_expression + function: (qualified_identifier + name: (qualified_identifier + name: (qualified_identifier + scope: (_) @reference.receiver + name: (identifier) @reference.name)))) @reference.call.qualified + +;; ─── References — member calls (obj.method() / ptr->method()) ─────── +(call_expression + function: (field_expression + argument: (_) @reference.receiver + field: (field_identifier) @reference.name)) @reference.call.member + +;; ─── References — template calls (func()) ──────────────────────── +(call_expression + function: (template_function + name: (identifier) @reference.name)) @reference.call.free + +;; Note: Ns::func() is parsed as qualified_identifier by tree-sitter-cpp, +;; already captured by the qualified calls pattern above. + +;; ─── References — field reads ─────────────────────────────────────── +(field_expression + argument: (_) @reference.receiver + field: (field_identifier) @reference.name) @reference.read + +;; ─── References — field writes (assignment) ───────────────────────── +(assignment_expression + left: (field_expression + argument: (_) @reference.receiver + field: (field_identifier) @reference.name)) @reference.write +`; + +let _parser: Parser | null = null; +let _query: Parser.Query | null = null; + +export function getCppParser(): Parser { + if (_parser === null) { + _parser = new Parser(); + _parser.setLanguage(CPP as Parameters[0]); + } + return _parser; +} + +export function getCppScopeQuery(): Parser.Query { + if (_query === null) { + _query = new Parser.Query(CPP as Parameters[0], CPP_SCOPE_QUERY); + } + return _query; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/range-bindings.ts b/gitnexus/src/core/ingestion/languages/cpp/range-bindings.ts new file mode 100644 index 000000000..204d1ab21 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/range-bindings.ts @@ -0,0 +1,255 @@ +import type { ParsedFile, Scope, TypeRef } from 'gitnexus-shared'; +import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; +import { getCppParser } from './query.js'; +import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; + +/** + * Populate range-for loop variable type bindings for C++. + * + * Handles three patterns: + * 1. `for (auto& user : users)` — simple range-for + * 2. `for (auto& [key, user] : userMap)` — structured binding + * 3. `for (auto& user : *usersPtr)` — dereference range-for + * + * Strategy: look up the range source variable's type in scope + * typeBindings, extract the last template argument as the element + * type, and inject a typeBinding for the loop variable. + */ +export function populateCppRangeBindings( + parsedFiles: readonly ParsedFile[], + _indexes: ScopeResolutionIndexes, + ctx: { + readonly fileContents: ReadonlyMap; + readonly treeCache?: { get(filePath: string): unknown }; + }, +): void { + const parser = getCppParser(); + + for (const parsed of parsedFiles) { + const sourceText = ctx.fileContents.get(parsed.filePath); + if (sourceText === undefined) continue; + + const cachedTree = ctx.treeCache?.get(parsed.filePath); + const tree = + (cachedTree as ReturnType | undefined) ?? + parseSourceSafe(parser, sourceText, undefined, { + bufferSize: getTreeSitterBufferSize(sourceText), + }); + + const moduleScope = parsed.scopes.find((s) => s.kind === 'Module'); + if (moduleScope === undefined) continue; + + const scopeMap = new Map(parsed.scopes.map((s) => [s.id, s])); + + // Build a map from parameter name → AST parameter_declaration node + // so we can extract the un-normalized template type from the AST. + const paramTypeMap = buildParamTemplateMap(tree.rootNode); + + for (const rangeNode of tree.rootNode.descendantsOfType('for_range_loop')) { + // Get the declarator (loop variable) + const declarator = rangeNode.childForFieldName('declarator'); + if (declarator === null) continue; + + // Get the range source expression (right side of ':') + const right = rangeNode.childForFieldName('right'); + if (right === null) continue; + + // Determine the loop variable name(s) and whether this is a structured binding + const varNames = extractLoopVarNames(declarator); + if (varNames.length === 0) continue; + + // Determine the range source variable name (handle dereference) + const sourceVarName = extractSourceVarName(right); + if (sourceVarName === null) continue; + + // Look up the source variable's full template type from the AST + // (scope typeBindings have been normalized and lost template params) + const fullType = paramTypeMap.get(sourceVarName); + if (fullType === undefined) continue; + + // Extract element type from the container type + const elementType = extractCppElementType(fullType); + if (elementType === null) continue; + + // Find the enclosing function scope + const functionScope = findEnclosingFunctionScope(rangeNode, scopeMap); + const targetScope = functionScope ?? moduleScope; + const mutable = targetScope.typeBindings as Map; + + // For structured binding [key, user], bind the last identifier to the element type + // For simple range-for, bind the single variable + const bindVar = varNames[varNames.length - 1]; + mutable.set(bindVar, { + rawName: elementType, + declaredAtScope: targetScope.id, + source: 'annotation', + }); + } + } +} + +/** Minimal tree-sitter node shape needed by range-binding helpers. */ +interface TsNode { + readonly type: string; + readonly text: string; + readonly childCount: number; + child(index: number): TsNode | null; + descendantsOfType(type: string): readonly TsNode[]; + childForFieldName(name: string): TsNode | null; +} + +/** + * Build a map from parameter name → full (un-normalized) type text + * by walking the AST for all `parameter_declaration` nodes. + * + * This bypasses `normalizeCppTypeName` which strips template params, + * giving us the raw `std::vector` text needed for element-type + * extraction. + */ +function buildParamTemplateMap(rootNode: TsNode): Map { + const map = new Map(); + for (const paramNode of rootNode.descendantsOfType('parameter_declaration')) { + const typeNode = paramNode.childForFieldName('type'); + if (typeNode === null) continue; + + // Extract the parameter name from the declarator subtree. + // The declarator may be: identifier, reference_declarator > identifier, + // or pointer_declarator > identifier. + const declNode = paramNode.childForFieldName('declarator'); + if (declNode === null) continue; + + const idents = declNode.descendantsOfType('identifier'); + if (idents.length === 0) continue; + const paramName = idents[idents.length - 1].text; + + // Use the full type node text (preserving template params) + map.set(paramName, typeNode.text); + } + return map; +} + +/** + * Extract loop variable name(s) from the declarator node. + * Handles both simple `identifier` and `structured_binding_declarator`. + */ +function extractLoopVarNames(declarator: TsNode): string[] { + // The declarator is typically reference_declarator or pointer_declarator wrapping + // either an identifier or a structured_binding_declarator. + const structBindings = declarator.descendantsOfType('structured_binding_declarator'); + if (structBindings.length > 0) { + // structured_binding_declarator contains identifiers like [key, user] + const idents = structBindings[0].descendantsOfType('identifier'); + return idents.map((id) => id.text).filter((t) => t !== '_'); + } + + // Simple case: reference_declarator > identifier or just identifier + const idents = declarator.descendantsOfType('identifier'); + if (idents.length > 0) { + return [idents[idents.length - 1].text]; + } + + return []; +} + +/** + * Extract the source variable name from the range expression. + * Handles plain identifiers and dereference expressions (*ptr). + */ +function extractSourceVarName(right: TsNode): string | null { + if (right.type === 'identifier') { + return right.text; + } + if (right.type === 'pointer_expression') { + // *usersPtr → get the argument (usersPtr) + const arg = right.childForFieldName('argument'); + if (arg !== null) return arg.text; + } + return null; +} + +/** + * Extract the element type from a C++ container type string. + * + * Examples: + * - `vector` → `User` + * - `std::vector` → `User` + * - `map` → `User` (last template arg) + * - `map` → `User` + * + * For structured bindings with maps, the last template arg is the value type. + * For vectors/sets, the first (and only) template arg is the element type. + */ +function extractCppElementType(rawType: string): string | null { + // Find the outermost template argument list + const ltIdx = rawType.indexOf('<'); + if (ltIdx === -1) return null; + + // Extract the template argument string (handle nested templates) + let depth = 0; + let lastCommaOrStart = ltIdx + 1; + let lastArg = ''; + + for (let i = ltIdx; i < rawType.length; i++) { + const ch = rawType[i]; + if (ch === '<') { + depth++; + } else if (ch === '>') { + depth--; + if (depth === 0) { + lastArg = rawType.slice(lastCommaOrStart, i).trim(); + break; + } + } else if (ch === ',' && depth === 1) { + lastCommaOrStart = i + 1; + } + } + + if (lastArg === '') return null; + + // Strip pointer/reference qualifiers and const + let elementType = lastArg + .replace(/^const\s+/, '') + .replace(/\s*[*&]+\s*$/, '') + .trim(); + + // Strip namespace prefix (std::string → string) + const lastColon = elementType.lastIndexOf('::'); + if (lastColon !== -1) { + elementType = elementType.slice(lastColon + 2); + } + + return elementType || null; +} + +/** + * Find the enclosing Function scope for a tree-sitter node by + * walking up the AST and matching source positions. + */ +function findEnclosingFunctionScope( + node: unknown, + scopeMap: ReadonlyMap, +): Scope | null { + const tsNode = node as { + readonly parent: unknown; + readonly type: string; + readonly startPosition: { readonly row: number; readonly column: number }; + }; + let current: typeof tsNode | null = tsNode; + while (current !== null) { + if (current.type === 'function_definition') { + for (const scope of scopeMap.values()) { + if ( + scope.kind === 'Function' && + scope.range.startLine === current.startPosition.row && + scope.range.startCol === current.startPosition.column + ) { + return scope; + } + } + break; + } + current = (current.parent as typeof tsNode) ?? null; + } + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/scope-resolver.ts b/gitnexus/src/core/ingestion/languages/cpp/scope-resolver.ts new file mode 100644 index 000000000..52c575cf4 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/scope-resolver.ts @@ -0,0 +1,268 @@ +import type { ParsedFile, SymbolDefinition } from 'gitnexus-shared'; +import { + findClassBindingInScope, + findEnclosingClassDef, +} from '../../scope-resolution/scope/walkers.js'; +import { SupportedLanguages } from 'gitnexus-shared'; +import { buildMro, defaultLinearize } from '../../scope-resolution/passes/mro.js'; +import { populateClassOwnedMembers } from '../../scope-resolution/scope/walkers.js'; +import type { ScopeResolver } from '../../scope-resolution/contract/scope-resolver.js'; +import { cppProvider } from '../c-cpp.js'; +import { cppArityCompatibility } from './arity.js'; +import { cppMergeBindings } from './merge-bindings.js'; +import { resolveCppImportTarget } from './import-target.js'; +import { scanCppHeaderFiles } from './header-scan.js'; +import { + expandCppWildcardNames, + isFileLocal, + clearFileLocalNames, + populateCppAnonymousNamespaceScopes, + populateCppNonGloballyVisible, + isCppDefGloballyVisible, +} from './file-local-linkage.js'; +import { + populateCppDependentBases, + clearCppDependentBases, + isCppDependentBaseMember, +} from './two-phase-lookup.js'; +import { populateCppAssociatedNamespaces, clearCppAdlState, pickCppAdlCandidates } from './adl.js'; +import { + clearCppInlineNamespaces, + populateCppInlineNamespaceScopes, + resolveCppQualifiedNamespaceMember, +} from './inline-namespaces.js'; +import { populateCppRangeBindings } from './range-bindings.js'; + +/** + * C++ `ScopeResolver` registered in `SCOPE_RESOLVERS` and consumed by + * the generic `runScopeResolution` orchestrator (RFC #909 Ring 3). + * + * C++ extends C's scope resolution with: + * - Namespaces (`namespace foo { ... }`) + * - Classes with methods and multiple inheritance + * - `using namespace` (wildcard import from namespace) + * - `using X::name` (named import from namespace) + * - Anonymous namespace (file-local linkage, like C `static`) + * - Default parameters (requiredParameterCount < parameterCount) + * - Overloading (arity-based disambiguation) + * - Templates (V1: generic-ignored, `List` ≡ `List`) + * - Leftmost-base MRO for multiple inheritance + */ +export const cppScopeResolver: ScopeResolver = { + language: SupportedLanguages.CPlusPlus, + languageProvider: cppProvider, + importEdgeReason: 'cpp-scope: include', + + loadResolutionConfig: (repoPath: string) => { + // Clear stale per-pipeline state from any previous invocation. + clearFileLocalNames(); + clearCppDependentBases(); + clearCppAdlState(); + clearCppInlineNamespaces(); + return scanCppHeaderFiles(repoPath); + }, + + resolveImportTarget: (targetRaw, fromFile, allFilePaths, resolutionConfig) => { + // Augment allFilePaths with header files discovered via loadResolutionConfig. + // C++ .h/.hpp/.hxx/.hh files may be classified differently by language + // detection but are importable from .cpp files via #include. + const headerPaths = resolutionConfig as ReadonlySet | undefined; + if (headerPaths !== undefined && headerPaths.size > 0) { + const augmented = new Set(allFilePaths); + for (const h of headerPaths) augmented.add(h); + return resolveCppImportTarget(targetRaw, fromFile, augmented); + } + return resolveCppImportTarget(targetRaw, fromFile, allFilePaths); + }, + + expandsWildcardTo: (targetModuleScope, parsedFiles) => + expandCppWildcardNames(targetModuleScope, parsedFiles), + + mergeBindings: (existing, incoming, scopeId) => cppMergeBindings(existing, incoming, scopeId), + + // Adapter: cppArityCompatibility predates ScopeResolver and uses + // (def, callsite). ScopeResolver contract is (callsite, def). + arityCompatibility: (callsite, def) => cppArityCompatibility(def, callsite), + + buildMro: (graph, parsedFiles, nodeLookup) => + buildMro(graph, parsedFiles, nodeLookup, defaultLinearize), + + populateOwners: (parsed: ParsedFile) => { + populateClassOwnedMembers(parsed); + // Resolve inline- and anonymous-namespace ranges (recorded at capture + // time) to ScopeIds BEFORE `populateCppNonGloballyVisible` runs, so + // both exemptions see the populated Sets. + populateCppInlineNamespaceScopes(parsed); + populateCppAnonymousNamespaceScopes(parsed); + // Track namespace-nested and class-nested defs so the global free-call + // fallback and wildcard expansion can suppress them as unqualified + // cross-file callables. + populateCppNonGloballyVisible(parsed); + // Build the class-def → enclosing-namespace-qualified-name map used + // by ADL (U2 of plan 2026-05-13-001) to identify each argument type's + // associated namespace for Koenig lookup. + populateCppAssociatedNamespaces(parsed); + }, + + // Resolve recorded template-class → dependent-base simple names to + // class nodeIds for two-phase template lookup (U3 of plan + // 2026-05-13-001). Runs AFTER all files have had `populateOwners` + // applied so that cross-file base classes (e.g. Base in base.h, + // Derived in derived.h) are reachable in the workspace index. + populateWorkspaceOwners: (parsedFiles: readonly ParsedFile[]) => { + populateCppDependentBases(parsedFiles); + }, + + // Simple `isSuperReceiver` returns false for C++. Real super + // classification is caller-context-dependent and lives in + // `isSuperReceiverInContext` below — without scope context the + // previous regex `/^[A-Z]\w*::/` misclassified namespace-qualified + // calls (e.g., `Singleton::getInstance()`) as super calls and routed + // them through the wrong resolution branch. + isSuperReceiver: () => false, + + isSuperReceiverInContext: (text, callerScope, scopes) => { + // The receiver text comes from the LHS of `::` in `qualified_identifier` + // (e.g., for `Base::method()`, text is `Base`). Strip template + // arguments (V1: name-only matching, generics ignored) and any leading + // namespace qualifier so the lookup matches the bare class def's + // simple name. `Base::method()` → `Base`; `outer::v1::Base` → + // `Base`. This handles the Phase 5 cross-unit composition where + // qualified base-method calls appear inside template bodies. + let lhs = text; + const sepIdx = lhs.indexOf('::'); + if (sepIdx > 0) lhs = lhs.slice(0, sepIdx).trim(); + // Strip trailing template-argument list (greedy: drop everything from + // the first `<` onward — V1 ignores generics). + const lt = lhs.indexOf('<'); + if (lt > 0) lhs = lhs.slice(0, lt).trim(); + // Strip nested namespace prefix from the receiver text itself (the + // `outer::v1::Base` shape that appears in derived-list `base_class_clause`). + const lastDoubleColon = lhs.lastIndexOf('::'); + if (lastDoubleColon >= 0) lhs = lhs.slice(lastDoubleColon + 2).trim(); + if (lhs.length === 0) return false; + + // Resolve the LHS in the caller's scope chain. Only class-like + // resolutions can be super receivers; Namespace and unresolved + // names are not super calls. + const lhsDef = findClassBindingInScope(callerScope, lhs, scopes); + if (lhsDef === undefined) return false; + + // The caller must have an enclosing class — super calls only make + // sense inside a class body. Free functions can use `ClassName::` + // for namespace-qualified calls but those are not super. + const enclosing = findEnclosingClassDef(callerScope, scopes); + if (enclosing === undefined) return false; + + // `lhsDef` must be in the caller's MRO (i.e., the caller's enclosing + // class derives from it). The class itself counts as its own MRO + // root — `Self::method()` is a qualified self-call, not a super + // call, so exclude the caller's own class. + if (lhsDef.nodeId === enclosing.nodeId) return false; + const mro = scopes.methodDispatch.mroFor(enclosing.nodeId); + return mro.includes(lhsDef.nodeId); + }, + + // C++ is statically typed — disable field fallback heuristic + fieldFallbackOnMethodLookup: false, + // C++ needs return type propagation across #include boundaries + propagatesReturnTypesAcrossImports: true, + // C++ #include brings in all symbols — enable global free call fallback + allowGlobalFreeCallFallback: true, + // Range-for element type inference: for (auto& user : users) → bind user to User + populateRangeBindings: populateCppRangeBindings, + // C++ method return-type bindings need to be visible from module scope + // for cross-file propagation and compound-receiver chain resolution. + // cppBindingScopeFor hoists @type-binding.return to Module scope. + hoistTypeBindingsToModule: true, + // Enable receiver-bound explicit-`this` fallback only for C++. + resolveThisViaEnclosingClass: true, + // The `isFileLocalDef` hook on the global free-call fallback names + // file-local linkage historically, but semantically gates "logically + // invisible cross-file" defs. C++ extends this to also reject class- + // owned methods/fields and namespace-nested symbols — an unqualified + // call from a free function MUST NOT resolve to `User::save` or + // `ns::foo` (Cppreference, "Unqualified name lookup"). Without this + // gate, the global fallback walks every callable in the workspace + // registry and matches any class method or namespace function by + // simple name. + isFileLocalDef: (def: SymbolDefinition) => { + const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName ?? ''; + if (isFileLocal(def.filePath, simple)) return true; + // Class-owned (Method/Field) — `populateClassOwnedMembers` already + // stamps `ownerId`; cheap fast-path before consulting the scope map. + if (def.ownerId !== undefined) return true; + // Namespace-nested defs — require qualification cross-file. Scope- + // walked at `populateOwners` time into a per-file nodeId set. + if (!isCppDefGloballyVisible(def.filePath, def.nodeId)) return true; + return false; + }, + + // C++ two-phase template lookup: inside a class template body, + // unqualified calls MUST NOT bind to members of a dependent base + // class. The standard requires `this->name()` or `Base::name()` + // forms to make the lookup dependent. Without this gate the global + // free-call fallback walks the workspace registry and silently binds + // unqualified calls to dependent-base members, producing CALLS edges + // the compiler would reject. See plan 2026-05-13-001 U3. + isCallableVisibleFromCaller: ({ candidate, callerScope, scopes }) => { + if (callerScope === undefined || scopes === undefined) return true; + // Reject when the candidate is a member of a dependent base of the + // caller's enclosing template class. Otherwise allow. + return !isCppDependentBaseMember(callerScope, candidate, scopes); + }, + + // C++ argument-dependent / Koenig lookup (U2 of plan 2026-05-13-001). + // Contributes candidates from associated namespaces of class-typed + // arguments; caller merges with ordinary unqualified lookup candidates. + // Current boundary: class-typed value/pointer/reference args and template + // specializations with explicit type arguments contribute associated + // namespaces. Function-pointer args and full conversion-ranking remain + // excluded. + resolveAdlCandidates: (site, callerParsed, scopes, parsedFiles) => { + // `using ns::name;` introduces `name` into ordinary unqualified lookup. + // For template-class method bodies, lexical scope walks can miss this + // named-using visibility; recover by resolving the imported namespace + // member directly when the local call name matches a named using import. + const usingNamedHits: SymbolDefinition[] = []; + const seenUsing = new Set(); + for (const imp of callerParsed.parsedImports) { + if (imp.kind !== 'named') continue; + if (imp.localName !== site.name) continue; + const member = resolveCppQualifiedNamespaceMember( + imp.targetRaw, + imp.importedName, + parsedFiles, + scopes, + ); + if (member === undefined || member === 'ambiguous') continue; + if (seenUsing.has(member.nodeId)) continue; + seenUsing.add(member.nodeId); + usingNamedHits.push(member); + } + const adlHits = pickCppAdlCandidates(site, callerParsed, scopes, parsedFiles); + if (usingNamedHits.length === 0) return adlHits; + if (adlHits === undefined || adlHits.length === 0) return usingNamedHits; + const merged: SymbolDefinition[] = []; + const seen = new Set(); + for (const hit of usingNamedHits) { + seen.add(hit.nodeId); + merged.push(hit); + } + for (const hit of adlHits) { + if (seen.has(hit.nodeId)) continue; + seen.add(hit.nodeId); + merged.push(hit); + } + return merged; + }, + + // C++ qualified namespace-member resolution (U5 of plan 2026-05-13-001). + // Handles `outer::foo()` where `outer` is a namespace (not a class). + // Walks each parsed file's namespace scopes by simple name, then + // descends transitively through inline-namespace children when + // searching for the called member. Returns undefined for non-namespace + // receivers so receiver-bound-calls Case 2 still gets a chance. + resolveQualifiedReceiverMember: (receiverName, memberName, _callerScope, scopes, parsedFiles) => + resolveCppQualifiedNamespaceMember(receiverName, memberName, parsedFiles, scopes), +}; diff --git a/gitnexus/src/core/ingestion/languages/cpp/simple-hooks.ts b/gitnexus/src/core/ingestion/languages/cpp/simple-hooks.ts new file mode 100644 index 000000000..63500abd5 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/simple-hooks.ts @@ -0,0 +1,79 @@ +import type { + CaptureMatch, + ParsedImport, + Scope, + ScopeId, + ScopeTree, + TypeRef, +} from 'gitnexus-shared'; + +/** + * C++ binding scope: default auto-hoist (null) for most declarations. + * + * For `for` statement init-scope variables (e.g. `for (int i = 0; ...)`), + * the variable is scoped to the for-block, not the enclosing function. + * The tree-sitter scope query already captures for_statement as @scope.block, + * so tree-sitter's scope nesting handles this automatically — we return null + * to let the default auto-hoist apply. + */ +export function cppBindingScopeFor( + decl: CaptureMatch, + innermost: Scope, + tree: ScopeTree, +): ScopeId | null { + // Hoist return-type bindings to Module scope so: + // 1. propagateImportedReturnTypes can mirror them across files + // 2. compound-receiver can find method return types via hoistTypeBindingsToModule + if (decl['@type-binding.return'] !== undefined) { + let cur: Scope | undefined = innermost; + while (cur !== undefined && cur.kind !== 'Module') { + const parentId: ScopeId | null = cur.parent ?? null; + if (parentId === null) break; + cur = tree.getScope(parentId); + } + if (cur !== undefined && cur.kind === 'Module') return cur.id; + } + return null; // default auto-hoist for other bindings +} + +/** + * C++ import owning scope: default (null). + * #include and using declarations are file-scoped in C++. + */ +export function cppImportOwningScope( + _imp: ParsedImport, + _innermost: Scope, + _tree: ScopeTree, +): ScopeId | null { + return null; +} + +/** + * C++ receiver binding: return `this` TypeRef for methods inside a class. + * + * When a function scope is inside a class scope, the implicit `this` pointer + * refers to the enclosing class. This enables `this->method()` and implicit + * `this` member access resolution. + */ +export function cppReceiverBinding(functionScope: Scope): TypeRef | null { + // Walk up the scope tree to find an enclosing class scope + if (functionScope.parent === null) return null; + + // The scope tree structure nests function scopes inside class scopes. + // The orchestrator provides the function scope; we need to check if + // its parent chain contains a class scope. + // + // However, the ScopeResolver.receiverBinding contract receives only + // the function Scope (not the full ScopeTree), and the Scope type + // includes `parent` (a ScopeId) but not a reference to the parent + // Scope object. + // + // The orchestrator already handles this by looking up the class owner + // via populateOwners. We return null here and let the shared infra + // handle receiver resolution through the class-ownership mechanism. + // + // This is consistent with how C# and Go handle it — the receiver + // binding is established through populateOwners + the MRO chain, + // not through this hook. + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/cpp/two-phase-lookup.ts b/gitnexus/src/core/ingestion/languages/cpp/two-phase-lookup.ts new file mode 100644 index 000000000..8d0050eb1 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/cpp/two-phase-lookup.ts @@ -0,0 +1,205 @@ +/** + * C++ two-phase template lookup support. + * + * Inside a class template body, names from a dependent base class are NOT + * found by ordinary unqualified lookup. The standard requires the + * `this->name` or `Base::name` forms to make the lookup dependent. + * GitNexus's global free-call fallback otherwise binds such names to the + * dependent base's members, producing CALLS edges the compiler would + * reject. + * + * This module records — during `emitCppScopeCaptures` — which template + * class declarations have which dependent base class names (per file). + * `populateCppDependentBases` then resolves those names to class nodeIds + * using a workspace-wide registry, building the per-class set the + * `isCppDependentBaseMember` predicate consumes. + * + * Cross-file resolution: `Base` may be declared in a different header + * than `Derived`. `populateCppDependentBases` therefore runs as a + * workspace-wide pass (`populateWorkspaceOwners` hook) after every file + * has had `populateOwners` applied, so all class defs are reachable. + * + * Namespace disambiguation: when multiple classes share a simple name + * (e.g., `Box` in two namespaces), the resolver prefers the candidate + * whose qualified-name prefix (namespace path) matches the deriving + * class's prefix. If no namespace match is found, a unique simple-name + * match is accepted; ambiguous matches (multiple candidates, no + * namespace winner) are skipped conservatively. + * + * NOTE: module-level state, single-process-single-repo use only. + * `clearFileLocalNames()` clears this state alongside file-local linkage + * (see `file-local-linkage.ts`). + */ + +import type { ParsedFile, ScopeId, SymbolDefinition } from 'gitnexus-shared'; +import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; +import { findEnclosingClassDef } from '../../scope-resolution/scope/walkers.js'; + +/** + * Capture-time record: for each template class declaration in a file, + * the simple names of its dependent base classes. + * + * Key: filePath + * Value: Map> + */ +const dependentBasesByFile = new Map>>(); + +/** + * Post-`populateOwners` resolution: per-class-nodeId, the set of + * dependent-base-class nodeIds. Built by `populateCppDependentBases` + * from `dependentBasesByFile` + the workspace registry. + */ +const dependentBaseNodeIds = new Map>(); + +/** + * Record a dependent-base relationship discovered during scope-capture + * emission. `className` is the simple name of the template class; + * `baseName` is the simple name of the dependent base class. + * + * The capture-time recorder uses simple names because the registry + * resolution that maps names → nodeIds runs later (in + * `populateCppDependentBases`). + */ +export function markCppDependentBase(filePath: string, className: string, baseName: string): void { + let perFile = dependentBasesByFile.get(filePath); + if (perFile === undefined) { + perFile = new Map(); + dependentBasesByFile.set(filePath, perFile); + } + let bases = perFile.get(className); + if (bases === undefined) { + bases = new Set(); + perFile.set(className, bases); + } + bases.add(baseName); +} + +/** Clear two-phase-lookup state. Called from `clearFileLocalNames`. */ +export function clearCppDependentBases(): void { + dependentBasesByFile.clear(); + dependentBaseNodeIds.clear(); +} + +/** + * Resolve recorded dependent-base simple names to class nodeIds using a + * workspace-wide index. Run as `populateWorkspaceOwners` after every + * file has had `populateOwners` applied, so class defs from ALL files + * are reachable. + * + * Disambiguation strategy (multiple classes sharing a simple name): + * 1. Prefer the candidate whose qualified-name namespace prefix matches + * the deriving class's namespace prefix (same-namespace bias). + * 2. Fall back to accepting a unique simple-name match. + * 3. Skip when multiple candidates exist and no namespace match is + * found (conservative: avoids false associations). + */ +export function populateCppDependentBases(parsedFiles: readonly ParsedFile[]): void { + if (dependentBasesByFile.size === 0) return; + + // Build workspace-wide index: simpleName → {nodeId, nsPrefix}[] + // nsPrefix is the dot-joined namespace path (qualifiedName without the + // last segment). Classes at global scope have nsPrefix = ''. + const classesBySimpleName = new Map(); + for (const parsed of parsedFiles) { + for (const def of parsed.localDefs) { + if (def.type !== 'Class' && def.type !== 'Struct' && def.type !== 'Interface') continue; + const qn = def.qualifiedName ?? ''; + const lastDot = qn.lastIndexOf('.'); + const simple = lastDot >= 0 ? qn.slice(lastDot + 1) : qn; + if (simple === '') continue; + const nsPrefix = lastDot >= 0 ? qn.slice(0, lastDot) : ''; + let entries = classesBySimpleName.get(simple); + if (entries === undefined) { + entries = []; + classesBySimpleName.set(simple, entries); + } + entries.push({ nodeId: def.nodeId, nsPrefix }); + } + } + + // Build a filePath → ParsedFile lookup for fast per-file access. + const parsedByFile = new Map(); + for (const parsed of parsedFiles) parsedByFile.set(parsed.filePath, parsed); + + for (const [filePath, perFile] of dependentBasesByFile) { + const parsed = parsedByFile.get(filePath); + if (parsed === undefined) continue; + + // Build a simple-name → {nodeId, nsPrefix} map for THIS file's + // class-like defs so we can identify each template class precisely + // (avoids cross-file name collisions for the deriving class itself). + const localClassByName = new Map(); + for (const def of parsed.localDefs) { + if (def.type !== 'Class' && def.type !== 'Struct' && def.type !== 'Interface') continue; + const qn = def.qualifiedName ?? ''; + const lastDot = qn.lastIndexOf('.'); + const simple = lastDot >= 0 ? qn.slice(lastDot + 1) : qn; + if (simple === '') continue; + const nsPrefix = lastDot >= 0 ? qn.slice(0, lastDot) : ''; + localClassByName.set(simple, { nodeId: def.nodeId, nsPrefix }); + } + + for (const [className, baseNames] of perFile) { + const classEntry = localClassByName.get(className); + if (classEntry === undefined) continue; + + let bases = dependentBaseNodeIds.get(classEntry.nodeId); + if (bases === undefined) { + bases = new Set(); + dependentBaseNodeIds.set(classEntry.nodeId, bases); + } + + for (const baseName of baseNames) { + const candidates = classesBySimpleName.get(baseName); + if (candidates === undefined || candidates.length === 0) continue; + + if (candidates.length === 1) { + // Unique simple-name match — accept regardless of namespace. + bases.add(candidates[0].nodeId); + continue; + } + + // Multiple classes share the same simple name — prefer the one + // whose namespace matches the deriving class's namespace. + // V1: exact dot-prefix match only. Cross-namespace inheritance + // (e.g., `ns::outer::Derived` extending bare `Inner` defined in + // `ns::outer::inner`) and inline-namespace cases are deferred to + // V2; the conservative skip-on-ambiguity below avoids false + // associations in those edge cases. + const nsMatch = candidates.find((c) => c.nsPrefix === classEntry.nsPrefix); + if (nsMatch !== undefined) { + bases.add(nsMatch.nodeId); + } + // else: ambiguous (multiple candidates, no namespace match) → skip. + } + } + } +} + +/** + * Two-phase lookup predicate: is the candidate def a member of a + * dependent base of the caller's enclosing template class? + * + * Used as an additional reject-filter in `pickUniqueGlobalCallable` and + * the receiver-bound member chain walk. ONLY apply for unqualified + * call forms — `this->name` and `Base::name` are dependent lookup + * forms that the standard allows. + * + * Conservative bias: when the caller's enclosing class can't be + * identified, return `false` (let normal resolution proceed). Over- + * rejection is acceptable for the template case because the standard + * itself requires `this->` or qualified forms for dependent base + * access; missing edges here match the compiler's diagnostic shape. + */ +export function isCppDependentBaseMember( + callerScopeId: ScopeId, + candidateDef: SymbolDefinition, + scopes: ScopeResolutionIndexes, +): boolean { + if (candidateDef.ownerId === undefined) return false; + const enclosing = findEnclosingClassDef(callerScopeId, scopes); + if (enclosing === undefined) return false; + const bases = dependentBaseNodeIds.get(enclosing.nodeId); + if (bases === undefined) return false; + return bases.has(candidateDef.ownerId); +} diff --git a/gitnexus/src/core/ingestion/languages/csharp/captures.ts b/gitnexus/src/core/ingestion/languages/csharp/captures.ts index e29552e78..a090b82f8 100644 --- a/gitnexus/src/core/ingestion/languages/csharp/captures.ts +++ b/gitnexus/src/core/ingestion/languages/csharp/captures.ts @@ -24,6 +24,7 @@ import { synthesizeCsharpReceiverBinding } from './receiver-binding.js'; import { getCsharpParser, getCsharpScopeQuery } from './query.js'; import { recordCacheHit, recordCacheMiss } from './cache-stats.js'; import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; /** Declaration anchors that carry function-like arity metadata. */ const FUNCTION_DECL_TAGS = [ @@ -86,7 +87,7 @@ export function emitCsharpScopeCaptures( // the LanguageProvider contract layer; cast here at the use site. let tree = cachedTree as ReturnType['parse']> | undefined; if (tree === undefined) { - tree = getCsharpParser().parse(sourceText, undefined, { + tree = parseSourceSafe(getCsharpParser(), sourceText, undefined, { bufferSize: getTreeSitterBufferSize(sourceText), }); recordCacheMiss(); diff --git a/gitnexus/src/core/ingestion/languages/csharp/namespace-siblings.ts b/gitnexus/src/core/ingestion/languages/csharp/namespace-siblings.ts index 2cd2cf724..b6de589e2 100644 --- a/gitnexus/src/core/ingestion/languages/csharp/namespace-siblings.ts +++ b/gitnexus/src/core/ingestion/languages/csharp/namespace-siblings.ts @@ -36,6 +36,7 @@ import type { BindingRef, ParsedFile, Scope, ScopeId, SymbolDefinition } from 'g import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; import { getCsharpParser } from './query.js'; import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; interface CsharpFileStructure { /** Declared namespace names in file source order. Empty array means @@ -56,7 +57,7 @@ function extractFileStructure(content: string, cachedTree: unknown): CsharpFileS type CsharpTree = ReturnType['parse']>; const tree = (cachedTree as CsharpTree | undefined) ?? - getCsharpParser().parse(content, undefined, { + parseSourceSafe(getCsharpParser(), content, undefined, { bufferSize: getTreeSitterBufferSize(content), }); const namespaces: string[] = []; @@ -359,7 +360,7 @@ export function populateCsharpNamespaceSiblings( const q = def.qualifiedName ?? ''; const key = q.includes('.') ? q.slice(q.lastIndexOf('.') + 1) : q; if (key === '') continue; - const arr = defsByName.get(key) ?? []; + const arr = [...(defsByName.get(key) ?? [])]; arr.push(def); defsByName.set(key, arr); } diff --git a/gitnexus/src/core/ingestion/languages/go/captures.ts b/gitnexus/src/core/ingestion/languages/go/captures.ts index 93fcbc51a..73fa61862 100644 --- a/gitnexus/src/core/ingestion/languages/go/captures.ts +++ b/gitnexus/src/core/ingestion/languages/go/captures.ts @@ -12,6 +12,7 @@ import { splitGoImportStatement } from './import-decomposer.js'; import { synthesizeGoReceiverBinding } from './receiver-binding.js'; import { synthesizeGoTypeBindings } from './type-binding.js'; import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; export function emitGoScopeCaptures( sourceText: string, @@ -20,7 +21,7 @@ export function emitGoScopeCaptures( ): readonly CaptureMatch[] { let tree = cachedTree as ReturnType['parse']> | undefined; if (tree === undefined) { - tree = getGoParser().parse(sourceText, undefined, { + tree = parseSourceSafe(getGoParser(), sourceText, undefined, { bufferSize: getTreeSitterBufferSize(sourceText), }); recordGoCacheMiss(); diff --git a/gitnexus/src/core/ingestion/languages/go/range-binding.ts b/gitnexus/src/core/ingestion/languages/go/range-binding.ts index 14e520c2d..1f06f3373 100644 --- a/gitnexus/src/core/ingestion/languages/go/range-binding.ts +++ b/gitnexus/src/core/ingestion/languages/go/range-binding.ts @@ -2,6 +2,7 @@ import type { ParsedFile, Scope, TypeRef } from 'gitnexus-shared'; import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; import { getGoParser } from './query.js'; import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; export function populateGoRangeBindings( parsedFiles: readonly ParsedFile[], @@ -20,7 +21,7 @@ export function populateGoRangeBindings( const cachedTree = ctx.treeCache?.get(parsed.filePath); const tree = (cachedTree as ReturnType | undefined) ?? - parser.parse(sourceText, undefined, { + parseSourceSafe(parser, sourceText, undefined, { bufferSize: getTreeSitterBufferSize(sourceText), }); const moduleScope = parsed.scopes.find((s) => s.kind === 'Module'); diff --git a/gitnexus/src/core/ingestion/languages/java.ts b/gitnexus/src/core/ingestion/languages/java.ts index 96139ccda..c70eacb10 100644 --- a/gitnexus/src/core/ingestion/languages/java.ts +++ b/gitnexus/src/core/ingestion/languages/java.ts @@ -27,6 +27,17 @@ import { javaMethodConfig } from '../method-extractors/configs/jvm.js'; import { createVariableExtractor } from '../variable-extractors/generic.js'; import { javaVariableConfig } from '../variable-extractors/configs/jvm.js'; import { createHeritageExtractor } from '../heritage-extractors/generic.js'; +import { + emitJavaScopeCaptures, + interpretJavaImport, + interpretJavaTypeBinding, + javaBindingScopeFor, + javaImportOwningScope, + javaMergeBindings, + javaReceiverBinding, + javaArityCompatibility, + resolveJavaImportTarget, +} from './java/index.js'; export const javaProvider = defineLanguage({ id: SupportedLanguages.Java, @@ -65,4 +76,15 @@ export const javaProvider = defineLanguage({ variableExtractor: createVariableExtractor(javaVariableConfig), classExtractor: createClassExtractor(javaClassConfig), heritageExtractor: createHeritageExtractor(SupportedLanguages.Java), + + // ── RFC #909 Ring 3: scope-based resolution hooks ── + emitScopeCaptures: emitJavaScopeCaptures, + interpretImport: interpretJavaImport, + interpretTypeBinding: interpretJavaTypeBinding, + bindingScopeFor: javaBindingScopeFor, + importOwningScope: javaImportOwningScope, + mergeBindings: (_scope, bindings) => javaMergeBindings(bindings), + receiverBinding: javaReceiverBinding, + arityCompatibility: javaArityCompatibility, + resolveImportTarget: resolveJavaImportTarget, }); diff --git a/gitnexus/src/core/ingestion/languages/java/arity-metadata.ts b/gitnexus/src/core/ingestion/languages/java/arity-metadata.ts new file mode 100644 index 000000000..47cccbff9 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/arity-metadata.ts @@ -0,0 +1,49 @@ +/** + * Extract Java arity metadata from a method-like tree-sitter node — + * `method_declaration` or `constructor_declaration`. + * + * Reuses `javaMethodConfig.extractParameters` so scope-extracted defs + * carry the same arity semantics as the legacy parse-worker path: + * - varargs (`...`) collapses `parameterCount` to `undefined` + * - `parameterTypes` collects declared type names; a literal + * `'varargs'` marker is appended for variadic methods so + * `javaArityCompatibility` can detect them. + */ + +import type { SyntaxNode } from '../../utils/ast-helpers.js'; +import { javaMethodConfig } from '../../method-extractors/configs/jvm.js'; + +export interface JavaArityMetadata { + readonly parameterCount: number | undefined; + readonly requiredParameterCount: number | undefined; + readonly parameterTypes: readonly string[] | undefined; +} + +export function computeJavaArityMetadata(fnNode: SyntaxNode): JavaArityMetadata { + const params = javaMethodConfig.extractParameters?.(fnNode) ?? []; + + let hasVariadic = false; + const types: string[] = []; + for (const p of params) { + if (p.isVariadic) hasVariadic = true; + if (p.type !== null) types.push(p.type); + } + if (hasVariadic) types.push('varargs'); + + const total = params.length; + // For varargs methods, `parameterCount` (max) is unknown — any number of + // trailing arguments is valid. But the fixed-prefix parameters (everything + // before the variadic `...` param) are still required, so we preserve that + // count in `requiredParameterCount` so `javaArityCompatibility` can reject + // calls that undersupply the fixed prefix (e.g. `f(int x, String... args)` + // called with 0 args). + const fixedCount = params.filter((p) => !p.isVariadic).length; + const parameterCount = hasVariadic ? undefined : total; + const requiredParameterCount = hasVariadic ? fixedCount : total; + + return { + parameterCount, + requiredParameterCount, + parameterTypes: types.length > 0 ? types : undefined, + }; +} diff --git a/gitnexus/src/core/ingestion/languages/java/arity.ts b/gitnexus/src/core/ingestion/languages/java/arity.ts new file mode 100644 index 000000000..f98a8209d --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/arity.ts @@ -0,0 +1,31 @@ +/** + * Java arity check, accommodating varargs (`...`). + * + * Verdicts: + * - `'compatible'` — argCount matches parameterCount, OR varargs present. + * - `'incompatible'` — argCount mismatches with no varargs. + * - `'unknown'` — metadata absent / incomplete. + */ + +import type { Callsite, SymbolDefinition } from 'gitnexus-shared'; + +export function javaArityCompatibility( + def: SymbolDefinition, + callsite: Callsite, +): 'compatible' | 'unknown' | 'incompatible' { + const max = def.parameterCount; + const min = def.requiredParameterCount; + if (max === undefined && min === undefined) return 'unknown'; + + const argCount = callsite.arity; + if (!Number.isFinite(argCount) || argCount < 0) return 'unknown'; + + const hasVarArgs = + def.parameterTypes !== undefined && + def.parameterTypes.some((t) => t === 'varargs' || t.includes('...')); + + if (min !== undefined && argCount < min) return 'incompatible'; + if (max !== undefined && argCount > max && !hasVarArgs) return 'incompatible'; + + return 'compatible'; +} diff --git a/gitnexus/src/core/ingestion/languages/java/cache-stats.ts b/gitnexus/src/core/ingestion/languages/java/cache-stats.ts new file mode 100644 index 000000000..a4c58f11f --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/cache-stats.ts @@ -0,0 +1,30 @@ +/** + * Dev-mode counters for the cross-phase scope-captures parse cache + * (Java mirror of `languages/csharp/cache-stats.ts`). + * + * Gated by `PROF_SCOPE_RESOLUTION=1`. Production builds fold every + * increment into dead code via the module-level `PROF` constant, so + * the hot path in `captures.ts` stays branch-free. + */ + +const PROF = process.env.PROF_SCOPE_RESOLUTION === '1'; + +let CACHE_HITS = 0; +let CACHE_MISSES = 0; + +export function recordCacheHit(): void { + if (PROF) CACHE_HITS++; +} + +export function recordCacheMiss(): void { + if (PROF) CACHE_MISSES++; +} + +export function getJavaCaptureCacheStats(): { hits: number; misses: number } { + return { hits: CACHE_HITS, misses: CACHE_MISSES }; +} + +export function resetJavaCaptureCacheStats(): void { + CACHE_HITS = 0; + CACHE_MISSES = 0; +} diff --git a/gitnexus/src/core/ingestion/languages/java/captures.ts b/gitnexus/src/core/ingestion/languages/java/captures.ts new file mode 100644 index 000000000..73ea605fe --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/captures.ts @@ -0,0 +1,235 @@ +/** + * `emitScopeCaptures` for Java. + * + * Drives the Java scope query against tree-sitter-java and groups raw + * matches into `CaptureMatch[]` for the central extractor. Layers: + * + * 1. **Decomposed import declarations** — each `import_declaration` + * is re-emitted with `@import.kind/source/name` markers. + * 2. **Receiver binding synthesis** — `this`/`super` type-bindings + * on instance methods. + * 3. **Arity metadata** on method/constructor declarations. + * 4. **Reference arity** on call sites. + * + * Pure given the input source text. No I/O, no globals consulted. + */ + +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { findNodeAtRange, nodeToCapture, syntheticCapture } from '../../utils/ast-helpers.js'; +import { splitImportDeclaration } from './import-decomposer.js'; +import { computeJavaArityMetadata } from './arity-metadata.js'; +import { synthesizeJavaReceiverBinding } from './receiver-binding.js'; +import { getJavaParser, getJavaScopeQuery } from './query.js'; +import { recordCacheHit, recordCacheMiss } from './cache-stats.js'; +import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; + +/** Declaration anchors that carry function-like arity metadata. */ +const FUNCTION_DECL_TAGS = ['@declaration.method', '@declaration.constructor'] as const; + +/** tree-sitter-java node types that the method extractor accepts. */ +const FUNCTION_NODE_TYPES = ['method_declaration', 'constructor_declaration'] as const; + +/** Suppress read.member emissions when the field_access is already + * covered by a method_invocation (object of a call) or an + * assignment_expression (write target). */ +function shouldEmitReadMember(memberNode: SyntaxNode): boolean { + const parent = memberNode.parent; + if (parent === null) return true; + + switch (parent.type) { + case 'method_invocation': + // Don't emit read.member when the field_access is the object of a method_invocation + // (the method call already handles this relationship) + return parent.childForFieldName('object')?.id !== memberNode.id; + case 'assignment_expression': + return parent.childForFieldName('left')?.id !== memberNode.id; + default: + return true; + } +} + +export function emitJavaScopeCaptures( + sourceText: string, + _filePath: string, + cachedTree?: unknown, +): readonly CaptureMatch[] { + let tree = cachedTree as ReturnType['parse']> | undefined; + if (tree === undefined) { + tree = parseSourceSafe(getJavaParser(), sourceText, undefined, { + bufferSize: getTreeSitterBufferSize(sourceText), + }); + recordCacheMiss(); + } else { + recordCacheHit(); + } + + const rawMatches = getJavaScopeQuery().matches(tree.rootNode); + const out: CaptureMatch[] = []; + + for (const m of rawMatches) { + const grouped: Record = {}; + for (const c of m.captures) { + const tag = '@' + c.name; + grouped[tag] = nodeToCapture(tag, c.node); + } + if (Object.keys(grouped).length === 0) continue; + + // Decompose each `import_declaration`. + if (grouped['@import.statement'] !== undefined) { + const stmtCapture = grouped['@import.statement']; + const stmtNode = findNodeAtRange(tree.rootNode, stmtCapture.range, 'import_declaration'); + if (stmtNode !== null) { + const decomposed = splitImportDeclaration(stmtNode); + if (decomposed !== null) { + out.push(decomposed); + continue; + } + } + out.push(grouped); + continue; + } + + // Skip free-call matches that are actually member calls. The query + // matches ALL method_invocations as @reference.call.free (without + // negation) because tree-sitter-java's query engine drops !object + // patterns when a positive object: pattern exists for the same node + // type. Filter here: if the match has @reference.call.free but also + // has @reference.receiver, it's a member call — skip the free match + // (the separate @reference.call.member match covers it). + if ( + grouped['@reference.call.free'] !== undefined && + grouped['@reference.receiver'] !== undefined + ) { + continue; + } + + // Filter read.member when it's a child of method_invocation or assignment. + if (grouped['@reference.read.member'] !== undefined) { + const anchor = grouped['@reference.read.member']; + const memberNode = findNodeAtRange(tree.rootNode, anchor.range, 'field_access'); + if (memberNode === null || !shouldEmitReadMember(memberNode)) { + continue; + } + } + + // Synthesize `this` / `super` receiver type-bindings on every + // instance method-like. + if (grouped['@scope.function'] !== undefined) { + out.push(grouped); + const anchor = grouped['@scope.function']!; + const fnNode = findFunctionNode(tree.rootNode, anchor.range); + if (fnNode !== null) { + for (const synth of synthesizeJavaReceiverBinding(fnNode)) { + out.push(synth); + } + } + continue; + } + + // Synthesize arity metadata on function-like declarations. + const declTag = FUNCTION_DECL_TAGS.find((t) => grouped[t] !== undefined); + if (declTag !== undefined) { + const anchor = grouped[declTag]!; + const fnNode = findFunctionNode(tree.rootNode, anchor.range); + if (fnNode !== null) { + const arity = computeJavaArityMetadata(fnNode); + if (arity.parameterCount !== undefined) { + grouped['@declaration.parameter-count'] = syntheticCapture( + '@declaration.parameter-count', + fnNode, + String(arity.parameterCount), + ); + } + if (arity.requiredParameterCount !== undefined) { + grouped['@declaration.required-parameter-count'] = syntheticCapture( + '@declaration.required-parameter-count', + fnNode, + String(arity.requiredParameterCount), + ); + } + if (arity.parameterTypes !== undefined) { + grouped['@declaration.parameter-types'] = syntheticCapture( + '@declaration.parameter-types', + fnNode, + JSON.stringify(arity.parameterTypes), + ); + } + } + } + + // Synthesize `@reference.arity` on every callsite. + const callTag = ( + ['@reference.call.free', '@reference.call.member', '@reference.call.constructor'] as const + ).find((t) => grouped[t] !== undefined); + if (callTag !== undefined && grouped['@reference.arity'] === undefined) { + const anchor = grouped[callTag]!; + const callNode = + findNodeAtRange(tree.rootNode, anchor.range, 'method_invocation') ?? + findNodeAtRange(tree.rootNode, anchor.range, 'object_creation_expression'); + if (callNode !== null) { + const argList = callNode.childForFieldName('arguments'); + const args = + argList === null + ? [] + : argList.namedChildren.filter((c) => c !== null && c.type !== 'comment'); + grouped['@reference.arity'] = syntheticCapture( + '@reference.arity', + callNode, + String(args.length), + ); + + const argTypes = args.map((arg) => inferArgType(arg!)); + grouped['@reference.parameter-types'] = syntheticCapture( + '@reference.parameter-types', + callNode, + JSON.stringify(argTypes), + ); + } + } + + out.push(grouped); + } + + return out; +} + +type SyntaxNode = ReturnType['parse']>['rootNode']; + +/** Infer a Java argument's static type from literal patterns. */ +function inferArgType(argNode: SyntaxNode): string { + switch (argNode.type) { + case 'decimal_integer_literal': + case 'hex_integer_literal': + case 'octal_integer_literal': + case 'binary_integer_literal': + return 'int'; + case 'decimal_floating_point_literal': + case 'hex_floating_point_literal': + return 'double'; + case 'string_literal': + return 'String'; + case 'character_literal': + return 'char'; + case 'true': + case 'false': + return 'boolean'; + case 'null_literal': + return 'null'; + case 'object_creation_expression': { + const typeNode = argNode.childForFieldName('type'); + return typeNode?.text ?? ''; + } + default: + return ''; + } +} + +/** Find the first Java function-like node at the given range. */ +function findFunctionNode(rootNode: SyntaxNode, range: Capture['range']): SyntaxNode | null { + for (const nodeType of FUNCTION_NODE_TYPES) { + const n = findNodeAtRange(rootNode, range, nodeType); + if (n !== null) return n as SyntaxNode; + } + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/java/import-decomposer.ts b/gitnexus/src/core/ingestion/languages/java/import-decomposer.ts new file mode 100644 index 000000000..59c74d144 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/import-decomposer.ts @@ -0,0 +1,104 @@ +/** + * Decompose a Java `import_declaration` into a `CaptureMatch` carrying + * the synthesized markers `@import.kind` / `@import.source` / + * `@import.name` that `interpretJavaImport` consumes. + * + * Unlike C#'s using-directive decomposer, Java has four import forms: + * + * import com.example.User; → named + * import com.example.*; → wildcard + * import static com.example.Utils.format; → static + * import static com.example.Utils.*; → static-wildcard + * + * Each produces exactly one import. The decomposer inspects the raw + * source text and tree-sitter children to determine the flavor. + */ + +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js'; + +type ImportKind = 'named' | 'wildcard' | 'static' | 'static-wildcard'; + +interface ImportSpec { + readonly kind: ImportKind; + /** Full dotted path: `com.example.User`. */ + readonly source: string; + /** Local binding name — last path segment for named/static, + * `'*'` for wildcard/static-wildcard. */ + readonly name: string; + /** Node to anchor the synthesized captures (range-wise). */ + readonly atNode: SyntaxNode; +} + +export function splitImportDeclaration(stmtNode: SyntaxNode): CaptureMatch | null { + if (stmtNode.type !== 'import_declaration') return null; + const spec = parseImportDeclaration(stmtNode); + if (spec === null) return null; + return buildImportMatch(stmtNode, spec); +} + +function parseImportDeclaration(node: SyntaxNode): ImportSpec | null { + // Detect `static` by checking for an anonymous `static` token child. + let isStatic = false; + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null && child.type === 'static') { + isStatic = true; + break; + } + } + + // Detect wildcard by checking for `asterisk` named child. + let isWildcard = false; + for (let i = 0; i < node.namedChildCount; i++) { + const child = node.namedChild(i); + if (child !== null && child.type === 'asterisk') { + isWildcard = true; + break; + } + } + + // Find the scoped_identifier (or identifier for single-segment imports). + let pathNode: SyntaxNode | null = null; + for (let i = 0; i < node.namedChildCount; i++) { + const child = node.namedChild(i); + if (child !== null && (child.type === 'scoped_identifier' || child.type === 'identifier')) { + pathNode = child; + break; + } + } + if (pathNode === null) return null; + + const fullPath = pathNode.text; + if (fullPath === '') return null; + + if (isStatic && isWildcard) { + // `import static com.example.Utils.*;` + return { kind: 'static-wildcard', source: fullPath, name: '*', atNode: node }; + } + if (isStatic) { + // `import static com.example.Utils.format;` + const lastDot = fullPath.lastIndexOf('.'); + const name = lastDot >= 0 ? fullPath.slice(lastDot + 1) : fullPath; + return { kind: 'static', source: fullPath, name, atNode: node }; + } + if (isWildcard) { + // `import com.example.*;` + return { kind: 'wildcard', source: fullPath, name: '*', atNode: node }; + } + + // `import com.example.User;` + const lastDot = fullPath.lastIndexOf('.'); + const name = lastDot >= 0 ? fullPath.slice(lastDot + 1) : fullPath; + return { kind: 'named', source: fullPath, name, atNode: node }; +} + +function buildImportMatch(stmtNode: SyntaxNode, spec: ImportSpec): CaptureMatch { + const m: Record = { + '@import.statement': nodeToCapture('@import.statement', stmtNode), + '@import.kind': syntheticCapture('@import.kind', spec.atNode, spec.kind), + '@import.source': syntheticCapture('@import.source', spec.atNode, spec.source), + '@import.name': syntheticCapture('@import.name', spec.atNode, spec.name), + }; + return m; +} diff --git a/gitnexus/src/core/ingestion/languages/java/import-target.ts b/gitnexus/src/core/ingestion/languages/java/import-target.ts new file mode 100644 index 000000000..b78b6369b --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/import-target.ts @@ -0,0 +1,108 @@ +/** + * Adapter from `(ParsedImport, WorkspaceIndex)` → concrete file path. + * + * Converts Java package paths (dots → slashes) and tries: + * 1. Exact file match: `com/example/User.java` + * 2. Suffix match for nested layouts + * 3. Directory match (wildcard imports) + * 4. Progressive prefix stripping for non-standard layouts + * + * Returns `null` for unresolvable / JDK imports. + */ + +import type { ParsedImport, WorkspaceIndex } from 'gitnexus-shared'; + +export interface JavaResolveContext { + readonly fromFile: string; + readonly allFilePaths: ReadonlySet; +} + +export function resolveJavaImportTarget( + parsedImport: ParsedImport, + workspaceIndex: WorkspaceIndex, +): string | null { + const ctx = workspaceIndex as JavaResolveContext | undefined; + if ( + ctx === undefined || + typeof (ctx as { fromFile?: unknown }).fromFile !== 'string' || + !((ctx as { allFilePaths?: unknown }).allFilePaths instanceof Set) + ) { + return null; + } + if (parsedImport.kind === 'dynamic-unresolved') return null; + if (parsedImport.targetRaw === null || parsedImport.targetRaw === '') return null; + + // Strip trailing `.*` for wildcard imports: `com.example.*` → `com.example` + let target = parsedImport.targetRaw; + if (target.endsWith('.*')) { + target = target.slice(0, -2); + } + + // Package path: `com.example.User` → `com/example/User` + const pathLike = target.replace(/\./g, '/'); + const suffix = `/${pathLike}`; + + let exactFile: string | null = null; + let suffixFile: string | null = null; + let directoryChild: string | null = null; + const dirPrefix = `${pathLike}/`; + const suffixDirPrefix = `/${dirPrefix}`; + + for (const raw of ctx.allFilePaths) { + const f = raw.replace(/\\/g, '/'); + if (!f.endsWith('.java')) continue; + if (f === `${pathLike}.java`) { + exactFile = raw; + break; + } + if (suffixFile === null && f.endsWith(`${suffix}.java`)) { + suffixFile = raw; + } + if (directoryChild === null) { + const atRoot = f.startsWith(dirPrefix); + const atNested = f.includes(suffixDirPrefix); + if (atRoot || atNested) { + const idx = atRoot ? 0 : f.indexOf(suffixDirPrefix) + 1; + const after = f.slice(idx + dirPrefix.length); + if (after.length > 0 && !after.includes('/')) { + directoryChild = raw; + } + } + } + } + + if (exactFile !== null) return exactFile; + if (suffixFile !== null) return suffixFile; + if (directoryChild !== null) return directoryChild; + + // Progressive prefix stripping — handles `import com.example.User;` + // in a repo laid out `User.java` (no `com/example/` prefix). + const segments = pathLike.split('/').filter(Boolean); + for (let skip = 1; skip < segments.length; skip++) { + const tail = segments.slice(skip).join('/'); + if (tail === '') continue; + const tailFile = `${tail}.java`; + const tailSuffix = `/${tailFile}`; + const tailDir = `${tail}/`; + const tailSuffixDir = `/${tailDir}`; + let tailDirectChild: string | null = null; + for (const raw of ctx.allFilePaths) { + const f = raw.replace(/\\/g, '/'); + if (!f.endsWith('.java')) continue; + if (f === tailFile) return raw; + if (f.endsWith(tailSuffix)) return raw; + if (tailDirectChild === null) { + const atRoot = f.startsWith(tailDir); + const atNested = f.includes(tailSuffixDir); + if (atRoot || atNested) { + const idx = atRoot ? 0 : f.indexOf(tailSuffixDir) + 1; + const after = f.slice(idx + tailDir.length); + if (after.length > 0 && !after.includes('/')) tailDirectChild = raw; + } + } + } + if (tailDirectChild !== null) return tailDirectChild; + } + + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/java/index.ts b/gitnexus/src/core/ingestion/languages/java/index.ts new file mode 100644 index 000000000..443faac4b --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/index.ts @@ -0,0 +1,30 @@ +/** + * Java scope-resolution hooks (RFC #909 Ring 3). + * + * Public API barrel. Consumers should import from this file rather than + * the individual modules. + * + * Module layout: + * + * - `query.ts` — tree-sitter query + lazy parser/query singletons + * - `captures.ts` — `emitJavaScopeCaptures` orchestrator + * - `import-decomposer.ts` — each `import` → ParsedImport-shaped captures + * - `interpret.ts` — capture-match → `ParsedImport` / `ParsedTypeBinding` + * - `simple-hooks.ts` — small hooks made explicit + * - `receiver-binding.ts` — synthesize `this`/`super` type-bindings on + * instance-method entry + * - `merge-bindings.ts` — Java import precedence + * - `arity.ts` — Java arity compatibility (varargs) + * - `arity-metadata.ts` — synthesize arity metadata from declarations + * - `import-target.ts` — `(ParsedImport, WorkspaceIndex) → file path` adapter + * - `scope-resolver.ts` — `ScopeResolver` registered in `SCOPE_RESOLVERS` + * - `cache-stats.ts` — PROF_SCOPE_RESOLUTION cache hit/miss counters + */ + +export { emitJavaScopeCaptures } from './captures.js'; +export { getJavaCaptureCacheStats, resetJavaCaptureCacheStats } from './cache-stats.js'; +export { interpretJavaImport, interpretJavaTypeBinding } from './interpret.js'; +export { javaMergeBindings } from './merge-bindings.js'; +export { javaArityCompatibility } from './arity.js'; +export { resolveJavaImportTarget, type JavaResolveContext } from './import-target.js'; +export { javaBindingScopeFor, javaImportOwningScope, javaReceiverBinding } from './simple-hooks.js'; diff --git a/gitnexus/src/core/ingestion/languages/java/interpret.ts b/gitnexus/src/core/ingestion/languages/java/interpret.ts new file mode 100644 index 000000000..9c207d451 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/interpret.ts @@ -0,0 +1,141 @@ +/** + * Capture-match → semantic-shape interpreters for Java. + * + * - `interpretJavaImport` → `ParsedImport` + * - `interpretJavaTypeBinding` → `ParsedTypeBinding` + * + * Import matches arrive pre-decomposed by `emitJavaScopeCaptures` + * (one import per match, with synthesized `@import.kind/source/name` + * markers). Type-binding matches arrive from the raw query captures. + */ + +import type { CaptureMatch, ParsedImport, ParsedTypeBinding, TypeRef } from 'gitnexus-shared'; + +// ─── interpretImport ────────────────────────────────────────────────────── + +export function interpretJavaImport(captures: CaptureMatch): ParsedImport | null { + const kindCap = captures['@import.kind']; + const sourceCap = captures['@import.source']; + const nameCap = captures['@import.name']; + + const kind = kindCap?.text; + if (kind === undefined || sourceCap === undefined) return null; + + switch (kind) { + case 'named': { + // `import com.example.User;` + return { + kind: 'named', + localName: nameCap?.text ?? sourceCap.text.split('.').pop() ?? sourceCap.text, + importedName: sourceCap.text, + targetRaw: sourceCap.text, + }; + } + case 'wildcard': { + // `import com.example.*;` + return { + kind: 'wildcard', + targetRaw: sourceCap.text + '.*', + }; + } + case 'static': { + // `import static com.example.Utils.format;` + // The source contains the full path including the member name + // (e.g. `com.example.Utils.format`). For file resolution we need + // the class path (`com.example.Utils`), so strip the final member + // segment. The local binding name is the member itself. + const fullSource = sourceCap.text; + const lastDot = fullSource.lastIndexOf('.'); + const classPath = lastDot >= 0 ? fullSource.slice(0, lastDot) : fullSource; + return { + kind: 'named', + localName: nameCap?.text ?? (lastDot >= 0 ? fullSource.slice(lastDot + 1) : fullSource), + importedName: fullSource, + targetRaw: classPath, + }; + } + case 'static-wildcard': { + // `import static com.example.Utils.*;` + // The source is the class path (e.g. `com.example.Utils`). + // Resolution should target the class file, not a wildcard directory + // scan — `Utils.java` is the file that contains the static members. + return { + kind: 'wildcard', + targetRaw: sourceCap.text + '.*', + }; + } + default: + return null; + } +} + +// ─── interpretTypeBinding ───────────────────────────────────────────────── + +export function interpretJavaTypeBinding(captures: CaptureMatch): ParsedTypeBinding | null { + const nameCap = captures['@type-binding.name']; + const typeCap = captures['@type-binding.type']; + if (nameCap === undefined || typeCap === undefined) return null; + + // Strip qualifier first so that `com.example.BaseModel` becomes + // `BaseModel` before stripGeneric — the JVM-erasure fallback pattern + // requires an unqualified identifier at the start of the string. + const rawType = stripGeneric(stripQualifier(typeCap.text.trim())); + + // Skip `var` — tree-sitter-java parses `var` as type_identifier with + // text "var". When used without a constructor initializer, there's no + // concrete type to bind. + if (rawType === 'var') return null; + + let source: TypeRef['source'] = 'parameter-annotation'; + if (captures['@type-binding.self'] !== undefined) source = 'self'; + else if (captures['@type-binding.constructor'] !== undefined) source = 'constructor-inferred'; + else if (captures['@type-binding.annotation'] !== undefined) source = 'annotation'; + else if (captures['@type-binding.return'] !== undefined) source = 'return-annotation'; + + return { boundName: nameCap.text, rawTypeName: rawType, source }; +} + +/** + * Unwrap generic type parameters from Java types. + * + * Three tiers, checked in order: + * 1. Known single-arg collection wrappers → extract the element type + * (`List` → `User`, `Optional` → `User`). + * 2. Known two-arg map/container types → extract the value type + * (`Map` → `User`). + * 3. **Fallback (JVM type erasure):** any other generic type → + * strip the generic parameters and keep the raw class name + * (`BaseModel` → `BaseModel`, `CustomList` → `CustomList`). + * This ensures receiver bindings (`this`/`super`) on classes with + * generic superclasses resolve to the correct class file. + */ +function stripGeneric(text: string): string { + // Single-type-argument containers — extract the element type. + const single = text.match( + /^(?:[A-Za-z_][A-Za-z0-9_.]*\.)?(?:List|ArrayList|LinkedList|Set|HashSet|TreeSet|SortedSet|LinkedHashSet|Collection|Iterable|Iterator|Optional|Stream|CompletableFuture|Future|Queue|Deque|ArrayDeque|PriorityQueue|Vector|Stack|Supplier|Consumer|Predicate|Function)<([^,<>]+)>$/, + ); + if (single !== null) return single[1].trim(); + + // Two-type-argument map/container types — extract the value type (second arg). + const twoArg = text.match( + /^(?:[A-Za-z_][A-Za-z0-9_.]*\.)?(?:Map|HashMap|TreeMap|LinkedHashMap|ConcurrentHashMap|ConcurrentMap|SortedMap|NavigableMap|Hashtable|EnumMap|WeakHashMap|IdentityHashMap|BiFunction|BiConsumer|BiPredicate|Pair|Entry)<[^,<>]+,\s*([^,<>]+)>$/, + ); + if (twoArg !== null) return twoArg[1].trim(); + + // Fallback: strip generic parameters from any unrecognized generic type. + // `BaseModel` → `BaseModel`, `Builder` → `Builder`. + // This mirrors JVM type erasure — the raw class name is the resolvable symbol. + // The pattern matches up to the first `<` to handle nested generics safely + // (e.g. `BaseModel>` → `BaseModel`). + const fallback = text.match(/^([A-Za-z_$][A-Za-z0-9_$]*)<.+>$/s); + if (fallback !== null) return fallback[1].trim(); + + return text; +} + +/** `com.example.User` → `User`. */ +function stripQualifier(text: string): string { + const lastDot = text.lastIndexOf('.'); + if (lastDot === -1) return text; + return text.slice(lastDot + 1); +} diff --git a/gitnexus/src/core/ingestion/languages/java/merge-bindings.ts b/gitnexus/src/core/ingestion/languages/java/merge-bindings.ts new file mode 100644 index 000000000..9056705d0 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/merge-bindings.ts @@ -0,0 +1,44 @@ +/** + * Java shadowing precedence for the `mergeBindings` hook. + * + * Tier ranking (lower wins): + * - 0: `local` — class member, method, local variable, parameter + * - 1: `import` / `namespace` / `reexport` — explicit imports + * - 2: `wildcard` — wildcard imports (`import x.y.*`) + * + * Within a surviving tier: de-dup by DefId, last-write-wins. + */ + +import type { BindingRef } from 'gitnexus-shared'; + +const TIER_LOCAL = 0; +const TIER_IMPORT = 1; +const TIER_WILDCARD = 2; +const TIER_UNKNOWN = 3; + +function tierOf(b: BindingRef): number { + switch (b.origin) { + case 'local': + return TIER_LOCAL; + case 'reexport': + case 'import': + case 'namespace': + return TIER_IMPORT; + case 'wildcard': + return TIER_WILDCARD; + default: + return TIER_UNKNOWN; + } +} + +export function javaMergeBindings(bindings: readonly BindingRef[]): readonly BindingRef[] { + if (bindings.length === 0) return bindings; + + let bestTier = Number.POSITIVE_INFINITY; + for (const b of bindings) bestTier = Math.min(bestTier, tierOf(b)); + const survivors = bindings.filter((b) => tierOf(b) === bestTier); + + const seen = new Map(); + for (const b of survivors) seen.set(b.def.nodeId, b); + return [...seen.values()]; +} diff --git a/gitnexus/src/core/ingestion/languages/java/query.ts b/gitnexus/src/core/ingestion/languages/java/query.ts new file mode 100644 index 000000000..3fabbb7bf --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/query.ts @@ -0,0 +1,197 @@ +/** + * Tree-sitter query for Java scope captures (RFC §5.1). + * + * Captures the structural skeleton the generic scope-resolution + * pipeline consumes: scopes (module/class/function), declarations + * (class-likes, method-likes, fields, variables), imports (import + * declarations), type bindings (parameter annotations, variable + * annotations, constructor inference), and references (call sites, + * member writes/reads). + * + * Java specifics that shape this query: + * + * - Java uses `program` as the root node (not `compilation_unit`). + * - `import_declaration` nodes carry `scoped_identifier` children + * and optional `asterisk` for wildcard imports. + * - `static` imports are detected by an anonymous `static` token + * child within `import_declaration`. + * - `var` (Java 10+ local variable type inference) parses as a + * `type_identifier` with text `"var"`, not a dedicated node type. + * - Modifiers (`public`, `static`, etc.) are grouped under a + * `modifiers` named child with anonymous keyword tokens. + * - Superclass inheritance uses a `superclass:` field containing + * a `superclass` node wrapping a `type_identifier`. + * + * Exposes lazy `Parser` and `Query` singletons so callers don't pay + * tree-sitter init cost per file. + */ + +import Parser from 'tree-sitter'; +import Java from 'tree-sitter-java'; + +const JAVA_SCOPE_QUERY = ` +;; Scopes +(program) @scope.module + +(class_declaration) @scope.class +(interface_declaration) @scope.class +(enum_declaration) @scope.class +(record_declaration) @scope.class +(annotation_type_declaration) @scope.class + +(method_declaration) @scope.function +(constructor_declaration) @scope.function + +;; Declarations — types +(class_declaration + name: (identifier) @declaration.name) @declaration.class + +(interface_declaration + name: (identifier) @declaration.name) @declaration.interface + +(enum_declaration + name: (identifier) @declaration.name) @declaration.enum + +(record_declaration + name: (identifier) @declaration.name) @declaration.record + +(annotation_type_declaration + name: (identifier) @declaration.name) @declaration.class + +;; Declarations — methods / constructors +(method_declaration + name: (identifier) @declaration.name) @declaration.method + +(constructor_declaration + name: (identifier) @declaration.name) @declaration.constructor + +;; Declarations — fields +(field_declaration + declarator: (variable_declarator + name: (identifier) @declaration.name)) @declaration.variable + +;; Declarations — local variables +(local_variable_declaration + declarator: (variable_declarator + name: (identifier) @declaration.name)) @declaration.variable + +;; Imports — single anchor per import_declaration +(import_declaration) @import.statement + +;; Type bindings — parameter annotations: void f(User u) +(formal_parameter + type: (type_identifier) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.parameter + +(formal_parameter + type: (generic_type) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.parameter + +(formal_parameter + type: (scoped_type_identifier) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.parameter + +;; Type bindings — local variable annotations: User u = new User(); +(local_variable_declaration + type: (type_identifier) @type-binding.type + declarator: (variable_declarator + name: (identifier) @type-binding.name)) @type-binding.annotation + +(local_variable_declaration + type: (generic_type) @type-binding.type + declarator: (variable_declarator + name: (identifier) @type-binding.name)) @type-binding.annotation + +;; Type bindings — var u = new User(); (Java 10+ local variable type inference) +;; tree-sitter-java parses \`var\` as a \`type_identifier\` with text "var". +;; The type-binding.constructor anchor fires when the rhs is an +;; object_creation_expression so interpretJavaTypeBinding can infer +;; the concrete type from the constructor call. +(local_variable_declaration + type: (type_identifier) @_var_type + declarator: (variable_declarator + name: (identifier) @type-binding.name + value: (object_creation_expression + type: (type_identifier) @type-binding.type))) @type-binding.constructor + +;; Type bindings — field declarations: private User user; +(field_declaration + type: (type_identifier) @type-binding.type + declarator: (variable_declarator + name: (identifier) @type-binding.name)) @type-binding.annotation + +(field_declaration + type: (generic_type) @type-binding.type + declarator: (variable_declarator + name: (identifier) @type-binding.name)) @type-binding.annotation + +;; Type bindings — method return type: public User getUser() { } +(method_declaration + type: (type_identifier) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.return + +(method_declaration + type: (generic_type) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.return + +;; Type bindings — enhanced for: for (User u : list) +(enhanced_for_statement + type: (type_identifier) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.annotation + +(enhanced_for_statement + type: (generic_type) @type-binding.type + name: (identifier) @type-binding.name) @type-binding.annotation + +;; References — all method calls: foo() and obj.method() +;; tree-sitter-java's query engine drops negation-based \`!object\` +;; patterns when a positive \`object:\` pattern exists for the same +;; node type, so we match all calls here and classify free vs +;; member in captures.ts based on the presence of @reference.receiver. +(method_invocation + object: (_) @reference.receiver + name: (identifier) @reference.name) @reference.call.member + +(method_invocation + name: (identifier) @reference.name) @reference.call.free + +;; References — constructor calls: new User(...) +(object_creation_expression + type: (type_identifier) @reference.name) @reference.call.constructor + +(object_creation_expression + type: (generic_type + (type_identifier) @reference.name)) @reference.call.constructor + +(object_creation_expression + type: (scoped_type_identifier) @reference.call.constructor.qualified) @reference.call.constructor + +;; References — field/property writes: obj.name = "x" +(assignment_expression + left: (field_access + object: (_) @reference.receiver + field: (identifier) @reference.name)) @reference.write.member + +;; References — field/property reads: obj.name +(field_access + object: (_) @reference.receiver + field: (identifier) @reference.name) @reference.read.member +`; + +let _parser: Parser | null = null; +let _query: Parser.Query | null = null; + +export function getJavaParser(): Parser { + if (_parser === null) { + _parser = new Parser(); + _parser.setLanguage(Java as Parameters[0]); + } + return _parser; +} + +export function getJavaScopeQuery(): Parser.Query { + if (_query === null) { + _query = new Parser.Query(Java as Parameters[0], JAVA_SCOPE_QUERY); + } + return _query; +} diff --git a/gitnexus/src/core/ingestion/languages/java/receiver-binding.ts b/gitnexus/src/core/ingestion/languages/java/receiver-binding.ts new file mode 100644 index 000000000..4d6d60ded --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/receiver-binding.ts @@ -0,0 +1,103 @@ +/** + * Synthesize `@type-binding.self` captures for Java instance methods — + * one for `this` (always on non-static methods inside a type + * declaration) and optionally one for `super` (only on class methods + * when the enclosing class has a `superclass`). + * + * Mirrors `languages/csharp/receiver-binding.ts` in structure. + */ + +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js'; + +const TYPE_DECL_NODE_TYPES = new Set([ + 'class_declaration', + 'interface_declaration', + 'enum_declaration', + 'record_declaration', +]); + +const FUNCTION_NODE_TYPES = new Set(['method_declaration', 'constructor_declaration']); + +/** Walk up to the enclosing type declaration. */ +function findEnclosingTypeDeclaration(node: SyntaxNode): SyntaxNode | null { + let cur: SyntaxNode | null = node.parent; + while (cur !== null) { + if (TYPE_DECL_NODE_TYPES.has(cur.type)) return cur; + cur = cur.parent; + } + return null; +} + +function typeName(typeNode: SyntaxNode): string | null { + return typeNode.childForFieldName('name')?.text ?? null; +} + +/** First superclass text. tree-sitter-java uses a `superclass` field + * containing a `superclass` node wrapping a `type_identifier`. */ +function firstSuperclassText(typeNode: SyntaxNode): string | null { + const superclass = typeNode.childForFieldName('superclass'); + if (superclass === null) return null; + // The superclass node wraps the type_identifier + for (let i = 0; i < superclass.namedChildCount; i++) { + const child = superclass.namedChild(i); + if (child !== null && (child.type === 'type_identifier' || child.type === 'generic_type')) { + return child.text; + } + } + return null; +} + +/** Check if a method has the `static` modifier. In tree-sitter-java, + * modifiers are grouped under a `modifiers` named child with anonymous + * keyword tokens. */ +function isStaticMethod(fnNode: SyntaxNode): boolean { + for (let i = 0; i < fnNode.namedChildCount; i++) { + const child = fnNode.namedChild(i); + if (child !== null && child.type === 'modifiers') { + for (let j = 0; j < child.childCount; j++) { + const mod = child.child(j); + if (mod !== null && mod.text.trim() === 'static') return true; + } + } + } + return false; +} + +export function synthesizeJavaReceiverBinding(fnNode: SyntaxNode): CaptureMatch[] { + if (!FUNCTION_NODE_TYPES.has(fnNode.type)) return []; + if (isStaticMethod(fnNode)) return []; + + const enclosingType = findEnclosingTypeDeclaration(fnNode); + if (enclosingType === null) return []; + + const enclosingName = typeName(enclosingType); + if (enclosingName === null) return []; + + // Anchor to the method body so the synthesized captures are inside + // the function scope. + const anchorNode = fnNode.childForFieldName('body'); + if (anchorNode === null) return []; + + const out: CaptureMatch[] = []; + out.push(buildReceiverMatch(anchorNode, 'this', enclosingName)); + + // `super` applies only to class/record methods with an explicit superclass. + if (enclosingType.type === 'class_declaration' || enclosingType.type === 'record_declaration') { + const superText = firstSuperclassText(enclosingType); + if (superText !== null) { + out.push(buildReceiverMatch(anchorNode, 'super', superText)); + } + } + + return out; +} + +function buildReceiverMatch(anchorNode: SyntaxNode, name: string, typeText: string): CaptureMatch { + const m: Record = { + '@type-binding.self': nodeToCapture('@type-binding.self', anchorNode), + '@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, name), + '@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeText), + }; + return m; +} diff --git a/gitnexus/src/core/ingestion/languages/java/scope-resolver.ts b/gitnexus/src/core/ingestion/languages/java/scope-resolver.ts new file mode 100644 index 000000000..dac974cc7 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/scope-resolver.ts @@ -0,0 +1,97 @@ +/** + * Java `ScopeResolver` registered in `SCOPE_RESOLVERS` and consumed by + * the generic `runScopeResolution` orchestrator (RFC #909 Ring 3). + * + * ## Registry-primary parity status + * + * Java is **not** in `MIGRATED_LANGUAGES` — the scope-resolution + * registry runs in shadow mode only. Parity in forced registry mode + * (`REGISTRY_PRIMARY_JAVA=1`) is 143/172 (83%). The 29 gaps fall into: + * + * - switch pattern binding / sealed-class exhaustiveness + * - Map.values() / entrySet() iteration type propagation + * - assignment / method chain return-type propagation across files + * - virtual dispatch / interface default methods + * + * These are the same category of advanced-resolution gaps seen in prior + * migrations (Python, C#, Go). Parity is below the ≥99% flip threshold + * per RFC §6.4. + * + * **CI visibility:** Because Java is absent from `MIGRATED_LANGUAGES`, + * the parity CI workflow (`ci-scope-parity.yml`) does not run Java in + * either `REGISTRY_PRIMARY_JAVA=0` or `=1` mode. Regressions in forced + * mode are only visible via manual `REGISTRY_PRIMARY_JAVA=1 npx vitest + * run java.test.ts`. Before flipping Java to registry-primary, a + * non-required CI step should be added to run Java tests in forced mode + * and report parity as a dashboard input. + * + * **Parity baseline (29 failures):** The 29 gaps in forced registry mode + * are tracked in this PR (#1482) and this JSDoc. If the gap count + * changes (up or down), update this baseline accordingly. + * + * ### Known flip-blockers (must fix before adding to MIGRATED_LANGUAGES) + * + * - Varargs arity: fixed-prefix count is now preserved, but no + * integration fixture exercises the 0-arg rejection path yet. + * - Static import resolution: `import static X.Y.m` now correctly + * resolves to `X/Y.java` (the class), not `X/Y/m.java` (the member). + * Edge cases with nested classes may remain. + * - Generic superclass receiver binding: `BaseModel` now strips + * to `BaseModel` via JVM type-erasure fallback in `stripGeneric`. + * - Wildcard import (`import com.example.*`) file selection is + * nondeterministic when multiple classes share a package directory. + * May produce wrong-file edges in forced mode. + * - Qualified generic type parameters in field/parameter annotations + * (`com.example.BaseModel`) — rare in practice but may miss + * resolution when the full qualifier is present with generics. + */ + +import type { ParsedFile } from 'gitnexus-shared'; +import { SupportedLanguages } from 'gitnexus-shared'; +import { buildMro, defaultLinearize } from '../../scope-resolution/passes/mro.js'; +import { populateClassOwnedMembers } from '../../scope-resolution/scope/walkers.js'; +import type { ScopeResolver } from '../../scope-resolution/contract/scope-resolver.js'; +import { javaProvider } from '../java.js'; +import { + javaArityCompatibility, + javaMergeBindings, + resolveJavaImportTarget, + type JavaResolveContext, +} from './index.js'; + +const javaScopeResolver: ScopeResolver = { + language: SupportedLanguages.Java, + languageProvider: javaProvider, + importEdgeReason: 'java-scope: import', + + resolveImportTarget: (targetRaw, fromFile, allFilePaths) => { + const ws: JavaResolveContext = { fromFile, allFilePaths }; + return resolveJavaImportTarget( + { kind: 'named', localName: '_', importedName: '_', targetRaw }, + ws, + ); + }, + + mergeBindings: (existing, incoming) => [...javaMergeBindings([...existing, ...incoming])], + + arityCompatibility: (callsite, def) => javaArityCompatibility(def, callsite), + + buildMro: (graph, parsedFiles, nodeLookup) => + buildMro(graph, parsedFiles, nodeLookup, defaultLinearize), + + populateOwners: (parsed: ParsedFile) => populateClassOwnedMembers(parsed), + + isSuperReceiver: (text) => text.trim() === 'super', + + // Java is statically typed — field-fallback heuristic stays off + fieldFallbackOnMethodLookup: false, + propagatesReturnTypesAcrossImports: true, + + // Java doesn't collapse member calls + collapseMemberCallsByCallerTarget: false, + + // Hoist return-type bindings to Module scope for cross-file propagation + hoistTypeBindingsToModule: true, +}; + +export { javaScopeResolver }; diff --git a/gitnexus/src/core/ingestion/languages/java/simple-hooks.ts b/gitnexus/src/core/ingestion/languages/java/simple-hooks.ts new file mode 100644 index 000000000..e69f768a6 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/java/simple-hooks.ts @@ -0,0 +1,54 @@ +/** + * Small hooks for the Java provider. Each is a few lines; they make + * the provider's choice explicit rather than relying on defaults. + */ + +import type { + CaptureMatch, + ParsedImport, + Scope, + ScopeId, + ScopeTree, + TypeRef, +} from 'gitnexus-shared'; + +// ─── bindingScopeFor ────────────────────────────────────────────────────── + +/** Method return-type bindings hoist to Module scope so cross-file + * `propagateImportedReturnTypes` and chain-follow can find them. */ +export function javaBindingScopeFor( + decl: CaptureMatch, + innermost: Scope, + tree: ScopeTree, +): ScopeId | null { + if (decl['@type-binding.return'] !== undefined) { + let cur: Scope | undefined = innermost; + while (cur !== undefined && cur.kind !== 'Module') { + const parentId: ScopeId | null = cur.parent ?? null; + if (parentId === null) break; + cur = tree.getScope(parentId); + } + if (cur !== undefined && cur.kind === 'Module') return cur.id; + } + return null; +} + +// ─── importOwningScope ──────────────────────────────────────────────────── + +/** Java imports are always at compilation-unit (Module) level (JLS §7.5). + * Return `null` unconditionally so the default Module scope is used. */ +export function javaImportOwningScope( + _imp: ParsedImport, + _innermost: Scope, + _tree: ScopeTree, +): ScopeId | null { + return null; +} + +// ─── receiverBinding ────────────────────────────────────────────────────── + +/** Look up `this` or `super` in the function scope's type bindings. */ +export function javaReceiverBinding(functionScope: Scope): TypeRef | null { + if (functionScope.kind !== 'Function') return null; + return functionScope.typeBindings.get('this') ?? functionScope.typeBindings.get('super') ?? null; +} diff --git a/gitnexus/src/core/ingestion/languages/php.ts b/gitnexus/src/core/ingestion/languages/php.ts index eb8f296f8..caca85335 100644 --- a/gitnexus/src/core/ingestion/languages/php.ts +++ b/gitnexus/src/core/ingestion/languages/php.ts @@ -5,12 +5,22 @@ * and standard export/import resolution. PHP files can use a variety of * extensions from legacy versions through modern PHP 8. */ +import { + emitPhpScopeCaptures, + interpretPhpImport, + interpretPhpTypeBinding, + phpArityCompatibility, + phpMergeBindings, + resolvePhpImportTarget, + phpBindingScopeFor, + phpImportOwningScope, + phpReceiverBinding, +} from './php/index.js'; import { SupportedLanguages } from 'gitnexus-shared'; import { createClassExtractor } from '../class-extractors/generic.js'; import { phpClassConfig } from '../class-extractors/configs/php.js'; -import { defineLanguage } from '../language-provider.js'; -import type { AstFrameworkPatternConfig } from '../language-provider.js'; +import { defineLanguage, type AstFrameworkPatternConfig } from '../language-provider.js'; import { typeConfig as phpConfig } from '../type-extractors/php.js'; import { phpExportChecker } from '../export-detection.js'; import { createImportResolver } from '../import-resolvers/resolver-factory.js'; @@ -289,4 +299,18 @@ export const phpProvider = defineLanguage({ descriptionExtractor: phpDescriptionExtractor, isRouteFile: isPhpRouteFile, builtInNames: BUILT_INS, + // ── RFC #909 Ring 3: scope-based resolution hooks ────────────────────── + emitScopeCaptures: emitPhpScopeCaptures, + interpretImport: interpretPhpImport, + interpretTypeBinding: interpretPhpTypeBinding, + // LanguageProvider uses (def, callsite); phpArityCompatibility uses (def, callsite) — same. + arityCompatibility: phpArityCompatibility, + // LanguageProvider adapter: (parsedImport, workspaceIndex) → string | null + resolveImportTarget: resolvePhpImportTarget, + // mergeBindings on LanguageProvider: (scope, bindings) — ignore scope id, + // delegate to phpMergeBindings which uses binding origin tiers. + mergeBindings: (_scope, bindings) => [...phpMergeBindings(bindings)], + bindingScopeFor: phpBindingScopeFor, + importOwningScope: phpImportOwningScope, + receiverBinding: phpReceiverBinding, }); diff --git a/gitnexus/src/core/ingestion/languages/php/arity-metadata.ts b/gitnexus/src/core/ingestion/languages/php/arity-metadata.ts new file mode 100644 index 000000000..40662bd61 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/arity-metadata.ts @@ -0,0 +1,73 @@ +/** + * Extract PHP arity metadata from a method-like tree-sitter node — + * `method_declaration` or `function_definition`. + * + * Reuses `phpMethodConfig.extractParameters` so scope-extracted defs + * carry the same arity semantics as the legacy parse-worker path: + * - `variadic_parameter` (`...$args`) collapses `parameterCount` to + * `undefined`, which `phpArityCompatibility` then treats as + * "max unknown" — the candidate stays eligible at `argCount >= required`. + * - Defaulted parameters (`= expr`) contribute to `optionalCount`; + * `requiredParameterCount = total − optionalCount − (variadic ? 1 : 0)`. + * The variadic slot itself accepts zero args so it is subtracted from + * the required count — `f(int $a, ...$rest)` requires exactly 1 arg, + * not 2, and `f(...$rest)` requires 0. + * - `property_promotion_parameter` (constructor-promoted) is counted + * the same as `simple_parameter` since both consume an argument slot. + * - `parameterTypes` collects declared type names; a literal `'...'` + * marker is appended for variadic methods so `phpArityCompatibility` + * can detect them without re-reading the AST. + */ + +import type { SyntaxNode } from '../../utils/ast-helpers.js'; +import { phpMethodConfig } from '../../method-extractors/configs/php.js'; + +interface PhpArityMetadata { + readonly parameterCount: number | undefined; + readonly requiredParameterCount: number | undefined; + readonly parameterTypes: readonly string[] | undefined; +} + +export function computePhpArityMetadata(fnNode: SyntaxNode): PhpArityMetadata { + const params = phpMethodConfig.extractParameters?.(fnNode) ?? []; + + let hasVariadic = false; + let optionalCount = 0; + const types: string[] = []; + + for (const p of params) { + if (p.isVariadic) { + hasVariadic = true; + } else if (p.isOptional) { + optionalCount++; + } + if (p.type !== null) types.push(p.type); + } + // PHP variadic marker convention: append the literal '...' string to + // `parameterTypes`. This is intentionally DIFFERENT from C#, which uses + // the literal 'params' (its source-language keyword). The shared + // `narrowOverloadCandidates` pass in `scope-resolution/passes/overload- + // narrowing.ts` checks for the C# 'params' marker — that branch is + // dead code for PHP because PHP variadic methods set `parameterCount + // = undefined` (see line below), which skips the `max !== undefined` + // gate that hosts the 'params' check. PHP's actual variadic-aware + // arity logic lives in `phpArityCompatibility` (arity.ts) and now + // also in `phpEmitUnresolvedReceiverEdges` (scope-resolver.ts), both + // of which check `'...'`. Finding 9 of PR #1497 adversarial review. + if (hasVariadic) types.push('...'); + + const total = params.length; + // Variadic methods accept any arg count ≥ required — leave `parameterCount` + // undefined so the registry treats max as unknown. + const parameterCount = hasVariadic ? undefined : total; + // The variadic slot itself accepts zero args; subtract it from the required + // count so PHP's ArgumentCountError-equivalent calls (too few args before + // the variadic) are correctly rejected by arity compatibility. + const requiredParameterCount = total - optionalCount - (hasVariadic ? 1 : 0); + + return { + parameterCount, + requiredParameterCount, + parameterTypes: types.length > 0 ? types : undefined, + }; +} diff --git a/gitnexus/src/core/ingestion/languages/php/arity.ts b/gitnexus/src/core/ingestion/languages/php/arity.ts new file mode 100644 index 000000000..5b99a73c7 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/arity.ts @@ -0,0 +1,47 @@ +/** + * PHP arity check, accommodating variadic (`...$args`) and default parameters. + * + * The `def` metadata synthesized by `arity-metadata.ts`: + * - `parameterCount` — total formal parameters; `undefined` when + * the method has a variadic `...$param`. + * - `requiredParameterCount` — min required (excludes defaulted params + * and the variadic itself). + * - `parameterTypes` — declared type strings; contains the + * literal `'...'` when the method is variadic. + * + * Verdicts: + * - `'compatible'` — `required <= argCount <= max`, OR the def has + * variadic (any `argCount >= required`). + * - `'incompatible'` — argCount below required, or above max with no variadic. + * - `'unknown'` — metadata absent / incomplete; named-args can satisfy + * any arity so we return unknown when we detect them. + * + * PHP supports named arguments (PHP 8.0+): `save(force: true)`. Named-arg + * call sites cannot be arity-checked statically without parsing arg names, + * so we return `'unknown'` when the callsite carries named args (signalled + * by a negative `arity` value per the shared Callsite contract). + */ + +import type { Callsite, SymbolDefinition } from 'gitnexus-shared'; + +export function phpArityCompatibility( + def: SymbolDefinition, + callsite: Callsite, +): 'compatible' | 'unknown' | 'incompatible' { + const max = def.parameterCount; + const min = def.requiredParameterCount; + if (max === undefined && min === undefined) return 'unknown'; + + const argCount = callsite.arity; + // Negative arity signals named-argument call sites — can't narrow statically. + if (!Number.isFinite(argCount) || argCount < 0) return 'unknown'; + + const hasVarArgs = + def.parameterTypes !== undefined && + def.parameterTypes.some((t) => t === '...' || t.startsWith('...')); + + if (min !== undefined && argCount < min) return 'incompatible'; + if (max !== undefined && argCount > max && !hasVarArgs) return 'incompatible'; + + return 'compatible'; +} diff --git a/gitnexus/src/core/ingestion/languages/php/cache-stats.ts b/gitnexus/src/core/ingestion/languages/php/cache-stats.ts new file mode 100644 index 000000000..508eec580 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/cache-stats.ts @@ -0,0 +1,30 @@ +/** + * Dev-mode counters for the cross-phase scope-captures parse cache + * (PHP mirror of `languages/csharp/cache-stats.ts`). + * + * Gated by `PROF_SCOPE_RESOLUTION=1`. Production builds fold every + * increment into dead code via the module-level `PROF` constant, so + * the hot path in `captures.ts` stays branch-free. + */ + +const PROF = process.env.PROF_SCOPE_RESOLUTION === '1'; + +let CACHE_HITS = 0; +let CACHE_MISSES = 0; + +export function recordCacheHit(): void { + if (PROF) CACHE_HITS++; +} + +export function recordCacheMiss(): void { + if (PROF) CACHE_MISSES++; +} + +export function getPhpCaptureCacheStats(): { hits: number; misses: number } { + return { hits: CACHE_HITS, misses: CACHE_MISSES }; +} + +export function resetPhpCaptureCacheStats(): void { + CACHE_HITS = 0; + CACHE_MISSES = 0; +} diff --git a/gitnexus/src/core/ingestion/languages/php/captures.ts b/gitnexus/src/core/ingestion/languages/php/captures.ts new file mode 100644 index 000000000..692d87bc1 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/captures.ts @@ -0,0 +1,806 @@ +/** + * `emitScopeCaptures` for PHP (RFC #909 Ring 3 LANG-php). + * + * Drives the PHP scope query against tree-sitter-php and groups raw + * matches into `CaptureMatch[]` for the central extractor. Layers two + * synthesized streams on top: + * + * 1. **Decomposed use declarations** — each `namespace_use_declaration` + * is re-emitted with `@import.kind/source/name/alias` markers so + * `interpretPhpImport` can recover the ParsedImport shape without + * re-parsing raw text. Grouped uses fan out to one match per clause. + * + * 2. **Receiver-binding synthesis** — `$this` and `parent` type-bindings + * are synthesized on every non-static method entry. PHP's grammar + * does not express "implicit receiver of a non-static class method" + * via a clean `.scm` pattern, so we walk up the AST in code. + * + * 3. **Arity metadata synthesis** — `@declaration.parameter-count` / + * `@declaration.required-parameter-count` / `@declaration.parameter-types` + * are synthesized on function-like declarations so the registry can + * narrow overloads. + * + * 4. **PHPDoc synthesis** — @param and @return annotations in comment + * nodes preceding method/function declarations are extracted and emitted + * as `@type-binding.parameter` and `@type-binding.return` matches. + * + * 5. **Foreach loop synthesis** — `foreach ($users as $user)` emits + * a `@type-binding.alias` match binding the loop variable to the + * element type of the iterable (resolved from PHPDoc or scopeEnv). + * + * Pure given the input source text. No I/O, no globals consulted. + */ + +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { findNodeAtRange, nodeToCapture, syntheticCapture } from '../../utils/ast-helpers.js'; +import { splitNamespaceUseDeclaration } from './import-decomposer.js'; +import { computePhpArityMetadata } from './arity-metadata.js'; +import { synthesizePhpReceiverBinding } from './receiver-binding.js'; +import { getPhpParser, getPhpScopeQuery } from './query.js'; +import { recordCacheHit, recordCacheMiss } from './cache-stats.js'; +import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; + +type SyntaxNode = ReturnType['parse']>['rootNode']; + +/** Declaration anchors that carry function-like arity metadata. */ +const FUNCTION_DECL_TAGS = ['@declaration.method', '@declaration.function'] as const; + +/** tree-sitter-php node types that the method extractor accepts. */ +const FUNCTION_NODE_TYPES = [ + 'method_declaration', + 'function_definition', + 'anonymous_function', + 'arrow_function', +] as const; + +export function emitPhpScopeCaptures( + sourceText: string, + _filePath: string, + cachedTree?: unknown, +): readonly CaptureMatch[] { + // Skip the parse when the caller already produced a Tree for this source. + // The cachedTree parameter is typed as `unknown` at the LanguageProvider + // contract layer; cast here at the use site. + let tree = cachedTree as ReturnType['parse']> | undefined; + if (tree === undefined) { + tree = parseSourceSafe(getPhpParser(), sourceText, undefined, { + bufferSize: getTreeSitterBufferSize(sourceText), + }); + recordCacheMiss(); + } else { + recordCacheHit(); + } + + const rawMatches = getPhpScopeQuery().matches(tree.rootNode); + const out: CaptureMatch[] = []; + + // Pre-scan: collect anchor node IDs of property_declaration nodes already + // matched by the typed @declaration.property pattern (query.ts ~lines 95–98). + // The untyped @declaration.variable catch-all (query.ts ~lines 101–103) is + // intentionally loose — it has no `type:` constraint, so tree-sitter also + // matches it against typed property declarations and emits a second capture + // for the same property_declaration anchor. Graph-level def-id collision + // currently masks the duplicate at the node-emit layer, but the catch-all + // capture still flows through scope-binding / name-keyed registries with a + // `$`-prefixed name that the typed branch's `$`-strip never normalizes — + // a known vector for receiver-binding lookup pollution. The two patterns + // produce separate rawMatches entries with separate `grouped` maps, so the + // dedup has to be cross-match: build the set here, then skip + // @declaration.variable matches whose anchor is in it (loop below). + const typedPropertyAnchorIds = new Set(); + for (const m of rawMatches) { + for (const c of m.captures) { + if (c.name === 'declaration.property') { + typedPropertyAnchorIds.add(c.node.id); + break; + } + } + } + + for (const m of rawMatches) { + // Group captures by their tag name. Tree-sitter strips the leading + // `@`; we put it back so the central extractor's prefix lookups work. + const grouped: Record = {}; + for (const c of m.captures) { + const tag = '@' + c.name; + grouped[tag] = nodeToCapture(tag, c.node); + } + if (Object.keys(grouped).length === 0) continue; + + // Cross-match dedup for the typed-property double-match described above: + // skip @declaration.variable matches whose anchor was already captured as + // @declaration.property in an earlier match. + if (grouped['@declaration.variable'] !== undefined) { + const varCap = m.captures.find((c) => c.name === 'declaration.variable'); + if (varCap !== undefined && typedPropertyAnchorIds.has(varCap.node.id)) continue; + } + + // Normalize PHP property declarations: strip leading `$` from + // `@declaration.name` for @declaration.property matches. PHP stores + // field names WITHOUT the `$` sigil in the graph so that member access + // lookups like `$user->address` can find the property named `address` + // (not `$address`). `@type-binding.annotation` already strips `$` in + // `interpretPhpTypeBinding`; this mirrors that for the declaration side. + // + // Only applies to `@declaration.property` — typed class properties and + // constructor-promoted parameters. Untyped `@declaration.variable` keeps + // its `$` prefix (those defs are Variable type and not in the field + // registry, so their name doesn't affect member lookup). + if ( + grouped['@declaration.property'] !== undefined && + grouped['@declaration.name'] !== undefined + ) { + const nameCap = grouped['@declaration.name']; + if (nameCap.text.startsWith('$')) { + grouped['@declaration.name'] = { ...nameCap, text: nameCap.text.slice(1) }; + } + } + + // Normalize PHP receiver expressions so the compound-receiver resolver + // can walk chains expressed with `->` (PHP) as if they used `.` (the + // resolver's canonical separator). Without this, `$user->address->save()` + // has receiver text `$user->address` — the resolver sees no `.` separator, + // treats it as a bare identifier, and cannot walk field types. + // + // Transformation applied to `@reference.receiver` captures: + // 1. Replace `->` with `.` ($user->address → $user.address) + // 2. Strip leading `$` from each segment ($user.address → user.address) + // 3. Strip trailing `?` on null-safe receivers ($user? → user) + // + // This is a PHP-local normalization — no shared pipeline code is changed. + if (grouped['@reference.receiver'] !== undefined) { + const recvCap = grouped['@reference.receiver']!; + const normalized = normalizePhpReceiver(recvCap.text); + if (normalized !== recvCap.text) { + grouped['@reference.receiver'] = { ...recvCap, text: normalized }; + } + } + + // Normalize static property write: strip leading `$` from `@reference.name` + // so `User::$count` resolves to property `count` (stored without `$` in graph). + if (grouped['@reference.write.static'] !== undefined) { + const nameCap = grouped['@reference.name']; + if (nameCap !== undefined && nameCap.text.startsWith('$')) { + grouped['@reference.name'] = { + ...nameCap, + text: nameCap.text.slice(1), + }; + } + // Re-tag as @reference.write.member so downstream passes see a uniform write kind. + grouped['@reference.write.member'] = grouped['@reference.write.static']!; + delete grouped['@reference.write.static']; + } + + // Decompose each `namespace_use_declaration` so `interpretPhpImport` + // sees the kind/source/name/alias markers it consumes. + if (grouped['@import.statement'] !== undefined) { + const stmtCapture = grouped['@import.statement']; + const stmtNode = findNodeAtRange( + tree.rootNode, + stmtCapture.range, + 'namespace_use_declaration', + ); + if (stmtNode !== null) { + const decomposed = splitNamespaceUseDeclaration(stmtNode); + if (decomposed.length > 0) { + for (const d of decomposed) out.push(d); + continue; + } + } + // Defensive fallback: emit the raw match. + out.push(grouped); + continue; + } + + // Synthesize `$this` / `parent` receiver type-bindings on every + // non-static method-like. Mirrors C#'s `this` / `base` synthesis. + if (grouped['@scope.function'] !== undefined) { + out.push(grouped); + const anchor = grouped['@scope.function']!; + const fnNode = findFunctionNode(tree.rootNode, anchor.range); + if (fnNode !== null) { + for (const synth of synthesizePhpReceiverBinding(fnNode)) { + out.push(synth); + } + // Synthesize PHPDoc @param and @return type bindings for this fn. + for (const synth of synthesizePhpDocBindings(fnNode)) { + out.push(synth); + } + // Synthesize foreach loop variable bindings inside this fn body. + for (const synth of synthesizeForeachBindings(fnNode)) { + out.push(synth); + } + } + continue; + } + + // Synthesize arity metadata on function-like declarations so the + // registry can narrow overloads. + const declTag = FUNCTION_DECL_TAGS.find((t) => grouped[t] !== undefined); + if (declTag !== undefined) { + const anchor = grouped[declTag]!; + const fnNode = findFunctionNode(tree.rootNode, anchor.range); + if (fnNode !== null) { + const arity = computePhpArityMetadata(fnNode); + if (arity.parameterCount !== undefined) { + grouped['@declaration.parameter-count'] = syntheticCapture( + '@declaration.parameter-count', + fnNode, + String(arity.parameterCount), + ); + } + if (arity.requiredParameterCount !== undefined) { + grouped['@declaration.required-parameter-count'] = syntheticCapture( + '@declaration.required-parameter-count', + fnNode, + String(arity.requiredParameterCount), + ); + } + if (arity.parameterTypes !== undefined) { + grouped['@declaration.parameter-types'] = syntheticCapture( + '@declaration.parameter-types', + fnNode, + JSON.stringify(arity.parameterTypes), + ); + } + } + } + + // Synthesize `@reference.arity` on every call site so the registry's + // arity filter can narrow overloads. Count the `argument` children of + // the backing `arguments` node. Mirrors C#'s pattern (csharp/captures.ts + // lines 149-186). PHP needs this for arity-based dispatch (Cluster H). + const callTag = ( + ['@reference.call.free', '@reference.call.member', '@reference.call.constructor'] as const + ).find((t) => grouped[t] !== undefined); + if (callTag !== undefined && grouped['@reference.arity'] === undefined) { + const anchor = grouped[callTag]!; + const callNode = + findNodeAtRange(tree.rootNode, anchor.range, 'function_call_expression') ?? + findNodeAtRange(tree.rootNode, anchor.range, 'member_call_expression') ?? + findNodeAtRange(tree.rootNode, anchor.range, 'nullsafe_member_call_expression') ?? + findNodeAtRange(tree.rootNode, anchor.range, 'scoped_call_expression') ?? + findNodeAtRange(tree.rootNode, anchor.range, 'object_creation_expression'); + if (callNode !== null) { + const argList = callNode.childForFieldName('arguments'); + const args: SyntaxNode[] = []; + if (argList !== null) { + for (let i = 0; i < argList.namedChildCount; i++) { + const child = argList.namedChild(i); + if (child !== null && child.type === 'argument') args.push(child); + } + } + grouped['@reference.arity'] = syntheticCapture( + '@reference.arity', + callNode, + String(args.length), + ); + // Infer argument types from literal nodes for type-based narrowing. + // Non-literal arguments emit empty string ("unknown" = any-match). + const argTypes = args.map((arg) => inferPhpArgType(arg)); + grouped['@reference.parameter-types'] = syntheticCapture( + '@reference.parameter-types', + callNode, + JSON.stringify(argTypes), + ); + } + } + + out.push(grouped); + } + + return out; +} + +/** Find the first PHP function-like node at the given range. */ +function findFunctionNode(rootNode: SyntaxNode, range: Capture['range']): SyntaxNode | null { + for (const nodeType of FUNCTION_NODE_TYPES) { + const n = findNodeAtRange(rootNode, range, nodeType); + if (n !== null) return n as SyntaxNode; + } + return null; +} + +// ─── PHP receiver normalization ────────────────────────────────────────────── + +/** + * Normalize a PHP receiver expression so the language-agnostic + * compound-receiver resolver (which splits on `.`) can walk field-type chains. + * + * The compound-receiver resolver: + * - splits on `.` to get chain segments + * - looks up the first segment in `typeBindings` (keyed with `$` for variables) + * - walks subsequent segments as field names (stored without `$` in the graph) + * + * Transformation: + * 1. Replace `->` and `?->` with `.` so the resolver's splitter works + * 2. Strip any bare `?` fragment left by null-safe chain ends + * 3. Strip `$` from all segments EXCEPT the first (which is a variable + * and must keep `$` for typeBindings lookup — e.g. `$user → User`) + * + * Examples: + * `$user` → `$user` (bare variable — unchanged) + * `$user->address` → `$user.address` + * `$user->address->city` → `$user.address.city` + * `$user?` → `$user` (null-safe trailing `?` stripped) + * `$this` → `$this` (receiverBinding uses `$this`) + * `parent` → `parent` (super-receiver check) + */ +function normalizePhpReceiver(raw: string): string { + // Keep `$this`, `parent`, and `self` as-is. + if (raw === '$this' || raw === 'parent' || raw === 'self') return raw; + + // Replace `?->` (null-safe) and plain `->` with `.`. + let text = raw.replace(/\?->/g, '.').replace(/->/g, '.'); + // Strip a trailing `?` (null-safe fragment on the last object node). + text = text.replace(/\?$/, ''); + // Collapse any doubled dots from `?->` where `?` was on its own. + text = text.replace(/\.{2,}/g, '.'); + // Strip trailing dot. + text = text.replace(/\.$/, ''); + + // Split on `.` and strip `$` from all segments EXCEPT the first. + // The first segment is a PHP variable (typeBinding key includes `$`). + // Subsequent segments are property/method names (stored without `$`). + const segments = text.split('.'); + for (let i = 1; i < segments.length; i++) { + const s = segments[i]; + if (s !== undefined && s.startsWith('$')) segments[i] = s.slice(1); + } + return segments.join('.'); +} + +// ─── PHP argument type inference ───────────────────────────────────────────── + +/** + * Infer the PHP type of a call argument from its literal shape. + * Returns an empty string for non-literals (treated as "unknown" = any-match). + * Mirrors C#'s `inferArgType` helper. + */ +function inferPhpArgType(argNode: SyntaxNode): string { + // argument node wraps the actual expression + const expr = argNode.firstNamedChild ?? argNode; + switch (expr.type) { + case 'integer': + return 'int'; + case 'float': + return 'float'; + case 'string': + case 'encapsed_string': + case 'heredoc': + case 'nowdoc': + return 'string'; + case 'boolean': + case 'true': + case 'false': + return 'bool'; + case 'null': + return 'null'; + default: + return ''; + } +} + +// ─── PHPDoc synthesis ───────────────────────────────────────────────────────── + +/** PHP 8+ attribute_list nodes that appear between PHPDoc and method. */ +const SKIP_SIBLING_TYPES = new Set(['attribute_list', 'attribute', 'comment']); + +/** Regex for PHPDoc @param: standard `@param Type $name` */ +const PHPDOC_PARAM_RE = /@param\s+(\S+)\s+\$(\w+)/g; +/** Regex for PHPDoc @param: alternate `@param $name Type` */ +const PHPDOC_PARAM_ALT_RE = /@param\s+\$(\w+)\s+(\S+)/g; +/** Regex for PHPDoc @return: `@return Type` */ +const PHPDOC_RETURN_RE = /@return\s+(\S+)/; + +/** + * Normalize a PHP type string to a simple class name for binding purposes. + * Returns null for primitives or uninformative types. + * Mirrors `normalizePhpType` in `interpret.ts` but operates on raw PHPDoc strings. + */ +function normalizePhpDocType(raw: string): string | null { + let type = raw.trim(); + // Strip nullable prefix + if (type.startsWith('?')) type = type.slice(1).trim(); + // Strip array suffix: User[] → User + if (type.endsWith('[]')) type = type.slice(0, -2).trim(); + // Strip union with null/false/void + if (type.includes('|')) { + const parts = type + .split('|') + .map((p) => p.trim()) + .filter((p) => p !== 'null' && p !== 'false' && p !== 'void' && p !== 'mixed' && p !== ''); + if (parts.length !== 1) return null; + type = parts[0]; + } + // Strip intersection: take first part + if (type.includes('&')) { + const first = type.split('&')[0].trim(); + if (first === '') return null; + type = first; + } + // Strip generic wrapper: Collection → User + const genericMatch = type.match(/^\w[\w\\]*\s*<([^,<>]+)>$/); + if (genericMatch) { + type = genericMatch[1].trim(); + // Strip array suffix again inside generic + if (type.endsWith('[]')) type = type.slice(0, -2).trim(); + } + // Strip namespace qualifier: \App\Models\User → User + if (type.includes('\\')) { + const segs = type.split('\\').filter(Boolean); + type = segs[segs.length - 1] ?? type; + } + // Reject primitives + if (PHP_PRIMITIVES.has(type.toLowerCase())) return null; + // Must be a simple identifier + if (!/^\w+$/.test(type)) return null; + return type; +} + +const PHP_PRIMITIVES = new Set([ + 'int', + 'integer', + 'float', + 'double', + 'string', + 'bool', + 'boolean', + 'array', + 'object', + 'callable', + 'iterable', + 'null', + 'void', + 'never', + 'mixed', + 'false', + 'true', + 'self', + 'static', + 'parent', +]); + +/** + * Collect comment text from siblings immediately before `fnNode`. + * Skips PHP 8+ attribute_list nodes. + */ +function collectPrecedingComments(fnNode: SyntaxNode): string { + const texts: string[] = []; + let sibling = fnNode.previousSibling; + while (sibling !== null) { + if (sibling.type === 'comment') { + texts.unshift(sibling.text); + } else if (sibling.isNamed && !SKIP_SIBLING_TYPES.has(sibling.type)) { + break; + } + sibling = sibling.previousSibling; + } + return texts.join('\n'); +} + +/** + * Synthesize PHPDoc @param and @return type-binding captures for a + * method_declaration or function_definition node. + * + * PHPDoc @param Type $name → `@type-binding.parameter` match (anchored at fn body/return_type). + * PHPDoc @return Type → `@type-binding.return` match (anchored at fn name). + */ +function synthesizePhpDocBindings(fnNode: SyntaxNode): CaptureMatch[] { + if (fnNode.type !== 'method_declaration' && fnNode.type !== 'function_definition') return []; + + const commentBlock = collectPrecedingComments(fnNode); + if (commentBlock === '') return []; + + const out: CaptureMatch[] = []; + + // Anchor for parameter type-bindings: the function body (or return_type as fallback). + // The binding must be inside the function scope so it's visible to body statements. + const bodyNode = fnNode.childForFieldName('body'); + const anchorNode = bodyNode ?? fnNode; + + // ── @param annotations ──────────────────────────────────────────────────── + PHPDOC_PARAM_RE.lastIndex = 0; + let m: RegExpExecArray | null; + const seenParams = new Set(); + + while ((m = PHPDOC_PARAM_RE.exec(commentBlock)) !== null) { + const rawType = m[1]; + const paramName = '$' + m[2]; + const typeName = normalizePhpDocType(rawType); + if (typeName === null) continue; + seenParams.add(paramName); + out.push({ + '@type-binding.parameter': nodeToCapture('@type-binding.parameter', anchorNode), + '@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, paramName), + '@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeName), + }); + } + + // Also check alternate PHPDoc order: @param $name Type + PHPDOC_PARAM_ALT_RE.lastIndex = 0; + while ((m = PHPDOC_PARAM_ALT_RE.exec(commentBlock)) !== null) { + const paramName = '$' + m[1]; + if (seenParams.has(paramName)) continue; // standard format takes priority + const rawType = m[2]; + const typeName = normalizePhpDocType(rawType); + if (typeName === null) continue; + out.push({ + '@type-binding.parameter': nodeToCapture('@type-binding.parameter', anchorNode), + '@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, paramName), + '@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeName), + }); + } + + // ── @return annotation ──────────────────────────────────────────────────── + const returnMatch = PHPDOC_RETURN_RE.exec(commentBlock); + if (returnMatch !== null) { + const rawType = returnMatch[1]; + const typeName = normalizePhpDocType(rawType); + if (typeName !== null) { + // @return bindings must be anchored at the method name and hoisted to Module scope + // by phpBindingScopeFor (which checks for @type-binding.return presence). + // Use the function_definition/method_declaration node itself as the anchor — it + // coincides with the innermost scope's range, so auto-hoist kicks in. + const nameNode = fnNode.childForFieldName('name') ?? fnNode; + out.push({ + '@type-binding.return': nodeToCapture('@type-binding.return', fnNode), + '@type-binding.name': syntheticCapture('@type-binding.name', nameNode, nameNode.text), + '@type-binding.type': syntheticCapture('@type-binding.type', nameNode, typeName), + }); + } + } + + return out; +} + +// ─── Foreach synthesis ─────────────────────────────────────────────────────── + +/** + * Walk all `foreach_statement` nodes inside `fnNode` and synthesize + * `@type-binding.alias` captures binding the loop variable to the + * element type of the iterable. + * + * Supports: + * - `foreach ($users as $user)` — simple iterable variable + * - `foreach ($users as $k => $user)` — key→value pair + * - `foreach ($this->users as $user)` — member access iterable + * - `foreach (getUsers() as $user)` — NOT yet supported (needs return type) + * + * The element type is resolved by: + * 1. Looking up the iterable name in PHPDoc @param bindings already + * collected for this function (passed via typeBindingsByName). + * 2. Direct resolution when iterable's env type IS the element type + * (because PHPDoc normalizes `User[]` → `User` already). + */ +function synthesizeForeachBindings(fnNode: SyntaxNode): CaptureMatch[] { + if ( + fnNode.type !== 'method_declaration' && + fnNode.type !== 'function_definition' && + fnNode.type !== 'anonymous_function' && + fnNode.type !== 'arrow_function' + ) { + return []; + } + + const out: CaptureMatch[] = []; + + // Build a mini type map from the function's PHPDoc @param annotations. + // This is re-parsed here (not cached from synthesizePhpDocBindings) for simplicity; + // the cost is negligible given the small comment sizes. + const commentBlock = collectPrecedingComments(fnNode); + const paramTypeMap = buildParamTypeMap(commentBlock); + + // Walk the function body for foreach_statement nodes. + const bodyNode = fnNode.childForFieldName('body'); + if (bodyNode === null) return []; + collectForeachBindings(bodyNode, fnNode, paramTypeMap, out); + + return out; +} + +/** Build a map of `$paramName → elementTypeName` from PHPDoc @param in a comment block. */ +function buildParamTypeMap(commentBlock: string): Map { + const map = new Map(); + if (commentBlock === '') return map; + + PHPDOC_PARAM_RE.lastIndex = 0; + let m: RegExpExecArray | null; + while ((m = PHPDOC_PARAM_RE.exec(commentBlock)) !== null) { + const rawType = m[1]; + const paramName = '$' + m[2]; + const typeName = normalizePhpDocType(rawType); + if (typeName !== null) map.set(paramName, typeName); + } + PHPDOC_PARAM_ALT_RE.lastIndex = 0; + while ((m = PHPDOC_PARAM_ALT_RE.exec(commentBlock)) !== null) { + const paramName = '$' + m[1]; + if (map.has(paramName)) continue; + const rawType = m[2]; + const typeName = normalizePhpDocType(rawType); + if (typeName !== null) map.set(paramName, typeName); + } + return map; +} + +/** + * Walk a subtree and collect foreach_statement bindings. + * Recursively descends into all child nodes. + */ +function collectForeachBindings( + node: SyntaxNode, + fnNode: SyntaxNode, + paramTypeMap: Map, + out: CaptureMatch[], +): void { + if (node.type === 'foreach_statement') { + const synth = synthesizeSingleForeach(node, fnNode, paramTypeMap); + if (synth !== null) out.push(synth); + } + for (let i = 0; i < node.childCount; i++) { + const child = node.child(i); + if (child !== null) { + collectForeachBindings(child, fnNode, paramTypeMap, out); + } + } +} + +/** + * Synthesize a single `@type-binding.alias` match for a `foreach_statement`. + * + * AST structure for foreach_statement (tree-sitter-php): + * foreach ( as ) + * Named children (excluding body): first = iterable, second = value or pair. + */ +function synthesizeSingleForeach( + foreachNode: SyntaxNode, + fnNode: SyntaxNode, + paramTypeMap: Map, +): CaptureMatch | null { + // Collect non-body named children: [iterable, value_or_pair] + const bodyNode = foreachNode.childForFieldName('body'); + const children: SyntaxNode[] = []; + for (let i = 0; i < foreachNode.namedChildCount; i++) { + const child = foreachNode.namedChild(i); + if (child !== null && child !== bodyNode) children.push(child); + } + if (children.length < 2) return null; + + const iterableNode = children[0]; + const valueOrPair = children[1]; + + // Determine the loop variable node + let loopVarNode: SyntaxNode; + if (valueOrPair.type === 'pair') { + // $key => $value — use the last named child of the pair + const lastChild = valueOrPair.namedChild(valueOrPair.namedChildCount - 1); + if (lastChild === null) return null; + loopVarNode = + lastChild.type === 'by_ref' ? (lastChild.firstNamedChild ?? lastChild) : lastChild; + } else { + loopVarNode = + valueOrPair.type === 'by_ref' ? (valueOrPair.firstNamedChild ?? valueOrPair) : valueOrPair; + } + + // Loop variable must be a variable_name + if (loopVarNode.type !== 'variable_name') return null; + const loopVarName = loopVarNode.text; // e.g. '$user' + + // Resolve the element type from the iterable + let elementType: string | null = null; + + if (iterableNode.type === 'variable_name') { + // foreach ($users as $user) — look up $users in param map + const iterableName = iterableNode.text; // e.g. '$users' + elementType = paramTypeMap.get(iterableName) ?? null; + } else if (iterableNode.type === 'member_access_expression') { + // foreach ($this->users as $user) — property name is the field + const propNameNode = iterableNode.childForFieldName('name'); + if (propNameNode !== null) { + // Property stored with $ prefix in paramTypeMap (rare for $this->prop patterns) + // Try both with and without $ prefix + const propKey = '$' + propNameNode.text; + elementType = paramTypeMap.get(propKey) ?? null; + if (elementType === null) { + // Try to find the property type from the enclosing class + elementType = findClassPropertyElementType(iterableNode, fnNode); + } + } + } else if (iterableNode.type === 'function_call_expression') { + // foreach (getUsers() as $user) — use the function name as a type alias. + // The function's @return annotation produces a @type-binding.return binding + // in the Module scope (e.g. getUsers → User). The scope-extractor's + // followChainedRef will resolve $user → getUsers → User. + const funcNode = iterableNode.childForFieldName('function'); + if (funcNode !== null && funcNode.type === 'name') { + elementType = funcNode.text; // e.g. 'getUsers' — chain will be resolved later + } + } else if (iterableNode.type === 'member_call_expression') { + // foreach ($this->getUsers() as $user) — use the method name as a type alias. + const methodNameNode = iterableNode.childForFieldName('name'); + if (methodNameNode !== null) { + elementType = methodNameNode.text; // e.g. 'getUsers' + } + } + + if (elementType === null) return null; + + // Anchor the binding inside the foreach body so it's scoped to the loop. + const anchorNode = bodyNode ?? foreachNode; + + return { + '@type-binding.alias': nodeToCapture('@type-binding.alias', anchorNode), + '@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, loopVarName), + '@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, elementType), + }; +} + +/** + * Try to find the element type for `$this->property` member access by walking + * up from the foreach to the enclosing class and scanning the property declaration. + */ +function findClassPropertyElementType( + memberAccessNode: SyntaxNode, + fnNode: SyntaxNode, +): string | null { + const propNameNode = memberAccessNode.childForFieldName('name'); + if (propNameNode === null) return null; + const propName = propNameNode.text; + + // Walk up from fnNode to find the enclosing class declaration + let cur: SyntaxNode | null = fnNode.parent; + while (cur !== null) { + if (cur.type === 'class_declaration' || cur.type === 'trait_declaration') { + break; + } + cur = cur.parent; + } + if (cur === null) return null; + + // Find the property_declaration with matching variable_name '$propName' + const declList = cur.childForFieldName('body'); + if (declList === null) return null; + + for (let i = 0; i < declList.namedChildCount; i++) { + const child = declList.namedChild(i); + if (child === null || child.type !== 'property_declaration') continue; + for (let j = 0; j < child.namedChildCount; j++) { + const elem = child.namedChild(j); + if (elem === null || elem.type !== 'property_element') continue; + const varNameNode = elem.firstNamedChild; + if (varNameNode === null || varNameNode.text !== '$' + propName) continue; + // Found the property — get its element type from @var PHPDoc or native type + return extractPropertyElementType(child); + } + } + return null; +} + +/** Regex for PHPDoc @var: `@var Type` */ +const PHPDOC_VAR_RE = /@var\s+(\S+)/; + +/** + * Extract element type from a property_declaration node: + * 1. PHPDoc @var annotation on a preceding comment sibling + * 2. PHP 7.4+ native type field (non-array) + */ +function extractPropertyElementType(propDecl: SyntaxNode): string | null { + // Strategy 1: PHPDoc @var on a preceding comment sibling + let sibling = propDecl.previousSibling; + while (sibling !== null) { + if (sibling.type === 'comment') { + const m = PHPDOC_VAR_RE.exec(sibling.text); + if (m !== null) return normalizePhpDocType(m[1]); + } else if (sibling.isNamed && !SKIP_SIBLING_TYPES.has(sibling.type)) { + break; + } + sibling = sibling.previousSibling; + } + // Strategy 2: native type field — skip generic 'array' + const typeNode = propDecl.childForFieldName('type'); + if (typeNode === null) return null; + const typeName = typeNode.text.trim(); + if (typeName === 'array' || typeName === '') return null; + return normalizePhpDocType(typeName); +} diff --git a/gitnexus/src/core/ingestion/languages/php/import-decomposer.ts b/gitnexus/src/core/ingestion/languages/php/import-decomposer.ts new file mode 100644 index 000000000..f17456805 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/import-decomposer.ts @@ -0,0 +1,304 @@ +/** + * Decompose a PHP `namespace_use_declaration` into one or more + * `CaptureMatch` objects carrying the synthesized markers + * `@import.kind` / `@import.source` / `@import.name` / `@import.alias` + * that `interpretPhpImport` consumes. + * + * PHP import forms handled: + * + * use Foo\Bar; → namespace, localName=Bar + * use Foo\Bar as Baz; → alias, localName=Baz + * use function Foo\bar; → function, localName=bar + * use const Foo\BAR; → const, localName=BAR + * use Foo\{A, B as C}; → grouped: one match per clause + * use function Foo\{f, g as h}; → grouped function variants + * use const Foo\{X, Y as Z}; → grouped const variants + * + * Unlike C#'s decomposer this is 1:N — each grouped use_declaration + * fans out to one CaptureMatch per inner clause. + */ + +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js'; + +export type PhpImportKind = 'namespace' | 'alias' | 'function' | 'const'; + +interface PhpImportSpec { + readonly kind: PhpImportKind; + /** Full backslash-separated path (backslashes intact): `Foo\Bar\Baz`. */ + readonly source: string; + /** Local binding name — last source segment for plain imports, the + * alias identifier for aliased imports. */ + readonly name: string; + /** Present iff kind === 'alias'. */ + readonly alias?: string; + /** Anchor node for synthesized captures (range-wise). */ + readonly atNode: SyntaxNode; +} + +/** + * Decompose a `namespace_use_declaration` node into one `CaptureMatch` + * per logical import. Returns `[]` when the node is unrecognized or + * carries no resolvable clauses. + */ +export function splitNamespaceUseDeclaration(stmtNode: SyntaxNode): CaptureMatch[] { + if (stmtNode.type !== 'namespace_use_declaration') return []; + + // Detect qualifier keyword: `use function` / `use const` + // tree-sitter-php uses a `use_type` or `function`/`const` keyword + // child to distinguish them. We scan the raw text before the first + // backslash-path child. + const qualifier = detectQualifier(stmtNode); + + // Grouped use: `use Foo\{A, B as C}` — find namespace_use_group child. + const groupNode = findNamedChild(stmtNode, 'namespace_use_group'); + if (groupNode !== null) { + return decomposeGrouped(stmtNode, groupNode, qualifier); + } + + // Single use clause (possibly aliased). + const spec = parseSingleUseClause(stmtNode, qualifier); + if (spec === null) return []; + return [buildImportMatch(stmtNode, spec)]; +} + +// ── Qualifier detection ──────────────────────────────────────────────────── + +/** + * Return the qualifier keyword appearing after `use`: + * `'function'`, `'const'`, or `null` for plain namespace use. + * + * tree-sitter-php emits the qualifier as a `name` node with text + * "function" or "const" (not a keyword token in recent grammars), + * or as a dedicated `use_type` node. We inspect the node's raw text + * to be grammar-version-agnostic. + */ +function detectQualifier(node: SyntaxNode): PhpImportKind { + const raw = node.text; + // Match `use function` or `use const` at the start (after optional whitespace) + if (/^\s*use\s+function\s/i.test(raw)) return 'function'; + if (/^\s*use\s+const\s/i.test(raw)) return 'const'; + return 'namespace'; +} + +// ── Single clause parsing ────────────────────────────────────────────────── + +function parseSingleUseClause(node: SyntaxNode, qualifier: PhpImportKind): PhpImportSpec | null { + // A plain `namespace_use_declaration` has one or more + // `namespace_use_clause` named children (each clause is one import, + // comma-separated for multiple). For the single case there is one. + const clause = findNamedChild(node, 'namespace_use_clause'); + if (clause !== null) return parseUseClause(clause, qualifier); + + // Older grammar versions may put the qualified_name directly under + // the declaration node. Check for a qualified_name or name child. + const qualName = findNamedChild(node, 'qualified_name') ?? findNamedChild(node, 'name'); + if (qualName === null) return null; + const source = qualName.text.trim(); + if (source === '') return null; + return { + kind: qualifier, + source, + name: lastSegment(source), + atNode: node, + }; +} + +function parseUseClause(clause: SyntaxNode, qualifier: PhpImportKind): PhpImportSpec | null { + // namespace_use_clause: + // qualified_name (or name) + // optional: alias_clause → "as" name (some grammar versions) + // optional: bare name node (tree-sitter-php ≥ 0.22 emits the + // alias as a sibling `name` node + // directly, not inside alias_clause) + const qualName = findNamedChild(clause, 'qualified_name') ?? findNamedChild(clause, 'name'); + if (qualName === null) return null; + const source = qualName.text.trim(); + if (source === '') return null; + + // Strategy 1: explicit alias_clause wrapper (older grammar versions). + const aliasClause = findNamedChild(clause, 'alias_clause'); + if (aliasClause !== null) { + // alias_clause: "as" name + const aliasName = findNamedChild(aliasClause, 'name') ?? aliasClause.firstNamedChild; + const alias = aliasName?.text.trim() ?? ''; + if (alias === '') return null; + return { + kind: 'alias', + source, + name: alias, + alias, + atNode: clause, + }; + } + + // Strategy 2: bare sibling `name` node after the qualified_name. + // tree-sitter-php (≥ 0.22) emits `use Foo\Bar as Baz` as: + // namespace_use_clause + // qualified_name "Foo\Bar" + // name "Baz" ← alias, no alias_clause wrapper + // Detect by: clause has ≥2 named children AND the last named child is + // a `name` node that differs from the qualName node. + if (clause.namedChildCount >= 2) { + const lastChild = clause.namedChild(clause.namedChildCount - 1); + if (lastChild !== null && lastChild !== qualName && lastChild.type === 'name') { + const alias = lastChild.text.trim(); + if (alias !== '') { + return { + kind: 'alias', + source, + name: alias, + alias, + atNode: clause, + }; + } + } + } + + return { + kind: qualifier, + source, + name: lastSegment(source), + atNode: clause, + }; +} + +// ── Grouped use decomposition ────────────────────────────────────────────── + +/** + * Decompose `use Foo\Bar\{A, B as C, function f, const X}` into one + * `CaptureMatch` per inner clause. + * + * The leading prefix (`Foo\Bar`) is prepended to each inner path. + * Inner clauses can override the qualifier with their own `function` / + * `const` keyword inside the group. + */ +function decomposeGrouped( + stmtNode: SyntaxNode, + groupNode: SyntaxNode, + outerQualifier: PhpImportKind, +): CaptureMatch[] { + // The prefix is the qualified_name that precedes the `{...}` group. + const prefixNode = findNamedChild(stmtNode, 'qualified_name') ?? findNamedChild(stmtNode, 'name'); + const prefix = prefixNode?.text.trim() ?? ''; + + const out: CaptureMatch[] = []; + + for (let i = 0; i < groupNode.namedChildCount; i++) { + const child = groupNode.namedChild(i); + if (child === null) continue; + + // Each child in a group may be: + // namespace_use_clause — plain or aliased + // namespace_use_type — `function` or `const` qualifier inside group + // We detect an inline qualifier by checking the raw text of the clause. + if (child.type !== 'namespace_use_clause') continue; + + const innerQualifier = detectInnerQualifier(child) ?? outerQualifier; + const spec = parseInnerClause(child, prefix, innerQualifier); + if (spec !== null) { + out.push(buildImportMatch(stmtNode, spec)); + } + } + + return out; +} + +/** + * Detect an inline qualifier keyword inside a grouped clause. + * e.g. `use Foo\{function bar, const BAZ}` — each clause may start with + * `function` or `const`. + */ +function detectInnerQualifier(clause: SyntaxNode): PhpImportKind | null { + const raw = clause.text.trim(); + if (/^function\s/i.test(raw)) return 'function'; + if (/^const\s/i.test(raw)) return 'const'; + return null; +} + +function parseInnerClause( + clause: SyntaxNode, + prefix: string, + qualifier: PhpImportKind, +): PhpImportSpec | null { + const qualName = findNamedChild(clause, 'qualified_name') ?? findNamedChild(clause, 'name'); + if (qualName === null) return null; + + // Strip inline `function` / `const` text prefix if present in the text. + let innerPath = qualName.text.trim(); + innerPath = innerPath.replace(/^(?:function|const)\s+/i, '').trim(); + if (innerPath === '') return null; + + const source = prefix !== '' ? `${prefix}\\${innerPath}` : innerPath; + + // Strategy 1: explicit alias_clause wrapper (older grammar versions). + const aliasClause = findNamedChild(clause, 'alias_clause'); + if (aliasClause !== null) { + const aliasName = findNamedChild(aliasClause, 'name') ?? aliasClause.firstNamedChild; + const alias = aliasName?.text.trim() ?? ''; + if (alias === '') return null; + return { + kind: 'alias', + source, + name: alias, + alias, + atNode: clause, + }; + } + + // Strategy 2: bare sibling `name` node after the qualified_name (tree-sitter-php ≥ 0.22). + if (clause.namedChildCount >= 2) { + const lastChild = clause.namedChild(clause.namedChildCount - 1); + if (lastChild !== null && lastChild !== qualName && lastChild.type === 'name') { + const alias = lastChild.text.trim(); + if (alias !== '') { + return { + kind: 'alias', + source, + name: alias, + alias, + atNode: clause, + }; + } + } + } + + return { + kind: qualifier, + source, + name: lastSegment(innerPath), + atNode: clause, + }; +} + +// ── CaptureMatch builder ─────────────────────────────────────────────────── + +function buildImportMatch(stmtNode: SyntaxNode, spec: PhpImportSpec): CaptureMatch { + const m: Record = { + '@import.statement': nodeToCapture('@import.statement', stmtNode), + '@import.kind': syntheticCapture('@import.kind', spec.atNode, spec.kind), + '@import.source': syntheticCapture('@import.source', spec.atNode, spec.source), + '@import.name': syntheticCapture('@import.name', spec.atNode, spec.name), + }; + if (spec.alias !== undefined) { + m['@import.alias'] = syntheticCapture('@import.alias', spec.atNode, spec.alias); + } + return m; +} + +// ── Helpers ──────────────────────────────────────────────────────────────── + +/** Last backslash-separated segment: `Foo\Bar\Baz` → `Baz`. */ +function lastSegment(path: string): string { + const parts = path.split('\\').filter(Boolean); + return parts[parts.length - 1] ?? path; +} + +/** Find the first named child with a given node type. */ +function findNamedChild(node: SyntaxNode, type: string): SyntaxNode | null { + for (let i = 0; i < node.namedChildCount; i++) { + const child = node.namedChild(i); + if (child !== null && child.type === type) return child; + } + return null; +} diff --git a/gitnexus/src/core/ingestion/languages/php/import-target.ts b/gitnexus/src/core/ingestion/languages/php/import-target.ts new file mode 100644 index 000000000..ebf7938b3 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/import-target.ts @@ -0,0 +1,140 @@ +/** + * Adapter from `(ParsedImport, WorkspaceIndex)` → concrete file path. + * + * Delegates to the existing `resolvePhpImportInternal` (PSR-4 via + * composer.json + suffix matching fallback). The `WorkspaceIndex` is + * opaque at this layer; consumers wire a `PhpResolveContext` shape + * carrying `fromFile` + `allFilePaths`. + * + * `loadPhpComposerConfig` is the `ScopeResolver.loadResolutionConfig` + * implementation — it loads `composer.json` once per workspace pass and + * threads the parsed config into every subsequent `resolveImportTarget` + * call via the opaque `resolutionConfig` parameter. + * + * Returning `null` lets the finalize algorithm mark the edge as + * `linkStatus: 'unresolved'`. + */ + +import type { ParsedImport, WorkspaceIndex } from 'gitnexus-shared'; +import { resolvePhpImportInternal } from '../../import-resolvers/php.js'; +import type { ComposerConfig } from '../../language-config.js'; +import { readFileSync } from 'node:fs'; +import { join } from 'node:path'; + +export interface PhpResolveContext { + readonly fromFile: string; + readonly allFilePaths: ReadonlySet; +} + +// ─── loadResolutionConfig ────────────────────────────────────────────────── + +/** + * Load and parse `composer.json` from the repo root. Returns a + * `ComposerConfig` object (PSR-4 namespace → directory mappings) or + * `null` when no `composer.json` is present or it cannot be parsed. + * + * The result is threaded into each `resolvePhpImportInternal` call as + * the `composerConfig` argument. + */ +export function loadPhpComposerConfig(repoPath: string): ComposerConfig | null { + try { + const composerPath = join(repoPath, 'composer.json'); + const raw = readFileSync(composerPath, 'utf8'); + const parsed = JSON.parse(raw) as unknown; + if (typeof parsed !== 'object' || parsed === null) return null; + + const composer = parsed as Record; + const autoload = composer['autoload'] as Record | undefined; + if (autoload === undefined) return null; + + const psr4Raw = (autoload['psr-4'] ?? {}) as Record; + const psr4 = new Map(); + + for (const [ns, dirs] of Object.entries(psr4Raw)) { + // namespace prefix ends with `\` — keep as-is; resolver strips it + const normalizedNs = ns.replace(/\\$/, ''); + const dir = Array.isArray(dirs) ? dirs[0] : dirs; + if (typeof dir === 'string') { + // Normalize directory path (strip trailing slash) + const normalizedDir = dir.replace(/\/+$/, ''); + psr4.set(normalizedNs, normalizedDir); + } + } + + return { psr4 }; + } catch { + return null; + } +} + +// ─── resolvePhpImportTarget ──────────────────────────────────────────────── + +/** + * LanguageProvider-shaped adapter: `(ParsedImport, WorkspaceIndex) → string | null`. + * + * The `WorkspaceIndex` is `unknown` in the shared contract. The scope-resolution + * orchestrator hands us a `PhpResolveContext`-shaped object; narrow structurally + * rather than via a cast chain so unexpected shapes return `null` cleanly. + */ +export function resolvePhpImportTarget( + parsedImport: ParsedImport, + workspaceIndex: WorkspaceIndex, +): string | null { + const ctx = workspaceIndex as PhpResolveContext | undefined; + if ( + ctx === undefined || + typeof (ctx as { fromFile?: unknown }).fromFile !== 'string' || + !((ctx as { allFilePaths?: unknown }).allFilePaths instanceof Set) + ) { + return null; + } + if (parsedImport.kind === 'dynamic-unresolved') return null; + if (parsedImport.targetRaw === null || parsedImport.targetRaw === '') return null; + + const allFiles = ctx.allFilePaths as Set; + const normalizedFileList = [...allFiles].map((f) => f.replace(/\\/g, '/')); + const allFileList = [...allFiles]; + + return resolvePhpImportInternal( + parsedImport.targetRaw, + null, // composerConfig not available through LanguageProvider path + allFiles, + normalizedFileList, + allFileList, + undefined, + ); +} + +/** + * ScopeResolver-shaped adapter: `(targetRaw, fromFile, allFilePaths, resolutionConfig?) → string | null`. + * + * Used inside `scope-resolver.ts`. Accepts the optional `resolutionConfig` + * (a `ComposerConfig | null` loaded once per workspace by + * `loadPhpComposerConfig`) and threads it into `resolvePhpImportInternal`. + */ +export function resolvePhpImportTargetInternal( + targetRaw: string, + _fromFile: string, + allFilePaths: ReadonlySet, + resolutionConfig?: unknown, +): string | null { + if (targetRaw === '') return null; + + const composerConfig = + resolutionConfig !== undefined && resolutionConfig !== null + ? (resolutionConfig as ComposerConfig) + : null; + + const allFiles = allFilePaths as Set; + const normalizedFileList = [...allFiles].map((f) => f.replace(/\\/g, '/')); + const allFileList = [...allFiles]; + + return resolvePhpImportInternal( + targetRaw, + composerConfig, + allFiles, + normalizedFileList, + allFileList, + undefined, + ); +} diff --git a/gitnexus/src/core/ingestion/languages/php/index.ts b/gitnexus/src/core/ingestion/languages/php/index.ts new file mode 100644 index 000000000..9b549bc3d --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/index.ts @@ -0,0 +1,73 @@ +/** + * PHP scope-resolution hooks (RFC #909 Ring 3 LANG-php, #938). + * + * Public API barrel. Consumers should import from this file rather than + * the individual modules. + * + * Module layout (each file is a single concern): + * + * - `query.ts` — tree-sitter query + lazy parser/query singletons + * - `captures.ts` — `emitPhpScopeCaptures` orchestrator + * - `import-decomposer.ts` — each `namespace_use_declaration` → ParsedImport captures + * - `interpret.ts` — capture-match → `ParsedImport` / `ParsedTypeBinding` + * - `simple-hooks.ts` — small/no-op hooks made explicit + * - `receiver-binding.ts` — synthesize `$this` / `parent` type-bindings on + * instance-method entry + * - `merge-bindings.ts` — PHP `use` precedence (local > import > wildcard) + * - `arity.ts` — PHP arity compatibility (variadic, defaults) + * - `arity-metadata.ts` — synthesize arity metadata from declarations + * - `import-target.ts` — `(ParsedImport, WorkspaceIndex) → file path` adapter + * wrapping `resolvePhpImportInternal` (PSR-4 + composer.json) + * - `scope-resolver.ts` — `ScopeResolver` registered in `SCOPE_RESOLVERS` + * - `cache-stats.ts` — PROF_SCOPE_RESOLUTION cache hit/miss counters + * + * ## Known limitations + * + * The PHP registry-primary path intentionally does NOT resolve the following. + * Each is a conscious trade-off at migration time. + * + * 1. **Trait `$this` → using-class binding** — for methods defined in a + * trait, `$this` is synthesized as a binding to the trait itself. + * Resolving `$this` to the actual using-class type requires cross-file + * analysis of all `use TraitName;` declarations in class bodies. + * Deferred to a follow-up; trait method resolution falls back to the + * trait scope. + * + * 2. **Anonymous classes** — `new class extends Foo { }` have no stable + * class name and are skipped by receiver-binding synthesis. The class + * body is still scoped; member lookups inside it will fall back to + * free-call resolution. + * + * 3. **Dynamic property/method access** — `$obj->{$name}()` and + * `$$varName` are not followed. The dynamic receiver is ignored and + * the call falls through to the shared free-call resolver. + * + * 4. **Magic methods** — `__get`, `__set`, `__call`, `__callStatic` are + * not modeled as virtual dispatch; they appear as regular method + * declarations in the graph but calls that would route through them + * at runtime are not distinguished. + * + * 5. **Laravel facade magic** — `App::make(...)`, `Cache::get(...)` etc. + * resolve statically to the Facade class rather than the underlying + * bound implementation. Deferred to a Laravel-specific plugin. + * + * 6. **Intersection types in parameters** — `T&U $param` takes the first + * named part (`T`). This matches the legacy type-extractor's behavior. + * + * Shadow-harness corpus parity is the authoritative signal for which of + * these matter in practice. The CI parity gate blocks any PR that regresses + * either the legacy or registry-primary run of + * `test/integration/resolvers/php.test.ts`. + */ + +export { emitPhpScopeCaptures } from './captures.js'; +export { getPhpCaptureCacheStats, resetPhpCaptureCacheStats } from './cache-stats.js'; +export { interpretPhpImport, interpretPhpTypeBinding } from './interpret.js'; +export { phpMergeBindings } from './merge-bindings.js'; +export { phpArityCompatibility } from './arity.js'; +export { resolvePhpImportTarget, type PhpResolveContext } from './import-target.js'; +export { phpBindingScopeFor, phpImportOwningScope, phpReceiverBinding } from './simple-hooks.js'; +// NOTE: phpScopeResolver is intentionally NOT re-exported from this barrel. +// Importing it here would create a circular dependency: +// php.ts → php/index.js → php/scope-resolver.js → ../php.js +// Registry and other consumers must import directly from './php/scope-resolver.js'. diff --git a/gitnexus/src/core/ingestion/languages/php/interpret.ts b/gitnexus/src/core/ingestion/languages/php/interpret.ts new file mode 100644 index 000000000..8aa07a736 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/interpret.ts @@ -0,0 +1,250 @@ +/** + * Capture-match → semantic-shape interpreters for PHP. + * + * - `interpretPhpImport` → `ParsedImport` + * - `interpretPhpTypeBinding` → `ParsedTypeBinding` + * + * Import matches arrive pre-decomposed by `emitPhpScopeCaptures` (one + * CaptureMatch per logical import, with synthesized `@import.kind / + * source / name / alias` markers). Type-binding matches arrive from + * the raw query captures — each `@type-binding.*` anchor carries + * `@type-binding.name` + `@type-binding.type`. + */ + +import type { CaptureMatch, ParsedImport, ParsedTypeBinding, TypeRef } from 'gitnexus-shared'; + +// ─── interpretImport ────────────────────────────────────────────────────── + +export function interpretPhpImport(captures: CaptureMatch): ParsedImport | null { + const kindCap = captures['@import.kind']; + const sourceCap = captures['@import.source']; + const nameCap = captures['@import.name']; + const aliasCap = captures['@import.alias']; + + const kind = kindCap?.text; + if (kind === undefined || sourceCap === undefined) return null; + + const source = sourceCap.text.trim(); + if (source === '') return null; + + switch (kind) { + case 'namespace': { + // `use Foo\Bar;` — PHP `use` is a NAMED import (binds the class + // `Bar`, not the namespace `Foo`). This differs from C# `using`, + // which is a true namespace import. Producing 'named' here makes + // `new Bar()` resolve to the imported class def. + const localName = nameCap?.text.trim() ?? lastSegment(source); + return { + kind: 'named', + localName, + importedName: localName, + targetRaw: source, + }; + } + case 'alias': { + // `use Foo\Bar as Baz;` + if (aliasCap === undefined) return null; + const alias = aliasCap.text.trim(); + if (alias === '') return null; + const importedName = lastSegment(source); + return { + kind: 'alias', + localName: alias, + importedName, + alias, + targetRaw: source, + }; + } + case 'function': { + // `use function Foo\bar;` — treat as named import; importedName is + // the function name (last segment). targetRaw is the full path. + const localName = nameCap?.text.trim() ?? lastSegment(source); + return { + kind: 'named', + localName, + importedName: localName, + targetRaw: source, + }; + } + case 'const': { + // `use const Foo\BAR;` — same shape as function. + const localName = nameCap?.text.trim() ?? lastSegment(source); + return { + kind: 'named', + localName, + importedName: localName, + targetRaw: source, + }; + } + default: + return null; + } +} + +// ─── interpretTypeBinding ───────────────────────────────────────────────── + +export function interpretPhpTypeBinding(captures: CaptureMatch): ParsedTypeBinding | null { + const nameCap = captures['@type-binding.name']; + const typeCap = captures['@type-binding.type']; + if (nameCap === undefined || typeCap === undefined) return null; + + // Determine source from anchor captures. Order: most-specific first. + let source: TypeRef['source'] = 'parameter-annotation'; + if (captures['@type-binding.self'] !== undefined) source = 'self'; + else if (captures['@type-binding.constructor'] !== undefined) source = 'constructor-inferred'; + else if (captures['@type-binding.annotation'] !== undefined) source = 'annotation'; + else if (captures['@type-binding.alias'] !== undefined) source = 'assignment-inferred'; + else if (captures['@type-binding.return'] !== undefined) source = 'return-annotation'; + + let rawType: string | null; + + if (source === 'assignment-inferred') { + // `@type-binding.alias` captures cover several assignment RHS shapes: + // - `$alias = $u` → rawType = '$u' (variable alias) + // - `$u = getUser()` → rawType = 'getUser' (callable alias) + // - `$u = new User()` → rawType = 'User' (constructor — via @type-binding.constructor; handled below) + // - `$role = UserRole::Viewer` → rawType = 'UserRole' (enum/class constant) + // + // For variable aliases (`$u`), `normalizePhpType` returns null because + // `$` is not a word character. We must preserve the raw `$`-prefixed name + // so `followChainedRef` can walk the chain `$alias → $u → User`. + // For callable/class names, `normalizePhpType` strips qualifiers correctly. + const rawText = typeCap.text.trim(); + if (rawText.startsWith('$')) { + // Variable alias: keep as-is for chain-following. + rawType = rawText; + } else { + rawType = normalizePhpType(rawText); + } + } else { + // All other sources: strip PHP type decoration to get the simple class name: + // ?User → User (nullable prefix) + // User|null → User (union with null/false/void) + // User&Loggable → User (intersection — take first meaningful) + // Collection → User (PHPDoc generic wrapper) + // User[] → User (array suffix) + // \App\Models\User → User (backslash qualifier) + rawType = normalizePhpType(typeCap.text.trim()); + } + + if (rawType === null) return null; + + // PHP variable names include the `$` sigil (e.g. `$user`). Most + // bindings keep it because they are looked up via the variable + // (`$user->method()` finds binding `$user`). Property field bindings + // are different: `$user->address` looks up `address` (no sigil) on + // the User class. Property declarations carry source `'annotation'`, + // so we strip the leading `$` for that source only. + let boundName = nameCap.text.trim(); + if (source === 'annotation' && boundName.startsWith('$')) { + boundName = boundName.slice(1); + } + + return { boundName, rawTypeName: rawType, source }; +} + +// ─── Type normalization ─────────────────────────────────────────────────── + +/** + * Normalize a PHP type string to a simple class identifier, or `null` + * when the type is uninformative (primitive, void, mixed, self, etc.). + * + * Rules applied in order: + * 1. Strip nullable prefix `?` + * 2. Split on `|` (union) — keep only if exactly one non-null part + * 3. Take first part of `&` intersection + * 4. Strip array suffix `[]` + * 5. Strip generic wrapper `Collection` → `User` + * 6. Canonicalize leading backslash off: `\App\Models\User` → `App\Models\User` + * 7. Reject PHP primitive / pseudo types + * + * The qualified form is preserved on `TypeRef.rawName` so downstream PHP + * receiver resolution can distinguish `\App\Other\User` from a same-simple-name + * `User` reachable via `use`. Without this, fully-qualified type hints collapse + * to ambiguous simple names and resolve against the caller's scope chain + * instead of the explicit target the source named (Codex PR #1497 review, + * finding 1). + */ +export function normalizePhpType(raw: string): string | null { + // 1. Strip nullable prefix + let type = raw.startsWith('?') ? raw.slice(1).trim() : raw; + + // 2. Union type — keep only if one non-null/false/void part remains + if (type.includes('|')) { + const parts = type + .split('|') + .map((p) => p.trim()) + .filter((p) => p !== 'null' && p !== 'false' && p !== 'void' && p !== 'mixed' && p !== ''); + if (parts.length !== 1) return null; + type = parts[0]; + } + + // 3. Intersection type — take the first part + if (type.includes('&')) { + const first = type.split('&')[0].trim(); + if (first === '') return null; + type = first; + } + + // 4. Strip array suffix + if (type.endsWith('[]')) type = type.slice(0, -2).trim(); + + // 5. Strip single-arg generic wrapper: Collection → User + // Qualified inner types (Collection<\App\Models\User>) survive — the + // capture group preserves whatever the writer named. + const genericMatch = type.match(/^\w[\w\\]*\s*<([^,<>]+)>$/); + if (genericMatch) { + type = genericMatch[1].trim(); + } + + // 6. Canonicalize leading backslash off — keep the qualified path intact. + // `\App\Models\User` → `App\Models\User`. `App\Models\User` → unchanged. + // Unqualified `User` stays as `User`. The qualified form is the lookup + // key into the workspace QualifiedNameIndex (PHP defs are indexed by + // namespace-joined qualifiedName); the leading-backslash distinction in + // source is only an "absolute path" anchor, not part of the canonical key. + if (type.startsWith('\\')) type = type.replace(/^\\+/, ''); + + // 7. Reject primitives / pseudo-types + if (isPrimitiveOrPseudo(type)) return null; + + // Must be a (possibly qualified) PHP identifier — segments of word chars + // separated by single backslashes. Empty segments (consecutive backslashes, + // trailing backslash) are rejected. + if (!/^\w+(?:\\\w+)*$/.test(type)) return null; + + return type; +} + +const PHP_PRIMITIVE_TYPES = new Set([ + 'int', + 'integer', + 'float', + 'double', + 'string', + 'bool', + 'boolean', + 'array', + 'object', + 'callable', + 'iterable', + 'null', + 'void', + 'never', + 'mixed', + 'false', + 'true', + 'self', + 'static', + 'parent', +]); + +function isPrimitiveOrPseudo(type: string): boolean { + return PHP_PRIMITIVE_TYPES.has(type.toLowerCase()); +} + +/** Last backslash-separated segment: `Foo\Bar\Baz` → `Baz`. */ +function lastSegment(path: string): string { + const parts = path.split('\\').filter(Boolean); + return parts[parts.length - 1] ?? path; +} diff --git a/gitnexus/src/core/ingestion/languages/php/merge-bindings.ts b/gitnexus/src/core/ingestion/languages/php/merge-bindings.ts new file mode 100644 index 000000000..257496550 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/merge-bindings.ts @@ -0,0 +1,51 @@ +/** + * PHP shadowing precedence for the `mergeBindings` hook. + * + * Tier ranking (lower wins in shadowing): + * + * - 0: `local` — a class member, method, local variable, or parameter + * declared in this scope. + * - 1: `import` / `namespace` / `reexport` — `use Foo\Bar;`, + * `use Foo\Bar as Baz;`, `use function`, `use const`. + * All use-statement flavors that introduce a name sit at this tier. + * - 2: `wildcard` — grouped uses / wildcard imports (deferred; mapped + * here for completeness). + * + * Within a surviving tier we de-dup by `DefId`, last-write-wins so a + * `use` re-declared further down the file cleanly replaces the earlier + * binding. + */ + +import type { BindingRef } from 'gitnexus-shared'; + +const TIER_LOCAL = 0; +const TIER_IMPORT = 1; +const TIER_WILDCARD = 2; +const TIER_UNKNOWN = 3; + +function tierOf(b: BindingRef): number { + switch (b.origin) { + case 'local': + return TIER_LOCAL; + case 'reexport': + case 'import': + case 'namespace': + return TIER_IMPORT; + case 'wildcard': + return TIER_WILDCARD; + default: + return TIER_UNKNOWN; + } +} + +export function phpMergeBindings(bindings: readonly BindingRef[]): readonly BindingRef[] { + if (bindings.length === 0) return bindings; + + let bestTier = Number.POSITIVE_INFINITY; + for (const b of bindings) bestTier = Math.min(bestTier, tierOf(b)); + const survivors = bindings.filter((b) => tierOf(b) === bestTier); + + const seen = new Map(); + for (const b of survivors) seen.set(b.def.nodeId, b); + return [...seen.values()]; +} diff --git a/gitnexus/src/core/ingestion/languages/php/namespace-siblings.ts b/gitnexus/src/core/ingestion/languages/php/namespace-siblings.ts new file mode 100644 index 000000000..20b99d971 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/namespace-siblings.ts @@ -0,0 +1,335 @@ +/** + * PHP same-namespace cross-file visibility. + * + * In PHP, every class declared in `namespace Foo\Bar` is visible to all + * other files in the same namespace WITHOUT an explicit `use` statement. + * Without this pass, `Service.php` (namespace `App\Services`) can't see + * `User` declared in `Models.php` (namespace `App\Models`) unless + * `UserService.php` has an explicit `use App\Models\User` statement. + * + * More importantly, A.php (namespace `App\Models`) can return `Greeting` + * (same namespace `App\Models`) without importing it, and the compound- + * receiver resolver needs to find `Greeting` as a class binding in the + * scope chain. + * + * Implementation mirrors C#'s `namespace-siblings.ts`: + * 1. Extract the declared namespace from each PHP file's source. + * 2. Group class-like defs by namespace. + * 3. Inject sibling class defs into each file's Module scope's + * `bindingAugmentations` with `origin: 'namespace'`. + * 4. Also mirror return-type bindings from same-namespace siblings + * so cross-file chain-follow finds return types without explicit imports. + * + * Uses the PHP tree-sitter parser (via the lazy singleton in `query.ts`) + * to extract namespace declarations — same AST that `extractParsedFile` + * already parsed, reused via `treeCache` to avoid double-parsing. + */ + +import type { BindingRef, ParsedFile, Scope, ScopeId, SymbolDefinition } from 'gitnexus-shared'; +import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; +import { getPhpParser } from './query.js'; +import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; + +// ─── PHP file structure extraction ────────────────────────────────────────── + +interface PhpFileStructure { + /** The declared namespace (backslash-separated), or '' for global namespace. */ + readonly namespace: string; +} + +type PhpTree = ReturnType['parse']>; + +/** + * Extract the declared namespace from a PHP file's source. + * Uses the cached AST tree when available to avoid re-parsing. + */ +function extractPhpFileStructure(content: string, cachedTree: unknown): PhpFileStructure { + const tree = + (cachedTree as PhpTree | undefined) ?? + parseSourceSafe(getPhpParser(), content, undefined, { + bufferSize: getTreeSitterBufferSize(content), + }); + + // Walk top-level nodes looking for namespace_definition. + // PHP files have at most one namespace declaration (PSR-4 convention). + // `namespace_definition` has a `name:` field of type `namespace_name`. + const root = tree.rootNode; + for (let i = 0; i < root.namedChildCount; i++) { + const child = root.namedChild(i); + if (child === null) continue; + if (child.type === 'namespace_definition') { + const nameNode = child.childForFieldName('name'); + if (nameNode !== null) { + return { namespace: nameNode.text }; + } + } + } + + return { namespace: '' }; +} + +// ─── Augmentation bucket helper ───────────────────────────────────────────── + +function getAugmentationBucket( + augmentations: Map>, + scopeId: ScopeId, + name: string, +): BindingRef[] { + let scopeBindings = augmentations.get(scopeId); + if (scopeBindings === undefined) { + scopeBindings = new Map(); + augmentations.set(scopeId, scopeBindings); + } + let bucket = scopeBindings.get(name); + if (bucket === undefined) { + bucket = []; + scopeBindings.set(name, bucket); + } + return bucket; +} + +function isClassLikeDef(def: SymbolDefinition): boolean { + return ( + def.type === 'Class' || + def.type === 'Interface' || + def.type === 'Struct' || + def.type === 'Enum' || + def.type === 'Trait' + ); +} + +// ─── Public entry point ────────────────────────────────────────────────────── + +export interface PhpSiblingInputs { + readonly fileContents: ReadonlyMap; + readonly treeCache?: { get(filePath: string): unknown }; +} + +/** + * Side-channel cache populated by `populatePhpNamespaceSiblings` so that + * later visibility-check hooks (e.g., `isCallableVisibleFromCaller`) can + * look up a file's PHP namespace without re-parsing. Cleared at the start + * of every populate run so stale entries don't leak across resolutions. + */ +const namespaceByFilePath = new Map(); + +/** + * Read the cached PHP namespace for a given filePath. Returns `''` (global) + * when the file has no namespace_definition or hasn't been processed yet. + * Callers should only consult this AFTER either `populatePhpClassQualifiedNames` + * or `populatePhpNamespaceSiblings` has run for the current resolution. + */ +export function getPhpNamespaceForFile(filePath: string): string { + return namespaceByFilePath.get(filePath) ?? ''; +} + +/** + * Inject same-namespace class defs and return-type bindings into each + * PHP file's Module scope's `bindingAugmentations`. This makes classes + * in the same PHP namespace visible to each other without explicit `use` + * statements, mirroring PHP's actual runtime behavior. + * + * Uses `origin: 'namespace'` so `phpMergeBindings` tiers it below + * explicit `use` imports (`origin: 'import'`) and local declarations. + */ +export function populatePhpNamespaceSiblings( + parsedFiles: readonly ParsedFile[], + indexes: ScopeResolutionIndexes, + inputs: PhpSiblingInputs, +): void { + // Step 1: extract namespace structure for each file. Also seed the + // side-channel cache used by visibility-check hooks downstream. + namespaceByFilePath.clear(); + const structureByFile = new Map(); + for (const parsed of parsedFiles) { + const content = inputs.fileContents.get(parsed.filePath); + if (content === undefined) continue; + const cachedTree = inputs.treeCache?.get(parsed.filePath); + const struct = extractPhpFileStructure(content, cachedTree); + structureByFile.set(parsed.filePath, struct); + namespaceByFilePath.set(parsed.filePath, struct.namespace); + } + + // Step 2: group class-like defs and module scopes by namespace. + interface NamespaceBucket { + readonly scopes: { filePath: string; scopeId: ScopeId; scope: Scope }[]; + readonly classDefs: SymbolDefinition[]; + } + const buckets = new Map(); + const getBucket = (ns: string): NamespaceBucket => { + let b = buckets.get(ns); + if (b === undefined) { + b = { scopes: [], classDefs: [] }; + buckets.set(ns, b); + } + return b; + }; + + for (const parsed of parsedFiles) { + const struct = structureByFile.get(parsed.filePath); + if (struct === undefined) continue; + const ns = struct.namespace; + const bucket = getBucket(ns); + + // Register the file's module scope in the bucket. + const moduleScope = parsed.scopes.find((s) => s.kind === 'Module'); + if (moduleScope !== undefined) { + bucket.scopes.push({ + filePath: parsed.filePath, + scopeId: moduleScope.id, + scope: moduleScope, + }); + } + + // Collect class-like defs declared at the top-level of this file + // (defs in Class or Module scopes, excluding nested inner classes). + for (const scope of parsed.scopes) { + if (scope.kind !== 'Class') continue; + // Only top-level class scopes (parent is Module or Namespace scope). + if (scope.parent === null) continue; + const parentScope = parsed.scopes.find((s) => s.id === scope.parent); + if ( + parentScope === undefined || + (parentScope.kind !== 'Module' && parentScope.kind !== 'Namespace') + ) { + continue; + } + for (const def of scope.ownedDefs) { + if (isClassLikeDef(def)) { + bucket.classDefs.push(def); + break; // one class-like per scope + } + } + } + } + + const augmentations = indexes.bindingAugmentations as Map>; + + // Step 3: For each namespace bucket, inject sibling class bindings + // into every file's Module scope (that is NOT the declaring file). + for (const [, bucket] of buckets) { + // Build name → def map (simple name of qualifiedName). + const defsByName = new Map(); + for (const def of bucket.classDefs) { + const q = def.qualifiedName ?? ''; + const simpleName = q.includes('.') + ? q.slice(q.lastIndexOf('.') + 1) + : q.includes('\\') + ? q.slice(q.lastIndexOf('\\') + 1) + : q; + if (simpleName === '') continue; + const arr = defsByName.get(simpleName) ?? []; + arr.push(def); + defsByName.set(simpleName, arr); + } + + for (const { filePath, scopeId, scope } of bucket.scopes) { + for (const [name, defs] of defsByName) { + // Skip if already locally declared (origin: 'local' wins). + const local = scope.bindings.get(name); + if (local !== undefined && local.some((b) => b.origin === 'local')) continue; + + for (const def of defs) { + if (def.filePath === filePath) continue; // don't self-inject + const arr = getAugmentationBucket(augmentations, scopeId, name); + if (arr.some((b) => b.def.nodeId === def.nodeId)) continue; + arr.push({ def, origin: 'namespace' }); + } + } + } + } + + // Step 3b: Inject fully-qualified-name bindings into every PHP file's + // Module scope. PHP `\App\Models\User` (leading-backslash FQN) and + // `App\Models\User` (already-qualified relative) on a parameter or + // typed receiver must resolve to the exact namespace-qualified class + // regardless of which simple-name `User` the caller's `use` imports + // shadowed. The shared `findClassBindingInScope` scope-chain walk + // consumes these augmentations via `lookupBindingsAt`, so adding the + // qualified key on every file's module scope routes FQN-receivers to + // the right def. Codex PR #1497 review, finding 1. + // + // Cost: O(PHP files × class-like defs in the workspace) augmentation + // entries. Bounded and acceptable in practice — typical PHP projects + // have hundreds of files and classes, not tens of thousands. + for (const parsed of parsedFiles) { + const moduleScope = parsed.scopes.find((s) => s.kind === 'Module'); + if (moduleScope === undefined) continue; + const moduleScopeId = moduleScope.id; + + for (const [ns, bucket] of buckets) { + if (ns === '') continue; // global-namespace classes have no qualified form to register + for (const def of bucket.classDefs) { + const q = def.qualifiedName ?? ''; + const simpleName = q.includes('\\') ? q.slice(q.lastIndexOf('\\') + 1) : q; + if (simpleName === '') continue; + const fqn = `${ns}\\${simpleName}`; + const arr = getAugmentationBucket(augmentations, moduleScopeId, fqn); + if (arr.some((b) => b.def.nodeId === def.nodeId)) continue; + arr.push({ def, origin: 'namespace' }); + } + } + } + + // Step 4: Mirror return-type bindings from same-namespace sibling files. + // This enables chain-follow like `$c->greet()->save()` where `greet()` + // returns `Greeting` (declared in A.php, same namespace) and `Greeting` + // isn't imported in the calling file. Without this, the compound-receiver + // resolver can't resolve `Greeting` as a class binding in the importer's + // scope chain. + // + // Additionally, mirror from files that are imported via `use` (different + // namespace) so return types from dependencies are chain-followable too. + for (const parsed of parsedFiles) { + const moduleScope = parsed.scopes.find((s) => s.kind === 'Module'); + if (moduleScope === undefined) continue; + const moduleTypeBindings = moduleScope.typeBindings as Map< + string, + import('gitnexus-shared').TypeRef + >; + + const struct = structureByFile.get(parsed.filePath); + const ownNs = struct?.namespace ?? ''; + + // Collect namespaces accessible from this file: + // 1. Own namespace (same-ns siblings) + // 2. Namespaces of directly imported files (via parsedImports → targetRaw → PSR-4 namespace) + const accessibleFiles = new Set(); + + // Same-namespace siblings. + const sameBucket = buckets.get(ownNs); + if (sameBucket !== undefined) { + for (const { filePath } of sameBucket.scopes) { + if (filePath !== parsed.filePath) accessibleFiles.add(filePath); + } + } + + // Files directly imported by this file (finalized import edges). + const ownModuleScopeBindings = indexes.bindings.get(moduleScope.id); + if (ownModuleScopeBindings !== undefined) { + for (const [, refs] of ownModuleScopeBindings) { + for (const ref of refs) { + if (ref.origin === 'import' || ref.origin === 'namespace') { + const importFilePath = ref.def.filePath; + if (importFilePath !== parsed.filePath) { + accessibleFiles.add(importFilePath); + } + } + } + } + } + + // Mirror return-type bindings from accessible files. + for (const srcFilePath of accessibleFiles) { + const srcParsed = parsedFiles.find((p) => p.filePath === srcFilePath); + if (srcParsed === undefined) continue; + const srcModuleScope = srcParsed.scopes.find((s) => s.kind === 'Module'); + if (srcModuleScope === undefined) continue; + for (const [boundName, typeRef] of srcModuleScope.typeBindings) { + if (moduleTypeBindings.has(boundName)) continue; + moduleTypeBindings.set(boundName, typeRef); + } + } + } +} diff --git a/gitnexus/src/core/ingestion/languages/php/query.ts b/gitnexus/src/core/ingestion/languages/php/query.ts new file mode 100644 index 000000000..fa84c911f --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/query.ts @@ -0,0 +1,332 @@ +/** + * Tree-sitter query for PHP scope captures (RFC #909 Ring 3 LANG-php). + * + * Captures the structural skeleton the generic scope-resolution pipeline + * consumes: scopes (program/namespace/class/function), declarations + * (class-likes, method-likes, properties, variables), imports + * (namespace_use_declaration), type bindings (parameter annotations, + * property types, constructor-inferred locals, return types), and + * references (call sites, member writes). + * + * PHP specifics that shape this query: + * + * - `namespace_use_declaration` is an import only at top level / inside + * namespace blocks. Class-body `use_declaration` (trait-use) is a + * different node type and is NOT captured here. + * + * - `object_creation_expression` has `name` and `qualified_name` as + * direct children (no wrapping node). + * + * - `method_declaration` exposes a `return_type:` named field containing + * a `type` node, which may be `named_type`, `optional_type`, etc. + * + * - `property_element` has a `name:` field of type `variable_name`. + * + * - `variable_name` nodes always include the `$` sigil in their text. + * + * Exposes lazy `Parser` and `Query` singletons so callers don't pay + * tree-sitter init cost per file. + */ + +import Parser from 'tree-sitter'; +import Php from 'tree-sitter-php'; + +// tree-sitter-php exports `{ php, php_only, html }` in recent versions, or the +// language directly in older versions. +// +// IMPORTANT: must match the grammar used by the central parse phase +// (`src/core/tree-sitter/parser-loader.ts` line: `[SupportedLanguages.PHP]: PHP.php_only`). +// Using a different grammar variant causes tree-sitter to throw when running +// a query built against grammar A on a tree parsed by grammar B — this error +// is swallowed by `scope-extractor-bridge.ts`, producing silent empty results. +const Php_typed = Php as unknown as { php_only?: unknown; php?: unknown }; +const PHP_LANG = Php_typed.php_only ?? Php_typed.php ?? Php; + +const PHP_SCOPE_QUERY = ` +;; ── Scopes ──────────────────────────────────────────────────────────────── + +(program) @scope.module + +;; Both block-scoped and statement-scoped namespace declarations. +(namespace_definition) @scope.namespace + +(class_declaration) @scope.class +(interface_declaration) @scope.class +(trait_declaration) @scope.class +(enum_declaration) @scope.class + +(method_declaration) @scope.function +(function_definition) @scope.function +(anonymous_function) @scope.function +(arrow_function) @scope.function + +;; ── Declarations — types ────────────────────────────────────────────────── + +(class_declaration + name: (name) @declaration.name) @declaration.class + +(interface_declaration + name: (name) @declaration.name) @declaration.interface + +(trait_declaration + name: (name) @declaration.name) @declaration.trait + +(enum_declaration + name: (name) @declaration.name) @declaration.enum + +;; ── Declarations — methods / functions / constructors ───────────────────── + +(method_declaration + name: (name) @declaration.name) @declaration.method + +(function_definition + name: (name) @declaration.name) @declaration.function + +;; ── Declarations — properties ───────────────────────────────────────────── + +;; PHP 7.4+ typed property: private UserRepo $repo; +;; property_element has name: (variable_name) field. +;; Emits BOTH a declaration (so SemanticModel registers the property) AND a type-binding. +(property_declaration + type: (_) @type-binding.type + (property_element + name: (variable_name) @type-binding.name)) @type-binding.annotation + +(property_declaration + type: (_) + (property_element + name: (variable_name) @declaration.name)) @declaration.property + +;; Untyped property: public $id; — capture as plain declaration. +(property_declaration + (property_element + name: (variable_name) @declaration.name)) @declaration.variable + +;; ── Imports — namespace_use_declaration ─────────────────────────────────── +;; +;; Captures ALL forms: plain, alias, function/const qualifiers, and grouped. +;; The import-decomposer in captures.ts fans out grouped uses. +;; +;; NOTE: class-body use_declaration = trait-use, NOT an import. +;; Only namespace_use_declaration (top-level / namespace scope) is an import. + +(namespace_use_declaration) @import.statement + +;; ── Type bindings — parameters ──────────────────────────────────────────── + +;; simple_parameter with a type hint: function f(User $u) +;; type field is a 'type' supertype (named_type, optional_type, union_type, etc.) +(simple_parameter + type: (_) @type-binding.type + name: (variable_name) @type-binding.name) @type-binding.parameter + +;; property_promotion_parameter: function __construct(private User $u) +;; Emits type-binding so the constructor body can resolve $u as the typed param. +(property_promotion_parameter + type: (_) @type-binding.type + name: (variable_name) @type-binding.name) @type-binding.parameter + +;; Also emit a @type-binding.annotation for the promoted parameter so that +;; phpBindingScopeFor can hoist it to the Class scope (stripping the $ sigil). +;; This enables compound-receiver resolution: $user->address->save() resolves +;; address → Address via the Class scope's typeBindings. +;; The @type-binding.parameter above stays for constructor-body resolution ($address). +(property_promotion_parameter + type: (_) @type-binding.type + name: (variable_name) @type-binding.name) @type-binding.annotation + +;; Also emit a @declaration.property so SemanticModel registers the promoted +;; parameter as a class-owned property (enabling $obj->propName lookups). +(property_promotion_parameter + name: (variable_name) @declaration.name) @declaration.property + +;; ── Type bindings — local assignment: $u = new User() ───────────────────── + +;; new ClassName() — name is a direct child of object_creation_expression +(assignment_expression + left: (variable_name) @type-binding.name + right: (object_creation_expression + (name) @type-binding.type)) @type-binding.constructor + +;; new Foo\Bar\ClassName() — qualified_name wraps name +(assignment_expression + left: (variable_name) @type-binding.name + right: (object_creation_expression + (qualified_name + (name) @type-binding.type))) @type-binding.constructor + +;; ── Type bindings — $alias = $u (identifier alias) ─────────────────────── + +(assignment_expression + left: (variable_name) @type-binding.name + right: (variable_name) @type-binding.type) @type-binding.alias + +;; ── Type bindings — $u = factory() (free call return alias) ────────────── + +(assignment_expression + left: (variable_name) @type-binding.name + right: (function_call_expression + function: (name) @type-binding.type)) @type-binding.alias + +;; ── Type bindings — $u = $svc->getUser() (method call return alias) ─────── + +(assignment_expression + left: (variable_name) @type-binding.name + right: (member_call_expression + name: (name) @type-binding.type)) @type-binding.alias + +;; ── Type bindings — method return type ─────────────────────────────────── + +;; method_declaration exposes return_type: field (type node supertype). +;; named_type wraps the class name: function getUser(): User +(method_declaration + name: (name) @type-binding.name + return_type: (named_type + (name) @type-binding.type)) @type-binding.return + +;; nullable return type via optional_type: function getUser(): ?User +(method_declaration + name: (name) @type-binding.name + return_type: (optional_type + (named_type + (name) @type-binding.type))) @type-binding.return + +;; function_definition (top-level or namespace-level) return type: User +;; Enables cross-file return-type propagation for free functions. +(function_definition + name: (name) @type-binding.name + return_type: (named_type + (name) @type-binding.type)) @type-binding.return + +;; nullable return type for function_definition: ?User +(function_definition + name: (name) @type-binding.name + return_type: (optional_type + (named_type + (name) @type-binding.type))) @type-binding.return + +;; ── References — free calls: foo() ─────────────────────────────────────── + +(function_call_expression + function: (name) @reference.name) @reference.call.free + +;; ── References — member calls: $obj->method() ──────────────────────────── +;; +;; SAFETY-INVARIANT (Finding 1 of PR #1497 adversarial review): the name: +;; field is constrained to (name), NOT (_) — tree-sitter-php emits +;; variable_name nodes for dynamic method names ($obj->$method(), +;; $obj->{$method}()). Keeping the pattern at (name) is what suppresses +;; capture of those dynamic shapes. The resolver is structural-only and +;; cannot infer the bound method name from runtime values; relaxing this +;; pattern to (_) would silently emit zero-confidence false-positive +;; edges. Regression: test/fixtures/lang-resolution/php-dynamic-calls/. + +(member_call_expression + object: (_) @reference.receiver + name: (name) @reference.name) @reference.call.member + +;; ── References — null-safe member calls: $obj?->method() (PHP 8+) ───────── + +(nullsafe_member_call_expression + object: (_) @reference.receiver + name: (name) @reference.name) @reference.call.member + +;; ── References — static calls: X::method() ─────────────────────────────── +;; +;; Same SAFETY-INVARIANT as member_call_expression above: name: (name) +;; deliberately excludes variable_name so Class::$method() and +;; $className::$method() shapes do not capture. The receiver field uses +;; (_) because static dispatch on a variable receiver +;; ($className::method()) IS captured — but resolution falls through +;; harmlessly when $className has no class type binding. See +;; php-dynamic-calls/ regression suite. + +(scoped_call_expression + scope: (_) @reference.receiver + name: (name) @reference.name) @reference.call.member + +;; ── Type bindings — $x = X::Constant or $x = X::CASE (enum case) ───────── +;; Binds the variable to the class name X so member calls on $x dispatch +;; to X's methods (e.g. UserRole::Viewer → label()). +;; +;; tree-sitter-php emits class_constant_access_expression with two name +;; children: [0]=class/enum name, [1]=constant/case name. The dot-anchor +;; before (name) matches only the FIRST name child (the class). + +(assignment_expression + left: (variable_name) @type-binding.name + right: (class_constant_access_expression + . (name) @type-binding.type)) @type-binding.alias + +(assignment_expression + left: (variable_name) @type-binding.name + right: (class_constant_access_expression + (qualified_name + (name) @type-binding.type))) @type-binding.alias + +;; ── Type bindings — $x = SomeClass::staticFactory() ────────────────────── +;; Binds $x to the type returned by the static factory method, anchored on +;; the method name (chain-follow resolves the actual return type later). + +(assignment_expression + left: (variable_name) @type-binding.name + right: (scoped_call_expression + name: (name) @type-binding.type)) @type-binding.alias + +;; ── Type bindings — null-safe member-call result: $x = $a?->getY() ─────── + +(assignment_expression + left: (variable_name) @type-binding.name + right: (nullsafe_member_call_expression + name: (name) @type-binding.type)) @type-binding.alias + +;; ── References — constructor calls: new User() ─────────────────────────── + +(object_creation_expression + (name) @reference.name) @reference.call.constructor + +(object_creation_expression + (qualified_name + (name) @reference.name)) @reference.call.constructor + +;; ── References — member writes: $obj->prop = $x ────────────────────────── + +(assignment_expression + left: (member_access_expression + object: (_) @reference.receiver + name: (name) @reference.name)) @reference.write.member + +;; ── References — static property writes: User::$count = $x ────────────── +;; Uses @reference.write.static anchor so captures.ts can strip the leading +;; $ from the variable_name capture (static props are stored without $ in graph). +;; +;; SAFETY-INVARIANT (Finding 2 of PR #1497 adversarial review): no +;; read-access property capture exists in this query — dynamic property +;; reads ($obj->$prop, $obj->{$prop}) produce no captures, which is the +;; desired behavior for a structural-only resolver. Adding a read pattern +;; in the future MUST keep name: (name) (not (_)) to preserve the +;; suppression. Regression: php-dynamic-calls/ fixture dynamicPropertyRead. + +(assignment_expression + left: (scoped_property_access_expression + scope: (_) @reference.receiver + name: (variable_name) @reference.name)) @reference.write.static +`; + +let _parser: Parser | null = null; +let _query: Parser.Query | null = null; + +export function getPhpParser(): Parser { + if (_parser === null) { + _parser = new Parser(); + _parser.setLanguage(PHP_LANG as Parameters[0]); + } + return _parser; +} + +export function getPhpScopeQuery(): Parser.Query { + if (_query === null) { + _query = new Parser.Query(PHP_LANG as Parameters[0], PHP_SCOPE_QUERY); + } + return _query; +} diff --git a/gitnexus/src/core/ingestion/languages/php/receiver-binding.ts b/gitnexus/src/core/ingestion/languages/php/receiver-binding.ts new file mode 100644 index 000000000..79709fe61 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/receiver-binding.ts @@ -0,0 +1,136 @@ +/** + * Synthesize `@type-binding.self` captures for PHP instance methods — + * one for `$this` (always on non-static methods inside a type + * declaration) and optionally one for `parent` (only on class methods + * when the enclosing class has an explicit `base_clause`). + * + * Mirrors `languages/csharp/receiver-binding.ts` in structure. PHP's + * grammar doesn't give us a clean `.scm` pattern for "implicit receiver + * on every instance method inside an enclosing type" because `$this` is + * not a parameter — it's an implicit receiver. Synthesis in code is the + * same approach C# uses for `this` / `base`. + * + * ## Known limitations + * + * - **Trait `$this`**: for methods defined in a trait, `$this` is + * synthesized as a binding to the trait itself. The actual using-class + * type is not known at single-file parse time. V1 limitation — + * documented in `index.ts`. + * - **Anonymous classes**: skipped (no stable enclosing class name). + */ + +import type { Capture, CaptureMatch } from 'gitnexus-shared'; +import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js'; + +const TYPE_DECL_NODE_TYPES = new Set([ + 'class_declaration', + 'interface_declaration', + 'trait_declaration', + 'enum_declaration', +]); + +const FUNCTION_NODE_TYPES = new Set([ + 'method_declaration', + 'function_definition', + 'anonymous_function', + 'arrow_function', +]); + +/** Walk up to find the enclosing type declaration. */ +function findEnclosingTypeDeclaration(node: SyntaxNode): SyntaxNode | null { + let cur: SyntaxNode | null = node.parent; + while (cur !== null) { + if (TYPE_DECL_NODE_TYPES.has(cur.type)) return cur; + cur = cur.parent; + } + return null; +} + +function typeName(typeNode: SyntaxNode): string | null { + return typeNode.childForFieldName('name')?.text ?? null; +} + +/** + * Return the base class name from a `base_clause` child of the class node. + * `base_clause` contains a `qualified_name` or `name` child. + */ +function baseClauseText(typeNode: SyntaxNode): string | null { + for (let i = 0; i < typeNode.namedChildCount; i++) { + const child = typeNode.namedChild(i); + if (child === null || child.type !== 'base_clause') continue; + const nameNode = child.firstNamedChild; + if (nameNode === null) return null; + // Take last segment of qualified name (e.g. \App\Models\BaseModel → BaseModel) + const text = nameNode.text.trim(); + const segments = text.split('\\').filter(Boolean); + return segments[segments.length - 1] ?? text; + } + return null; +} + +/** Check whether this method has a `static_modifier` child. */ +function isStaticMethod(fnNode: SyntaxNode): boolean { + for (let i = 0; i < fnNode.namedChildCount; i++) { + const child = fnNode.namedChild(i); + if (child !== null && child.type === 'static_modifier') return true; + } + return false; +} + +/** + * Build zero, one, or two `@type-binding.self` matches for `fnNode`: + * + * - Returns `[]` if the function is free (no enclosing type), static, + * or the enclosing type has no resolvable name. + * - Returns one match (`$this`) for non-static methods inside a + * class / trait / interface / enum body. + * - Returns two matches (`$this` + `parent`) only when the function + * lives in a `class_declaration` that has an explicit `base_clause`. + * + * The caller is responsible for guaranteeing + * `FUNCTION_NODE_TYPES.has(fnNode.type)`. + */ +export function synthesizePhpReceiverBinding(fnNode: SyntaxNode): CaptureMatch[] { + if (!FUNCTION_NODE_TYPES.has(fnNode.type)) return []; + if (isStaticMethod(fnNode)) return []; + + const enclosingType = findEnclosingTypeDeclaration(fnNode); + if (enclosingType === null) return []; + + // Anonymous class — skip (no stable name). + if (enclosingType.type === 'anonymous_class_declaration') return []; + + const enclosingName = typeName(enclosingType); + if (enclosingName === null) return []; + + // Anchor the synthesized captures to the method body (compound_statement) + // so they land inside the function scope, not at the class scope. + // For interface/abstract methods that have no body, skip. + const bodyNode = + fnNode.childForFieldName('body') ?? + // arrow_function: body is the expression after `=>` + fnNode.childForFieldName('return_value'); + if (bodyNode === null) return []; + + const out: CaptureMatch[] = []; + out.push(buildReceiverMatch(bodyNode, '$this', enclosingName)); + + // `parent` applies only to class methods with an explicit base_clause. + if (enclosingType.type === 'class_declaration') { + const baseText = baseClauseText(enclosingType); + if (baseText !== null) { + out.push(buildReceiverMatch(bodyNode, 'parent', baseText)); + } + } + + return out; +} + +function buildReceiverMatch(anchorNode: SyntaxNode, name: string, typeText: string): CaptureMatch { + const m: Record = { + '@type-binding.self': nodeToCapture('@type-binding.self', anchorNode), + '@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, name), + '@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeText), + }; + return m; +} diff --git a/gitnexus/src/core/ingestion/languages/php/scope-resolver.ts b/gitnexus/src/core/ingestion/languages/php/scope-resolver.ts new file mode 100644 index 000000000..8b1fcf41b --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/scope-resolver.ts @@ -0,0 +1,421 @@ +/** + * PHP `ScopeResolver` registered in `SCOPE_RESOLVERS` and consumed by + * the generic `runScopeResolution` orchestrator (RFC #909 Ring 3 LANG-php). + * + * Third migration after Python and C#. See `pythonScopeResolver` for the + * canonical shape. + * + * ## Circular-import avoidance + * + * The old PR had `php/scope-resolver.ts` importing `phpProvider` from + * `../php.js` while `php.ts` imported `phpScopeResolver` from `./php/index.js` + * — undefined at module load. The canonical fix (mirroring C#): + * + * - `scope-resolver.ts` imports `phpProvider` from `../php.js` ✓ + * - `php.ts` imports individual hook FUNCTIONS from `./php/index.js` ✗ + * + * Node's ESM handles the cycle correctly because `phpProvider` is a named + * export that is live-binding — by the time `phpScopeResolver` is first + * read (lazily, at resolution time), `phpProvider` is fully initialized. + */ + +import type { ParsedFile } from 'gitnexus-shared'; +import { SupportedLanguages } from 'gitnexus-shared'; +import { buildMro, defaultLinearize } from '../../scope-resolution/passes/mro.js'; +import { + findReceiverTypeBinding, + populateClassOwnedMembers, +} from '../../scope-resolution/scope/walkers.js'; +import type { ScopeResolver } from '../../scope-resolution/contract/scope-resolver.js'; +import type { KnowledgeGraph } from '../../../graph/types.js'; +import type { GraphNodeLookup } from '../../scope-resolution/graph-bridge/node-lookup.js'; +import { + resolveCallerGraphId, + resolveDefGraphId, +} from '../../scope-resolution/graph-bridge/ids.js'; +import { narrowOverloadCandidates } from '../../scope-resolution/passes/overload-narrowing.js'; +import type { SemanticModel } from '../../model/semantic-model.js'; +import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js'; +import type { SymbolDefinition } from 'gitnexus-shared'; +import { phpProvider } from '../php.js'; +import { phpArityCompatibility, phpMergeBindings } from './index.js'; +import { resolvePhpImportTargetInternal, loadPhpComposerConfig } from './import-target.js'; +import { populatePhpNamespaceSiblings, getPhpNamespaceForFile } from './namespace-siblings.js'; + +/** + * PHP MRO builder — extends the generic EXTENDS-only MRO with trait-use + * relationships encoded as IMPLEMENTS edges. + * + * PHP trait-use (`use TraitName;` inside a class body) is recorded in the + * graph as an IMPLEMENTS edge from the using class to the Trait node. The + * generic `buildMro` only walks EXTENDS edges, so trait methods are invisible + * to the MRO-based dispatch index. This variant: + * + * 1. Runs the generic `buildMro` (EXTENDS edges, Class defs only). + * 2. Indexes Trait defs from `parsedFiles` alongside Class defs. + * 3. Walks IMPLEMENTS edges; for each edge whose target resolves to a + * Trait DefId, prepends that Trait DefId to the source class's MRO. + * + * Trait methods are searched BEFORE parent-class methods (PHP semantics: + * a trait method shadows the parent-class method but is overridden by the + * using class's own methods). + */ +/** + * PHP free-call visibility check for `pickUniqueGlobalCallable`. Returns + * true when the candidate function is reachable from the caller's PHP + * namespace context, false when the cross-namespace bridge would be a + * false positive (e.g., `\App\Utils\format` is not visible from `\App` + * without an explicit `use function App\Utils\format;`). + * + * Rules (PHP semantics): + * 1. Same-namespace candidates are always visible. + * 2. Global-namespace candidates (no namespace prefix) are visible from + * every caller — PHP's global fallback for functions/constants. + * 3. Candidates in a different namespace are visible only when the + * caller has a `use function` import that matches the candidate's + * fully-qualified name. + */ +function phpIsCallableVisibleFromCaller(ctx: { + callerParsed: ParsedFile; + candidate: SymbolDefinition; +}): boolean { + const { callerParsed, candidate } = ctx; + const callerNs = getPhpNamespaceForFile(callerParsed.filePath); + const candNs = getPhpNamespaceForFile(candidate.filePath); + + // Global-namespace candidate: PHP falls back to global for functions + // and constants when the local namespace doesn't define them. + if (candNs === '') return true; + + // Same-namespace: caller can see the candidate without an explicit use. + if (candNs === callerNs) return true; + + // Cross-namespace: require an explicit `use function` import in the + // caller's parsedImports that matches the candidate's fully-qualified + // name. interpret.ts maps `use function Foo\bar` to a named import with + // localName = 'bar' and targetRaw = 'Foo\\bar'. + const candQualified = + candidate.qualifiedName === undefined + ? '' + : candNs !== '' && !candidate.qualifiedName.includes('\\') + ? `${candNs}\\${candidate.qualifiedName}` + : candidate.qualifiedName; + if (candQualified === '') return false; + return callerParsed.parsedImports.some( + (imp) => + imp.kind === 'named' && + imp.targetRaw.replace(/^\\+/, '') === candQualified.replace(/^\\+/, ''), + ); +} + +/** + * Compute the EXTENDS-only ancestor chain for every class — no trait + * augmentation. PHP semantics: `parent::method()` walks this view so + * that `parent::` resolves to the parent class's method, even when a + * composed trait shadows the same name. + * + * Returns the same shape as `buildPhpMro` so callers can swap views + * without changing dispatch logic. Just `buildMro` + `defaultLinearize` + * — no trait IMPLEMENTS edge walk. + */ +function buildPhpExtendsOnlyMro( + graph: KnowledgeGraph, + parsedFiles: readonly ParsedFile[], + nodeLookup: GraphNodeLookup, +): Map { + return buildMro(graph, parsedFiles, nodeLookup, defaultLinearize); +} + +function buildPhpMro( + graph: KnowledgeGraph, + parsedFiles: readonly ParsedFile[], + nodeLookup: GraphNodeLookup, +): Map { + // Step 1: run generic MRO (Class-only, EXTENDS-only). + const mro = buildMro(graph, parsedFiles, nodeLookup, defaultLinearize); + + // Step 2: build a graphId → defId map for ALL class-like defs including Traits. + // After the `isLinkableLabel` fix, Trait nodes are now indexed in nodeLookup. + const defIdByGraphId = new Map(); + for (const parsed of parsedFiles) { + for (const def of parsed.localDefs) { + if (def.type !== 'Class' && def.type !== 'Trait') continue; + const graphId = resolveDefGraphId(parsed.filePath, def, nodeLookup); + if (graphId !== undefined) defIdByGraphId.set(graphId, def.nodeId); + } + } + + // Step 2b: build a Set of Trait defIds for O(1) trait-vs-interface checks. + const traitDefIds = new Set(); + for (const parsed of parsedFiles) { + for (const def of parsed.localDefs) { + if (def.type === 'Trait') traitDefIds.add(def.nodeId); + } + } + + // Step 3: collect direct trait-use edges (IMPLEMENTS where target is a Trait). + // Maps class/trait defId → [traitDefId, ...] for direct `use TraitName;`. + const directTraitUse = new Map(); + for (const rel of graph.iterRelationshipsByType('IMPLEMENTS')) { + const sourceDefId = defIdByGraphId.get(rel.sourceId); + if (sourceDefId === undefined) continue; + const targetDefId = defIdByGraphId.get(rel.targetId); + if (targetDefId === undefined) continue; + if (!traitDefIds.has(targetDefId)) continue; + + let list = directTraitUse.get(sourceDefId); + if (list === undefined) { + list = []; + directTraitUse.set(sourceDefId, list); + } + if (!list.includes(targetDefId)) list.push(targetDefId); + } + + // Step 4: augment every class's MRO by prepending the traits used by + // any class in its ancestor chain (transitively closed). PHP semantics: + // a trait used by a parent class is also visible on the child, and a + // trait-using-trait chain is flattened to a single ancestor set. + // + // For each class, walk its (already-computed) EXTENDS-based MRO and + // collect all transitively-used traits via BFS — `trait A { use B; } + // trait B { use C; } class X { use A; }` must include C in X's MRO. + // Prepend them before the EXTENDS ancestors so the method dispatch + // index finds trait methods before falling back to the parent class + // hierarchy. + for (const [classDefId, extendsMro] of mro) { + const ancestorChain = [classDefId, ...extendsMro]; + const seeds: string[] = []; + for (const ancestorId of ancestorChain) { + for (const traitId of directTraitUse.get(ancestorId) ?? []) { + seeds.push(traitId); + } + } + const allTraits = collectTransitiveTraits(seeds, directTraitUse); + + if (allTraits.length > 0) { + // Prepend traits before EXTENDS ancestors: own class's traits first, + // then parent traits (in ancestor order). This ensures trait methods + // are found before falling back to the inheritance chain. + mro.set(classDefId, [...allTraits, ...extendsMro]); + } + } + + // Step 5: also insert Trait-only entries for classes that use traits + // directly but have no EXTENDS parents (not in `mro` yet). + for (const [classDefId, traits] of directTraitUse) { + if (!mro.has(classDefId) && !traitDefIds.has(classDefId)) { + // Class with no EXTENDS but with trait-use — add to MRO map. + const allTraits = collectTransitiveTraits([...traits], directTraitUse); + mro.set(classDefId, allTraits); + } + } + + return mro; +} + +/** + * Collect the transitive closure of traits reachable from the seed set. + * BFS over `directTraitUse` until fixpoint. The `seen` set guards against + * cycles (invalid PHP but defensively handled) and prevents duplicate + * entries when multiple seeds converge on the same trait. Insertion order + * is preserved — first-seen wins for MRO ordering. + */ +function collectTransitiveTraits( + seeds: readonly string[], + directTraitUse: ReadonlyMap, +): string[] { + const out: string[] = []; + const seen = new Set(); + const queue: string[] = [...seeds]; + while (queue.length > 0) { + const t = queue.shift()!; + if (seen.has(t)) continue; + seen.add(t); + out.push(t); + for (const next of directTraitUse.get(t) ?? []) { + if (!seen.has(next)) queue.push(next); + } + } + return out; +} + +/** + * Emit CALLS edges for PHP member-call sites whose receiver has no type + * binding (e.g. `mixed`-typed parameters, untyped variables). + * + * PHP is dynamically typed: a parameter declared as `mixed` (or with no + * type hint) cannot be resolved by the generic receiver-bound pass, which + * requires a `TypeRef` in scope. This hook does a workspace-wide method + * name lookup: when exactly one def in the workspace matches the called + * method name, emit the CALLS edge. + * + * Only fires for sites that are NOT already in `handledSites` and whose + * receiver has no type binding in the scope chain. Unique-name-match + * constraint avoids false positives for common method names. + */ +function phpEmitUnresolvedReceiverEdges( + graph: KnowledgeGraph, + scopes: ScopeResolutionIndexes, + parsedFiles: readonly ParsedFile[], + nodeLookup: GraphNodeLookup, + handledSites: Set, + model: SemanticModel, +): number { + let emitted = 0; + const seen = new Set(); + + for (const parsed of parsedFiles) { + for (const site of parsed.referenceSites) { + if (site.kind !== 'call') continue; + if (site.explicitReceiver === undefined) continue; + + const siteKey = `${parsed.filePath}:${site.atRange.startLine}:${site.atRange.startCol}`; + if (handledSites.has(siteKey)) continue; + + // Only proceed when the receiver has NO type binding — it's unresolvable + // by the generic pass. This is the `mixed` / unannotated case. + const typeRef = findReceiverTypeBinding(site.inScope, site.explicitReceiver.name, scopes); + if (typeRef !== undefined) continue; + + // Workspace-wide lookup: collect all methods matching the called name. + // Filter out defs with no qualifiedName (legacy parse stubs without full + // metadata) and deduplicate by nodeId so reconcileOwnership double-registration + // doesn't inflate the count. + const allCandidates = model.methods.lookupMethodByName(site.name); + const seen2 = new Set(); + const candidates = allCandidates.filter((c) => { + if (c.qualifiedName === undefined) return false; + if (seen2.has(c.nodeId)) return false; + seen2.add(c.nodeId); + return true; + }); + if (candidates.length !== 1) continue; // ambiguous or missing — skip + + const fnDef = candidates[0]; + if (fnDef === undefined) continue; + + // Apply arity narrowing — a unique method name match is not enough + // when arity says the call is definitively incompatible (e.g., PHP + // f(int $req, ...$rest) called with zero args). This prevents the + // fallback from emitting edges that the receiver-bound pass already + // rejected for arity reasons. + if (narrowOverloadCandidates([fnDef], site.arity, site.argumentTypes).length === 0) { + continue; + } + + // Tighten the fallback further with an EXACT-required-arity gate + // (Finding 8 / U4): the first-stage `narrowOverloadCandidates` + // accepts any argCount in `min..max` (or `>= min` when variadic), + // which over-emits 0.6-confidence edges for common method names + // whose only workspace candidate has optional / defaulted params. + // For the fallback path only, require argCount === required for + // fixed-arity candidates. Variadic candidates keep the relaxed + // `argCount >= required` semantics (already enforced by the first- + // stage check, so no extra work here). + const min = fnDef.requiredParameterCount; + const hasVarArgs = + fnDef.parameterTypes !== undefined && + fnDef.parameterTypes.some((t) => t === '...' || t.startsWith('...')); + if ( + min !== undefined && + Number.isFinite(site.arity) && + site.arity >= 0 && + !hasVarArgs && + site.arity !== min + ) { + continue; + } + + const callerGraphId = resolveCallerGraphId(site.inScope, scopes, nodeLookup); + if (callerGraphId === undefined) continue; + const tgtGraphId = resolveDefGraphId(fnDef.filePath, fnDef, nodeLookup); + if (tgtGraphId === undefined) continue; + + handledSites.add(siteKey); + const relId = `rel:CALLS:${callerGraphId}->${tgtGraphId}`; + if (seen.has(relId)) continue; + seen.add(relId); + graph.addRelationship({ + id: relId, + sourceId: callerGraphId, + targetId: tgtGraphId, + type: 'CALLS', + confidence: 0.6, + reason: 'php-unresolved-receiver-fallback', + }); + emitted++; + } + } + return emitted; +} + +const phpScopeResolver: ScopeResolver = { + language: SupportedLanguages.PHP, + languageProvider: phpProvider, + importEdgeReason: 'php-scope: use', + + resolveImportTarget: (targetRaw, fromFile, allFilePaths, resolutionConfig) => + resolvePhpImportTargetInternal(targetRaw, fromFile, allFilePaths, resolutionConfig), + + loadResolutionConfig: (repoPath) => loadPhpComposerConfig(repoPath), + + // PHP LEGB-like precedence: local > import/namespace/reexport > wildcard. + // The per-scope id is unused by phpMergeBindings (tier ordering computed + // purely from BindingRef.origin), so we don't synthesize a Scope. + mergeBindings: (existing, incoming) => [...phpMergeBindings([...existing, ...incoming])], + + // Adapter: phpArityCompatibility uses (def, callsite); the contract is (callsite, def). + arityCompatibility: (callsite, def) => phpArityCompatibility(def, callsite), + + buildMro: (graph, parsedFiles, nodeLookup) => buildPhpMro(graph, parsedFiles, nodeLookup), + + // PHP-specific: parent::method() must walk inheritance only, skipping + // composed traits. See buildPhpExtendsOnlyMro and the super-branch use + // in `passes/receiver-bound-calls.ts`. + buildExtendsOnlyMro: (graph, parsedFiles, nodeLookup) => + buildPhpExtendsOnlyMro(graph, parsedFiles, nodeLookup), + + // PHP free-call visibility: cross-namespace candidates are blocked + // unless explicitly `use function`-imported by the caller. Prevents + // false-positive CALLS edges between unrelated namespaces sharing a + // function name. Same-namespace and global-namespace candidates pass + // unchanged. + isCallableVisibleFromCaller: phpIsCallableVisibleFromCaller, + + populateOwners: (parsed: ParsedFile) => populateClassOwnedMembers(parsed), + + // PHP same-namespace cross-file visibility — classes in the same + // PHP namespace are visible without explicit `use` statements. + // Mirrors C#'s `populateNamespaceSiblings`. + populateNamespaceSiblings: populatePhpNamespaceSiblings, + + // PHP uses `parent` for super-class dispatch (not `super()`). + isSuperReceiver: (text) => text.trim() === 'parent', + + // PHP is dynamically typed — field-fallback heuristic on so that + // method calls on `mixed`-typed receivers (no annotation) fall back + // to a workspace-wide name search rather than silently dropping the edge. + fieldFallbackOnMethodLookup: true, + + // PHP: allow free-call fallback to unique workspace-wide callable when + // lexical/import bindings miss. Needed for two cases: + // 1. `use function` imports where PSR-4 directory resolution is + // non-deterministic (multiple .php files in same namespace dir). + // 2. Unimported free calls within the same namespace (same-namespace + // visibility without an explicit use statement, e.g. test fixtures). + allowGlobalFreeCallFallback: true, + + // Return-type propagation on — PHP method signatures are authoritative + // enough for cross-file chain-follow. + propagatesReturnTypesAcrossImports: true, + + // PHP hoists method return-type bindings to the Module scope so + // `propagateImportedReturnTypes` can pick them up across files. + hoistTypeBindingsToModule: true, + + // PHP recovers member calls on `mixed`/untyped receivers via a + // workspace-wide unique-method-name lookup, mirroring the legacy DAG. + emitUnresolvedReceiverEdges: phpEmitUnresolvedReceiverEdges, +}; + +export { phpScopeResolver }; diff --git a/gitnexus/src/core/ingestion/languages/php/simple-hooks.ts b/gitnexus/src/core/ingestion/languages/php/simple-hooks.ts new file mode 100644 index 000000000..89a9a2658 --- /dev/null +++ b/gitnexus/src/core/ingestion/languages/php/simple-hooks.ts @@ -0,0 +1,134 @@ +/** + * Trivial / no-op-ish hooks for the PHP provider. Made explicit so + * reviewers don't have to re-derive the analysis from "absence == default". + */ + +import type { + CaptureMatch, + ParsedImport, + Scope, + ScopeId, + ScopeTree, + TypeRef, +} from 'gitnexus-shared'; + +// ─── bindingScopeFor ────────────────────────────────────────────────────── + +/** + * PHP method return-type bindings (`@type-binding.return`) must hoist + * to the enclosing Module scope so `propagateImportedReturnTypes` can + * mirror them across files. Without this hoist, the return binding gets + * stuck at the Class scope and is invisible to the cross-file propagation + * pass that reads only `sourceModule.typeBindings`. + * + * All other bindings delegate to the default "innermost scope" rule. + */ +export function phpBindingScopeFor( + decl: CaptureMatch, + innermost: Scope, + tree: ScopeTree, +): ScopeId | null { + if (decl['@type-binding.return'] !== undefined) { + let cur: Scope | undefined = innermost; + while (cur !== undefined && cur.kind !== 'Module') { + const parentId: ScopeId | null = cur.parent ?? null; + if (parentId === null) break; + cur = tree.getScope(parentId); + } + if (cur !== undefined && cur.kind === 'Module') return cur.id; + } + + // Constructor-promoted properties (`function __construct(public User $u)`) + // are declared inside the constructor's Function scope in the AST, but they + // are class-owned fields. Hoist the @declaration.property binding to the + // enclosing Class scope so `populateClassOwnedMembers` assigns the correct + // ownerId and `findOwnedMember` can resolve `$obj->u`. + if (decl['@declaration.property'] !== undefined && innermost.kind === 'Function') { + let cur: Scope | undefined = innermost; + while (cur !== undefined && cur.kind !== 'Class') { + const parentId: ScopeId | null = cur.parent ?? null; + if (parentId === null) break; + cur = tree.getScope(parentId); + } + if (cur !== undefined && cur.kind === 'Class') return cur.id; + } + + // Constructor-promoted property TYPE BINDING (`function __construct(public Address $address)`) + // produces both a @type-binding.parameter (stays in Function scope for `$address` lookups + // inside the constructor body) AND a @type-binding.annotation (query.ts). The annotation + // capture is emitted so this hoist branch can place `address → Address` in the CLASS scope. + // + // The compound-receiver resolver (`resolveCompoundReceiverClass`) reads typeBindings from + // the class scope: `cs.typeBindings.get('address')`. Without hoisting, `$user->address->save()` + // fails to resolve `address` because the type binding is in the constructor's Function scope. + // + // `@type-binding.annotation` for a promoted param appears with innermost = Function scope + // (the constructor). Regular typed class properties (`private Address $addr;`) have their + // annotation already in the Class scope, so this branch only fires for promoted params. + if (decl['@type-binding.annotation'] !== undefined && innermost.kind === 'Function') { + let cur: Scope | undefined = innermost; + while (cur !== undefined && cur.kind !== 'Class') { + const parentId: ScopeId | null = cur.parent ?? null; + if (parentId === null) break; + cur = tree.getScope(parentId); + } + if (cur !== undefined && cur.kind === 'Class') return cur.id; + } + + return null; +} + +// ─── importOwningScope ──────────────────────────────────────────────────── + +/** + * Determine which scope owns a `use` import declaration. + * + * - `use` inside `namespace Foo { }` → attach to that Namespace scope. + * - Top-level `use` (no enclosing namespace) → innermost (Module). + * - `use TraitName;` inside a class body → this is a trait-use + * (heritage), NOT a namespace import. The grammar emits + * `use_declaration` for trait-use (distinct from + * `namespace_use_declaration`). Our query only captures + * `namespace_use_declaration`, so trait-use never reaches this hook + * in practice. Returning `null` here is a safety fallback. + */ +export function phpImportOwningScope( + _imp: ParsedImport, + innermost: Scope, + _tree: ScopeTree, +): ScopeId | null { + // Namespace-scoped or module-scoped imports attach to the innermost scope + // (either Namespace or Module). Class-scoped imports should not occur for + // namespace_use_declaration; if they do, attach to the class scope. + if ( + innermost.kind === 'Namespace' || + innermost.kind === 'Module' || + innermost.kind === 'Class' || + innermost.kind === 'Function' + ) { + return innermost.id; + } + return null; +} + +// ─── receiverBinding ────────────────────────────────────────────────────── + +/** + * Look up `$this` or `parent` in the function scope's type bindings. + * + * Both are synthesized as `@type-binding.self` captures during capture + * emission (`receiver-binding.ts`) — `$this` for every non-static + * method inside a class/trait/interface/enum body, `parent` additionally + * for class methods with an explicit `base_clause`. + * + * Returns `null` for: + * - static methods (no `$this` synthesized) + * - free functions (no enclosing class) + * - non-Function scopes + */ +export function phpReceiverBinding(functionScope: Scope): TypeRef | null { + if (functionScope.kind !== 'Function') return null; + return ( + functionScope.typeBindings.get('$this') ?? functionScope.typeBindings.get('parent') ?? null + ); +} diff --git a/gitnexus/src/core/ingestion/languages/python/captures.ts b/gitnexus/src/core/ingestion/languages/python/captures.ts index be891b5cc..bc4911546 100644 --- a/gitnexus/src/core/ingestion/languages/python/captures.ts +++ b/gitnexus/src/core/ingestion/languages/python/captures.ts @@ -24,6 +24,7 @@ import { synthesizeReceiverTypeBinding } from './receiver-binding.js'; import { computePythonArityMetadata } from './arity-metadata.js'; import { recordCacheHit, recordCacheMiss } from './cache-stats.js'; import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; import { pythonFunctionDefinitionLabel } from './simple-hooks.js'; export function emitPythonScopeCaptures( @@ -39,7 +40,7 @@ export function emitPythonScopeCaptures( let tree = cachedTree as ReturnType['parse']> | undefined; if (tree === undefined) { try { - tree = getPythonParser().parse(sourceText, undefined, { + tree = parseSourceSafe(getPythonParser(), sourceText, undefined, { bufferSize: getTreeSitterBufferSize(sourceText), }); } catch (err) { diff --git a/gitnexus/src/core/ingestion/languages/typescript/captures.ts b/gitnexus/src/core/ingestion/languages/typescript/captures.ts index 9d083c15c..b82edcff8 100644 --- a/gitnexus/src/core/ingestion/languages/typescript/captures.ts +++ b/gitnexus/src/core/ingestion/languages/typescript/captures.ts @@ -38,6 +38,7 @@ import { recordCacheHit, recordCacheMiss } from './cache-stats.js'; import { synthesizeTsReceiverBinding } from './receiver-binding.js'; import { computeTsArityMetadata } from './arity-metadata.js'; import { getTreeSitterBufferSize } from '../../constants.js'; +import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js'; /** tree-sitter-typescript node types for function-like scopes that may * carry a synthesized `this` binding. Kept in sync with the @@ -134,7 +135,7 @@ export function emitTsScopeCaptures( tree = undefined; } if (tree === undefined) { - tree = getTsParser(filePath).parse(sourceText, undefined, { + tree = parseSourceSafe(getTsParser(filePath), sourceText, undefined, { bufferSize: getTreeSitterBufferSize(sourceText), }); recordCacheMiss(); diff --git a/gitnexus/src/core/ingestion/markdown-processor.ts b/gitnexus/src/core/ingestion/markdown-processor.ts index dc0e7fee4..b2013ee7a 100644 --- a/gitnexus/src/core/ingestion/markdown-processor.ts +++ b/gitnexus/src/core/ingestion/markdown-processor.ts @@ -36,7 +36,12 @@ export const processMarkdown = ( // Skip if file node doesn't exist (shouldn't happen, structure-processor creates it) if (!graph.getNode(fileNodeId)) continue; - const lines = file.content.split('\n'); + // Normalize CRLF/CR to LF before splitting so that line-end agnostic + // markdown files (Windows-authored, mixed) yield correct headings. + // Without this, splitting on `\n` alone leaves `## Heading\r` on each line; + // `$` in HEADING_RE only matches at end-of-string, while `.+` stops before + // the trailing `\r`, so the line never matches as a heading. + const lines = file.content.split(/\r\n|\r|\n/); // --- Extract headings and build hierarchy --- // First pass: collect all heading positions so we can compute endLine spans diff --git a/gitnexus/src/core/ingestion/model/symbol-table.ts b/gitnexus/src/core/ingestion/model/symbol-table.ts index c22f63acb..a730c66eb 100644 --- a/gitnexus/src/core/ingestion/model/symbol-table.ts +++ b/gitnexus/src/core/ingestion/model/symbol-table.ts @@ -128,6 +128,7 @@ export interface AddMetadata { parameterTypes?: string[]; returnType?: string; declaredType?: string; + templateArguments?: string[]; ownerId?: string; qualifiedName?: string; } @@ -277,6 +278,9 @@ export const createSymbolTable = (): InternalSymbolTable => { : {}), ...(metadata?.returnType !== undefined ? { returnType: metadata.returnType } : {}), ...(metadata?.declaredType !== undefined ? { declaredType: metadata.declaredType } : {}), + ...(metadata?.templateArguments !== undefined + ? { templateArguments: metadata.templateArguments } + : {}), ...(metadata?.ownerId !== undefined ? { ownerId: metadata.ownerId } : {}), }; diff --git a/gitnexus/src/core/ingestion/parsing-processor.ts b/gitnexus/src/core/ingestion/parsing-processor.ts index 98036fbe8..f88e78ed9 100644 --- a/gitnexus/src/core/ingestion/parsing-processor.ts +++ b/gitnexus/src/core/ingestion/parsing-processor.ts @@ -5,12 +5,11 @@ import { loadParser, loadLanguage, isLanguageAvailable } from '../tree-sitter/pa import { getProvider } from './languages/index.js'; import { generateId } from '../../lib/utils.js'; import type { SymbolTableReader, SymbolTableWriter, ExtractedHeritage } from './model/index.js'; -// SymbolTableReader is used for the FieldExtractorContext stub; the -// parsing functions themselves need Writer because they call .add(). import { ASTCache } from './ast-cache.js'; import { getLanguageFromFilename, SupportedLanguages } from 'gitnexus-shared'; import { extractVueScript, isVueSetupTopLevel } from './vue-sfc-extractor.js'; import { yieldToEventLoop } from './utils/event-loop.js'; +import { parseSourceSafe } from '../tree-sitter/safe-parse.js'; import { isVerboseIngestionEnabled } from './utils/verbose.js'; import { getDefinitionNodeFromCaptures, @@ -31,6 +30,7 @@ import { constTagForId, buildCollisionGroups, } from './utils/method-props.js'; +import { extractTemplateArguments, templateArgumentsIdTag } from './utils/template-arguments.js'; import type { LanguageProvider } from './language-provider.js'; import type { ParsedFile } from 'gitnexus-shared'; import { WorkerPool } from './workers/worker-pool.js'; @@ -83,6 +83,89 @@ export interface WorkerExtractedData { // Worker-based parallel parsing // ============================================================================ +/** + * Merge a list of `ParseWorkerResult`s into the running graph + symbol + * table state and produce the chunk-aggregated `WorkerExtractedData`. + * + * Extracted from `processParsingWithWorkers` so the same merge logic can + * be applied to both freshly-parsed worker output AND cached worker + * output replayed during incremental analyze. Idempotent on the + * accumulator fields (push-only); idempotent on graph if the caller + * starts from a clean graph (otherwise duplicate `addNode` calls are + * silently no-op'd by `KnowledgeGraph`). + */ +export const mergeChunkResults = ( + graph: KnowledgeGraph, + symbolTable: SymbolTableWriter, + chunkResults: readonly ParseWorkerResult[], +): WorkerExtractedData => { + const allImports: ExtractedImport[] = []; + const allCalls: ExtractedCall[] = []; + const allAssignments: ExtractedAssignment[] = []; + const allHeritage: ExtractedHeritage[] = []; + const allRoutes: ExtractedRoute[] = []; + const allFetchCalls: ExtractedFetchCall[] = []; + const allDecoratorRoutes: ExtractedDecoratorRoute[] = []; + const allToolDefs: ExtractedToolDef[] = []; + const allORMQueries: ExtractedORMQuery[] = []; + const allConstructorBindings: FileConstructorBindings[] = []; + const fileScopeBindingsByFile: FileScopeBindings[] = []; + const allParsedFiles: ParsedFile[] = []; + + for (const result of chunkResults) { + for (const node of result.nodes) { + graph.addNode({ + id: node.id, + label: node.label as NodeLabel, + properties: node.properties, + }); + } + for (const rel of result.relationships) { + graph.addRelationship(rel); + } + for (const sym of result.symbols) { + symbolTable.add(sym.filePath, sym.name, sym.nodeId, sym.type, { + parameterCount: sym.parameterCount, + requiredParameterCount: sym.requiredParameterCount, + parameterTypes: sym.parameterTypes, + returnType: sym.returnType, + declaredType: sym.declaredType, + templateArguments: sym.templateArguments, + ownerId: sym.ownerId, + qualifiedName: sym.qualifiedName, + }); + } + for (const item of result.imports) allImports.push(item); + for (const item of result.calls) allCalls.push(item); + for (const item of result.assignments) allAssignments.push(item); + for (const item of result.heritage) allHeritage.push(item); + for (const item of result.routes) allRoutes.push(item); + for (const item of result.fetchCalls) allFetchCalls.push(item); + for (const item of result.decoratorRoutes) allDecoratorRoutes.push(item); + for (const item of result.toolDefs) allToolDefs.push(item); + if (result.ormQueries) for (const item of result.ormQueries) allORMQueries.push(item); + for (const item of result.constructorBindings) allConstructorBindings.push(item); + if (result.fileScopeBindings) + for (const item of result.fileScopeBindings) fileScopeBindingsByFile.push(item); + if (result.parsedFiles) for (const item of result.parsedFiles) allParsedFiles.push(item); + } + + return { + imports: allImports, + calls: allCalls, + assignments: allAssignments, + heritage: allHeritage, + routes: allRoutes, + fetchCalls: allFetchCalls, + decoratorRoutes: allDecoratorRoutes, + toolDefs: allToolDefs, + ormQueries: allORMQueries, + constructorBindings: allConstructorBindings, + fileScopeBindings: fileScopeBindingsByFile, + parsedFiles: allParsedFiles, + }; +}; + const processParsingWithWorkers = async ( graph: KnowledgeGraph, files: { path: string; content: string }[], @@ -90,6 +173,14 @@ const processParsingWithWorkers = async ( astCache: ASTCache, workerPool: WorkerPool, onFileProgress?: FileProgressCallback, + /** + * When provided, populated with the raw worker results before merging. + * Used by the incremental-indexing parse cache to capture the per-chunk + * worker output for caching across runs. The mutation happens in-place + * so the caller (parse-impl) can keep a reference. See + * `gitnexus/src/storage/parse-cache.ts`. + */ + outRawResults?: ParseWorkerResult[], ): Promise => { // Filter to parseable files only const parseableFiles: ParseWorkerInput[] = []; @@ -124,63 +215,16 @@ const processParsingWithWorkers = async ( }, ); - // Merge results from all workers into graph and symbol table - const allImports: ExtractedImport[] = []; - const allCalls: ExtractedCall[] = []; - const allAssignments: ExtractedAssignment[] = []; - const allHeritage: ExtractedHeritage[] = []; - const allRoutes: ExtractedRoute[] = []; - const allFetchCalls: ExtractedFetchCall[] = []; - const allDecoratorRoutes: ExtractedDecoratorRoute[] = []; - const allToolDefs: ExtractedToolDef[] = []; - const allORMQueries: ExtractedORMQuery[] = []; - const allConstructorBindings: FileConstructorBindings[] = []; - const fileScopeBindingsByFile: FileScopeBindings[] = []; - const allParsedFiles: ParsedFile[] = []; - for (const result of chunkResults) { - for (const node of result.nodes) { - graph.addNode({ - id: node.id, - label: node.label as NodeLabel, - properties: node.properties, - }); - } - - for (const rel of result.relationships) { - graph.addRelationship(rel); - } - - for (const sym of result.symbols) { - symbolTable.add(sym.filePath, sym.name, sym.nodeId, sym.type, { - parameterCount: sym.parameterCount, - requiredParameterCount: sym.requiredParameterCount, - parameterTypes: sym.parameterTypes, - returnType: sym.returnType, - declaredType: sym.declaredType, - ownerId: sym.ownerId, - qualifiedName: sym.qualifiedName, - }); - } - - for (const item of result.imports) allImports.push(item); - for (const item of result.calls) allCalls.push(item); - for (const item of result.assignments) allAssignments.push(item); - for (const item of result.heritage) allHeritage.push(item); - for (const item of result.routes) allRoutes.push(item); - for (const item of result.fetchCalls) allFetchCalls.push(item); - for (const item of result.decoratorRoutes) allDecoratorRoutes.push(item); - for (const item of result.toolDefs) allToolDefs.push(item); - if (result.ormQueries) for (const item of result.ormQueries) allORMQueries.push(item); - for (const item of result.constructorBindings) allConstructorBindings.push(item); - if (result.fileScopeBindings) - for (const item of result.fileScopeBindings) fileScopeBindingsByFile.push(item); - // RFC #909 Ring 2: aggregate per-file scope artifacts. Tolerant of - // workers that don't emit the field yet (older worker builds or - // partial rollouts), since the additive contract means undefined = - // "this worker produced no ParsedFiles for this chunk". - if (result.parsedFiles) for (const item of result.parsedFiles) allParsedFiles.push(item); + // Capture the raw chunk results for the incremental parse cache before + // merging — the cache stores the unmerged worker output so a future run + // can re-merge them into a fresh graph state. + if (outRawResults) { + for (const r of chunkResults) outRawResults.push(r); } + // Merge results from all workers into graph and symbol table. + const merged = mergeChunkResults(graph, symbolTable, chunkResults); + // Merge and log skipped languages from workers const skippedLanguages = new Map(); for (const result of chunkResults) { @@ -197,20 +241,7 @@ const processParsingWithWorkers = async ( // Final progress onFileProgress?.(total, total, 'done'); - return { - imports: allImports, - calls: allCalls, - assignments: allAssignments, - heritage: allHeritage, - routes: allRoutes, - fetchCalls: allFetchCalls, - decoratorRoutes: allDecoratorRoutes, - toolDefs: allToolDefs, - ormQueries: allORMQueries, - constructorBindings: allConstructorBindings, - fileScopeBindings: fileScopeBindingsByFile, - parsedFiles: allParsedFiles, - }; + return merged; }; // ============================================================================ @@ -384,7 +415,7 @@ const processParsingSequential = async ( let tree: Parser.Tree; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch (parseError) { @@ -454,6 +485,23 @@ const processParsingSequential = async ( }) : null; const nodeLabel = extractedClassSymbol?.type ?? defaultNodeLabel; + const isClassLikeLabel = + nodeLabel === 'Class' || + nodeLabel === 'Struct' || + nodeLabel === 'Interface' || + nodeLabel === 'Enum' || + nodeLabel === 'Record'; + if ( + isClassLikeLabel && + provider.classExtractor?.shouldSkipClassCapture?.({ + captureMap, + definitionNode, + nameNode, + nodeLabel, + }) === true + ) { + return; + } // Synthesize name for constructors without explicit @name capture (e.g. Swift init) if (!nameNode && nodeLabel !== 'Constructor' && !extractedClassSymbol) return; const nodeName = extractedClassSymbol?.name ?? (nameNode ? nameNode.text : 'init'); @@ -581,7 +629,31 @@ const processParsingSequential = async ( cached.groups, ); } - const nodeId = generateId(nodeLabel, `${file.path}:${qualifiedName}${arityTag}`); + const classTemplateArguments = + extractedClassSymbol?.templateArguments ?? + provider.classExtractor?.extractTemplateArgumentsFromCapture?.({ + captureMap, + definitionNode, + nameNode, + }) ?? + (captureMap['template-arguments'] + ? extractTemplateArguments(captureMap['template-arguments'].text) + : undefined) ?? + (nameNode && nameNode.text ? extractTemplateArguments(nameNode.text) : undefined); + const classTemplateTag = + (nodeLabel === 'Class' || + nodeLabel === 'Struct' || + nodeLabel === 'Interface' || + nodeLabel === 'Enum' || + nodeLabel === 'Record') && + classTemplateArguments !== undefined && + classTemplateArguments.length > 0 + ? templateArgumentsIdTag(classTemplateArguments) + : ''; + const nodeId = generateId( + nodeLabel, + `${file.path}:${qualifiedName}${classTemplateTag}${arityTag}`, + ); const classNodeForSymbol = definitionNodeForRange || definitionNode || nameNode; const qualifiedTypeName = extractedClassSymbol?.qualifiedName ?? @@ -614,6 +686,9 @@ const processParsingSequential = async ( nodeName, ), ...(qualifiedTypeName !== undefined ? { qualifiedName: qualifiedTypeName } : {}), + ...(classTemplateArguments !== undefined && classTemplateArguments.length > 0 + ? { templateArguments: classTemplateArguments } + : {}), ...(frameworkHint ? { astFrameworkMultiplier: frameworkHint.entryPointMultiplier, @@ -671,6 +746,7 @@ const processParsingSequential = async ( parameterTypes: methodProps.parameterTypes as string[] | undefined, returnType: methodProps.returnType as string | undefined, declaredType, + templateArguments: classTemplateArguments, ownerId: enclosingClassId ?? undefined, qualifiedName: qualifiedTypeName, }); @@ -733,6 +809,14 @@ export const processParsing = async ( scopeTreeCache: ASTCache | undefined, onFileProgress?: FileProgressCallback, workerPool?: WorkerPool, + /** + * Optional out-parameter for the incremental parse cache. When + * provided AND the worker-pool path runs successfully, populated + * with the raw `ParseWorkerResult[]` from the workers (pre-merge). + * Stays empty for the sequential fallback path (no per-chunk + * artifact to cache there). See `gitnexus/src/storage/parse-cache.ts`. + */ + outRawResults?: ParseWorkerResult[], ): Promise => { let lastProgress = 0; const reportProgress: FileProgressCallback | undefined = onFileProgress @@ -760,6 +844,7 @@ export const processParsing = async ( astCache, workerPool, reportProgress, + outRawResults, ); } catch (err) { const message = err instanceof Error ? err.message : String(err); diff --git a/gitnexus/src/core/ingestion/pipeline-phases/parse-impl.ts b/gitnexus/src/core/ingestion/pipeline-phases/parse-impl.ts index bd39a4330..17cfaab3f 100644 --- a/gitnexus/src/core/ingestion/pipeline-phases/parse-impl.ts +++ b/gitnexus/src/core/ingestion/pipeline-phases/parse-impl.ts @@ -17,7 +17,10 @@ import { enrichExportedTypeMap, type BindingEntry, } from '../binding-accumulator.js'; -import { processParsing } from '../parsing-processor.js'; +import { processParsing, mergeChunkResults } from '../parsing-processor.js'; +import { fileContentHash, computeChunkHash } from '../../../storage/parse-cache.js'; +import type { ParseWorkerResult } from '../workers/parse-worker.js'; +import type { WorkerExtractedData } from '../parsing-processor.js'; import { processImports, processImportsFromExtracted, @@ -72,8 +75,21 @@ import { extractORMQueriesInline } from './orm-extraction.js'; import { logger } from '../../logger.js'; // ── Constants ────────────────────────────────────────────────────────────── -/** Max bytes of source content to load per parse chunk. */ -const CHUNK_BYTE_BUDGET = 20 * 1024 * 1024; // 20MB +/** Max bytes of source content to load per parse chunk. + * + * Memory bound for the worker pool dispatch + a granularity knob for + * the parse cache. A single file change invalidates only its enclosing + * chunk, so smaller budgets → finer-grained invalidation. + * + * Override via GITNEXUS_CHUNK_BYTE_BUDGET (bytes) — the default of 2MB + * gives a useful invalidation floor (~1/N chunks on a multi-MB repo) + * while keeping worker dispatch overhead under 5% on cold runs. + */ +const CHUNK_BYTE_BUDGET = (() => { + const env = Number(process.env.GITNEXUS_CHUNK_BYTE_BUDGET); + if (Number.isFinite(env) && env > 0) return env; + return 2 * 1024 * 1024; +})(); // ── Main parse + resolve function ────────────────────────────────────────── @@ -119,6 +135,11 @@ export async function runChunkedParseAndResolve( * source. See plan * docs/plans/2026-04-20-002-perf-parse-heritage-mro-plan.md (Unit 4). */ scopeTreeCache: ASTCache; + /** Worker-produced ParsedFile artifacts aggregated across chunks. + * Threaded into scope-resolution as a re-extract cache so the warm- + * cache analyze run can skip the dominant `extractParsedFile` cost + * (otherwise ~58s on a 1000-file repo). */ + parsedFiles: import('gitnexus-shared').ParsedFile[]; }> { const ctx = createResolutionContext(); const symbolTable = ctx.model.symbols; @@ -142,6 +163,15 @@ export async function runChunkedParseAndResolve( ); } + // Sort parseableScanned alphabetically for stable chunk membership + // across runs (Finding 4). Without this, filesystem-scan order can + // shift between runs (notably on macOS APFS where directory entry + // order can change after modifications) — different files in the + // same chunk → different chunk hash → cache miss even when no file + // content changed. The cache also becomes platform-specific: a + // Linux-built cache misses on macOS for the same repo. + parseableScanned.sort((a, b) => (a.path < b.path ? -1 : a.path > b.path ? 1 : 0)); + const totalParseable = parseableScanned.length; if (totalParseable === 0) { @@ -271,6 +301,20 @@ export async function runChunkedParseAndResolve( const deferredWorkerHeritage: ExtractedHeritage[] = []; const deferredConstructorBindings: FileConstructorBindings[] = []; const deferredAssignments: ExtractedAssignment[] = []; + // Aggregated per-file ParsedFile artifacts produced by workers' calls + // to `extractParsedFile`. Threaded through to the scope-resolution + // phase so it can SKIP its own re-extraction on cache hits — this is + // the second-half of the parse-cache speedup since scope-resolution's + // re-parse otherwise dominates the warm-cache wall-clock time. + const allParsedFiles: import('gitnexus-shared').ParsedFile[] = []; + + // Incremental parse cache (Option B): chunk-level content-addressed. + // When the chunk's (filePath, content-hash) signature matches a prior + // run's, replay the cached ParseWorkerResult[] instead of dispatching + // to workers. See gitnexus/src/storage/parse-cache.ts. + const parseCache = options?.parseCache; + let chunkCacheHits = 0; + let chunkCacheMisses = 0; try { for (let chunkIdx = 0; chunkIdx < numChunks; chunkIdx++) { @@ -281,29 +325,89 @@ export async function runChunkedParseAndResolve( .filter((p) => chunkContents.has(p)) .map((p) => ({ path: p, content: chunkContents.get(p)! })); - const chunkWorkerData = await processParsing( - graph, - chunkFiles, - symbolTable, - astCache, - scopeTreeCache, - (current, _total, filePath) => { - const globalCurrent = filesParsedSoFar + current; - const parsingProgress = 20 + (globalCurrent / totalParseable) * 62; - onProgress({ - phase: 'parsing', - percent: Math.round(parsingProgress), - message: `Parsing chunk ${chunkIdx + 1}/${numChunks}...`, - detail: filePath, - stats: { - filesProcessed: globalCurrent, - totalFiles: totalParseable, - nodesCreated: graph.nodeCount, - }, - }); - }, - workerPool, - ); + // Compute the chunk's content-hash signature (if cache available). + let chunkHash: string | null = null; + if (parseCache) { + const entries = chunkFiles.map((f) => ({ + filePath: f.path, + contentHash: fileContentHash(f.content), + })); + chunkHash = computeChunkHash(entries); + } + + let chunkWorkerData: WorkerExtractedData | null; + const cachedRaw = chunkHash ? parseCache!.entries.get(chunkHash) : undefined; + + // Track every chunk hash we touched so the orchestrator can + // prune stale entries (chunks whose composition no longer + // corresponds to a live chunk in the current scan) before saving. + if (parseCache && chunkHash) parseCache.usedKeys.add(chunkHash); + + if (cachedRaw && cachedRaw.length > 0) { + // Cache hit: replay the cached worker output through the same + // merge logic the live worker path uses. + chunkCacheHits++; + chunkWorkerData = mergeChunkResults(graph, symbolTable, cachedRaw); + if (isDev) { + logger.info( + `📦 parse-cache HIT: chunk ${chunkIdx + 1}/${numChunks} (${chunkFiles.length} files, ${chunkHash!.slice(0, 8)})`, + ); + } + // Progress update so UI advances even on a cache hit. + const cachedFiles = chunkFiles.length; + onProgress({ + phase: 'parsing', + percent: Math.round(20 + ((filesParsedSoFar + cachedFiles) / totalParseable) * 62), + message: `Parsing chunk ${chunkIdx + 1}/${numChunks} (cache)...`, + stats: { + filesProcessed: filesParsedSoFar + cachedFiles, + totalFiles: totalParseable, + nodesCreated: graph.nodeCount, + }, + }); + } else { + // Cache miss: dispatch to workers, capture the raw results, store + // them under the chunk hash for the next run. + chunkCacheMisses++; + const rawResults: ParseWorkerResult[] = []; + chunkWorkerData = await processParsing( + graph, + chunkFiles, + symbolTable, + astCache, + scopeTreeCache, + (current, _total, filePath) => { + const globalCurrent = filesParsedSoFar + current; + const parsingProgress = 20 + (globalCurrent / totalParseable) * 62; + onProgress({ + phase: 'parsing', + percent: Math.round(parsingProgress), + message: `Parsing chunk ${chunkIdx + 1}/${numChunks}...`, + detail: filePath, + stats: { + filesProcessed: globalCurrent, + totalFiles: totalParseable, + nodesCreated: graph.nodeCount, + }, + }); + }, + workerPool, + // Capture raw results only when we have a cache to write to — + // otherwise we'd retain extra arrays for nothing. + parseCache && chunkHash ? rawResults : undefined, + ); + // Persist the raw results for this chunk hash. Sequential path + // doesn't populate rawResults (it writes directly to graph), so + // small repos without worker pool simply don't cache. That's fine. + if (parseCache && chunkHash && rawResults.length > 0) { + parseCache.entries.set(chunkHash, rawResults); + if (isDev) { + logger.info( + `📦 parse-cache MISS+store: chunk ${chunkIdx + 1}/${numChunks} (${chunkFiles.length} files, ${chunkHash.slice(0, 8)})`, + ); + } + } + } const chunkBasePercent = 20 + (filesParsedSoFar / totalParseable) * 62; @@ -349,6 +453,12 @@ export async function runChunkedParseAndResolve( for (const item of chunkWorkerData.heritage) deferredWorkerHeritage.push(item); for (const item of chunkWorkerData.constructorBindings) deferredConstructorBindings.push(item); + // Aggregate worker-produced ParsedFile artifacts so scope- + // resolution can use them as a re-extraction cache (skips its + // own tree-sitter re-parse on warm runs). + if (chunkWorkerData.parsedFiles?.length) { + for (const item of chunkWorkerData.parsedFiles) allParsedFiles.push(item); + } if (chunkWorkerData.assignments?.length) { for (const item of chunkWorkerData.assignments) deferredAssignments.push(item); } @@ -422,6 +532,12 @@ export async function runChunkedParseAndResolve( astCache.clear(); } + if (isDev && parseCache && (chunkCacheHits > 0 || chunkCacheMisses > 0)) { + logger.info( + `📦 parse-cache summary: ${chunkCacheHits} chunk hit(s), ${chunkCacheMisses} miss(es) across ${numChunks} chunk(s)`, + ); + } + const fullWorkerHeritageMap = deferredWorkerHeritage.length > 0 ? buildHeritageMap(deferredWorkerHeritage, ctx, getHeritageStrategyForLanguage) @@ -621,5 +737,12 @@ export async function runChunkedParseAndResolve( // chunk-local `astCache` above is intentionally NOT exposed // because parse-impl clears it between chunks. scopeTreeCache, + // Per-file ParsedFile artifacts produced by workers' calls to + // `extractParsedFile`. Empty when only the sequential path ran + // (sequential doesn't go through the worker, and extracts ParsedFile + // inline rather than emitting it). Consumed by scope-resolution as + // a re-extraction cache: when the file's ParsedFile is here, + // scope-resolution skips its own `extractParsedFile` call. + parsedFiles: allParsedFiles, }; } diff --git a/gitnexus/src/core/ingestion/pipeline-phases/parse.ts b/gitnexus/src/core/ingestion/pipeline-phases/parse.ts index a20d1e4b0..a3fa81be7 100644 --- a/gitnexus/src/core/ingestion/pipeline-phases/parse.ts +++ b/gitnexus/src/core/ingestion/pipeline-phases/parse.ts @@ -20,6 +20,7 @@ import type { PipelinePhase, PipelineContext, PhaseResult } from './types.js'; import { getPhaseOutput } from './types.js'; import type { StructureOutput } from './structure.js'; import type { BindingAccumulator } from '../binding-accumulator.js'; +import type { ParsedFile } from 'gitnexus-shared'; import type { ExtractedFetchCall, ExtractedRoute, @@ -81,6 +82,19 @@ export interface ParseOutput { * `scopeTreeCache.clear()` after its extract loop finishes. */ readonly scopeTreeCache: ASTCache; + /** + * Per-file `ParsedFile` artifacts produced by workers' calls to + * `extractParsedFile`. Threaded through to `scopeResolutionPhase` + * as a re-extraction cache: when a file's ParsedFile is present here, + * scope-resolution can skip its own `extractParsedFile` (which would + * otherwise re-parse the file with tree-sitter on the main thread, + * costing ~58s on a 1000-file repo). + * + * Empty for files that went through the sequential parse fallback — + * sequential doesn't emit ParsedFile artifacts; scope-resolution + * falls back to a fresh extract for those. + */ + readonly parsedFiles: readonly ParsedFile[]; } export const parsePhase: PipelinePhase = { diff --git a/gitnexus/src/core/ingestion/pipeline.ts b/gitnexus/src/core/ingestion/pipeline.ts index c220ea224..1ee8e102f 100644 --- a/gitnexus/src/core/ingestion/pipeline.ts +++ b/gitnexus/src/core/ingestion/pipeline.ts @@ -55,6 +55,19 @@ export interface PipelineOptions { minFiles?: number; minBytes?: number; }; + /** + * Incremental-indexing parse cache. When provided: + * - The parse phase looks up each chunk's content hash in + * `parseCache.entries`. On hit, it replays the cached + * `ParseWorkerResult[]` instead of dispatching to workers. + * - On miss, it runs the workers as today and stores the new + * results in `parseCache.entries` keyed by chunk hash. + * The caller (`run-analyze.ts`) is responsible for loading the cache + * before the pipeline runs and persisting it after. Cache survives + * `--force` because keys are content-addressed. + * See `gitnexus/src/storage/parse-cache.ts`. + */ + parseCache?: import('../../storage/parse-cache.js').ParseCache; } // ── Phase registry ───────────────────────────────────────────────────────── diff --git a/gitnexus/src/core/ingestion/registry-primary-flag.ts b/gitnexus/src/core/ingestion/registry-primary-flag.ts index 713b32c07..869157adb 100644 --- a/gitnexus/src/core/ingestion/registry-primary-flag.ts +++ b/gitnexus/src/core/ingestion/registry-primary-flag.ts @@ -71,6 +71,9 @@ export const MIGRATED_LANGUAGES: ReadonlySet = new Set; + /** + * Optional parallel MRO that EXCLUDES mixin-like augmentation (e.g., PHP + * traits). Returns the inheritance-only ancestor chain — the same kind + * of map as `buildMro` but built only from inheritance edges (EXTENDS). + * + * Used by the shared super-branch dispatch in `receiver-bound-calls` + * so that `parent::method()` walks the inheritance chain only, not the + * trait-augmented one. PHP semantics: `parent::` explicitly bypasses + * traits, even when a composed trait shadows a same-named parent method. + * + * Languages without mixin-like semantics leave this undefined — callers + * fall back to `buildMro`/`mroFor`, which for those languages is already + * the inheritance chain. + */ + readonly buildExtendsOnlyMro?: ( + graph: KnowledgeGraph, + parsedFiles: readonly ParsedFile[], + nodeLookup: GraphNodeLookup, + ) => Map; + /** * Mutate `parsed.localDefs[i].ownerId` to point at the structural * owner. Python's rule: methods (Function defs whose parent scope @@ -412,9 +435,47 @@ export interface ScopeResolver { * `/^super\s*\(/.test(t)`. Java returns `t === 'super'`. C++ may * also need `this` capture. Languages without inheritance return * constant `false`. + * + * For languages where the answer depends on caller context (e.g. + * C++, where `Base::method()` is a super call ONLY when `Base` is + * actually a base of the caller's enclosing class, and namespace- + * qualified calls like `Singleton::getInstance()` must NOT be + * misclassified), implement the optional `isSuperReceiverInContext` + * variant below. The receiver-bound-calls pass prefers the context- + * aware variant when both are defined. */ isSuperReceiver(receiverText: string): boolean; + /** + * Optional context-aware variant of `isSuperReceiver`. When defined, + * the receiver-bound-calls pass prefers this hook over the simple + * `isSuperReceiver(text)` form. Languages where super classification + * is purely text-driven (Python, Java, PHP) omit this hook and the + * simple form is used unchanged. + * + * C++ uses this to distinguish `Base::method()` (super call when + * `Base` is in the caller's MRO) from `Singleton::getInstance()` + * (ordinary namespace-qualified call). Without this, the regex + * heuristic `/^[A-Z]\w*::/` misclassifies any uppercase-qualified + * call as a super-receiver call and routes it through the wrong + * resolution branch. + * + * Returns `true` ONLY when: + * - the receiver text parses as `::<...>` (or another super- + * form the language recognizes), AND + * - `` resolves (via scope chain) to a class-like def, AND + * - that class is in the MRO of the caller's enclosing class. + * + * Returns `false` for namespace-qualified calls, unresolved names, + * class-qualified calls where the class is NOT in the caller's MRO, + * and any text the simple `isSuperReceiver` hook also rejects. + */ + readonly isSuperReceiverInContext?: ( + receiverText: string, + callerScope: ScopeId, + scopes: ScopeResolutionIndexes, + ) => boolean; + // ─── Optional toggles ────────────────────────────────────────────────────── /** @@ -472,6 +533,112 @@ export interface ScopeResolver { */ readonly allowGlobalFreeCallFallback?: boolean; + /** + * Optional predicate to identify definitions with file-local linkage + * (e.g. C `static` functions). When provided, `pickUniqueGlobalCallable` + * excludes defs where `isFileLocalDef(def) === true` and the def lives + * in a different file from the caller. This prevents the global free-call + * fallback from creating CALLS edges to file-local symbols that are + * logically invisible from the caller's translation unit. + * + * Languages without file-local linkage semantics leave this undefined. + */ + readonly isFileLocalDef?: (def: SymbolDefinition) => boolean; + + /** + * Optional predicate to gate free-call fallback emission by caller-side + * visibility. When provided, `pickUniqueGlobalCallable` rejects candidates + * the caller cannot legally reach — e.g., a PHP function in a different + * namespace with no `use function` import, which PHP runtime would treat + * as `Call to undefined function`. Returning `false` blocks the candidate; + * returning `true` allows it; undefined-default keeps current behavior + * (no visibility filtering, equivalent to "all candidates visible"). + * + * The hook receives the caller's `ParsedFile` (so it can consult + * `parsedImports`, `moduleScope`, etc.) and the candidate `SymbolDefinition`. + * The predicate must be pure: same inputs → same answer. + * + * Languages without namespace-scoped function resolution leave this undefined. + */ + readonly isCallableVisibleFromCaller?: (ctx: { + readonly callerParsed: ParsedFile; + readonly candidate: SymbolDefinition; + /** Caller's enclosing scope id. Languages that gate visibility on + * caller scope (e.g. C++ two-phase template lookup) consult it; + * others ignore. Optional so existing implementations stay valid. */ + readonly callerScope?: ScopeId; + /** ScopeResolutionIndexes for scope-tree walks. Optional for the + * same reason as `callerScope`. */ + readonly scopes?: ScopeResolutionIndexes; + }) => boolean; + + /** + * Optional argument-dependent-lookup (ADL / Koenig lookup) hook for + * languages with C++-style associated-namespace candidate addition. + * + * Runs in the free-call fallback alongside ordinary unqualified lookup. + * The fallback merges ordinary candidates with ADL candidates and applies + * overload narrowing over the union. + * + * The hook inspects the call site's argument types, computes the + * associated namespace set, and returns either: + * - an array of candidate `SymbolDefinition`s to add to the + * ordinary-lookup candidate pool. + * - `undefined` when ADL contributes no candidates. + * + * Languages without C++-style ADL leave this undefined. The + * cross-language contract is "additive tier" — defining the hook never + * removes candidates the prior tier would have produced. + */ + readonly resolveAdlCandidates?: ( + site: { + readonly name: string; + readonly arity?: number; + readonly argumentTypes?: readonly string[]; + readonly atRange: { readonly startLine: number; readonly startCol: number }; + }, + callerParsed: ParsedFile, + scopes: ScopeResolutionIndexes, + parsedFiles: readonly ParsedFile[], + ) => readonly SymbolDefinition[] | undefined; + + /** + * Optional resolver for qualified-receiver member calls where the + * receiver is a namespace (not a class) and ordinary scope-chain / + * import resolution doesn't find the member. C++ uses this for + * `outer::foo()` style calls and to walk through inline-namespace + * children transitively (`outer::v1::foo` reachable as `outer::foo`). + * + * Languages whose qualified-name semantics are already covered by the + * receiver-bound-calls Case-1 namespace-targets path (e.g., Python's + * `import X; X.foo()`) leave this undefined. + * + * Receiver-bound-calls invokes this hook AFTER Case 1 (namespace + * imports) and AFTER Case 2 (class-name receiver) fail to resolve. + * Returns the target def, `'ambiguous'` when multiple inline-namespace + * children declare the same name (suppresses edge emission), or + * `undefined` to fall through to the remaining cases. + */ + readonly resolveQualifiedReceiverMember?: ( + receiverName: string, + memberName: string, + callerScope: ScopeId, + scopes: ScopeResolutionIndexes, + parsedFiles: readonly ParsedFile[], + ) => SymbolDefinition | 'ambiguous' | undefined; + + /** + * Enable the receiver-bound Case 0.5 fallback for explicit `this` + * receivers (`this->m()` / `this.m()`) that resolves against the + * enclosing class + MRO even when no explicit `this` typeBinding is + * present in scope. + * + * Keep disabled for languages where the existing type-binding path + * (Case 4) already handles `this` correctly and overload ambiguity + * suppression must remain unchanged. + */ + readonly resolveThisViaEnclosingClass?: boolean; + /** * Optional post-finalize hook to inject cross-file bindings that * aren't modeled via explicit imports. Runs after @@ -564,4 +731,32 @@ export interface ScopeResolver { readonly treeCache?: { get(filePath: string): unknown }; }, ) => void; + + /** + * Optional post-resolution pass: emit CALLS edges for member-call sites + * whose receiver cannot be typed by the scope chain (no `TypeRef`). + * Dynamically-typed languages with untyped/`mixed`/`Any` parameters use + * this hook to recover the call edge via workspace-wide method-name + * lookup, mirroring what their legacy resolvers did. + * + * Runs AFTER `emitReceiverBoundCalls` and BEFORE `emitFreeCallFallback`. + * Implementations MUST: + * - Skip sites already in `handledSites` (Invariant I2). + * - Add resolved site keys to `handledSites` before returning. + * - Stay narrow: a unique workspace-wide match is the safe baseline. + * Multi-candidate fallbacks should narrow by arity / argument types + * before emitting to keep false-positive rate bounded. + * + * Returns the number of edges emitted (for telemetry). + * + * Default: undefined (no unresolved-receiver fallback). + */ + readonly emitUnresolvedReceiverEdges?: ( + graph: KnowledgeGraph, + scopes: ScopeResolutionIndexes, + parsedFiles: readonly ParsedFile[], + nodeLookup: GraphNodeLookup, + handledSites: Set, + model: SemanticModel, + ) => number; } diff --git a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/ids.ts b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/ids.ts index ad59f4f10..adc32bbd3 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/ids.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/ids.ts @@ -71,7 +71,12 @@ function isCallerAnchorLabel(label: NodeLabel): boolean { */ export function resolveDefGraphId( filePath: string, - def: { qualifiedName?: string; type?: NodeLabel; parameterTypes?: readonly string[] }, + def: { + qualifiedName?: string; + type?: NodeLabel; + parameterTypes?: readonly string[]; + templateArguments?: readonly string[]; + }, nodeLookup: GraphNodeLookup, ): string | undefined { const qn = def.qualifiedName; @@ -89,6 +94,19 @@ export function resolveDefGraphId( const pHit = nodeLookup.get(pKey); if (pHit !== undefined) return pHit; } + if ( + (def.type === 'Class' || + def.type === 'Struct' || + def.type === 'Interface' || + def.type === 'Enum' || + def.type === 'Record') && + def.templateArguments !== undefined && + def.templateArguments.length > 0 + ) { + const tKey = qualifiedKey(filePath, def.type, `${qn}~${def.templateArguments.join(',')}`); + const tHit = nodeLookup.get(tKey); + if (tHit !== undefined) return tHit; + } const qualifiedHit = nodeLookup.get(qualifiedKey(filePath, def.type, qn)); if (qualifiedHit !== undefined) return qualifiedHit; } diff --git a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/method-dispatch.ts b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/method-dispatch.ts index 164147ac6..419ab478f 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/method-dispatch.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/method-dispatch.ts @@ -22,8 +22,9 @@ const EMPTY_DEFS: readonly string[] = Object.freeze([]); export function buildPopulatedMethodDispatch( mroByDefId: ReadonlyMap, + extendsOnlyMroByDefId?: ReadonlyMap, ): MethodDispatchIndex { - return { + const base: MethodDispatchIndex = { mroByOwnerDefId: mroByDefId, implsByInterfaceDefId: new Map(), mroFor(ownerDefId) { @@ -33,4 +34,14 @@ export function buildPopulatedMethodDispatch( return EMPTY_DEFS; }, }; + if (extendsOnlyMroByDefId !== undefined) { + return { + ...base, + extendsOnlyMroByOwnerDefId: extendsOnlyMroByDefId, + extendsOnlyMroFor(ownerDefId) { + return extendsOnlyMroByDefId.get(ownerDefId) ?? EMPTY_DEFS; + }, + }; + } + return base; } diff --git a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts index 70aa875fb..d712c29e3 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/graph-bridge/node-lookup.ts @@ -67,6 +67,7 @@ export function buildGraphNodeLookup(graph: KnowledgeGraph): GraphNodeLookup { filePath?: string; name?: string; qualifiedName?: string; + templateArguments?: readonly string[]; }; if (props.filePath === undefined || props.name === undefined) continue; if (!isLinkableLabel(node.label)) continue; @@ -96,6 +97,22 @@ export function buildGraphNodeLookup(graph: KnowledgeGraph): GraphNodeLookup { // Each overload is unique — set unconditionally. lookup.set(pKey, node.id); } + if ( + (node.label === 'Class' || + node.label === 'Struct' || + node.label === 'Interface' || + node.label === 'Enum' || + node.label === 'Record') && + props.templateArguments !== undefined && + props.templateArguments.length > 0 + ) { + const tKey = qualifiedKey( + props.filePath, + node.label, + `${qualified}~${props.templateArguments.join(',')}`, + ); + if (!lookup.has(tKey)) lookup.set(tKey, node.id); + } } // Fallback key: simple name. First-wins within a file — used when @@ -117,6 +134,11 @@ export function isLinkableLabel(label: NodeLabel): boolean { label === 'Interface' || label === 'Struct' || label === 'Enum' || + // Trait nodes are linkable so MRO builders can bridge PHP/Rust trait + // defs between scope-resolution DefIds and the graph's node ids. + // IMPLEMENTS edges from classes to traits are otherwise invisible to + // the scope-resolution MRO pass. + label === 'Trait' || // Variable / Property are linkable too — receiver-bound write/read // ACCESSES edges target field nodes (e.g. `user.name = "x"` → // ACCESSES edge to User's `name` Variable/Property node). diff --git a/gitnexus/src/core/ingestion/scope-resolution/passes/free-call-fallback.ts b/gitnexus/src/core/ingestion/scope-resolution/passes/free-call-fallback.ts index 248ee439f..d9e4cdaa3 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/passes/free-call-fallback.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/passes/free-call-fallback.ts @@ -24,8 +24,15 @@ import type { SemanticModel } from '../../model/semantic-model.js'; import type { WorkspaceResolutionIndex } from '../workspace-index.js'; import type { GraphNodeLookup } from '../graph-bridge/node-lookup.js'; import { resolveCallerGraphId, resolveDefGraphId } from '../graph-bridge/ids.js'; -import { findCallableBindingInScope, findClassBindingInScope } from '../scope/walkers.js'; -import { narrowOverloadCandidates } from './overload-narrowing.js'; +import { + findCallableBindingInScope, + findCallableBindingsAndAdlBlocker, + findClassBindingInScope, +} from '../scope/walkers.js'; +import { + isOverloadAmbiguousAfterNormalization, + narrowOverloadCandidates, +} from './overload-narrowing.js'; export function emitFreeCallFallback( graph: KnowledgeGraph, @@ -36,7 +43,27 @@ export function emitFreeCallFallback( handledSites: Set, model: SemanticModel, workspaceIndex: WorkspaceResolutionIndex, - options: { readonly allowGlobalFallback?: boolean } = {}, + options: { + readonly allowGlobalFallback?: boolean; + readonly isFileLocalDef?: (def: SymbolDefinition) => boolean; + readonly isCallableVisibleFromCaller?: (ctx: { + readonly callerParsed: ParsedFile; + readonly candidate: SymbolDefinition; + readonly callerScope?: ScopeId; + readonly scopes?: ScopeResolutionIndexes; + }) => boolean; + readonly resolveAdlCandidates?: ( + site: { + readonly name: string; + readonly arity?: number; + readonly argumentTypes?: readonly string[]; + readonly atRange: { readonly startLine: number; readonly startCol: number }; + }, + callerParsed: ParsedFile, + scopes: ScopeResolutionIndexes, + parsedFiles: readonly ParsedFile[], + ) => readonly SymbolDefinition[] | undefined; + } = {}, ): number { let emitted = 0; const seen = new Set(); @@ -66,14 +93,98 @@ export function emitFreeCallFallback( fnDef = pickImplicitThisOverload(site, scopes, workspaceIndex, model); } if (fnDef === undefined) { - fnDef = findCallableBindingInScope(site.inScope, site.name, scopes); + if (options.resolveAdlCandidates === undefined) { + fnDef = findCallableBindingInScope(site.inScope, site.name, scopes); + } else { + // ISO C++ `[basic.lookup.unqual]` §7: ADL is suppressed when + // ordinary lookup finds a non-function name (variable, class, enum) + // or a block-scope function declaration (not via using-declaration) + // at the nearest scope where the name exists. + const { + callables: ordinary, + nonCallableFound, + blockScopeDeclFound, + } = findCallableBindingsAndAdlBlocker(site.inScope, site.name, scopes); + const adlSuppressed = nonCallableFound || blockScopeDeclFound; + const adl = adlSuppressed + ? undefined + : options.resolveAdlCandidates( + { + name: site.name, + arity: site.arity, + argumentTypes: site.argumentTypes, + atRange: { startLine: site.atRange.startLine, startCol: site.atRange.startCol }, + }, + parsed, + scopes, + parsedFiles, + ); + + // Preserve existing ordinary-lookup behavior when ADL contributed + // no candidates. + if (adl === undefined || adl.length === 0) { + fnDef = ordinary[0]; + } else { + const siteKey = `${parsed.filePath}:${site.atRange.startLine}:${site.atRange.startCol}`; + const merged: SymbolDefinition[] = []; + const seen = new Set(); + const push = (defs: readonly SymbolDefinition[]): void => { + for (const d of defs) { + if (seen.has(d.nodeId)) continue; + seen.add(d.nodeId); + merged.push(d); + } + }; + push(ordinary); + push(adl); + + const narrowed = narrowOverloadCandidates(merged, site.arity, site.argumentTypes); + if (narrowed.length === 1) { + fnDef = narrowed[0]; + } else if (narrowed.length === 0) { + // ADL contributed candidates, but none survived arity/type + // narrowing. Treat as handled to avoid global-name fallback + // binding to the same mismatched symbol by simple-name + // uniqueness. + handledSites.add(siteKey); + continue; + } else if (narrowed.length > 1) { + // Suppress ambiguous overload calls (emit zero edges) when + // merged ordinary+ADL candidate sets cannot be disambiguated. + if (isOverloadAmbiguousAfterNormalization(narrowed, site.arity)) { + handledSites.add(siteKey); + continue; + } + // Multiple survivors remain but no conversion-ranking step + // exists yet; suppress instead of picking arbitrarily. + handledSites.add(siteKey); + continue; + } + } + } } // V1: pickUniqueGlobalCallable ignores import context — resolves to any // globally-unique callable. False cross-package edges are possible when // the caller does not import the target package. Same-package calls are - // caught by findCallableBindingInScope above before reaching here. + // usually caught by nearest-scope lookup before reaching here. if (fnDef === undefined && options.allowGlobalFallback === true) { - fnDef = pickUniqueGlobalCallable(site.name, model, scopes); + fnDef = pickUniqueGlobalCallable( + site.name, + model, + scopes, + parsed.filePath, + options.isFileLocalDef, + site.arity, + options.isCallableVisibleFromCaller !== undefined + ? (candidate) => + options.isCallableVisibleFromCaller!({ + callerParsed: parsed, + candidate, + callerScope: site.inScope, + scopes, + }) + : undefined, + ); } if (fnDef === undefined) continue; const callerGraphId = resolveCallerGraphId(site.inScope, scopes, nodeLookup); @@ -107,6 +218,10 @@ function pickUniqueGlobalCallable( name: string, model: SemanticModel, scopes: ScopeResolutionIndexes, + callerFilePath: string, + isFileLocalDef?: (def: SymbolDefinition) => boolean, + callArity?: number, + isCallerVisible?: (candidate: SymbolDefinition) => boolean, ): SymbolDefinition | undefined { const scopeDefs: SymbolDefinition[] = []; const scopeSeen = new Set(); @@ -114,6 +229,18 @@ function pickUniqueGlobalCallable( const simple = def.qualifiedName?.split('.').pop() ?? def.qualifiedName; if (simple !== name) continue; if (def.type !== 'Function' && def.type !== 'Method' && def.type !== 'Constructor') continue; + // Skip file-local defs (e.g. C `static` functions) that live in a + // different file from the caller — they are logically invisible. + if (isFileLocalDef !== undefined && def.filePath !== callerFilePath && isFileLocalDef(def)) { + continue; + } + // Caller-side visibility filter (e.g., PHP namespace + use-function + // import gating). When defined, blocks candidates the caller cannot + // legally reach. Languages without namespace-scoped function resolution + // leave this undefined → no filtering. + if (isCallerVisible !== undefined && !isCallerVisible(def)) { + continue; + } const key = logicalCallableKey(def); if (scopeSeen.has(key)) continue; scopeSeen.add(key); @@ -121,10 +248,29 @@ function pickUniqueGlobalCallable( } if (scopeDefs.length === 1) return scopeDefs[0]; + // When multiple scope-index candidates exist, attempt arity narrowing + // before falling back to the semantic-model lookup. This handles + // registry-primary languages where the model is not populated for the + // migrated language's files (call-processor skips them). + if (scopeDefs.length > 1 && callArity !== undefined) { + const arityMatch = narrowByArity(scopeDefs, callArity); + if (arityMatch !== undefined) return arityMatch; + } + const defs: SymbolDefinition[] = []; const seen = new Set(); const push = (pool: readonly SymbolDefinition[]): void => { for (const def of pool) { + // Apply the same file-local linkage filter as Phase 1 — + // cross-file static defs must never leak through the + // SemanticModel fallback path. + if (isFileLocalDef !== undefined && def.filePath !== callerFilePath && isFileLocalDef(def)) { + continue; + } + // Same caller-visibility filter applied to the model-side pool. + if (isCallerVisible !== undefined && !isCallerVisible(def)) { + continue; + } const key = logicalCallableKey(def); if (seen.has(key)) continue; seen.add(key); @@ -135,7 +281,35 @@ function pickUniqueGlobalCallable( push(model.symbols.lookupCallableByName(name)); push(model.methods.lookupMethodByName(name)); - return defs.length === 1 ? defs[0] : undefined; + if (defs.length === 1) return defs[0]; + + // When multiple candidates exist and the call site has a known arity, + // narrow by parameter count. + if (defs.length > 1 && callArity !== undefined) { + const arityMatch = narrowByArity(defs, callArity); + if (arityMatch !== undefined) return arityMatch; + } + + return undefined; +} + +/** + * Narrow a list of callable candidates by call-site arity. + * A def is compatible when `requiredParameterCount <= arity <= parameterCount`. + * Defs with `parameterCount === undefined` (variadic/unknown) are always kept. + * Returns the single compatible def, or `undefined` when zero or multiple match. + */ +function narrowByArity( + defs: readonly SymbolDefinition[], + callArity: number, +): SymbolDefinition | undefined { + const compatible = defs.filter((d) => { + const total = d.parameterCount; + if (total === undefined) return true; // unknown arity — keep + const required = d.requiredParameterCount ?? total; + return required <= callArity && callArity <= total; + }); + return compatible.length === 1 ? compatible[0] : undefined; } function logicalCallableKey(def: SymbolDefinition): string { @@ -167,10 +341,18 @@ function pickConstructorOrClass( /** Walk up from the call-site scope to the enclosing class scope, * pick a method member by name with overload narrowing on arity + - * argument types. Returns undefined if there's no enclosing class - * or no matching method. Used for implicit-this calls inside a - * class body where multiple overloads share the call name. */ -function pickImplicitThisOverload( + * argument types. Returns undefined if there's no enclosing class, + * no matching method, OR narrowing leaves multiple compatible + * candidates — in the multi-candidate case, picking + * `candidates[0]` would emit a high-confidence CALLS edge whose + * target depends on registration order rather than a defensible + * resolution. Mirrors `pickUniqueGlobalCallable`'s uniqueness check + * in the same file (Codex PR #1497 review, finding 2). + * + * Exported for unit testing — language-agnostic logic, exercised + * via synthetic stubs in `pick-implicit-this-overload.test.ts`. The + * production call site is `applyFreeCallFallback` immediately above. */ +export function pickImplicitThisOverload( site: { readonly inScope: ScopeId; readonly name: string; @@ -203,6 +385,11 @@ function pickImplicitThisOverload( if (overloads.length === 0) return undefined; if (overloads.length === 1) return overloads[0]; + // Narrow on arity + argument types. Require a UNIQUE survivor — + // ambiguous narrowing (multiple compatible candidates with no + // disambiguating signal) leaves the call unresolved rather than + // routing to an arbitrary first overload by registration order. const candidates = narrowOverloadCandidates(overloads, site.arity, site.argumentTypes); + if (candidates.length !== 1) return undefined; return candidates[0]; } diff --git a/gitnexus/src/core/ingestion/scope-resolution/passes/imported-return-types.ts b/gitnexus/src/core/ingestion/scope-resolution/passes/imported-return-types.ts index cbdfc62aa..33716778d 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/passes/imported-return-types.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/passes/imported-return-types.ts @@ -151,7 +151,8 @@ export function propagateImportedReturnTypes( const refs = lookupBindingsAt(importerModule.id, localName, indexes); for (const ref of refs) { - if (ref.origin !== 'import' && ref.origin !== 'reexport') continue; + if (ref.origin !== 'import' && ref.origin !== 'reexport' && ref.origin !== 'wildcard') + continue; const sourceModule = moduleScopeByFile.get(ref.def.filePath); if (sourceModule === undefined) continue; diff --git a/gitnexus/src/core/ingestion/scope-resolution/passes/overload-narrowing.ts b/gitnexus/src/core/ingestion/scope-resolution/passes/overload-narrowing.ts index 922afb36c..bff16d27e 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/passes/overload-narrowing.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/passes/overload-narrowing.ts @@ -13,9 +13,13 @@ * 2. Exact-required-match wins over variadic. Variadic is detected * via a `parameterTypes` entry equal to `'params'` or starting * with `'params '` (C# `params` / variadic marker). - * 3. If the arity filter empties the set, fall back to the full - * overload list rather than returning nothing — the caller still - * needs a best-effort candidate. + * 3. If the arity filter empties the set AND any candidate had + * unknown bounds (both `parameterCount` and `requiredParameterCount` + * undefined), fall back to the full overload list — the empty + * result may be due to missing metadata rather than a real mismatch. + * If EVERY rejected candidate had definite arity bounds, trust the + * filter and return empty — the call is genuinely arity-incompatible + * (e.g., PHP `f(int $req, ...$rest)` called with zero args). * 4. If `argTypes` is present, filter further by per-slot type * equality. An empty string in `argTypes[i]` means "unknown" and * counts as a match. Mismatches disqualify. A non-empty typed @@ -39,6 +43,16 @@ export function narrowOverloadCandidates( const max = d.parameterCount; const min = d.requiredParameterCount; if (max !== undefined && argCount > max) { + // Variadic marker check is C#-specific (the 'params' keyword). + // Other languages use their own marker — PHP uses '...' (see + // `languages/php/arity-metadata.ts:46`), Python uses '*args'- + // shaped metadata that lives outside `parameterTypes` entirely. + // This branch is dead code for those languages because they + // set `parameterCount = undefined` for variadic functions, + // which keeps `max` undefined and skips this check entirely. + // Adding new variadic markers here changes behavior for those + // other languages too — don't extend without auditing each + // adapter's `arity-metadata.ts`. Finding 9 of PR #1497. const variadic = d.parameterTypes !== undefined && d.parameterTypes.some((t) => t === 'params' || t.startsWith('params ')); @@ -48,8 +62,16 @@ export function narrowOverloadCandidates( return true; }); + // When the arity filter empties the set, only fall back to the full + // overload list if some candidate had unknown bounds — otherwise the + // empty result is authoritative (every candidate definitively failed + // arity, e.g., PHP variadic with required-prefix called with too few + // args). + const anyUnknownBounds = overloads.some( + (d) => d.parameterCount === undefined && d.requiredParameterCount === undefined, + ); const candidates: readonly SymbolDefinition[] = - arityMatches.length > 0 ? arityMatches : overloads; + arityMatches.length > 0 ? arityMatches : anyUnknownBounds ? overloads : []; if (argTypes !== undefined && argTypes.length > 0) { const typed = candidates.filter((d) => { @@ -66,3 +88,63 @@ export function narrowOverloadCandidates( return candidates; } + +/** + * Detect when >1 candidate share identical `parameterTypes` after the + * per-language normalizer has collapsed distinct underlying types. This + * signals "the resolver cannot pick the right overload — the + * normalization that helps single-candidate flows now hides a real + * ambiguity" and lets callers suppress the edge rather than pick + * arbitrarily. + * + * Concrete trigger (PR #1520 review follow-up plan U2, Claude review + * Finding 5): the C++ `arity-metadata.ts` normalizer collapses `int`, + * `long`, `short`, `unsigned`, and `size_t` to `'int'`. Without this + * check, `process(int)` and `process(long)` both end up with + * `parameterTypes === ['int']`, and `pickOverload` arbitrarily picks + * the first — emitting a false CALLS edge to the wrong overload. + * + * Returns false when: + * - 0 or 1 candidates (no ambiguity to detect) + * - any candidate has undefined `parameterTypes` (can't compare) + * - candidates differ in arity or in any parameter-type slot + * + * Other languages: this check is a precondition gate, not a behavior + * change for normal narrowing. Languages whose normalizers do not + * collapse distinct types (verified by grep over `*-arity-metadata.ts` + * — no `int → int` collapse outside C++) will never produce >1 + * candidate with identical `parameterTypes` from genuinely distinct + * declarations, so this returns false for them. The branch is + * effectively C++-only in practice. + */ +export function isOverloadAmbiguousAfterNormalization( + candidates: readonly SymbolDefinition[], + argCount?: number, +): boolean { + if (candidates.length < 2) return false; + const first = candidates[0].parameterTypes; + if (first === undefined) return false; + // When argCount is provided, compare only the first `argCount` slots — + // this catches default-argument ambiguity: `void f(int); void f(int, int = 0);` + // called with `f(1)` (argCount=1) leaves both candidates viable because + // default args make them arity-compatible, and their first slot is + // identical even though full parameterTypes lengths differ. + // Without argCount, fall back to full-sequence comparison (the original + // int/long normalization-collapse case). + const compareUpTo = argCount !== undefined ? argCount : first.length; + if (compareUpTo === 0) return false; + if (first.length < compareUpTo) return false; + for (let i = 1; i < candidates.length; i++) { + const p = candidates[i].parameterTypes; + if (p === undefined) return false; + if (p.length < compareUpTo) return false; + for (let j = 0; j < compareUpTo; j++) { + if (p[j] !== first[j]) return false; + } + // When argCount is NOT provided, also require length equality so + // distinct-arity candidates that happen to share a prefix don't + // collapse to ambiguous (preserves the original int/long contract). + if (argCount === undefined && p.length !== first.length) return false; + } + return true; +} diff --git a/gitnexus/src/core/ingestion/scope-resolution/passes/receiver-bound-calls.ts b/gitnexus/src/core/ingestion/scope-resolution/passes/receiver-bound-calls.ts index 925151b6c..92b4c1ac1 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/passes/receiver-bound-calls.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/passes/receiver-bound-calls.ts @@ -51,7 +51,14 @@ import { import { tryEmitEdge } from '../graph-bridge/edges.js'; import { resolveCompoundReceiverClass } from '../passes/compound-receiver.js'; import { resolveDefGraphId } from '../graph-bridge/ids.js'; -import { narrowOverloadCandidates } from './overload-narrowing.js'; +import { + narrowOverloadCandidates, + isOverloadAmbiguousAfterNormalization, +} from './overload-narrowing.js'; +import { + extractTemplateArguments, + stripTemplateArguments, +} from '../../utils/template-arguments.js'; /** Subset of `ScopeResolver` consumed by this pass. Accepting the * subset rather than the full provider keeps tests and partial @@ -59,12 +66,62 @@ import { narrowOverloadCandidates } from './overload-narrowing.js'; type ReceiverBoundProviderSubset = Pick< ScopeResolver, | 'isSuperReceiver' + | 'isSuperReceiverInContext' | 'fieldFallbackOnMethodLookup' | 'collapseMemberCallsByCallerTarget' | 'unwrapCollectionAccessor' | 'hoistTypeBindingsToModule' + | 'resolveQualifiedReceiverMember' + | 'resolveThisViaEnclosingClass' >; +function normalizeTemplateArgToken(value: string): string { + return value.replace(/\s+/g, ''); +} + +function resolveClassBindingForName( + scopeId: string, + rawClassName: string, + scopes: ScopeResolutionIndexes, +): SymbolDefinition | undefined { + const direct = findClassBindingInScope(scopeId, rawClassName, scopes); + if (direct !== undefined) return direct; + + if (!rawClassName.includes('<')) return undefined; + const baseName = stripTemplateArguments(rawClassName).replace(/\s+/g, ''); + if (baseName.length === 0) return undefined; + + const wantedArgs = extractTemplateArguments(rawClassName)?.map(normalizeTemplateArgToken); + if (wantedArgs !== undefined && wantedArgs.length > 0) { + // qualifiedNames is a Map and may not contain the stripped base name at all + // (e.g., unresolved type binding or only template-qualified entries), so + // default to [] before checking `.length`. + const qnameIds = scopes.qualifiedNames.get(baseName) ?? []; + if (qnameIds.length === 0) { + return findClassBindingInScope(scopeId, baseName, scopes); + } + const matches: SymbolDefinition[] = []; + for (const id of qnameIds) { + const def = scopes.defs.get(id); + if (def === undefined || !isClassLike(def.type)) continue; + const defArgs = def.templateArguments?.map(normalizeTemplateArgToken); + if ( + defArgs !== undefined && + defArgs.length === wantedArgs.length && + defArgs.every((value, i) => value === wantedArgs[i]) + ) { + matches.push(def); + } + } + if (matches.length === 1) return matches[0]; + // Scope extractor only records class definitions with bodies in C++, so + // forward declarations are not expected here. Keep fallback behavior for + // safety in non-ODR or mixed-language edge cases. + } + + return findClassBindingInScope(scopeId, baseName, scopes); +} + export function emitReceiverBoundCalls( graph: KnowledgeGraph, scopes: ScopeResolutionIndexes, @@ -162,10 +219,26 @@ export function emitReceiverBoundCalls( const siteKey = `${parsed.filePath}:${site.atRange.startLine}:${site.atRange.startCol}`; // ── super branch ───────────────────────────────────────────── - if (provider.isSuperReceiver(receiverName)) { + // Languages with caller-context-dependent super classification + // (C++) define `isSuperReceiverInContext`; we prefer it. Simple + // text-only languages (Python, Java, PHP) use the plain hook. + const isSuper = + provider.isSuperReceiverInContext !== undefined + ? provider.isSuperReceiverInContext(receiverName, site.inScope, scopes) + : provider.isSuperReceiver(receiverName); + if (isSuper) { const enclosingClass = findEnclosingClassDef(site.inScope, scopes); if (enclosingClass !== undefined) { - const ancestors = scopes.methodDispatch.mroFor(enclosingClass.nodeId); + // For super-receiver dispatch (`parent::`, `base.`, `super()`), + // walk the inheritance-only ancestor chain when the language + // exposes it. PHP's `parent::` semantically bypasses composed + // traits; other languages without mixin augmentation have no + // `extendsOnlyMroFor` and fall back to `mroFor`. + const extendsOnly = scopes.methodDispatch.extendsOnlyMroFor; + const ancestors = + extendsOnly !== undefined + ? extendsOnly(enclosingClass.nodeId) + : scopes.methodDispatch.mroFor(enclosingClass.nodeId); let memberDef: SymbolDefinition | undefined; for (const ownerId of ancestors) { memberDef = findOwnedMember(ownerId, memberName, model); @@ -249,6 +322,88 @@ export function emitReceiverBoundCalls( } } + // ── Case 0.5: implicit `this` receiver ─────────────────────── + // C++ `this->member()` (and same-shape receivers in other OO + // languages) should resolve against the enclosing class + MRO + // even when there is no explicit `this` typeBinding in scope. + if (provider.resolveThisViaEnclosingClass === true && receiverName === 'this') { + const enclosingClass = findEnclosingClassDef(site.inScope, scopes); + if (enclosingClass !== undefined) { + const chain = [ + enclosingClass.nodeId, + ...scopes.methodDispatch.mroFor(enclosingClass.nodeId), + ]; + let memberDef: SymbolDefinition | undefined; + let ambiguous = false; + let hiddenByName = false; + for (const ownerId of chain) { + const methodOverloads = model.methods.lookupAllByOwner(ownerId, memberName); + if (methodOverloads.length > 0) { + const narrowed = narrowOverloadCandidates( + methodOverloads, + site.arity, + site.argumentTypes, + ); + if (isOverloadAmbiguousAfterNormalization(narrowed, site.arity)) { + ambiguous = true; + break; + } + if (narrowed.length === 0) { + // C++ name hiding: if the derived class declares `f`, base-class + // overloads named `f` are hidden for member lookup + // ([basic.lookup.classref]). A non-viable derived overload set + // therefore terminates lookup instead of falling through to base. + hiddenByName = true; + break; + } + memberDef = narrowed[0] ?? methodOverloads[0]; + break; + } + + // Field/property lookup intentionally runs only after the method + // lookup above: in C++ member-name lookup, functions with this + // name hide same-named base members; we therefore prefer method + // candidates first and only target a field when no methods with + // this name exist on the current owner. + memberDef = model.fields.lookupFieldByOwner(ownerId, memberName); + if (memberDef !== undefined) { + break; + } + } + if (ambiguous) { + handledSites.add(siteKey); + continue; + } + if (hiddenByName) { + handledSites.add(siteKey); + continue; + } + if (memberDef !== undefined) { + const reason = + site.kind === 'write' || site.kind === 'read' + ? site.kind + : memberDef.filePath !== parsed.filePath + ? 'import-resolved' + : 'global'; + const confidence = site.kind === 'write' || site.kind === 'read' ? 1.0 : 0.85; + const ok = tryEmitEdge( + graph, + scopes, + nodeLookup, + site, + memberDef, + reason, + seen, + confidence, + collapse, + ); + if (ok) emitted++; + handledSites.add(siteKey); + continue; + } + } + } + // ── Case 1: namespace receiver ─────────────────────────────── const targetFiles = namespaceTargets.get(receiverName); if (targetFiles !== undefined) { @@ -276,6 +431,44 @@ export function emitReceiverBoundCalls( if (found) continue; } + // ── Case 1.5: qualified namespace-receiver (language-specific) ─── + // Languages whose qualified-name semantics need workspace-wide + // namespace-scope walking (C++ `outer::foo()`, including inline- + // namespace transitive traversal) implement `resolveQualifiedReceiverMember`. + // Runs before Case 2 so namespace receivers don't accidentally match a + // class with the same simple name. + if (provider.resolveQualifiedReceiverMember !== undefined) { + const memberDef = provider.resolveQualifiedReceiverMember( + receiverName, + memberName, + site.inScope, + scopes, + parsedFiles, + ); + if (memberDef === 'ambiguous') { + // Same-name ambiguity across inline-namespace children (#1564): + // suppress edge emission, mark site handled. + handledSites.add(siteKey); + continue; + } + if (memberDef !== undefined) { + const ok = tryEmitEdge( + graph, + scopes, + nodeLookup, + site, + memberDef, + memberDef.filePath !== parsed.filePath ? 'import-resolved' : 'global', + seen, + 0.85, + collapse, + ); + if (ok) emitted++; + handledSites.add(siteKey); + continue; + } + } + // ── Case 2: class-name receiver ────────────────────────────── const classDef = findClassBindingInScope(site.inScope, receiverName, scopes); if (classDef !== undefined) { @@ -283,7 +476,21 @@ export function emitReceiverBoundCalls( let memberDef: SymbolDefinition | undefined; for (const ownerId of chain) { memberDef = findOwnedMember(ownerId, memberName, model); - if (memberDef !== undefined) break; + if (memberDef !== undefined) { + // The MRO chain is most-derived-first ([classDef, ...ancestors]). + // If the most-derived definition is arity-incompatible with the + // call site, PHP throws ArgumentCountError at runtime — it does + // NOT silently dispatch to an ancestor. Terminate the chain walk + // so no edge is emitted, rather than falling through to an + // arity-compatible ancestor (which would be a false positive). + if ( + narrowOverloadCandidates([memberDef], site.arity, site.argumentTypes).length === 0 + ) { + memberDef = undefined; + break; + } + break; + } } if (memberDef !== undefined) { const reason = @@ -403,7 +610,7 @@ export function emitReceiverBoundCalls( // ── Case 4: simple typeBinding (`u: U`) ────────────────────── if (typeRef !== undefined && !typeRef.rawName.includes('.')) { - let ownerDef = findClassBindingInScope(site.inScope, typeRef.rawName, scopes); + let ownerDef = resolveClassBindingForName(site.inScope, typeRef.rawName, scopes); // `findClassBindingInScope(..., typeRef.rawName)` only works when // rawName is itself a class symbol reachable through scope bindings. // For languages with namespace-style imports (Go), imported types @@ -431,9 +638,24 @@ export function emitReceiverBoundCalls( if (ownerDef !== undefined) { const chain = [ownerDef.nodeId, ...scopes.methodDispatch.mroFor(ownerDef.nodeId)]; let memberDef: SymbolDefinition | undefined; + let ambiguous = false; for (const ownerId of chain) { - memberDef = pickOverload(ownerId, memberName, site, model); - if (memberDef !== undefined) break; + const picked = pickOverload(ownerId, memberName, site, model); + if (picked === OVERLOAD_AMBIGUOUS) { + ambiguous = true; + break; + } + if (picked !== undefined) { + memberDef = picked; + break; + } + } + if (ambiguous) { + // Suppress and mark handled so `emitReferencesViaLookup` + // doesn't re-emit the pre-resolved reference. See + // OVERLOAD_AMBIGUOUS docstring for the upstream cause. + handledSites.add(siteKey); + continue; } if (memberDef !== undefined) { // For read/write ACCESSES, mirror the legacy DAG's reason @@ -486,7 +708,7 @@ function pickOverload( memberName: string, site: ParsedFile['referenceSites'][number], model: SemanticModel, -): SymbolDefinition | undefined { +): SymbolDefinition | typeof OVERLOAD_AMBIGUOUS | undefined { const overloads = model.methods.lookupAllByOwner(ownerId, memberName); if (overloads.length === 0) { // Non-callable member (field / property / variable) — ACCESSES @@ -497,5 +719,22 @@ function pickOverload( if (overloads.length === 1) return overloads[0]; const candidates = narrowOverloadCandidates(overloads, site.arity, site.argumentTypes); + // When narrowing leaves >1 candidate that share identical normalized + // parameter-types (e.g., C++ `f(int)` vs `f(long)` both collapsed to + // `['int']` by `normalizeCppParamType`), suppress the edge entirely. + // The graph schema has no ambiguous-target edge model, so emitting one + // would arbitrarily pick a candidate and lie about the call's target. + // PR #1520 review follow-up plan U2 / Claude review Finding 5. + if (isOverloadAmbiguousAfterNormalization(candidates, site.arity)) return OVERLOAD_AMBIGUOUS; return candidates[0] ?? overloads[0]; } + +/** + * Sentinel returned by `pickOverload` when narrowing leaves >1 candidate + * sharing identical normalized parameter-types. Callers should suppress + * the CALLS edge AND mark the site as handled so `emitReferencesViaLookup` + * does not re-emit from the pre-resolved reference index. See + * `pickOverload` JSDoc for the upstream cause (per-language normalizer + * collapses distinct types in arity-metadata). + */ +export const OVERLOAD_AMBIGUOUS = Symbol('overload-ambiguous'); diff --git a/gitnexus/src/core/ingestion/scope-resolution/pipeline/phase.ts b/gitnexus/src/core/ingestion/scope-resolution/pipeline/phase.ts index c2fda9777..98a9f8994 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/pipeline/phase.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/pipeline/phase.ts @@ -93,13 +93,25 @@ export const scopeResolutionPhase: PipelinePhase = { // Worker-mode parses leave the cache empty for those files; they // also fall back to a fresh parse — no correctness impact. const parseOutput = getPhaseOutput(deps, 'parse'); - const { scopeTreeCache, resolutionContext } = parseOutput; + const { scopeTreeCache, resolutionContext, parsedFiles: workerParsedFiles } = parseOutput; // SemanticModel populated during `parse`: scope-resolution consumes // TypeRegistry / MethodRegistry / SymbolTable lookups instead of // rebuilding parallel indexes. See ARCHITECTURE.md § "Semantic-model // source of truth". const model = resolutionContext.model; + // Build a per-file lookup of ParsedFile artifacts the workers (or + // sequential extracts) already produced. Threading this into + // `runScopeResolution` lets the per-language extract loop short- + // circuit `extractParsedFile` — the dominant cost on the warm-cache + // path, since workers can't return tree-sitter Trees across the + // MessageChannel and scope-resolution would otherwise re-parse + // every file from scratch on the main thread. + const preExtractedByPath = new Map(); + for (const pf of workerParsedFiles) { + preExtractedByPath.set(pf.filePath, pf); + } + let totalFiles = 0; let totalImports = 0; let totalRefs = 0; @@ -143,6 +155,7 @@ export const scopeResolutionPhase: PipelinePhase = { files, treeCache: scopeTreeCache, resolutionConfig, + preExtractedParsedFiles: preExtractedByPath, onWarn: (msg) => { if (isSemanticModelValidatorEnabled()) { logger.warn(`[scope-resolution:${lang}] ${msg}`); diff --git a/gitnexus/src/core/ingestion/scope-resolution/pipeline/registry.ts b/gitnexus/src/core/ingestion/scope-resolution/pipeline/registry.ts index 3d9915fd7..713497da4 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/pipeline/registry.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/pipeline/registry.ts @@ -15,6 +15,10 @@ import { pythonScopeResolver } from '../../languages/python/scope-resolver.js'; import { csharpScopeResolver } from '../../languages/csharp/scope-resolver.js'; import { typescriptScopeResolver } from '../../languages/typescript/scope-resolver.js'; import { goScopeResolver } from '../../languages/go/scope-resolver.js'; +import { javaScopeResolver } from '../../languages/java/scope-resolver.js'; +import { cScopeResolver } from '../../languages/c/scope-resolver.js'; +import { cppScopeResolver } from '../../languages/cpp/scope-resolver.js'; +import { phpScopeResolver } from '../../languages/php/scope-resolver.js'; /** Map of `SupportedLanguages` → `ScopeResolver`. The phase iterates * this map intersected with `MIGRATED_LANGUAGES` (the per-language @@ -28,4 +32,8 @@ export const SCOPE_RESOLVERS: ReadonlyMap = n [SupportedLanguages.CSharp, csharpScopeResolver], [SupportedLanguages.TypeScript, typescriptScopeResolver], [SupportedLanguages.Go, goScopeResolver], + [SupportedLanguages.Java, javaScopeResolver], + [SupportedLanguages.C, cScopeResolver], + [SupportedLanguages.CPlusPlus, cppScopeResolver], + [SupportedLanguages.PHP, phpScopeResolver], ]); diff --git a/gitnexus/src/core/ingestion/scope-resolution/pipeline/run.ts b/gitnexus/src/core/ingestion/scope-resolution/pipeline/run.ts index 558c9ef30..0809d59ca 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/pipeline/run.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/pipeline/run.ts @@ -32,16 +32,88 @@ import { extractParsedFile } from '../../scope-extractor-bridge.js'; import { finalizeScopeModel } from '../../finalize-orchestrator.js'; import { resolveReferenceSites, type ResolveStats } from '../../resolve-references.js'; import { buildGraphNodeLookup } from '../graph-bridge/node-lookup.js'; +import { resolveDefGraphId } from '../graph-bridge/ids.js'; import { buildPopulatedMethodDispatch } from '../graph-bridge/method-dispatch.js'; +import { tryEmitEdge } from '../graph-bridge/edges.js'; import { propagateImportedReturnTypes } from '../passes/imported-return-types.js'; import { emitReceiverBoundCalls } from '../passes/receiver-bound-calls.js'; import { emitFreeCallFallback } from '../passes/free-call-fallback.js'; import { emitReferencesViaLookup } from '../graph-bridge/references-to-edges.js'; import { emitImportEdges } from '../graph-bridge/imports-to-edges.js'; import type { ScopeResolver } from '../contract/scope-resolver.js'; +import { findClassBindingInScope, findEnclosingClassDef } from '../scope/walkers.js'; import { buildWorkspaceResolutionIndex } from '../workspace-index.js'; import { logger } from '../../../logger.js'; + +/** + * Resolve inheritance reference sites early and pre-emit their EXTENDS edges + * before MRO construction. This lets template-base captures contribute to the + * graph in time for `buildMro`, while `handledSites` prevents the generic + * reference-edge bridge from re-emitting the same sites later. + * + * @returns Site keys to seed the downstream handled-site skip set. + */ +function preEmitInheritanceEdges( + graph: KnowledgeGraph, + scopes: ReturnType, + nodeLookup: ReturnType, +): Set { + const handledSites = new Set(); + const seen = new Set(); + const existing = new Set(); + for (const rel of graph.iterRelationshipsByType('EXTENDS')) { + existing.add(`${rel.sourceId}->${rel.targetId}`); + } + + for (const site of scopes.referenceSites) { + if (site.kind !== 'inherits') continue; + const scope = scopes.scopeTree.getScope(site.inScope); + const siteKey = + scope?.filePath !== undefined + ? `${scope.filePath}:${site.atRange.startLine}:${site.atRange.startCol}` + : undefined; + if (siteKey !== undefined) { + // Intentionally suppress every `inherits` site from the generic + // reference bridge, even when this pre-pass can't emit an EXTENDS + // edge. The shared bridge resolves the source via + // `resolveCallerGraphId`, which can degrade class-heritage sites into + // method-owned EXTENDS edges once methods exist on the class. This + // pre-pass is the authoritative inheritance emitter, so broad + // suppression keeps `buildMro` and the final graph class-owned. + handledSites.add(siteKey); + } + + const targetDef = findClassBindingInScope(site.inScope, site.name, scopes); + if (targetDef === undefined) continue; + + const callerClass = findEnclosingClassDef(site.inScope, scopes); + if (callerClass === undefined) continue; + const callerGraphId = resolveDefGraphId(callerClass.filePath, callerClass, nodeLookup); + const targetGraphId = resolveDefGraphId(targetDef.filePath, targetDef, nodeLookup); + if (callerGraphId === undefined || targetGraphId === undefined) continue; + const edgeKey = `${callerGraphId}->${targetGraphId}`; + if (existing.has(edgeKey)) continue; + + if ( + tryEmitEdge( + graph, + scopes, + nodeLookup, + site, + targetDef, + 'scope-resolution: inherits', + seen, + 0.85, + ) + ) { + existing.add(edgeKey); + } + } + + return handledSites; +} + interface RunScopeResolutionInput { readonly graph: KnowledgeGraph; /** @@ -72,6 +144,22 @@ interface RunScopeResolutionInput { * provider doesn't supply a config loader. */ readonly resolutionConfig?: unknown; + /** + * Pre-extracted ParsedFile artifacts keyed by file path. When a + * file is present here, the extract loop reuses it directly and + * skips `extractParsedFile` (which would re-parse the file with + * tree-sitter on the main thread). Only files matching the + * provider's language are honored — the loop verifies this + * implicitly by language filter at the call-site (scopeResolution + * phase). + * + * Worker-mode parses produce these ParsedFile artifacts as a side + * effect of `extractParsedFile` running inside the worker; threading + * them here is what lets the warm-cache analyze run skip the ~58s + * scope-resolution re-parse loop on a multi-thousand-file repo. + * Cache miss is safe — falls back to fresh extract. + */ + readonly preExtractedParsedFiles?: ReadonlyMap; } interface RunScopeResolutionStats { @@ -104,22 +192,37 @@ export function runScopeResolution( const parsedFiles: ParsedFile[] = []; let filesSkipped = 0; const treeCache = input.treeCache; + const preExtracted = input.preExtractedParsedFiles; + let preExtractedHits = 0; for (const file of files) { - const cachedTree = treeCache?.get(file.path); - const parsed = extractParsedFile( - provider.languageProvider, - file.content, - file.path, - onWarn, - cachedTree, - ); + let parsed: ParsedFile | undefined; + // Fast path: a worker (during the parse phase) already produced a + // ParsedFile for this file via `extractParsedFile`. Reuse it + // directly — skips a tree-sitter re-parse on the main thread. + if (preExtracted !== undefined) { + parsed = preExtracted.get(file.path); + if (parsed !== undefined) preExtractedHits++; + } if (parsed === undefined) { - filesSkipped++; - continue; + const cachedTree = treeCache?.get(file.path); + parsed = extractParsedFile( + provider.languageProvider, + file.content, + file.path, + onWarn, + cachedTree, + ); + if (parsed === undefined) { + filesSkipped++; + continue; + } } provider.populateOwners(parsed); parsedFiles.push(parsed); } + if (PROF && preExtracted !== undefined) { + logger.warn(`[scope-resolution prof] pre-extracted hits: ${preExtractedHits}/${files.length}`); + } provider.populateWorkspaceOwners?.(parsedFiles, { fileContents: getFileContents() }); // Reconcile scope-resolution's ownership view into the SemanticModel. @@ -152,7 +255,6 @@ export function runScopeResolution( // ── Phase 2: finalize → ScopeResolutionIndexes ───────────────────────── const allFilePaths = new Set(parsedFiles.map((f) => f.filePath)); const nodeLookup = buildGraphNodeLookup(graph); - const mroByClassDefId = provider.buildMro(graph, parsedFiles, nodeLookup); const resolutionConfig = input.resolutionConfig; const finalized = finalizeScopeModel(parsedFiles, { @@ -165,6 +267,9 @@ export function runScopeResolution( provider.mergeBindings(existing, incoming, scopeId), }, }); + const preEmittedInheritanceSites = preEmitInheritanceEdges(graph, finalized, nodeLookup); + const mroByClassDefId = provider.buildMro(graph, parsedFiles, nodeLookup); + const extendsOnlyMroByClassDefId = provider.buildExtendsOnlyMro?.(graph, parsedFiles, nodeLookup); // Replace the empty MethodDispatchIndex that finalizeScopeModel // builds by design with the populated one derived from the @@ -174,7 +279,7 @@ export function runScopeResolution( // the type system. const indexes = { ...finalized, - methodDispatch: buildPopulatedMethodDispatch(mroByClassDefId), + methodDispatch: buildPopulatedMethodDispatch(mroByClassDefId, extendsOnlyMroByClassDefId), }; // Build the workspace resolution index ONCE — scope-valued lookups @@ -241,7 +346,7 @@ export function runScopeResolution( const tResolve = PROF ? process.hrtime.bigint() : 0n; // ── Phase 4: emit graph edges (LOAD-BEARING ORDER — see I1) ──────────── - const handledSites = new Set(); + const handledSites = new Set(preEmittedInheritanceSites); const receiverExtras = emitReceiverBoundCalls( graph, indexes, @@ -252,6 +357,17 @@ export function runScopeResolution( workspaceIndex, readonlyModel, ); + const unresolvedReceiverExtras = + provider.emitUnresolvedReceiverEdges !== undefined + ? provider.emitUnresolvedReceiverEdges( + graph, + indexes, + parsedFiles, + nodeLookup, + handledSites, + readonlyModel, + ) + : 0; const freeCallExtras = emitFreeCallFallback( graph, indexes, @@ -261,7 +377,12 @@ export function runScopeResolution( handledSites, readonlyModel, workspaceIndex, - { allowGlobalFallback: provider.allowGlobalFreeCallFallback === true }, + { + allowGlobalFallback: provider.allowGlobalFreeCallFallback === true, + isFileLocalDef: provider.isFileLocalDef, + isCallableVisibleFromCaller: provider.isCallableVisibleFromCaller, + resolveAdlCandidates: provider.resolveAdlCandidates, + }, ); const { emitted, skipped } = emitReferencesViaLookup( graph, @@ -296,7 +417,7 @@ export function runScopeResolution( filesSkipped, importsEmitted, resolve: resolveStats, - referenceEdgesEmitted: emitted + receiverExtras + freeCallExtras, + referenceEdgesEmitted: emitted + receiverExtras + unresolvedReceiverExtras + freeCallExtras, referenceSkipped: skipped, }; } diff --git a/gitnexus/src/core/ingestion/scope-resolution/scope/walkers.ts b/gitnexus/src/core/ingestion/scope-resolution/scope/walkers.ts index 3e347cd4e..6e087d4f7 100644 --- a/gitnexus/src/core/ingestion/scope-resolution/scope/walkers.ts +++ b/gitnexus/src/core/ingestion/scope-resolution/scope/walkers.ts @@ -226,33 +226,132 @@ export function findCallableBindingInScope( callableName: string, scopes: ScopeResolutionIndexes, ): SymbolDefinition | undefined { + return findAllCallableBindingsInScope(startScope, callableName, scopes)[0]; +} + +/** + * Look up all callable bindings (Function/Method/Constructor) by name + * from the nearest scope in the chain that binds `callableName`. + * + * Preserves the original scope-walk boundary used by + * `findCallableBindingInScope`: once any callable binding is found in a + * scope, outer scopes are not consulted. + */ +export function findAllCallableBindingsInScope( + startScope: ScopeId, + callableName: string, + scopes: ScopeResolutionIndexes, +): readonly SymbolDefinition[] { let currentId: ScopeId | null = startScope; const visited = new Set(); while (currentId !== null) { - if (visited.has(currentId)) return undefined; + if (visited.has(currentId)) return []; visited.add(currentId); const scope = scopes.scopeTree.getScope(currentId); - if (scope === undefined) return undefined; + if (scope === undefined) return []; + + const out: SymbolDefinition[] = []; + const seen = new Set(); + const pushCallable = (def: SymbolDefinition): void => { + if (def.type !== 'Function' && def.type !== 'Method' && def.type !== 'Constructor') return; + if (seen.has(def.nodeId)) return; + seen.add(def.nodeId); + out.push(def); + }; const localBindings = scope.bindings.get(callableName); if (localBindings !== undefined) { for (const b of localBindings) { - if (b.def.type === 'Function' || b.def.type === 'Method' || b.def.type === 'Constructor') { - return b.def; - } + pushCallable(b.def); } } const importedBindings = lookupBindingsAt(currentId, callableName, scopes); for (const b of importedBindings) { - if (b.def.type === 'Function' || b.def.type === 'Method' || b.def.type === 'Constructor') { - return b.def; + pushCallable(b.def); + } + + if (out.length > 0) return out; + currentId = scope.parent; + } + return []; +} + +/** + * ISO C++ `[basic.lookup.unqual]` §7: ADL is suppressed when ordinary + * unqualified lookup finds: + * - a name that is NOT a function or function template, OR + * - a block-scope function declaration that is NOT a using-declaration. + * + * Combined walker that stops at the **nearest scope** where `name` has any + * binding (callable or non-callable) and returns: + * - `callables`: Function/Method/Constructor defs found at that scope + * - `nonCallableFound`: a non-function binding was present (variable, class, etc.) + * - `blockScopeDeclFound`: a callable was found at a Function or Block scope + * (block-scope function declaration that blocks ADL) + * + * One pass, one stop — no divergence between callable collection and blocker + * detection. + */ +export function findCallableBindingsAndAdlBlocker( + startScope: ScopeId, + name: string, + scopes: ScopeResolutionIndexes, +): { + callables: readonly SymbolDefinition[]; + nonCallableFound: boolean; + blockScopeDeclFound: boolean; +} { + let currentId: ScopeId | null = startScope; + const visited = new Set(); + while (currentId !== null) { + if (visited.has(currentId)) + return { callables: [], nonCallableFound: false, blockScopeDeclFound: false }; + visited.add(currentId); + const scope = scopes.scopeTree.getScope(currentId); + if (scope === undefined) + return { callables: [], nonCallableFound: false, blockScopeDeclFound: false }; + + const callables: SymbolDefinition[] = []; + const seen = new Set(); + let nonCallableFound = false; + let anyBinding = false; + + const process = (def: SymbolDefinition): void => { + anyBinding = true; + if (def.type === 'Function' || def.type === 'Method' || def.type === 'Constructor') { + if (!seen.has(def.nodeId)) { + seen.add(def.nodeId); + callables.push(def); + } + } else { + nonCallableFound = true; + } + }; + + const localBindings = scope.bindings.get(name); + if (localBindings !== undefined) { + for (const b of localBindings) { + process(b.def); } } + const importedBindings = lookupBindingsAt(currentId, name, scopes); + for (const b of importedBindings) { + process(b.def); + } + + if (anyBinding) { + // ISO C++: a block-scope function declaration (Function or Block scope) + // that is NOT a using-declaration blocks ADL. If we found callables at + // a function/block scope, ADL must be suppressed. + const blockScopeDeclFound = + callables.length > 0 && (scope.kind === 'Function' || scope.kind === 'Block'); + return { callables, nonCallableFound, blockScopeDeclFound }; + } currentId = scope.parent; } - return undefined; + return { callables: [], nonCallableFound: false, blockScopeDeclFound: false }; } /** diff --git a/gitnexus/src/core/ingestion/tree-sitter-queries.ts b/gitnexus/src/core/ingestion/tree-sitter-queries.ts index 88a127eb6..74f4f5165 100644 --- a/gitnexus/src/core/ingestion/tree-sitter-queries.ts +++ b/gitnexus/src/core/ingestion/tree-sitter-queries.ts @@ -680,7 +680,15 @@ export const GO_QUERIES = ` export const CPP_QUERIES = ` ; Classes, Structs, Namespaces (class_specifier name: (type_identifier) @name) @definition.class +(class_specifier + name: (template_type + (type_identifier) @name + (template_argument_list) @template-arguments)) @definition.class (struct_specifier name: (type_identifier) @name) @definition.struct +(struct_specifier + name: (template_type + (type_identifier) @name + (template_argument_list) @template-arguments)) @definition.struct (namespace_definition name: (namespace_identifier) @name) @definition.namespace (enum_specifier name: (type_identifier) @name) @definition.enum @@ -762,6 +770,11 @@ export const CPP_QUERIES = ` ; Templates (template_declaration (class_specifier name: (type_identifier) @name)) @definition.template +(template_declaration + (class_specifier + name: (template_type + (type_identifier) @name + (template_argument_list) @template-arguments))) @definition.template (template_declaration (function_definition declarator: (function_declarator declarator: (identifier) @name))) @definition.template ; Includes @@ -1020,6 +1033,16 @@ export const PHP_QUERIES = ` (use_declaration [(name) (qualified_name)] @heritage.trait))) @heritage +; ── Heritage: trait uses another trait (transitive trait composition) ──────── +; PHP allows a trait body to contain "use OtherTrait;". The trait-uses-trait +; IMPLEMENTS edge is required by buildPhpMro to compute the full transitive +; trait closure (depth 3+ chains). +(trait_declaration + name: (name) @heritage.class + body: (declaration_list + (use_declaration + [(name) (qualified_name)] @heritage.trait))) @heritage + ; PHP HTTP consumers: file_get_contents('/path'), curl_init('/path') (function_call_expression function: (name) @_php_http (#match? @_php_http "^(file_get_contents|curl_init)$") diff --git a/gitnexus/src/core/ingestion/utils/ast-helpers.ts b/gitnexus/src/core/ingestion/utils/ast-helpers.ts index ec76cd1db..351cfdedb 100644 --- a/gitnexus/src/core/ingestion/utils/ast-helpers.ts +++ b/gitnexus/src/core/ingestion/utils/ast-helpers.ts @@ -2,6 +2,11 @@ import type Parser from 'tree-sitter'; import type { Capture, NodeLabel, Range } from 'gitnexus-shared'; import type { LanguageProvider } from '../language-provider.js'; import { generateId } from '../../../lib/utils.js'; +import { + extractTemplateArguments, + stripTemplateArguments, + templateArgumentsIdTag, +} from './template-arguments.js'; /** Tree-sitter AST node. Re-exported for use across ingestion modules. */ export type SyntaxNode = Parser.SyntaxNode; @@ -390,8 +395,13 @@ export const findEnclosingClassInfo = ( ) { label = 'Interface'; } + const templateArguments = extractTemplateArguments(nameNode.text); + const classIdName = + templateArguments !== undefined + ? `${stripTemplateArguments(nameNode.text)}${templateArgumentsIdTag(templateArguments)}` + : nameNode.text; return { - classId: generateId(label, `${filePath}:${nameNode.text}`), + classId: generateId(label, `${filePath}:${classIdName}`), className: nameNode.text, }; } diff --git a/gitnexus/src/core/ingestion/utils/template-arguments.ts b/gitnexus/src/core/ingestion/utils/template-arguments.ts new file mode 100644 index 000000000..e1c6e3463 --- /dev/null +++ b/gitnexus/src/core/ingestion/utils/template-arguments.ts @@ -0,0 +1,57 @@ +/** + * Parse top-level generic/template arguments from a type-like string. + * + * Examples: + * - `List` -> ['int'] + * - `Map>` -> ['string', 'vector'] + * - `List` -> ['T*'] + */ +export function extractTemplateArguments(text: string): string[] | undefined { + const start = text.indexOf('<'); + if (start === -1) return undefined; + let depth = 0; + let end = -1; + for (let i = start; i < text.length; i += 1) { + const ch = text[i]; + if (ch === '<') depth += 1; + else if (ch === '>') { + depth -= 1; + if (depth === 0) { + end = i; + break; + } + if (depth < 0) return undefined; + } + } + if (end === -1) return undefined; + const inner = text.slice(start + 1, end); + if (inner.trim().length === 0) return undefined; + + const args: string[] = []; + let tokenStart = 0; + let nested = 0; + for (let i = 0; i < inner.length; i += 1) { + const ch = inner[i]; + if (ch === '<') nested += 1; + else if (ch === '>') nested -= 1; + else if (ch === ',' && nested === 0) { + const token = inner.slice(tokenStart, i).replace(/\s+/g, ''); + if (token.length > 0) args.push(token); + tokenStart = i + 1; + } + } + const last = inner.slice(tokenStart).replace(/\s+/g, ''); + if (last.length > 0) args.push(last); + return args.length > 0 ? args : undefined; +} + +export function stripTemplateArguments(text: string): string { + const start = text.indexOf('<'); + if (start === -1) return text; + return text.slice(0, start); +} + +export function templateArgumentsIdTag(templateArguments?: readonly string[]): string { + if (templateArguments === undefined || templateArguments.length === 0) return ''; + return `~${templateArguments.join(',')}`; +} diff --git a/gitnexus/src/core/ingestion/workers/parse-worker.ts b/gitnexus/src/core/ingestion/workers/parse-worker.ts index 4442b5a65..e22b927ed 100644 --- a/gitnexus/src/core/ingestion/workers/parse-worker.ts +++ b/gitnexus/src/core/ingestion/workers/parse-worker.ts @@ -20,6 +20,7 @@ import { getTreeSitterContentByteLength, TREE_SITTER_MAX_BUFFER, } from '../constants.js'; +import { parseSourceSafe } from '../../tree-sitter/safe-parse.js'; import type { SymbolTableReader } from '../model/symbol-table.js'; import type { ExtractedHeritage } from '../model/heritage-map.js'; @@ -81,6 +82,7 @@ import { constTagForId, buildCollisionGroups, } from '../utils/method-props.js'; +import { extractTemplateArguments, templateArgumentsIdTag } from '../utils/template-arguments.js'; import type { LanguageProvider } from '../language-provider.js'; import type { ParsedFile } from 'gitnexus-shared'; import { extractParsedFile } from '../scope-extractor-bridge.js'; @@ -128,6 +130,7 @@ interface ParsedSymbol { parameterTypes?: string[]; returnType?: string; declaredType?: string; + templateArguments?: string[]; ownerId?: string; visibility?: string; isStatic?: boolean; @@ -180,6 +183,8 @@ export interface ExtractedAssignment { propertyName: string; /** Resolved type name of the receiver if available from TypeEnv */ receiverTypeName?: string; + /** 1-indexed line number of the assignment site (used for per-site dedup) */ + line?: number; } // `ExtractedHeritage` now lives in `../model/heritage-map.ts` and is @@ -1416,7 +1421,7 @@ const processFileGroup = ( let tree; try { - tree = parser.parse(parseContent, undefined, { + tree = parseSourceSafe(parser, parseContent, undefined, { bufferSize: getTreeSitterBufferSize(parseContent), }); } catch (err) { @@ -1579,6 +1584,7 @@ const processFileGroup = ( sourceId: srcId, receiverText, propertyName, + line: captureMap['assignment'].startPosition.row + 1, ...(receiverTypeName ? { receiverTypeName } : {}), }); } @@ -1997,6 +2003,23 @@ const processFileGroup = ( }) : null; const nodeLabel = extractedClassSymbol?.type ?? defaultNodeLabel; + const isClassLikeLabel = + nodeLabel === 'Class' || + nodeLabel === 'Struct' || + nodeLabel === 'Interface' || + nodeLabel === 'Enum' || + nodeLabel === 'Record'; + if ( + isClassLikeLabel && + provider.classExtractor?.shouldSkipClassCapture?.({ + captureMap, + definitionNode, + nameNode, + nodeLabel, + }) === true + ) { + continue; + } // Dedup: variable captures (Const/Static/Variable) may overlap with higher-priority // captures (e.g. `const fn = () => {}` matches both @definition.function and @definition.const). @@ -2110,7 +2133,31 @@ const processFileGroup = ( ); arityTag += constTagForId(defMethodMap, nodeName, arityForId, defMethodInfo, groups); } - const nodeId = generateId(nodeLabel, `${file.path}:${qualifiedName}${arityTag}`); + const classTemplateArguments = + extractedClassSymbol?.templateArguments ?? + provider.classExtractor?.extractTemplateArgumentsFromCapture?.({ + captureMap, + definitionNode, + nameNode, + }) ?? + (captureMap['template-arguments'] + ? extractTemplateArguments(captureMap['template-arguments'].text) + : undefined) ?? + (nameNode && nameNode.text ? extractTemplateArguments(nameNode.text) : undefined); + const classTemplateTag = + (nodeLabel === 'Class' || + nodeLabel === 'Struct' || + nodeLabel === 'Interface' || + nodeLabel === 'Enum' || + nodeLabel === 'Record') && + classTemplateArguments !== undefined && + classTemplateArguments.length > 0 + ? templateArgumentsIdTag(classTemplateArguments) + : ''; + const nodeId = generateId( + nodeLabel, + `${file.path}:${qualifiedName}${classTemplateTag}${arityTag}`, + ); const classNodeForSymbol = definitionNode || nameNode; const qualifiedTypeName = extractedClassSymbol?.qualifiedName ?? @@ -2233,6 +2280,9 @@ const processFileGroup = ( ? isVueSetupTopLevel(nameNode || definitionNode) : cachedExportCheck(provider.exportChecker, nameNode || definitionNode, nodeName), ...(qualifiedTypeName !== undefined ? { qualifiedName: qualifiedTypeName } : {}), + ...(classTemplateArguments !== undefined && classTemplateArguments.length > 0 + ? { templateArguments: classTemplateArguments } + : {}), ...(frameworkHint ? { astFrameworkMultiplier: frameworkHint.entryPointMultiplier, @@ -2258,6 +2308,9 @@ const processFileGroup = ( parameterTypes: methodProps.parameterTypes as string[] | undefined, returnType: methodProps.returnType as string | undefined, ...(declaredType !== undefined ? { declaredType } : {}), + ...(classTemplateArguments !== undefined && classTemplateArguments.length > 0 + ? { templateArguments: classTemplateArguments } + : {}), ...(enclosingClassId ? { ownerId: enclosingClassId } : {}), visibility: methodProps.visibility as string | undefined, isStatic: methodProps.isStatic as boolean | undefined, diff --git a/gitnexus/src/core/lbug/lbug-adapter.ts b/gitnexus/src/core/lbug/lbug-adapter.ts index cb88986ca..cf8f1cb71 100644 --- a/gitnexus/src/core/lbug/lbug-adapter.ts +++ b/gitnexus/src/core/lbug/lbug-adapter.ts @@ -218,6 +218,65 @@ const runWithSessionLock = async (operation: () => Promise): Promise => const normalizeCopyPath = (filePath: string): string => filePath.replace(/\\/g, '/'); +const closeQueryResult = async (result: lbug.QueryResult): Promise => { + try { + await result.close(); + } catch { + // Best-effort cleanup only. + } +}; + +const drainQueryResult = async ( + queryResult: lbug.QueryResult | lbug.QueryResult[], +): Promise => { + const results = Array.isArray(queryResult) ? queryResult : [queryResult]; + let firstError: unknown; + let hasError = false; + for (const result of results) { + try { + await result.getAll(); + } catch (err) { + if (!hasError) { + firstError = err; + hasError = true; + } + } finally { + await closeQueryResult(result); + } + } + if (hasError) throw firstError; +}; + +const readQueryRows = async ( + queryResult: lbug.QueryResult | lbug.QueryResult[], +): Promise => { + const results = Array.isArray(queryResult) ? queryResult : [queryResult]; + let rows: any[] = []; + let firstError: unknown; + let hasError = false; + for (let i = 0; i < results.length; i++) { + const result = results[i]; + try { + const resultRows = await result.getAll(); + if (i === 0) rows = resultRows; + } catch (err) { + if (!hasError) { + firstError = err; + hasError = true; + } + } finally { + await closeQueryResult(result); + } + } + if (hasError) throw firstError; + return rows; +}; + +const queryAndDrain = async (targetConn: lbug.Connection, cypher: string): Promise => { + const queryResult = await targetConn.query(cypher); + await drainQueryResult(queryResult); +}; + export const initLbug = async (dbPath: string) => { return runWithSessionLock(() => ensureLbugInitialized(dbPath)); }; @@ -319,7 +378,7 @@ const doInitLbug = async (dbPath: string) => { for (const schemaQuery of SCHEMA_QUERIES) { try { - await conn.query(schemaQuery); + await queryAndDrain(conn, schemaQuery); } catch (err) { const msg = err instanceof Error ? err.message : String(err); // Suppression list: @@ -384,14 +443,14 @@ export const loadGraphToLbug = async ( const copyQuery = getCopyQuery(table, normalizedPath); try { - await conn.query(copyQuery); + await queryAndDrain(conn, copyQuery); } catch (err) { try { const retryQuery = copyQuery.replace( 'auto_detect=false)', 'auto_detect=false, IGNORE_ERRORS=true)', ); - await conn.query(retryQuery); + await queryAndDrain(conn, retryQuery); } catch (retryErr) { const retryMsg = retryErr instanceof Error ? retryErr.message : String(retryErr); throw new Error(`COPY failed for ${table}: ${retryMsg.slice(0, 200)}`); @@ -433,14 +492,14 @@ export const loadGraphToLbug = async ( } try { - await conn.query(copyQuery); + await queryAndDrain(conn, copyQuery); } catch (err) { try { const retryQuery = copyQuery.replace( 'auto_detect=false)', 'auto_detect=false, IGNORE_ERRORS=true)', ); - await conn.query(retryQuery); + await queryAndDrain(conn, retryQuery); } catch (retryErr) { const retryMsg = retryErr instanceof Error ? retryErr.message : String(retryErr); warnings.push(`${fromLabel}->${toLabel} (${rows} edges): ${retryMsg.slice(0, 80)}`); @@ -562,11 +621,14 @@ const fallbackRelationshipInserts = async ( const esc = (s: string) => s.replace(/'/g, "''").replace(/\\/g, '\\\\').replace(/\n/g, '\\n').replace(/\r/g, '\\r'); - await conn.query(` + await queryAndDrain( + conn, + ` MATCH (a:${escapeLabel(fromLabel)} {id: '${esc(fromId)}' }), (b:${escapeLabel(toLabel)} {id: '${esc(toId)}' }) CREATE (a)-[:${REL_TABLE_NAME} {type: '${esc(relType)}', confidence: ${confidence}, reason: '${esc(reason)}', step: ${step}}]->(b) - `); + `, + ); } catch { // skip } @@ -679,14 +741,14 @@ export const insertNodeToLbug = async ( if (targetDbPath) { const tempHandle = await openLbugConnection(lbug, targetDbPath); try { - await tempHandle.conn.query(query); + await queryAndDrain(tempHandle.conn, query); return true; } finally { await closeLbugConnection(tempHandle); } } else if (conn) { // Use existing persistent connection (when called from analyze) - await conn.query(query); + await queryAndDrain(conn, query); return true; } @@ -757,7 +819,7 @@ export const batchInsertNodesToLbug = async ( query = `MERGE (n:${t} {id: ${escapeValue(properties.id)}}) SET n.name = ${escapeValue(properties.name)}, n.filePath = ${escapeValue(properties.filePath)}, n.startLine = ${properties.startLine || 0}, n.endLine = ${properties.endLine || 0}, n.content = ${escapeValue(properties.content || '')}${descPart}`; } - await tempConn.query(query); + await queryAndDrain(tempConn, query); inserted++; } catch (e: any) { // Don't console.error here - it corrupts MCP JSON-RPC on stderr @@ -777,11 +839,7 @@ export const executeQuery = async (cypher: string): Promise => { } const queryResult = await conn.query(cypher); - // LadybugDB uses getAll() instead of hasNext()/getNext() - // Query returns QueryResult for single queries, QueryResult[] for multi-statement - const result = Array.isArray(queryResult) ? queryResult[0] : queryResult; - const rows = await result.getAll(); - return rows; + return await readQueryRows(queryResult); }; export const streamQuery = async ( @@ -793,8 +851,10 @@ export const streamQuery = async ( } const queryResult = await conn.query(cypher); - const result = Array.isArray(queryResult) ? queryResult[0] : queryResult; + const results = Array.isArray(queryResult) ? queryResult : [queryResult]; + const result = results[0]; let rowCount = 0; + let streamError: unknown; try { while (await result.hasNext()) { @@ -803,11 +863,14 @@ export const streamQuery = async ( rowCount++; } return rowCount; + } catch (err) { + streamError = err; + throw err; } finally { try { - await result.close(); - } catch { - // Best-effort cleanup only. + await drainQueryResult(results); + } catch (err) { + if (streamError === undefined) throw err; } } }; @@ -829,8 +892,7 @@ export const executePrepared = async ( throw new Error(`Prepare failed: ${errMsg}`); } const queryResult = await conn.execute(stmt, params); - const result = Array.isArray(queryResult) ? queryResult[0] : queryResult; - return await result.getAll(); + return await readQueryRows(queryResult); }; export const executeWithReusedStatement = async ( @@ -852,7 +914,7 @@ export const executeWithReusedStatement = async ( } try { for (const params of subBatch) { - await conn.execute(stmt, params); + await drainQueryResult(await conn.execute(stmt, params)); } } catch (e) { const msg = e instanceof Error ? e.message : String(e); @@ -874,8 +936,7 @@ export const getLbugStats = async (): Promise<{ nodes: number; edges: number }> const queryResult = await conn.query( `MATCH (n:${escapeTableName(tableName)}) RETURN count(n) AS cnt`, ); - const nodeResult = Array.isArray(queryResult) ? queryResult[0] : queryResult; - const nodeRows = await nodeResult.getAll(); + const nodeRows = await readQueryRows(queryResult); if (nodeRows.length > 0) { totalNodes += Number(nodeRows[0]?.cnt ?? nodeRows[0]?.[0] ?? 0); } @@ -889,8 +950,7 @@ export const getLbugStats = async (): Promise<{ nodes: number; edges: number }> const queryResult = await conn.query( `MATCH ()-[r:${REL_TABLE_NAME}]->() RETURN count(r) AS cnt`, ); - const edgeResult = Array.isArray(queryResult) ? queryResult[0] : queryResult; - const edgeRows = await edgeResult.getAll(); + const edgeRows = await readQueryRows(queryResult); if (edgeRows.length > 0) { totalEdges = Number(edgeRows[0]?.cnt ?? edgeRows[0]?.[0] ?? 0); } @@ -926,8 +986,7 @@ export const loadCachedEmbeddings = async (): Promise<{ const check = await conn.query( `MATCH (e:${EMBEDDING_TABLE_NAME}) RETURN e.nodeId AS nodeId, e.chunkIndex AS chunkIndex LIMIT 1`, ); - const checkResult = Array.isArray(check) ? check[0] : check; - await checkResult.getAll(); + await readQueryRows(check); } catch { return { embeddingNodeIds: new Set(), embeddings: [] }; } @@ -951,8 +1010,7 @@ export const loadCachedEmbeddings = async (): Promise<{ throw err; } } - const result = Array.isArray(rows) ? rows[0] : rows; - for (const row of await result.getAll()) { + for (const row of await readQueryRows(rows)) { const nodeId = String(row.nodeId ?? row[0] ?? ''); if (!nodeId) continue; embeddingNodeIds.add(nodeId); @@ -1060,7 +1118,8 @@ export const fetchExistingEmbeddingHashes = async ( export const flushWAL = async (): Promise => { if (!conn) return; try { - await conn.query('CHECKPOINT'); + const checkpointResult = await conn.query('CHECKPOINT'); + await drainQueryResult(checkpointResult); } catch { /* ignore — older LadybugDB or schemaless DB may not accept it */ } @@ -1170,13 +1229,13 @@ export const deleteNodesForFile = async ( const countResult = await targetConn!.query( `MATCH (n:${tn}) WHERE n.filePath = '${escapedPath}' RETURN count(n) AS cnt`, ); - const result = Array.isArray(countResult) ? countResult[0] : countResult; - const rows = await result.getAll(); + const rows = await readQueryRows(countResult); const count = Number(rows[0]?.cnt ?? rows[0]?.[0] ?? 0); if (count > 0) { // Delete nodes (and implicitly their relationships via DETACH) - await targetConn!.query( + await queryAndDrain( + targetConn!, `MATCH (n:${tn}) WHERE n.filePath = '${escapedPath}' DETACH DELETE n`, ); deletedNodes += count; @@ -1188,7 +1247,8 @@ export const deleteNodesForFile = async ( // Also delete any embeddings for nodes in this file try { - await targetConn!.query( + await queryAndDrain( + targetConn!, `MATCH (e:${EMBEDDING_TABLE_NAME}) WHERE e.nodeId STARTS WITH '${escapedPath}' DELETE e`, ); } catch { @@ -1204,6 +1264,77 @@ export const deleteNodesForFile = async ( export const getEmbeddingTableName = (): string => EMBEDDING_TABLE_NAME; +/** + * Return the distinct repo-relative paths of files that import + * `targetFilePath` according to the IMPORTS edges currently in the + * DB. Used by the incremental writeback path to expand the + * "files-to-rewrite" set so that files importing a changed file get + * their edges (which may have been refined by cross-file resolution) + * re-emitted, rather than left stale in the DB. + * + * The DB query reads the *previous* run's state — pre-pipeline, before + * any nodes are deleted — so the returned importers are "files that + * USED TO import the target". That's the right set to invalidate: + * those are the files whose edges in the DB might no longer match + * what cross-file resolution produces given the changed file's new + * exports. + */ +export const queryImporters = async (targetFilePath: string): Promise => { + if (!conn) { + throw new Error('LadybugDB not initialized. Call initLbug first.'); + } + const escaped = targetFilePath.replace(/'/g, "''"); + const cypher = ` + MATCH (a)-[r:${REL_TABLE_NAME}]->(b) + WHERE r.type = 'IMPORTS' AND b.filePath = '${escaped}' + RETURN DISTINCT a.filePath AS importer + `; + try { + const queryResult = await conn.query(cypher); + const result = Array.isArray(queryResult) ? queryResult[0] : queryResult; + const rows = await result.getAll(); + const out: string[] = []; + for (const row of rows) { + const v = (row as { importer?: unknown }).importer; + if (typeof v === 'string' && v.length > 0) out.push(v); + } + return out; + } catch { + return []; + } +}; + +/** + * Drop every Community and Process node (and their MEMBER_OF / + * STEP_IN_PROCESS edges via DETACH DELETE). Used at the start of an + * incremental run so the communities and processes phases regenerate + * them from scratch on the merged graph — required for the + * "Leiden runs on the FULL graph" correctness invariant. + */ +export const deleteAllCommunitiesAndProcesses = async (): Promise<{ + nodesDeleted: number; +}> => { + if (!conn) { + throw new Error('LadybugDB not initialized. Call initLbug first.'); + } + let nodesDeleted = 0; + for (const label of ['Community', 'Process']) { + try { + const countResult = await conn.query(`MATCH (n:${label}) RETURN count(n) AS cnt`); + const result = Array.isArray(countResult) ? countResult[0] : countResult; + const rows = await result.getAll(); + const count = Number(rows[0]?.cnt ?? rows[0]?.[0] ?? 0); + if (count > 0) { + await conn.query(`MATCH (n:${label}) DETACH DELETE n`); + nodesDeleted += count; + } + } catch { + // Table may not exist yet on a freshly-initialized DB — fine. + } + } + return { nodesDeleted }; +}; + // ============================================================================ // Full-Text Search (FTS) Functions // ============================================================================ @@ -1232,7 +1363,7 @@ export const loadFTSExtension = async ( throw new Error('LadybugDB not initialized. Call initLbug first.'); } - const loaded = await extensionManager.ensure((sql) => c.query(sql), 'fts', 'FTS', opts); + const loaded = await extensionManager.ensure((sql) => queryAndDrain(c, sql), 'fts', 'FTS', opts); if (loaded && useModuleState) ftsLoaded = true; return loaded; }; @@ -1248,6 +1379,13 @@ export const loadVectorExtension = async ( ): Promise => { const useModuleState = targetConn === undefined; if (useModuleState && vectorExtensionLoaded) return true; + // INSTALL VECTOR crashes with SIGSEGV on Windows: the KuzuDB native extension + // installer has an unhandled error path on Windows that raises a fatal signal + // that JS try/catch cannot intercept. Skip loading — vector/embedding search + // is unavailable but all graph index queries still work. Do NOT set + // vectorExtensionLoaded here: the flag means "successfully loaded", and a + // subsequent call would otherwise short-circuit to `return true` at the top. + if (process.platform === 'win32') return false; if (!isVectorExtensionSupportedByPlatform()) return false; const c: lbug.Connection | null = targetConn ?? conn; @@ -1255,7 +1393,12 @@ export const loadVectorExtension = async ( throw new Error('LadybugDB not initialized. Call initLbug first.'); } - const loaded = await extensionManager.ensure((sql) => c.query(sql), 'VECTOR', 'VECTOR', opts); + const loaded = await extensionManager.ensure( + (sql) => queryAndDrain(c, sql), + 'VECTOR', + 'VECTOR', + opts, + ); if (loaded && useModuleState) vectorExtensionLoaded = true; return loaded; }; @@ -1287,7 +1430,7 @@ export const createFTSIndex = async ( const query = `CALL CREATE_FTS_INDEX('${tableName}', '${indexName}', [${propList}], stemmer := '${stemmer}')`; try { - await conn.query(query); + await queryAndDrain(conn, query); ensuredFTSIndexes.add(key); } catch (e: any) { if (e.message?.includes('already exists')) { @@ -1371,8 +1514,7 @@ export const queryFTS = async ( try { const queryResult = await conn.query(cypher); - const result = Array.isArray(queryResult) ? queryResult[0] : queryResult; - const rows = await result.getAll(); + const rows = await readQueryRows(queryResult); return rows.map((row: any) => { const node = row.node || row[0] || {}; @@ -1403,7 +1545,7 @@ export const dropFTSIndex = async (tableName: string, indexName: string): Promis } try { - await conn.query(`CALL DROP_FTS_INDEX('${tableName}', '${indexName}')`); + await queryAndDrain(conn, `CALL DROP_FTS_INDEX('${tableName}', '${indexName}')`); } catch { // Index may not exist } finally { diff --git a/gitnexus/src/core/lbug/pool-adapter.ts b/gitnexus/src/core/lbug/pool-adapter.ts index ed999907e..f18d7fcc3 100644 --- a/gitnexus/src/core/lbug/pool-adapter.ts +++ b/gitnexus/src/core/lbug/pool-adapter.ts @@ -420,7 +420,17 @@ async function doInitLbug(repoId: string, dbPath: string): Promise { // install; analyze owns extension installation. If LOAD fails, search // features degrade gracefully and the user-facing query path proceeds. if (!shared.ftsLoaded) { - shared.ftsLoaded = await loadFTSExtension(available[0], { policy: 'load-only' }); + // Windows guard: LOAD EXTENSION fts crashes with SIGSEGV on Windows when + // the FTS extension binary is not installed locally (@ladybugdb/core native + // bug — the extension loader hits an unhandled error path that signals SIGSEGV + // rather than throwing a JS exception, so try/catch cannot protect here). + // Skip the load on Windows; bm25-index.js catches the resulting Kuzu catalog + // errors and returns empty BM25 results gracefully. Graph queries are unaffected. + if (process.platform === 'win32') { + shared.ftsLoaded = true; + } else { + shared.ftsLoaded = await loadFTSExtension(available[0], { policy: 'load-only' }); + } } // Register pool entry only after all connections are pre-warmed and FTS is @@ -484,8 +494,13 @@ export async function initLbugWithDb( // Load FTS extension if not already loaded on this Database. // policy: 'load-only' — same contract as initLbug above; the read pool // must not block on a network install during query execution. + // Windows guard: same SIGSEGV risk as doInitLbug above — skip on Windows. if (!shared.ftsLoaded) { - shared.ftsLoaded = await loadFTSExtension(available[0], { policy: 'load-only' }); + if (process.platform === 'win32') { + shared.ftsLoaded = true; + } else { + shared.ftsLoaded = await loadFTSExtension(available[0], { policy: 'load-only' }); + } } pool.set(repoId, { diff --git a/gitnexus/src/core/run-analyze.ts b/gitnexus/src/core/run-analyze.ts index 7227fd945..425f18f9a 100644 --- a/gitnexus/src/core/run-analyze.ts +++ b/gitnexus/src/core/run-analyze.ts @@ -11,6 +11,7 @@ import path from 'path'; import fs from 'fs/promises'; +import { execFileSync } from 'child_process'; import { runPipelineFromRepo } from './ingestion/pipeline.js'; import { initLbug, @@ -20,6 +21,9 @@ import { executeWithReusedStatement, closeLbug, loadCachedEmbeddings, + deleteNodesForFile, + deleteAllCommunitiesAndProcesses, + queryImporters, } from './lbug/lbug-adapter.js'; import { createSearchFTSIndexes } from './search/fts-indexes.js'; import { @@ -29,7 +33,15 @@ import { ensureGitNexusIgnored, registerRepo, cleanupOldKuzuFiles, + INCREMENTAL_SCHEMA_VERSION, } from '../storage/repo-manager.js'; +import { computeFileHashes, diffFileHashes } from '../storage/file-hash.js'; +import { + extractChangedSubgraph, + computeEffectiveWriteSet, +} from './incremental/subgraph-extract.js'; +import { shadowCandidatesFor } from './incremental/shadow-candidates.js'; +import { loadParseCache, saveParseCache, pruneCache } from '../storage/parse-cache.js'; import { getCurrentCommit, getRemoteUrl, @@ -81,6 +93,8 @@ export interface AnalyzeOptions { skipAgentsMd?: boolean; /** Omit volatile symbol/relationship counts from AGENTS.md and CLAUDE.md. */ noStats?: boolean; + /** Skip installing standard GitNexus skill files to .claude/skills/gitnexus/. */ + skipSkills?: boolean; /** * User-provided alias for the registry `name` (#829). When set, * forwarded to `registerRepo` so the indexed repo is stored under @@ -176,23 +190,81 @@ export async function runFullAnalysis( const currentCommit = repoHasGit ? getCurrentCommit(repoPath) : ''; const existingMeta = await loadMeta(storagePath); + // ── Crash recovery: dirty flag forces full rebuild ──────────────── + // If the previous incremental run set incrementalInProgress and didn't + // clear it, the on-disk index may be in a half-state. Cheapest path + // back to a known-good index is to wipe + rebuild from scratch. + if (existingMeta?.incrementalInProgress) { + log( + 'Previous incremental run did not complete cleanly (incrementalInProgress flag set); ' + + 'forcing full rebuild to restore a known-good index.', + ); + options = { ...options, force: true }; + // Reload meta after clearing the flag in-memory; we still want fileHashes + // for the post-rebuild meta carry-over, but force=true ensures the + // rebuild path executes. + } + // ── Early-return: already up to date ────────────────────────────── if (existingMeta && !options.force && existingMeta.lastCommit === currentCommit) { // Non-git folders have currentCommit = '' — always rebuild since we can't detect changes if (currentCommit !== '') { - await ensureGitNexusIgnored(repoPath); - return { - // `resolveRepoIdentityRoot` collapses worktree roots to the - // canonical repo basename (#1259) but leaves arbitrary subdirs - // and `--skip-git` paths unchanged (#1232/#1233 intent preserved). - repoName: - options.registryName ?? - getInferredRepoName(repoPath) ?? - path.basename(resolveRepoIdentityRoot(repoPath)), - repoPath, - stats: existingMeta.stats ?? {}, - alreadyUpToDate: true, - }; + // For git repos, even if HEAD matches lastCommit, the working tree + // may have uncommitted changes. Only short-circuit when the working + // tree is also clean — otherwise fall through to the incremental + // path which will hash-diff and update only changed files. + // + // We exclude paths that GitNexus itself writes during analyze: + // .gitnexus/ — db / parse cache / meta.json + // .claude/, .cursor/ — auto-generated agent skill files + // AGENTS.md, CLAUDE.md — auto-updated stats blocks + // Counting them as dirty would perpetually defeat the up-to-date + // fast path because the previous analyze just wrote them + // (regression vs PR #1233 behavior). + const dirty = (() => { + try { + const out = execFileSync( + 'git', + [ + 'status', + '--porcelain', + '--', + '.', + ':(exclude).gitnexus', + ':(exclude).gitnexus/**', + ':(exclude).claude', + ':(exclude).claude/**', + ':(exclude).cursor', + ':(exclude).cursor/**', + ':(exclude)AGENTS.md', + ':(exclude)CLAUDE.md', + ], + { + cwd: repoPath, + stdio: ['ignore', 'pipe', 'ignore'], + encoding: 'utf8', + }, + ); + return out.trim().length > 0; + } catch { + return true; // conservative on git failure + } + })(); + if (!dirty) { + await ensureGitNexusIgnored(repoPath); + return { + // `resolveRepoIdentityRoot` collapses worktree roots to the + // canonical repo basename (#1259) but leaves arbitrary subdirs + // and `--skip-git` paths unchanged (#1232/#1233 intent preserved). + repoName: + options.registryName ?? + getInferredRepoName(repoPath) ?? + path.basename(resolveRepoIdentityRoot(repoPath)), + repoPath, + stats: existingMeta.stats ?? {}, + alreadyUpToDate: true, + }; + } } } @@ -241,6 +313,14 @@ export async function runFullAnalysis( ); } + // We *always* load the embedding cache when one is requested (regardless + // of the predicted `willTryIncremental`). The post-pipeline branch may + // disagree with the prediction (e.g. when the pipeline produces zero + // File nodes, `isIncremental` flips false and the full-rebuild path + // wipes the DB) — loading unconditionally is cheap insurance against + // silently dropping embeddings on a mispredicted run. The re-insert + // step gates itself on the actual `isIncremental` value to avoid + // PK-conflicts when the incremental writeback path keeps the rows. if (shouldLoadCache && existingMeta) { try { progress('embeddings', 0, 'Caching embeddings...'); @@ -268,24 +348,89 @@ export async function runFullAnalysis( } } + // ── Load incremental parse cache ────────────────────────────────── + // Content-addressed: safe to reuse across `--force` runs (chunks whose + // file contents haven't changed produce identical worker output). + // Loaded into a single ParseCache object that the pipeline mutates + // in-place (cache hits leave entries unchanged; misses add new ones). + const parseCache = await loadParseCache(storagePath); + // ── Phase 1: Full Pipeline (0–60%) ──────────────────────────────── - const pipelineResult = await runPipelineFromRepo(repoPath, (p) => { - const phaseLabel = PHASE_LABELS[p.phase] || p.phase; - const scaled = Math.round(p.percent * 0.6); - const message = p.detail ? `${p.message || phaseLabel} (${p.detail})` : p.message || phaseLabel; - progress(p.phase, scaled, message); - }); + const pipelineResult = await runPipelineFromRepo( + repoPath, + (p) => { + const phaseLabel = PHASE_LABELS[p.phase] || p.phase; + const scaled = Math.round(p.percent * 0.6); + const message = p.detail + ? `${p.message || phaseLabel} (${p.detail})` + : p.message || phaseLabel; + progress(p.phase, scaled, message); + }, + { parseCache }, + ); // ── Phase 2: LadybugDB (60–85%) ────────────────────────────────── progress('lbug', 60, 'Loading into LadybugDB...'); - await closeLbug(); - const lbugFiles = [lbugPath, `${lbugPath}.wal`, `${lbugPath}.lock`]; - for (const f of lbugFiles) { - try { - await fs.rm(f, { recursive: true, force: true }); - } catch { - /* swallow */ + // Compute current per-file content hashes from the pipeline's File nodes. + // Used both to drive the incremental DB writeback (when eligible) and to + // populate meta.json.fileHashes for the next run. + const allFilePaths: string[] = []; + pipelineResult.graph.forEachNode((n) => { + if (n.label === 'File') { + const fp = n.properties?.filePath as string | undefined; + if (fp) allFilePaths.push(fp); + } + }); + const newFileHashes = await computeFileHashes(repoPath, allFilePaths); + + // Decide incremental vs full at THIS point (post-pipeline, pre-DB). + // All eligibility conditions are checked here against the actual + // pipeline output — no separate pre-pipeline prediction to desync from + // (Bugbot review on PR #1479: a prediction that flipped post-pipeline + // could skip the embedding cache load and then take the full-rebuild + // path, silently losing embeddings). + const isIncremental = + !options.force && + !!existingMeta && + existingMeta.schemaVersion === INCREMENTAL_SCHEMA_VERSION && + !!existingMeta.fileHashes && + Object.keys(existingMeta.fileHashes).length > 0 && + repoHasGit && + allFilePaths.length > 0; + + const hashDiff = isIncremental + ? diffFileHashes(newFileHashes, existingMeta!.fileHashes) + : undefined; + + if (isIncremental && hashDiff) { + log( + `Incremental: changed=${hashDiff.changed.length}, ` + + `added=${hashDiff.added.length}, ` + + `deleted=${hashDiff.deleted.length} ` + + `(skipping wipe + ${ + allFilePaths.length - hashDiff.toWrite.length + } unchanged file rows preserved)`, + ); + // Set the dirty flag BEFORE any destructive DB mutation. Cleared on + // success at the meta-save step. + await saveMeta(storagePath, { + ...existingMeta!, + incrementalInProgress: { + startedAt: Date.now(), + toWriteCount: hashDiff.toWrite.length, + }, + }); + } else { + // Full rebuild path: wipe DB files first. + await closeLbug(); + const lbugFiles = [lbugPath, `${lbugPath}.wal`, `${lbugPath}.lock`]; + for (const f of lbugFiles) { + try { + await fs.rm(f, { recursive: true, force: true }); + } catch { + /* swallow */ + } } } @@ -296,11 +441,145 @@ export async function runFullAnalysis( // must be released to avoid blocking subsequent invocations. let lbugMsgCount = 0; - await loadGraphToLbug(pipelineResult.graph, pipelineResult.repoPath, storagePath, (msg) => { - lbugMsgCount++; - const pct = Math.min(84, 60 + Math.round((lbugMsgCount / (lbugMsgCount + 10)) * 24)); - progress('lbug', pct, msg); - }); + if (isIncremental && hashDiff) { + // ── Incremental DB writeback ─────────────────────────────────── + // 0. Expand the writable set with transitive importers of + // changed/deleted files (bounded BFS). + // + // Reason (Bugbot/Claude review on PR #1479): when a barrel / + // re-export file C changes, cross-file resolution may update + // CALLS edges between two unchanged files A and B (A imports + // from C, C re-exports something from B). Those refined edges + // live in `ctx.graph` but would be excluded from the subgraph + // if neither endpoint is in the changed set. To catch this, + // files that imported (directly OR transitively, through + // other unchanged intermediaries) any changed file get pulled + // into the writable set so their rows are deleted + rewritten + // against the refined edges. + // + // BFS bound: MAX_IMPORTER_BFS_DEPTH. Practically sized to + // catch nested barrel chains (e.g. `index.ts → submodule/index.ts + // → submodule/impl.ts`) without ballooning into a near-full- + // rebuild on monorepos with deep re-export pyramids. Beyond + // this depth, the "incremental ≡ full-rebuild" invariant is + // self-acknowledged as best-effort; `--force` remains the + // escape hatch documented in GUARDRAILS.md. + // + // `queryImporters` reads `IMPORTS` from the pre-pipeline DB + // state, so the result is "files that USED TO import the + // target" — exactly the set whose previously-stored edges may + // no longer match what cross-file resolution produces this run. + const MAX_IMPORTER_BFS_DEPTH = 4; + const writableFiles = new Set(hashDiff.toWrite); + const directlyChangedCount = writableFiles.size; + + // Shadow-seed: for ADDED files, queryImporters returns 0 (the new + // file has no IMPORTS rows in the pre-pipeline DB yet). But pre- + // existing unchanged files may have IMPORTS edges whose module- + // resolution claim the newcomer can steal under standard JS/TS + // resolution (Bugbot review on PR #1479). For each added file we + // derive the shadow candidates and, if the candidate was a known + // file in the prior meta, seed it into the BFS frontier so its + // importers — surfaced via queryImporters — get their CALLS edges + // re-resolved against the new file. See shadow-candidates.ts for + // the full pattern catalogue. + const priorFileSet = new Set( + existingMeta?.fileHashes ? Object.keys(existingMeta.fileHashes) : [], + ); + const shadowSeed: string[] = []; + for (const added of hashDiff.added) { + for (const cand of shadowCandidatesFor(added)) { + if (priorFileSet.has(cand) && !writableFiles.has(cand)) { + shadowSeed.push(cand); + } + } + } + + { + let frontier: string[] = [...hashDiff.toWrite, ...hashDiff.deleted, ...shadowSeed]; + for (let depth = 0; depth < MAX_IMPORTER_BFS_DEPTH && frontier.length > 0; depth++) { + const nextFrontier: string[] = []; + for (const f of frontier) { + try { + const importers = await queryImporters(f); + for (const i of importers) { + if (!writableFiles.has(i)) { + writableFiles.add(i); + nextFrontier.push(i); + } + } + } catch { + /* per-file importer query failure → skip; correctness degrades on + that branch, but DB stays writable. */ + } + } + frontier = nextFrontier; + } + } + const importerExpansion = writableFiles.size - directlyChangedCount; + if (importerExpansion > 0) { + log( + `Incremental: +${importerExpansion} importer(s) added to writable set ` + + `(BFS depth ≤ ${MAX_IMPORTER_BFS_DEPTH}` + + (shadowSeed.length > 0 ? `, ${shadowSeed.length} shadow-seed(s)` : '') + + `)`, + ); + } + + // 1. Compute the EFFECTIVE write-set (Finding 1). Two layers, + // composed: + // (a) `writableFiles` — toWrite ∪ transitive importers of + // changed/deleted files (the bounded BFS above, reading + // IMPORTS from the pre-pipeline DB). + // (b) `computeEffectiveWriteSet` — walks the NEW graph's + // edges and pulls in any unchanged-side file that sits + // on a writable-boundary-crossing edge (catches refined + // cross-file CALLS edges that the pre-run DB couldn't + // predict, e.g. a barrel re-export shifting `foo` from + // B to D). + // The composed set is the input to BOTH deleteNodesForFile + // and extractChangedSubgraph — asymmetry between the two would + // leave stale rows or PK-conflict at COPY time. + const effectiveWriteSet = computeEffectiveWriteSet(pipelineResult.graph, writableFiles); + // Deduped: deleted entries may already appear via importer-BFS + // expansion (queryImporters can return a now-deleted path), which + // would otherwise call deleteNodesForFile twice for the same file + // (Bugbot LOW finding on PR #1479). + const filesToDelete = [...new Set([...effectiveWriteSet, ...hashDiff.deleted])]; + for (let i = 0; i < filesToDelete.length; i++) { + const f = filesToDelete[i]; + try { + await deleteNodesForFile(f); + } catch { + /* file may not have rows (e.g. an unparseable file) — fine */ + } + if (i % 20 === 0) { + progress('lbug', 62, `Removing rows for changed files (${i}/${filesToDelete.length})...`); + } + } + // 2. Drop graph-wide nodes (Community, Process). They'll be re-inserted + // from the fresh pipeline output below. Required for the + // "Leiden runs on the FULL graph" correctness invariant. + await deleteAllCommunitiesAndProcesses(); + + // 3. Extract the changed subgraph from the FULL ctx.graph and write + // only that. Unchanged-file rows in the DB stay untouched. Pass + // the SAME effectiveWriteSet so the subgraph and the deletes + // cover identical files (asymmetry would silently corrupt). + const subgraph = extractChangedSubgraph(pipelineResult.graph, effectiveWriteSet); + await loadGraphToLbug(subgraph, pipelineResult.repoPath, storagePath, (msg) => { + lbugMsgCount++; + const pct = Math.min(84, 65 + Math.round((lbugMsgCount / (lbugMsgCount + 10)) * 19)); + progress('lbug', pct, msg); + }); + } else { + // ── Full rebuild ─────────────────────────────────────────────── + await loadGraphToLbug(pipelineResult.graph, pipelineResult.repoPath, storagePath, (msg) => { + lbugMsgCount++; + const pct = Math.min(84, 60 + Math.round((lbugMsgCount / (lbugMsgCount + 10)) * 24)); + progress('lbug', pct, msg); + }); + } // ── Phase 3: FTS (85–90%) ───────────────────────────────────────── progress('fts', 85, 'Creating search indexes...'); @@ -308,6 +587,19 @@ export async function runFullAnalysis( progress('fts', 90, 'Search indexes ready'); // ── Phase 3.5: Re-insert cached embeddings ──────────────────────── + // Runs on BOTH the full-rebuild path and the incremental path: + // - Full rebuild: DB was wiped, every cached row needs to come back. + // - Incremental: changed-file rows were just deleted by + // deleteNodesForFile (which cascades to their + // embedding rows) — so their cached vectors need + // to come back too. Unchanged-file rows still + // exist; re-inserting their cached vectors would + // PK-conflict, but the per-batch try/catch below + // silently ignores those (matches the existing + // "some may fail if node was removed, that's + // fine" semantics). Bugbot review on PR #1479 + // flagged that gating this on `!isIncremental` + // silently lost changed-file embeddings. if (cachedEmbeddings.length > 0) { const cachedDims = cachedEmbeddings[0].embedding.length; const { EMBEDDING_DIMS } = await import('./lbug/schema.js'); @@ -454,6 +746,12 @@ export async function runFullAnalysis( const effectiveSemanticMode = semanticMode ?? (runtimeCapabilities.semanticMode === 'vector-index' ? 'vector-index' : 'exact-scan'); + + // Convert the post-run file-hash map to the on-disk Record + // shape consumed by RepoMeta.fileHashes. + const newFileHashesRecord: Record = {}; + for (const [k, v] of newFileHashes) newFileHashesRecord[k] = v; + const meta = { repoPath, lastCommit: currentCommit, @@ -483,8 +781,33 @@ export async function runFullAnalysis( reason: runtimeCapabilities.reason, }, }, + // Incremental-indexing fields. Populated for git repos so the next + // analyze run can take the incremental DB-writeback path. Setting + // incrementalInProgress to undefined explicitly clears any prior + // dirty flag (full and incremental success paths converge here). + schemaVersion: hasGitDir(repoPath) ? INCREMENTAL_SCHEMA_VERSION : undefined, + fileHashes: hasGitDir(repoPath) ? newFileHashesRecord : undefined, + incrementalInProgress: undefined as { startedAt: number; toWriteCount: number } | undefined, }; await saveMeta(storagePath, meta); + + // Persist the incremental parse cache for the next run. Wraps in + // try/catch so a cache-write failure never breaks an otherwise + // successful indexing run. Prune stale chunk-hash entries first so + // the cache file size stays bounded across runs (chunks whose + // composition no longer matches anything in the current scan are + // dead weight; the parse phase populates `usedKeys` as it processes + // chunks). + try { + const pruned = pruneCache(parseCache, parseCache.usedKeys); + if (pruned > 0) { + log(`Parse cache: pruned ${pruned} stale chunk entries`); + } + await saveParseCache(storagePath, parseCache); + } catch (e) { + log(`Warning: could not save parse cache (${(e as Error).message}); continuing.`); + } + // Forward the --name alias and the registry-collision bypass bit. // `allowDuplicateName` is its own concern — independent from the // pipeline `force` above. The CLI maps it from @@ -527,7 +850,11 @@ export async function runFullAnalysis( processes: pipelineResult.processResult?.stats.totalProcesses, }, undefined, - { skipAgentsMd: options.skipAgentsMd, noStats: options.noStats }, + { + skipAgentsMd: options.skipAgentsMd, + skipSkills: options.skipSkills, + noStats: options.noStats, + }, ); } catch { // Best-effort — don't fail the entire analysis for context file issues diff --git a/gitnexus/src/core/search/hybrid-search.ts b/gitnexus/src/core/search/hybrid-search.ts index b76a9f5e9..a2521dd83 100644 --- a/gitnexus/src/core/search/hybrid-search.ts +++ b/gitnexus/src/core/search/hybrid-search.ts @@ -50,9 +50,15 @@ export const mergeWithRRF = ( ): HybridSearchResult[] => { const merged = new Map(); + // Guard against undefined/null inputs (#1489) — when FTS is unavailable + // in the MCP process, bm25Results can arrive as undefined and the + // for-loop would throw "bm25Results is not iterable". + const safeBm25 = bm25Results ?? []; + const safeSemantic = semanticResults ?? []; + // Process BM25 results - for (let i = 0; i < bm25Results.length; i++) { - const r = bm25Results[i]; + for (let i = 0; i < safeBm25.length; i++) { + const r = safeBm25[i]; const rrfScore = 1 / (RRF_K + i + 1); // i+1 because rank starts at 1 merged.set(r.filePath, { @@ -65,8 +71,8 @@ export const mergeWithRRF = ( } // Process semantic results and merge - for (let i = 0; i < semanticResults.length; i++) { - const r = semanticResults[i]; + for (let i = 0; i < safeSemantic.length; i++) { + const r = safeSemantic[i]; const rrfScore = 1 / (RRF_K + i + 1); const existing = merged.get(r.filePath); @@ -149,6 +155,9 @@ export const formatHybridResults = (results: HybridSearchResult[]): string => { * Execute BM25 + semantic search and merge with RRF. * Uses LadybugDB FTS for always-fresh BM25 results (no cached data). * The semanticSearch function is injected to keep this module environment-agnostic. + * + * When FTS is unavailable (e.g. read-only MCP connection, missing indexes), + * falls back to semantic-only results instead of crashing (#1489). */ export const hybridSearch = async ( query: string, @@ -160,8 +169,16 @@ export const hybridSearch = async ( k?: number, ) => Promise, ): Promise => { - // Use LadybugDB FTS for always-fresh BM25 results - const { results: bm25Results } = await searchFTSFromLbug(query, limit); + // Use LadybugDB FTS for always-fresh BM25 results. + // If FTS fails (e.g. extension not loaded in MCP process), fall back to + // semantic-only search instead of crashing with "bm25Results is not iterable". + let bm25Results: BM25SearchResult[] = []; + try { + const ftsResponse = await searchFTSFromLbug(query, limit); + bm25Results = ftsResponse?.results ?? []; + } catch { + // FTS unavailable — continue with semantic-only search + } const semanticResults = await semanticSearch(executeQuery, query, limit); return mergeWithRRF(bm25Results, semanticResults, limit); }; diff --git a/gitnexus/src/core/tree-sitter/safe-parse.ts b/gitnexus/src/core/tree-sitter/safe-parse.ts new file mode 100644 index 000000000..1b3bc4fc5 --- /dev/null +++ b/gitnexus/src/core/tree-sitter/safe-parse.ts @@ -0,0 +1,40 @@ +import type Parser from 'tree-sitter'; + +/** + * tree-sitter 0.21.x's Node native binding crashes (SIGSEGV) on Windows when + * `parser.parse(string, …)` is handed a JS string longer than 32 767 chars. + * The crash happens inside the binding's V8 string-to-buffer conversion and + * cannot be intercepted from JavaScript. The callback (`Parser.Input`) overload + * pulls source in fixed-size chunks via repeated callback invocations and + * bypasses that conversion path entirely. + * + * Chunk size is comfortably below the boundary; any value < 32 767 works. + */ +const SAFE_PARSE_CHUNK_CHARS = 16 * 1024; + +/** + * Files at or below this length skip the callback machinery and use the + * direct string overload — the bug only manifests above the int16 boundary, + * so small inputs save the cost of N callback invocations per parse. + */ +const DIRECT_PARSE_LIMIT_CHARS = 16 * 1024; + +/** + * Parse `sourceText` safely on every platform. See {@link SAFE_PARSE_CHUNK_CHARS} + * for the underlying tree-sitter binding bug this works around. + */ +export function parseSourceSafe( + parser: Parser, + sourceText: string, + oldTree?: Parser.Tree, + options?: Parser.Options, +): Parser.Tree { + if (sourceText.length <= DIRECT_PARSE_LIMIT_CHARS) { + return parser.parse(sourceText, oldTree, options); + } + const input: Parser.Input = (index) => { + if (index >= sourceText.length) return null; + return sourceText.slice(index, index + SAFE_PARSE_CHUNK_CHARS); + }; + return parser.parse(input, oldTree, options); +} diff --git a/gitnexus/src/core/wiki/generator.ts b/gitnexus/src/core/wiki/generator.ts index 9f65d26e8..dc9c2e74e 100644 --- a/gitnexus/src/core/wiki/generator.ts +++ b/gitnexus/src/core/wiki/generator.ts @@ -28,6 +28,7 @@ import { type FileWithExports, } from './graph-queries.js'; import { generateHTMLViewer } from './html-viewer.js'; +import { sanitizeMermaidMarkdown } from './mermaid-sanitizer.js'; import { callLLM, @@ -591,7 +592,7 @@ export class WikiGenerator { const response = await this.invokeLLM(prompt, MODULE_SYSTEM_PROMPT, this.streamOpts(node.name)); // Write page with front matter - const pageContent = `# ${node.name}\n\n${response.content}`; + const pageContent = sanitizeMermaidMarkdown(`# ${node.name}\n\n${response.content}`); await fs.writeFile(path.join(this.wikiDir, `${node.slug}.md`), pageContent, 'utf-8'); } @@ -631,7 +632,7 @@ export class WikiGenerator { const response = await this.invokeLLM(prompt, PARENT_SYSTEM_PROMPT, this.streamOpts(node.name)); - const pageContent = `# ${node.name}\n\n${response.content}`; + const pageContent = sanitizeMermaidMarkdown(`# ${node.name}\n\n${response.content}`); await fs.writeFile(path.join(this.wikiDir, `${node.slug}.md`), pageContent, 'utf-8'); } @@ -681,7 +682,9 @@ export class WikiGenerator { this.streamOpts('Generating overview', 88), ); - const pageContent = `# ${path.basename(this.repoPath)} — Wiki\n\n${response.content}`; + const pageContent = sanitizeMermaidMarkdown( + `# ${path.basename(this.repoPath)} — Wiki\n\n${response.content}`, + ); await fs.writeFile(path.join(this.wikiDir, 'overview.md'), pageContent, 'utf-8'); } diff --git a/gitnexus/src/core/wiki/html-viewer.ts b/gitnexus/src/core/wiki/html-viewer.ts index f961d36ae..c0fd7323a 100644 --- a/gitnexus/src/core/wiki/html-viewer.ts +++ b/gitnexus/src/core/wiki/html-viewer.ts @@ -7,6 +7,7 @@ import fs from 'fs/promises'; import path from 'path'; +import { sanitizeMermaidMarkdown } from './mermaid-sanitizer.js'; interface ModuleTreeNode { name: string; @@ -42,7 +43,7 @@ export async function generateHTMLViewer(wikiDir: string, projectName: string): const dirEntries = await fs.readdir(wikiDir); for (const f of dirEntries.filter((f) => f.endsWith('.md'))) { const content = await fs.readFile(path.join(wikiDir, f), 'utf-8'); - pages[f.replace(/\.md$/, '')] = content; + pages[f.replace(/\.md$/, '')] = sanitizeMermaidMarkdown(content); } const html = buildHTML(projectName, moduleTree, pages, meta); diff --git a/gitnexus/src/core/wiki/llm-client.ts b/gitnexus/src/core/wiki/llm-client.ts index 172b8b00f..40ef831bf 100644 --- a/gitnexus/src/core/wiki/llm-client.ts +++ b/gitnexus/src/core/wiki/llm-client.ts @@ -1,4 +1,5 @@ import { logger } from '../logger.js'; +import { CircuitOpenError, ResilientFetchExhaustedError, resilientFetch } from 'gitnexus-shared'; /** * LLM Client for Wiki Generation * @@ -22,6 +23,10 @@ export interface LLMConfig { apiVersion?: string; /** When true, strips sampling params and uses max_completion_tokens instead of max_tokens */ isReasoningModel?: boolean; + /** Per-attempt fetch timeout in ms (default: 60_000). */ + requestTimeoutMs?: number; + /** Max fetch attempts before giving up (default: 3). */ + maxAttempts?: number; } export interface LLMResponse { @@ -76,6 +81,49 @@ export function estimateTokens(text: string): number { return Math.ceil(text.length / 4); } +/** + * Validate that a base URL supplied for LLM API calls is a safe HTTP/HTTPS + * endpoint (CWE-918 / CodeQL js/http-to-file-access). + * + * Allowed: + * - https:// with any hostname (public LLM APIs, Azure, OpenRouter, …) + * - http:// restricted to localhost / 127.0.0.1 (local servers: Ollama, LiteLLM, …) + * + * Rejected: + * - file://, data:, javascript:, and any other non-HTTP scheme + * - http:// aimed at non-loopback hosts (avoids SSRF against internal networks) + * + * Throws with a descriptive message on validation failure so callers surface a + * clear error rather than an opaque network error. + */ +export function validateLLMBaseUrl(baseUrl: string): void { + let parsed: URL; + try { + parsed = new URL(baseUrl); + } catch { + // Do not include the raw input in the message — it may contain credentials. + throw new Error('Invalid LLM base URL: must be a well-formed http:// or https:// URL'); + } + + if (!['https:', 'http:'].includes(parsed.protocol)) { + // Use parsed.protocol only (scheme), not the full URL, to avoid leaking credentials. + throw new Error(`LLM base URL must use http:// or https:// (got ${parsed.protocol})`); + } + + if (parsed.protocol === 'http:') { + // Node's URL parser preserves IPv6 brackets in hostname (e.g. "[::1]"), + // so strip them before comparing to bare address literals. + const host = parsed.hostname.toLowerCase().replace(/^\[|\]$/g, ''); + if (host !== 'localhost' && host !== '127.0.0.1' && host !== '::1') { + // Use parsed.origin (scheme+host+port, no credentials) instead of the full URL. + throw new Error( + `Insecure http:// LLM base URLs are only allowed for localhost/127.0.0.1. ` + + `Use https:// for remote endpoints (got ${parsed.origin})`, + ); + } + } +} + /** * Returns true if the given base URL is an Azure OpenAI endpoint. * Uses proper hostname matching to avoid spoofed URLs like @@ -127,6 +175,9 @@ export async function callLLM( systemPrompt?: string, options?: CallLLMOptions, ): Promise { + // Validate base URL before any fetch (CodeQL js/http-to-file-access) + validateLLMBaseUrl(config.baseUrl); + const messages: Array<{ role: string; content: string }> = []; if (systemPrompt) { messages.push({ role: 'system', content: systemPrompt }); @@ -170,86 +221,85 @@ export async function callLLM( ? { 'api-key': config.apiKey } : { Authorization: `Bearer ${config.apiKey}` }; - const MAX_RETRIES = 3; - let lastError: Error | null = null; - - for (let attempt = 0; attempt < MAX_RETRIES; attempt++) { - try { - const response = await fetch(url, { + // Network resilience (bounded retries with exponential-backoff jitter, + // 5xx + 429 + Retry-After handling, in-process circuit breaker on the + // LLM endpoint) is delegated to resilientFetch. Provider-specific + // error parsing (Azure content filter, empty-content checks) stays + // here since it requires response-body inspection. + let response: Response; + try { + response = await resilientFetch( + url, + { method: 'POST', headers: { 'Content-Type': 'application/json', ...authHeaders, }, body: JSON.stringify(body), - }); - - if (!response.ok) { - const errorText = await response.text().catch(() => 'unknown error'); - - // Azure content filter — surface a clear message instead of a generic API error - if ( - azure && - response.status === 400 && - (errorText.includes('content_filter') || - errorText.includes('ResponsibleAIPolicyViolation')) - ) { - throw new Error( - `Azure content filter blocked this request. The prompt triggered content policy. Details: ${errorText.slice(0, 300)}`, - ); - } - - // Rate limit — wait with exponential backoff and retry - if (response.status === 429 && attempt < MAX_RETRIES - 1) { - const retryAfter = parseInt(response.headers.get('retry-after') || '0', 10); - const delay = retryAfter > 0 ? retryAfter * 1000 : 2 ** attempt * 3000; - await sleep(delay); - continue; - } - - // Server error — retry with backoff - if (response.status >= 500 && attempt < MAX_RETRIES - 1) { - await sleep((attempt + 1) * 2000); - continue; - } - - throw new Error(`LLM API error (${response.status}): ${errorText.slice(0, 500)}`); - } - - // Streaming path - if (useStream && response.body) { - return await readSSEStream(response.body, options!.onChunk!); - } - - // Non-streaming path - const json = (await response.json()) as any; - const choice = json.choices?.[0]; - if (!choice?.message?.content) { - throw new Error('LLM returned empty response'); - } - - return { - content: choice.message.content, - promptTokens: json.usage?.prompt_tokens, - completionTokens: json.usage?.completion_tokens, - }; - } catch (err: any) { - lastError = err; - - // Network error — retry with backoff - if ( - attempt < MAX_RETRIES - 1 && - (err.code === 'ECONNREFUSED' || err.code === 'ETIMEDOUT' || err.message?.includes('fetch')) - ) { - await sleep((attempt + 1) * 3000); - continue; - } - - throw err; + // Per-attempt timeout. Without this each retry can hang + // indefinitely on a frozen TCP connection — the per-call + // signal is the only timeout `resilientFetch` honors; + // `capDelayMs` only bounds the *backoff* between attempts. + // Default 60s; raise via --timeout for slow models or large pages. + signal: AbortSignal.timeout(config.requestTimeoutMs ?? 60_000), + }, + { + breakerKey: `wiki-llm-${new URL(url).host}`, + retry: { maxAttempts: config.maxAttempts ?? 3, baseDelayMs: 2_000, capDelayMs: 30_000 }, + }, + ); + } catch (err) { + if (err instanceof CircuitOpenError) { + throw new Error( + `LLM endpoint circuit open: retry in ${Math.ceil(err.retryAfterMs / 1000)}s. ${err.message}`, + ); } + if (err instanceof ResilientFetchExhaustedError) { + const errorText = await err.response.text().catch(() => 'unknown error'); + throw new Error( + `LLM API error (${err.response.status} after retries): ${errorText.slice(0, 500)}`, + ); + } + throw err; } - throw lastError || new Error('LLM call failed after retries'); + if (!response.ok) { + const errorText = await response.text().catch(() => 'unknown error'); + + // Azure content filter — surface a clear message instead of a generic API error. + if ( + azure && + response.status === 400 && + (errorText.includes('content_filter') || errorText.includes('ResponsibleAIPolicyViolation')) + ) { + throw new Error( + `Azure content filter blocked this request. The prompt triggered content policy. Details: ${errorText.slice(0, 300)}`, + ); + } + + // Any other non-OK response here is a terminal 4xx — resilientFetch + // already retried 5xx/429 to exhaustion and would have thrown above. + throw new Error(`LLM API error (${response.status}): ${errorText.slice(0, 500)}`); + } + + // Streaming path + if (useStream && response.body) { + return await readSSEStream(response.body, options!.onChunk!); + } + + // Non-streaming path + const json = (await response.json()) as any; + const choice = json.choices?.[0]; + if (!choice?.message?.content) { + throw new Error('LLM returned empty response'); + } + + return { + content: choice.message.content, + promptTokens: json.usage?.prompt_tokens, + completionTokens: json.usage?.completion_tokens, + }; } /** @@ -312,7 +362,3 @@ async function readSSEStream( return { content }; } - -function sleep(ms: number): Promise { - return new Promise((resolve) => setTimeout(resolve, ms)); -} diff --git a/gitnexus/src/core/wiki/mermaid-sanitizer.ts b/gitnexus/src/core/wiki/mermaid-sanitizer.ts new file mode 100644 index 000000000..c8d443c78 --- /dev/null +++ b/gitnexus/src/core/wiki/mermaid-sanitizer.ts @@ -0,0 +1,119 @@ +const MERMAID_FENCE_RE = /```mermaid\s*\n([\s\S]*?)```/g; +const NODE_LABEL_RE = + /(\[[^\]\n]*(?:\\n)[^\]\n]*\]|\{[^}\n]*(?:\\n)[^}\n]*\}|\([^)\n]*(?:\\n)[^)\n]*\))/g; +const EDGE_LABEL_RE = /\|([^|\n]+)\|/g; +const UNSAFE_EDGE_LABEL_RE = /[()[\]{}<>]/; +const UNSAFE_NODE_ID_RE = /[^A-Za-z0-9_-]/; +const NODE_ID_RE = /^[A-Za-z0-9_.:/()-]+$/; + +const LINE_PREFIX_RE = /^(\s*(?:(?:[-A-Za-z0-9_]+)\s*:\s*)?)(.*)$/; +const EDGE_RE = + /(\s*(?:[ox])?(?:--+|==+|\.\.+)(?:[>|ox])?\|[^|\n]*\|(?:[>|ox])?|\s*(?:[ox])?(?:--+|==+|\.\.+)(?:[>|ox])?|\s*<--+>?\s*)/g; + +export function sanitizeMermaidMarkdown(markdown: string): string { + return markdown.replace(MERMAID_FENCE_RE, (_match, diagram: string) => { + return '```mermaid\n' + sanitizeMermaidDiagram(diagram) + '```'; + }); +} + +export function sanitizeMermaidDiagram(diagram: string): string { + const aliases = new Map(); + let nextAlias = 1; + + const aliasFor = (id: string): string => { + const existing = aliases.get(id); + if (existing) return existing; + + const base = id.replace(/[^A-Za-z0-9_-]/g, '_').replace(/^_+|_+$/g, '') || 'node'; + let alias = base; + while ([...aliases.values()].includes(alias)) { + nextAlias += 1; + alias = `${base}_${nextAlias}`; + } + aliases.set(id, alias); + return alias; + }; + + return diagram + .split('\n') + .map((line) => sanitizeMermaidLine(line, aliasFor)) + .join('\n'); +} + +function sanitizeMermaidLine(line: string, aliasFor: (id: string) => string): string { + let sanitized = replaceLiteralLineBreaksInLabels(line); + sanitized = quoteUnsafeEdgeLabels(sanitized); + + const prefixMatch = sanitized.match(LINE_PREFIX_RE); + if (!prefixMatch) return sanitized; + + const prefix = prefixMatch[1]; + const body = prefixMatch[2]; + if (isDirectiveLine(body)) return sanitized; + + const parts = body.split(EDGE_RE); + if (parts.length === 1) return sanitized; + + for (let i = 0; i < parts.length; i += 2) { + parts[i] = sanitizeNodeReference(parts[i], aliasFor); + } + + return prefix + parts.join(''); +} + +function replaceLiteralLineBreaksInLabels(line: string): string { + return line.replace(NODE_LABEL_RE, (label) => label.replace(/\\n/g, '
')); +} + +function quoteUnsafeEdgeLabels(line: string): string { + return line.replace(EDGE_LABEL_RE, (match, label: string) => { + const trimmed = label.trim(); + if (!UNSAFE_EDGE_LABEL_RE.test(trimmed)) return match; + if ( + (trimmed.startsWith('"') && trimmed.endsWith('"')) || + (trimmed.startsWith("'") && trimmed.endsWith("'")) + ) { + return match; + } + return `|"${escapeMermaidLabel(trimmed)}"|`; + }); +} + +function sanitizeNodeReference(segment: string, aliasFor: (id: string) => string): string { + const match = segment.match(/^(\s*)([A-Za-z0-9_.:/()-]+)(.*?)(\s*)$/); + if (!match) return segment; + + const [, leading, id, suffix, trailing] = match; + if (!NODE_ID_RE.test(id) || !UNSAFE_NODE_ID_RE.test(id)) return segment; + const hasInlineLabel = + suffix.trim().startsWith('[') || suffix.trim().startsWith('(') || suffix.trim().startsWith('{'); + + if (hasInlineLabel) return `${leading}${aliasFor(id)}${suffix}${trailing}`; + + return `${leading}${aliasFor(id)}["${escapeMermaidLabel(id)}"]${suffix}${trailing}`; +} + +function escapeMermaidLabel(label: string): string { + return label.replace(/\\/g, '\\\\').replace(/"/g, '\\"'); +} + +function isDirectiveLine(line: string): boolean { + const trimmed = line.trim(); + return ( + trimmed === '' || + trimmed.startsWith('%%') || + trimmed.startsWith('graph ') || + trimmed.startsWith('flowchart ') || + trimmed.startsWith('sequenceDiagram') || + trimmed.startsWith('classDiagram') || + trimmed.startsWith('stateDiagram') || + trimmed.startsWith('erDiagram') || + trimmed.startsWith('journey') || + trimmed.startsWith('gantt') || + trimmed.startsWith('pie ') || + trimmed.startsWith('mindmap') || + trimmed.startsWith('timeline') || + trimmed.startsWith('subgraph ') || + trimmed === 'end' + ); +} diff --git a/gitnexus/src/mcp/local/local-backend.ts b/gitnexus/src/mcp/local/local-backend.ts index 167c1db81..922a69f85 100644 --- a/gitnexus/src/mcp/local/local-backend.ts +++ b/gitnexus/src/mcp/local/local-backend.ts @@ -755,8 +755,10 @@ export class LocalBackend { timer.time('vector', this.semanticSearch(repo, searchQuery, searchLimit)), ]); - const bm25Results = bm25SearchResult.results; - const ftsUsed = bm25SearchResult.ftsUsed; + // Guard against undefined results (#1489) — when FTS is entirely + // unavailable the search helper may return an unexpected shape. + const bm25Results = bm25SearchResult?.results ?? []; + const ftsUsed = bm25SearchResult?.ftsUsed ?? false; // Merge via reciprocal rank fusion timer.start('merge'); @@ -774,8 +776,9 @@ export class LocalBackend { } } - for (let i = 0; i < semanticResults.length; i++) { - const result = semanticResults[i]; + const safeSemanticResults = semanticResults ?? []; + for (let i = 0; i < safeSemanticResults.length; i++) { + const result = safeSemanticResults[i]; const key = result.nodeId || result.filePath; const rrfScore = 1 / (60 + i); const existing = scoreMap.get(key); @@ -992,7 +995,17 @@ export class LocalBackend { query: string, limit: number, ): Promise<{ results: any[]; ftsUsed: boolean }> { - const { searchFTSFromLbug } = await import('../../core/search/bm25-index.js'); + let searchFTSFromLbug; + try { + ({ searchFTSFromLbug } = await import('../../core/search/bm25-index.js')); + } catch (err: any) { + // Module import can fail in sandboxed MCP contexts (#1489) + logger.warn( + { err: err?.message }, + 'GitNexus: bm25-index.js import failed — falling back to semantic-only', + ); + return { results: [], ftsUsed: false }; + } let ftsResponse; try { ftsResponse = await searchFTSFromLbug(query, limit, repo.id); @@ -1004,8 +1017,10 @@ export class LocalBackend { return { results: [], ftsUsed: false }; } - const bm25Results = ftsResponse.results; - const ftsUsed = ftsResponse.ftsAvailable; + // Guard against unexpected response shape (#1489) — ftsResponse.results + // could be undefined when the FTS extension is unavailable in the MCP process. + const bm25Results = ftsResponse?.results ?? []; + const ftsUsed = ftsResponse?.ftsAvailable ?? false; const results: any[] = []; diff --git a/gitnexus/src/server/api.ts b/gitnexus/src/server/api.ts index cc65daa3d..2d49fabc4 100644 --- a/gitnexus/src/server/api.ts +++ b/gitnexus/src/server/api.ts @@ -744,8 +744,13 @@ export const createServer = async (port: number, host: string = '127.0.0.1') => if (isMatch && ['queued', 'cloning', 'analyzing'].includes(job.status)) { if (process.env.DEBUG) { - console.log( - `[debug] resolveRepo waiting for active job ${job.id} (${normalizedName})...`, + // Sanitize user-controlled values to prevent log injection (CodeQL js/log-injection). + logger.debug( + { + jobId: String(job.id).replace(/[\r\n]/g, ' '), + repoName: String(normalizedName).replace(/[\r\n]/g, ' '), + }, + '[debug] resolveRepo waiting for active job', ); } for (let wait = 0; wait < HOLD_QUEUE_TIMEOUT_SECS; wait++) { @@ -769,7 +774,11 @@ export const createServer = async (port: number, host: string = '127.0.0.1') => // (e.g. registry file not yet flushed after clone completes). if (!found && normalizedName && !isRetry) { if (process.env.DEBUG) { - console.log(`[debug] resolveRepo 404 for "${normalizedName}". Triggering deep init...`); + // Sanitize user-controlled values to prevent log injection (CodeQL js/log-injection). + logger.debug( + { repoName: String(normalizedName).replace(/[\r\n]/g, ' ') }, + '[debug] resolveRepo 404, triggering deep init', + ); } await backend.init(); return await resolveRepo(normalizedName, true, req); diff --git a/gitnexus/src/server/git-clone.ts b/gitnexus/src/server/git-clone.ts index 861a16648..0ced1213a 100644 --- a/gitnexus/src/server/git-clone.ts +++ b/gitnexus/src/server/git-clone.ts @@ -11,6 +11,7 @@ import os from 'os'; import fs from 'fs/promises'; import { isIP } from 'net'; import { logger } from '../core/logger.js'; +import { parseRepoNameFromUrl } from '../storage/git.js'; /** Root directory for all cloned repositories. Targets must resolve inside this. */ const CLONE_ROOT = path.resolve(path.join(os.homedir(), '.gitnexus', 'repos')); @@ -29,20 +30,17 @@ const REPO_NAME_PATTERN = /^[a-zA-Z0-9._-]+$/; * clone root via path traversal. */ export function extractRepoName(url: string): string { - // Strip trailing slashes without a regex to avoid polynomial-ReDoS on - // pathological inputs like `https://x.com/y` + '/'.repeat(1e6). CodeQL's - // js/polynomial-redos flagged `/\/+$/` here. - let end = url.length; - while (end > 0 && url.charCodeAt(end - 1) === 47 /* '/' */) end--; - const cleaned = url.slice(0, end); - - const lastSegment = cleaned.split(/[/:]/).pop() || ''; - const stripped = lastSegment.endsWith('.git') ? lastSegment.slice(0, -4) : lastSegment; - - if (!stripped || stripped === '.' || stripped === '..' || !REPO_NAME_PATTERN.test(stripped)) { + const name = parseRepoNameFromUrl(url); + if ( + !name || + name === '.' || + name === '..' || + name === 'unknown' || + !REPO_NAME_PATTERN.test(name) + ) { throw new Error('Could not extract a valid repository name from URL'); } - return stripped; + return name; } /** Get the clone target directory for a repo name. */ @@ -399,8 +397,8 @@ export async function cloneOrPull( } // Always validate the requested URL — the prior shape only ran this in - // the clone branch, leaving the pull branch as an SSRF / blocked-host - // bypass when an existing clone shared the basename of an attacker URL. + // the code path where the repo was cloned. Now it runs unconditionally, + // preventing SSRF / blocked-host bypasses even when targetDir already exists. validateGitUrl(url); const exists = await fs.access(path.join(safeTarget, '.git')).then( diff --git a/gitnexus/src/storage/file-hash.ts b/gitnexus/src/storage/file-hash.ts new file mode 100644 index 000000000..b39111815 --- /dev/null +++ b/gitnexus/src/storage/file-hash.ts @@ -0,0 +1,104 @@ +/** + * Per-file content hashing for incremental DB writeback. + * + * On every analyze run we compute SHA-256 of every file's content and + * store the map in meta.json. The next run compares disk against the + * stored map and produces: + * - `changed` — content differs (re-emit DB rows for this file) + * - `added` — file is new on disk (insert DB rows) + * - `deleted` — file was in last meta but no longer on disk (drop rows) + * + * The pipeline still parses every file (correctness invariant: cross-file + * resolution needs full data). What this enables is a SELECTIVE DB + * writeback: instead of wipe-and-reload of the whole graph (~50s of CSV + * COPY on a 25K-node repo), we only delete-and-rewrite rows for the + * changed/added/deleted set. + * + * See docs/superpowers/specs/2026-05-10-incremental-indexing-design.md + * (Option B revision). + */ + +import { createHash } from 'crypto'; +import fs from 'fs/promises'; +import path from 'path'; + +/** + * Compute SHA-256 of a single file. Returns null when the file can't be + * read — caller treats that as "no signature, assume changed". + */ +export const computeFileHash = async (absPath: string): Promise => { + try { + const buf = await fs.readFile(absPath); + return createHash('sha256').update(buf).digest('hex'); + } catch { + return null; + } +}; + +/** + * Compute SHA-256 hashes for many files in parallel batches. Files that + * fail to read are omitted from the result map. + */ +export const computeFileHashes = async ( + repoPath: string, + relPaths: readonly string[], +): Promise> => { + const out = new Map(); + const BATCH = 100; + for (let i = 0; i < relPaths.length; i += BATCH) { + const batch = relPaths.slice(i, i + BATCH); + const results = await Promise.all( + batch.map(async (rel) => { + const h = await computeFileHash(path.join(repoPath, rel)); + return h ? ([rel, h] as const) : null; + }), + ); + for (const r of results) if (r) out.set(r[0], r[1]); + } + return out; +}; + +/** Result of comparing the current on-disk hashes against stored ones. */ +export interface FileHashDiff { + /** Files whose content hash differs from stored. */ + changed: string[]; + /** Files in the current scan that weren't in the stored map. */ + added: string[]; + /** Files in the stored map that aren't in the current scan. */ + deleted: string[]; + /** All files whose DB rows must be replaced (changed ∪ added). */ + toWrite: string[]; +} + +/** + * Diff a current hash map against a previously stored one. + * + * Sorted output so two runs produce identical diff arrays for the same + * changes — useful for stable logging / equivalence checks. + */ +export const diffFileHashes = ( + current: ReadonlyMap, + stored: Readonly> | undefined, +): FileHashDiff => { + const storedMap = new Map(stored ? Object.entries(stored) : []); + const changed: string[] = []; + const added: string[] = []; + for (const [p, h] of current) { + const prev = storedMap.get(p); + if (prev === undefined) added.push(p); + else if (prev !== h) changed.push(p); + } + const deleted: string[] = []; + for (const p of storedMap.keys()) { + if (!current.has(p)) deleted.push(p); + } + changed.sort(); + added.sort(); + deleted.sort(); + return { + changed, + added, + deleted, + toWrite: [...changed, ...added].sort(), + }; +}; diff --git a/gitnexus/src/storage/git.ts b/gitnexus/src/storage/git.ts index 4cb0154fe..75e6e91d3 100644 --- a/gitnexus/src/storage/git.ts +++ b/gitnexus/src/storage/git.ts @@ -255,24 +255,63 @@ export const getRemoteOriginUrl = (repoPath: string): string | null => { }; /** - * Parse a repository name out of a git remote URL. Handles the common - * SSH (`git@host:owner/repo.git`), HTTPS (`https://host/owner/repo.git`), - * `git://`, `ssh://`, and `file://` shapes. Returns `null` for empty / - * unparseable input. + * Sanitize a repository name to prevent argument injection and ensure + * cross-platform filesystem compatibility. * - * The heuristic: strip a trailing `.git` and trailing slashes, then - * take the segment after the last `/` or `:`. + * 1. Strips leading dashes to prevent git command-line argument injection + * (e.g., --upload-pack=evil). + * 2. Replaces characters that are unsafe for directory names across + * platforms (Windows/macOS/Linux) with underscores. + * 3. Blocks path traversal segments ("." and "..") and Windows reserved + * names (e.g., CON, NUL) to prevent directory escape. + */ +export const sanitizeRepoName = (name: string): string => { + // 1. Prevent argument injection by stripping leading dashes. + // 2. Remove characters that are not alphanumerics, dots, underscores, or dashes. + const sanitized = name.replace(/^-+/, '').replace(/[^a-zA-Z0-9._-]/g, '_'); + + // 3. Block path traversal segments and Windows reserved names. + // Windows reserved names like CON, PRN, AUX, NUL, COM1-9, LPT1-9 cannot + // be used as directory names on Windows even if they have an extension. + const reserved = /^(CON|PRN|AUX|NUL|COM[1-9]|LPT[1-9])(\..*)?$/i; + if (!sanitized || sanitized === '.' || sanitized === '..' || reserved.test(sanitized)) { + return 'unknown'; + } + + return sanitized; +}; + +/** + * Parse a repository name out of a git remote URL. Handles common shapes + * including SSH (git@host:owner/repo.git) and HTTPS (https://host/owner/repo.git). + * + * Returns a sanitized, filesystem-safe name or null if no name could be inferred. + * Returning null (rather than 'unknown') allows callers to use ?? null-coalescing + * for fallbacks without risk of registry collisions on 'unknown'. */ export const parseRepoNameFromUrl = (url: string | null | undefined): string | null => { if (!url) return null; const trimmed = url.trim(); if (!trimmed) return null; - // Strip `.git` suffix (case-insensitive) and any trailing slashes. - const withoutSuffix = trimmed.replace(/\.git\/*$/i, '').replace(/\/+$/, ''); - // Last path segment, splitting on either `/` or `:` (covers SSH form). - const m = withoutSuffix.match(/[/:]([^/:]+)$/); - const candidate = m ? m[1] : withoutSuffix; - return candidate || null; + + // Strip trailing slashes without a regex to avoid polynomial-ReDoS on + // pathological inputs like `https://x.com/y` + '/'.repeat(1e6). + let end = trimmed.length; + while (end > 0 && trimmed.charCodeAt(end - 1) === 47 /* '/' */) end--; + let cleaned = trimmed.slice(0, end); + + // Strip trailing .git (case-insensitive) + if (cleaned.toLowerCase().endsWith('.git')) { + cleaned = cleaned.slice(0, -4); + } + + // Last path segment, handling colons for SSH URLs and path traversal. + // Split on both / and : to consistently extract the last part. + const candidate = cleaned.split(/[/:]/).pop() || ''; + if (!candidate) return null; + + const safe = sanitizeRepoName(candidate); + return safe === 'unknown' ? null : safe; }; /** diff --git a/gitnexus/src/storage/parse-cache.ts b/gitnexus/src/storage/parse-cache.ts new file mode 100644 index 000000000..a1abf76fa --- /dev/null +++ b/gitnexus/src/storage/parse-cache.ts @@ -0,0 +1,213 @@ +/** + * Chunk-level content-addressed parse cache. + * + * The pipeline always parses every file (correctness invariant: cross-file + * resolution and downstream phases need full graph data). What this cache + * does is skip the tree-sitter worker dispatch when a chunk's contents + * haven't changed since the last run. + * + * Granularity: chunk-level. The parse phase chunks files into ~20MB byte + * budgets. The cache key is `sha256(joined(filePath:contentHash for each + * file in the chunk, sorted))`. A change to a single file invalidates only + * that file's chunk — typically 1 of ~50 chunks on a 1000-file repo. + * + * Why not per-file: + * - Workers process sub-batches and emit aggregated `ParseWorkerResult`s. + * Splitting back to per-file would require reworking the worker contract. + * - Chunk-level invalidation gives a useful speedup floor (98% on a single + * 1-of-50 invalidated chunk) without touching the worker. + * + * Survives `--force` because it's content-addressed: the same bytes always + * produce the same key. `--force` only matters for the LadybugDB writeback; + * the cache itself is always safe to reuse. + */ + +import { createHash } from 'crypto'; +import { createRequire } from 'module'; +import fs from 'fs/promises'; +import path from 'path'; +import { fileURLToPath } from 'url'; +import type { ParseWorkerResult } from '../core/ingestion/workers/parse-worker.js'; + +/** + * Cache version composed of: + * - A schema bump knob (`SCHEMA_BUMP`) for hand-controlled invalidation + * when ParseWorkerResult shape or upstream parse semantics change. + * - The current `gitnexus` npm package version, read at module load. + * Any release that ships an updated tree-sitter grammar or revised + * extractor logic implies a version bump in package.json, which + * automatically invalidates the on-disk cache. Without this, a user + * running `npm i -g gitnexus@latest` after a parser-affecting + * release would silently replay pre-upgrade ParseWorkerResults + * against the new graph schema (Bugbot/Claude review on #1479). + * + * On version mismatch, `loadParseCache` returns an empty cache and the + * next save overwrites the on-disk file with the new version baked in. + */ +const SCHEMA_BUMP = 1; +const GITNEXUS_PKG_VERSION = (() => { + try { + // package.json sits at gitnexus/package.json — two levels up from + // gitnexus/src/storage/parse-cache.ts (or its dist/ equivalent). + const here = path.dirname(fileURLToPath(import.meta.url)); + const candidates = [ + path.join(here, '..', '..', 'package.json'), // src/storage → gitnexus/ + path.join(here, '..', '..', '..', 'package.json'), // dist/storage → gitnexus/ + ]; + const requireCJS = createRequire(import.meta.url); + for (const c of candidates) { + try { + const pkg = requireCJS(c); + if (typeof pkg?.version === 'string') return pkg.version; + } catch { + /* try next candidate */ + } + } + } catch { + /* fall through to fallback */ + } + return '0.0.0-unknown'; +})(); +export const PARSE_CACHE_VERSION = `${SCHEMA_BUMP}+${GITNEXUS_PKG_VERSION}`; + +const CACHE_FILENAME = 'parse-cache.json'; + +/** On-disk shape. */ +interface ParseCacheFile { + version: string; + /** key = chunk hash (hex) → cached chunk result list. */ + entries: Record; +} + +/** Runtime view: keyed Map for fast lookup; mutated in place during a run. */ +export interface ParseCache { + version: string; + entries: Map; + /** + * Hashes referenced (hit OR miss-and-stored) by the current run. + * The parse phase populates this as it processes chunks; the orchestrator + * uses it as input to `pruneCache` before saving so entries that no + * longer correspond to any chunk in the current scan are discarded. + * Transient — never serialized to disk. + */ + usedKeys: Set; +} + +/** SHA-256 hex of a single string or buffer. */ +const sha256Hex = (input: Buffer | string): string => + createHash('sha256') + .update(typeof input === 'string' ? Buffer.from(input) : input) + .digest('hex'); + +/** Stable hash of a single file's contents — used by callers to compose a chunk hash. */ +export const fileContentHash = (content: Buffer | string): string => sha256Hex(content); + +/** + * Compute the canonical cache key for a chunk's contents. + * + * `entries` is the list of (filePath, file content hash) for every file + * in the chunk. We sort by filePath before hashing so chunks composed of + * the same files in different order produce the same key. + */ +export const computeChunkHash = ( + entries: Array<{ filePath: string; contentHash: string }>, +): string => { + const sorted = [...entries].sort((a, b) => (a.filePath < b.filePath ? -1 : 1)); + const joined = sorted.map((e) => `${e.filePath}:${e.contentHash}`).join('\n'); + return sha256Hex(joined); +}; + +/** + * JSON replacer that round-trips Map/Set instances through plain JSON. + * + * `ParseWorkerResult.parsedFiles[*].scopes[*].typeBindings` is a + * `ReadonlyMap`; without this transform it serializes + * to `{}` and downstream code that iterates / `.get()`s on it crashes + * with "is not iterable". Applied symmetrically by `mapReviver` on + * load so the in-memory shape stays Map-typed. + */ +const MAP_TAG = '__$mapEntries$__'; +const SET_TAG = '__$setValues$__'; + +const mapReplacer = (_key: string, value: unknown): unknown => { + if (value instanceof Map) return { [MAP_TAG]: Array.from(value.entries()) }; + if (value instanceof Set) return { [SET_TAG]: Array.from(value.values()) }; + return value; +}; + +const mapReviver = (_key: string, value: unknown): unknown => { + if (value && typeof value === 'object') { + const v = value as Record; + if (Array.isArray(v[MAP_TAG])) return new Map(v[MAP_TAG] as [unknown, unknown][]); + if (Array.isArray(v[SET_TAG])) return new Set(v[SET_TAG] as unknown[]); + } + return value; +}; + +/** + * Load the parse cache. Returns an empty cache on any failure (missing + * file, corrupt JSON, version mismatch). Never throws on a normal load. + */ +export const loadParseCache = async (storagePath: string): Promise => { + const cachePath = path.join(storagePath, CACHE_FILENAME); + try { + const raw = await fs.readFile(cachePath, 'utf-8'); + const data = JSON.parse(raw, mapReviver) as ParseCacheFile; + if ( + typeof data !== 'object' || + data === null || + data.version !== PARSE_CACHE_VERSION || + typeof data.entries !== 'object' || + data.entries === null + ) { + return emptyCache(); + } + const entries = new Map(); + for (const [k, v] of Object.entries(data.entries)) { + if (Array.isArray(v)) entries.set(k, v as ParseWorkerResult[]); + } + return { version: PARSE_CACHE_VERSION, entries, usedKeys: new Set() }; + } catch { + return emptyCache(); + } +}; + +/** + * Persist the cache to disk atomically (write-and-rename) so a crash + * mid-write doesn't leave a corrupt file. + */ +export const saveParseCache = async (storagePath: string, cache: ParseCache): Promise => { + await fs.mkdir(storagePath, { recursive: true }); + const cachePath = path.join(storagePath, CACHE_FILENAME); + const tmpPath = `${cachePath}.tmp`; + const out: ParseCacheFile = { + version: cache.version, + entries: Object.fromEntries(cache.entries), + }; + // Compact JSON; this file can be tens of MB on a large repo and pretty- + // printing roughly doubles size for no value. + await fs.writeFile(tmpPath, JSON.stringify(out, mapReplacer), 'utf-8'); + await fs.rename(tmpPath, cachePath); +}; + +/** + * Drop entries whose hashes are not in `usedHashes`. Called at the end + * of a run so chunks that no longer correspond to any current chunk + * don't keep their stale entries forever. + */ +export const pruneCache = (cache: ParseCache, usedHashes: ReadonlySet): number => { + let removed = 0; + for (const k of cache.entries.keys()) { + if (!usedHashes.has(k)) { + cache.entries.delete(k); + removed++; + } + } + return removed; +}; + +const emptyCache = (): ParseCache => ({ + version: PARSE_CACHE_VERSION, + entries: new Map(), + usedKeys: new Set(), +}); diff --git a/gitnexus/src/storage/repo-manager.ts b/gitnexus/src/storage/repo-manager.ts index 8c0bda95f..44446e0ec 100644 --- a/gitnexus/src/storage/repo-manager.ts +++ b/gitnexus/src/storage/repo-manager.ts @@ -11,6 +11,7 @@ import { realpathSync } from 'fs'; import path from 'path'; import os from 'os'; import { getInferredRepoName, resolveRepoIdentityRoot } from './git.js'; +import { logger } from '../core/logger.js'; /** * Normalise a repo path for registry comparison across platforms @@ -71,8 +72,40 @@ export interface RepoMeta { processes?: number; embeddings?: number; }; + /** + * Bumped whenever incremental-indexing invariants change in an + * incompatible way (delete-and-rewrite logic, subgraph extraction, + * graph-wide node handling). On mismatch, runFullAnalysis forces a + * full rebuild rather than risk an inconsistent incremental update. + */ + schemaVersion?: number; + /** + * SHA-256 of every file's content at the time of the last successful + * indexing run. The next run computes current hashes and diffs against + * this map to determine which files' DB rows must be replaced. + * Map keys are repo-relative paths. + */ + fileHashes?: Record; + /** + * Crash-recovery dirty flag. Written to meta.json BEFORE any + * destructive DB mutation in an incremental run; cleared on success + * by overwriting meta.json. If a run crashes between, the next run + * sees the flag and forces a full rebuild — the cheapest path back + * to a known-good index. + */ + incrementalInProgress?: { + /** When the incremental run started (epoch ms). */ + startedAt: number; + /** Number of files in the writable set, for diagnostic logs. */ + toWriteCount: number; + }; } +/** + * Bumped whenever incremental-indexing invariants change incompatibly. + */ +export const INCREMENTAL_SCHEMA_VERSION = 1; + export interface IndexedRepo { repoPath: string; storagePath: string; @@ -186,12 +219,23 @@ export const loadMeta = async (storagePath: string): Promise => }; /** - * Save metadata to storage + * Save metadata to storage. + * + * Atomic via tmp-file + rename (matches `saveParseCache`'s pattern). The + * `incrementalInProgress` dirty flag travels through this file — a crash + * mid-write would leave a corrupt `meta.json` that the next run's + * `loadMeta` would silently treat as "no prior index", losing the dirty + * flag and skipping the recovery full-rebuild. Write-and-rename rules + * that out: the rename is atomic on POSIX and on Windows (`fs.rename` + * on `node:fs/promises` uses `MoveFileEx(REPLACE_EXISTING)`), so either + * the old or the new file is observed at every moment. */ export const saveMeta = async (storagePath: string, meta: RepoMeta): Promise => { await fs.mkdir(storagePath, { recursive: true }); const metaPath = path.join(storagePath, 'meta.json'); - await fs.writeFile(metaPath, JSON.stringify(meta, null, 2), 'utf-8'); + const tmpPath = `${metaPath}.tmp`; + await fs.writeFile(tmpPath, JSON.stringify(meta, null, 2), 'utf-8'); + await fs.rename(tmpPath, metaPath); }; /** @@ -238,14 +282,44 @@ export const findRepo = async (startPath: string): Promise = return null; }; +function isReadOnlyFilesystemError(err: unknown): boolean { + const code = (err as NodeJS.ErrnoException)?.code; + return code === 'EROFS' || code === 'EACCES' || code === 'EPERM'; +} + /** * Keep generated index files ignored without modifying the user's root .gitignore. */ export const ensureGitNexusIgnored = async (repoPath: string): Promise => { const gitignorePath = path.join(getStoragePath(repoPath), '.gitignore'); + const desired = '*\n'; - await fs.mkdir(path.dirname(gitignorePath), { recursive: true }); - await fs.writeFile(gitignorePath, '*\n', 'utf-8'); + // Idempotent fast path: skip the write entirely when the file already has + // the expected content. Lets this run cleanly on read-only mounts (e.g. + // the documented Docker workflow with WORKSPACE_DIR bound :ro) when an + // earlier `analyze` already created the file. See issue #1549. + try { + if ((await fs.readFile(gitignorePath, 'utf-8')) === desired) { + await ensureGitInfoExclude(repoPath); + return; + } + } catch (err: any) { + if (err?.code !== 'ENOENT') throw err; + } + + try { + await fs.mkdir(path.dirname(gitignorePath), { recursive: true }); + await fs.writeFile(gitignorePath, desired, 'utf-8'); + } catch (err: any) { + if (isReadOnlyFilesystemError(err)) { + logger.warn( + { path: gitignorePath, code: err.code }, + 'GitNexus storage filesystem is not writable; skipping .gitnexus/.gitignore. Generated files may appear as untracked in this repo locally.', + ); + } else { + throw err; + } + } await ensureGitInfoExclude(repoPath); }; @@ -261,8 +335,6 @@ const ensureGitInfoExclude = async (repoPath: string): Promise => { return; } - await fs.mkdir(path.dirname(excludePath), { recursive: true }); - let content = ''; try { content = await fs.readFile(excludePath, 'utf-8'); @@ -277,7 +349,19 @@ const ensureGitInfoExclude = async (repoPath: string): Promise => { if (excludes.includes(GITNEXUS_DIR) || excludes.includes(GITNEXUS_EXCLUDE_ENTRY)) return; const separator = content.length === 0 || content.endsWith('\n') ? '' : '\n'; - await fs.writeFile(excludePath, `${content}${separator}${GITNEXUS_EXCLUDE_ENTRY}\n`, 'utf-8'); + try { + await fs.mkdir(path.dirname(excludePath), { recursive: true }); + await fs.writeFile(excludePath, `${content}${separator}${GITNEXUS_EXCLUDE_ENTRY}\n`, 'utf-8'); + } catch (err: any) { + if (isReadOnlyFilesystemError(err)) { + logger.warn( + { path: excludePath, code: err.code }, + 'GitNexus storage filesystem is not writable; skipping .git/info/exclude update. .gitnexus/ may appear as untracked in `git status` locally.', + ); + } else { + throw err; + } + } }; // ─── Global Registry (~/.gitnexus/registry.json) ─────────────────────── diff --git a/gitnexus/test/fixtures/cross-file-binding/php-consumer-before-provider/app/BProvider.php b/gitnexus/test/fixtures/cross-file-binding/php-consumer-before-provider/app/Models/User.php similarity index 100% rename from gitnexus/test/fixtures/cross-file-binding/php-consumer-before-provider/app/BProvider.php rename to gitnexus/test/fixtures/cross-file-binding/php-consumer-before-provider/app/Models/User.php diff --git a/gitnexus/test/fixtures/lang-resolution/c-static-isolation/a.c b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/a.c new file mode 100644 index 000000000..02a52c42a --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/a.c @@ -0,0 +1,9 @@ +/* a.c — contains a static (file-local) helper function. + * This function must NOT be resolvable from caller.c. */ +static int helper(void) { + return 42; +} + +int public_a(void) { + return helper(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/c-static-isolation/b.c b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/b.c new file mode 100644 index 000000000..231a8e434 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/b.c @@ -0,0 +1,11 @@ +/* b.c — contains a non-static (externally visible) helper function. + * This function SHOULD be resolvable from caller.c. */ +#include "b.h" + +int helper(void) { + return 99; +} + +int public_b(void) { + return helper(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/c-static-isolation/b.h b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/b.h new file mode 100644 index 000000000..bd9b6dd2f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/b.h @@ -0,0 +1,8 @@ +/* b.h — public header for b.c */ +#ifndef B_H +#define B_H + +int helper(void); +int public_b(void); + +#endif diff --git a/gitnexus/test/fixtures/lang-resolution/c-static-isolation/caller.c b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/caller.c new file mode 100644 index 000000000..802e134d9 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-static-isolation/caller.c @@ -0,0 +1,9 @@ +/* caller.c — includes only b.h, calls helper(). + * Should resolve to b.c:helper, NOT a.c:static helper. */ +#include "b.h" + +int main(void) { + int x = helper(); + int y = public_b(); + return x + y; +} diff --git a/gitnexus/test/fixtures/lang-resolution/c-structs/main.c b/gitnexus/test/fixtures/lang-resolution/c-structs/main.c new file mode 100644 index 000000000..334f36b16 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-structs/main.c @@ -0,0 +1,9 @@ +#include "service.h" + +int main(void) { + struct Service *svc = create_service(); + service_add_user(svc, "Alice", 25); + service_add_user(svc, "Bob", 32); + destroy_service(svc); + return 0; +} diff --git a/gitnexus/test/fixtures/lang-resolution/c-structs/service.c b/gitnexus/test/fixtures/lang-resolution/c-structs/service.c new file mode 100644 index 000000000..85c4cdef6 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-structs/service.c @@ -0,0 +1,20 @@ +#include "service.h" +#include + +struct Service *create_service(void) { + struct Service *svc = malloc(sizeof(struct Service)); + svc->admin = create_user("admin", 30); + svc->user_count = 0; + return svc; +} + +void service_add_user(struct Service *svc, const char *name, int age) { + struct User *user = create_user(name, age); + svc->user_count++; + free_user(user); +} + +void destroy_service(struct Service *svc) { + free_user(svc->admin); + free(svc); +} diff --git a/gitnexus/test/fixtures/lang-resolution/c-structs/service.h b/gitnexus/test/fixtures/lang-resolution/c-structs/service.h new file mode 100644 index 000000000..a5056edc7 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-structs/service.h @@ -0,0 +1,15 @@ +#ifndef SERVICE_H +#define SERVICE_H + +#include "user.h" + +struct Service { + struct User *admin; + int user_count; +}; + +struct Service *create_service(void); +void service_add_user(struct Service *svc, const char *name, int age); +void destroy_service(struct Service *svc); + +#endif diff --git a/gitnexus/test/fixtures/lang-resolution/c-structs/user.c b/gitnexus/test/fixtures/lang-resolution/c-structs/user.c new file mode 100644 index 000000000..2f3654913 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-structs/user.c @@ -0,0 +1,18 @@ +#include "user.h" +#include +#include + +struct User *create_user(const char *name, int age) { + struct User *user = malloc(sizeof(struct User)); + strncpy(user->name, name, sizeof(user->name) - 1); + user->age = age; + return user; +} + +void free_user(struct User *user) { + free(user); +} + +int get_user_age(const struct User *user) { + return user->age; +} diff --git a/gitnexus/test/fixtures/lang-resolution/c-structs/user.h b/gitnexus/test/fixtures/lang-resolution/c-structs/user.h new file mode 100644 index 000000000..6e14c2425 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/c-structs/user.h @@ -0,0 +1,13 @@ +#ifndef USER_H +#define USER_H + +struct User { + char name[64]; + int age; +}; + +struct User *create_user(const char *name, int age); +void free_user(struct User *user); +int get_user_age(const struct User *user); + +#endif diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-ambiguous/alpha.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-ambiguous/alpha.h new file mode 100644 index 000000000..c873a3a67 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-ambiguous/alpha.h @@ -0,0 +1,7 @@ +#pragma once + +namespace alpha { + struct Token {}; + void process(Token t, int n); + void process(Token t, long n); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-ambiguous/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-ambiguous/app.cpp new file mode 100644 index 000000000..94c283ac5 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-ambiguous/app.cpp @@ -0,0 +1,8 @@ +#include "alpha.h" + +namespace app { + void run() { + alpha::Token t; + process(t, 42); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-collision/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-collision/app.cpp new file mode 100644 index 000000000..dfde8899f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-collision/app.cpp @@ -0,0 +1,14 @@ +#include "base_lib.h" + +namespace app { + struct Token : base_one::Base {}; + + void run() { + Token t; + collide(t); + } +} + +namespace other { + struct Token : base_two::Base {}; +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-collision/base_lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-collision/base_lib.h new file mode 100644 index 000000000..684f45aeb --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-collision/base_lib.h @@ -0,0 +1,11 @@ +#pragma once + +namespace base_one { + struct Base {}; + void collide(Base); +} + +namespace base_two { + struct Base {}; + void collide(Base); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-negative/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-negative/app.cpp new file mode 100644 index 000000000..fe5185b3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-negative/app.cpp @@ -0,0 +1,16 @@ +#include "base_lib.h" + +namespace app { + struct HiddenDerived : HiddenBase {}; + struct MissingDerived : missing_ns::UnknownBase {}; + + void run_hidden() { + HiddenDerived d; + hidden_probe(d); + } + + void run_missing() { + MissingDerived d; + unresolved_probe(d); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-negative/base_lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-negative/base_lib.h new file mode 100644 index 000000000..64f282ccf --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces-negative/base_lib.h @@ -0,0 +1,6 @@ +#pragma once + +namespace { + struct HiddenBase {}; + void hidden_probe(HiddenBase); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces/app.cpp new file mode 100644 index 000000000..3fc28f632 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces/app.cpp @@ -0,0 +1,22 @@ +#include "base_lib.h" + +namespace app { + struct Derived : base_lib::Base {}; + struct MultiLevel : middle_lib::Mid {}; + struct DiamondDerived : diamond_lib::LeftBranch, diamond_lib::RightBranch {}; + + void run_single() { + Derived d; + log(d); + } + + void run_multi() { + MultiLevel m; + trace(m); + } + + void run_diamond() { + DiamondDerived d; + ping(d); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces/base_lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces/base_lib.h new file mode 100644 index 000000000..c3abf7d44 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-base-associated-namespaces/base_lib.h @@ -0,0 +1,20 @@ +#pragma once + +namespace base_lib { + struct Base {}; + void log(Base); + + struct Root {}; + void trace(Root); +} + +namespace middle_lib { + struct Mid : base_lib::Root {}; +} + +namespace diamond_lib { + struct DiamondBase {}; + struct LeftBranch : DiamondBase {}; + struct RightBranch : DiamondBase {}; + void ping(DiamondBase); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-basic/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-basic/app.cpp new file mode 100644 index 000000000..7fc21a0be --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-basic/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event e; + record(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-basic/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-basic/audit.h new file mode 100644 index 000000000..2c9803a3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-basic/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-block-scope-decl-blocks/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-block-scope-decl-blocks/app.cpp new file mode 100644 index 000000000..16dd2b539 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-block-scope-decl-blocks/app.cpp @@ -0,0 +1,13 @@ +#include "audit.h" + +namespace app { + void run() { + // Block-scope function declaration (not via using-declaration). + // Per ISO C++ [basic.lookup.argdep], this suppresses ADL — even + // though `e` is audit::Event, audit::record should NOT be discovered. + void record(int); + + audit::Event e; + record(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-block-scope-decl-blocks/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-block-scope-decl-blocks/audit.h new file mode 100644 index 000000000..2c9803a3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-block-scope-decl-blocks/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-enum-arg/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-enum-arg/app.cpp new file mode 100644 index 000000000..91d83d5e2 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-enum-arg/app.cpp @@ -0,0 +1,8 @@ +#include "color.h" + +namespace app { + void run() { + color::Channel ch = color::Channel::R; + serialize(ch); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-enum-arg/color.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-enum-arg/color.h new file mode 100644 index 000000000..49136c43a --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-enum-arg/color.h @@ -0,0 +1,6 @@ +#pragma once + +namespace color { + enum class Channel { R, G, B }; + void serialize(Channel c); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref-overloaded/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref-overloaded/app.cpp new file mode 100644 index 000000000..1a51ca699 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref-overloaded/app.cpp @@ -0,0 +1,7 @@ +#include "utils.h" + +namespace caller { + void run() { + with_callback(utils::worker); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref-overloaded/utils.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref-overloaded/utils.h new file mode 100644 index 000000000..53b82ca1e --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref-overloaded/utils.h @@ -0,0 +1,7 @@ +#pragma once + +namespace utils { + void worker(); + void worker(int n); + void with_callback(int n); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref/app.cpp new file mode 100644 index 000000000..1a51ca699 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref/app.cpp @@ -0,0 +1,7 @@ +#include "utils.h" + +namespace caller { + void run() { + with_callback(utils::worker); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref/utils.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref/utils.h new file mode 100644 index 000000000..33467d7ce --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-free-func-ref/utils.h @@ -0,0 +1,6 @@ +#pragma once + +namespace utils { + void worker(); + void with_callback(int n); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-arg/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-arg/app.cpp new file mode 100644 index 000000000..b9f99d201 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-arg/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + void (*g)(); + record(g); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-arg/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-arg/audit.h new file mode 100644 index 000000000..a0283cabc --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-arg/audit.h @@ -0,0 +1,5 @@ +#pragma once + +namespace audit { + void record(void (*g)()); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-before-class-arg/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-before-class-arg/app.cpp new file mode 100644 index 000000000..9e6cfd188 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-before-class-arg/app.cpp @@ -0,0 +1,9 @@ +#include "audit.h" + +namespace app { + void run() { + void (*fp)(); + audit::Event e; + record(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-before-class-arg/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-before-class-arg/audit.h new file mode 100644 index 000000000..2c9803a3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-before-class-arg/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-class-return-arg/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-class-return-arg/app.cpp new file mode 100644 index 000000000..0cf4ee3bb --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-class-return-arg/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event (*factory)(); + record(factory); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-class-return-arg/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-class-return-arg/audit.h new file mode 100644 index 000000000..a2438fe5e --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-function-pointer-class-return-arg/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event (*factory)()); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-hidden-friend/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-hidden-friend/app.cpp new file mode 100644 index 000000000..58849adaf --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-hidden-friend/app.cpp @@ -0,0 +1,8 @@ +#include "lib.h" + +namespace app { + void run() { + lib::Foo f; + process(f); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-hidden-friend/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-hidden-friend/lib.h new file mode 100644 index 000000000..3cc8042b4 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-hidden-friend/lib.h @@ -0,0 +1,7 @@ +#pragma once + +namespace lib { + struct Foo { + friend void process(Foo& f) {} + }; +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-inline-ns-expansion/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inline-ns-expansion/app.cpp new file mode 100644 index 000000000..7fc21a0be --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inline-ns-expansion/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event e; + record(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-inline-ns-expansion/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inline-ns-expansion/audit.h new file mode 100644 index 000000000..dacb11c15 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inline-ns-expansion/audit.h @@ -0,0 +1,13 @@ +#pragma once + +namespace audit { + struct Event {}; + + inline namespace v1 { + void record(Event e); + } +} + +namespace other { + void record(int x); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-inner-callable-outer-noncallable/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inner-callable-outer-noncallable/app.cpp new file mode 100644 index 000000000..4eebdfd2f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inner-callable-outer-noncallable/app.cpp @@ -0,0 +1,21 @@ +#include "data.h" + +// Outer namespace has a non-callable `swap` (variable). +namespace app { + int swap = 0; + + namespace inner { + // Inner namespace re-declares `swap` as a function. + void swap(int, int); + + void run() { + data::Pair a, b; + // Ordinary lookup finds `inner::swap(int,int)` first (callable at + // nearest scope). The outer `app::swap` variable should NOT suppress + // ADL because ordinary lookup stopped at `inner` scope where a + // callable was found. ADL contributes `data::swap(Pair&,Pair&)` which + // wins via argTypes narrowing. + swap(a, b); + } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-inner-callable-outer-noncallable/data.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inner-callable-outer-noncallable/data.h new file mode 100644 index 000000000..129f476b3 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-inner-callable-outer-noncallable/data.h @@ -0,0 +1,6 @@ +#pragma once + +namespace data { + struct Pair {}; + void swap(Pair& a, Pair& b); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-local-fp-shadows-free-func/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-local-fp-shadows-free-func/app.cpp new file mode 100644 index 000000000..1fb977e3b --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-local-fp-shadows-free-func/app.cpp @@ -0,0 +1,13 @@ +#include "audit.h" + +namespace app { + void run() { + // `g` is a locally-declared function-pointer variable. audit::g() also + // exists in the workspace. The local-fp guard (foundAsLocalFunctionPointer) + // must detect `g` as a function-pointer variable declaration and return + // EMPTY_ADL_ARG, preventing the workspace scan that would otherwise find + // audit::g and contribute `audit` to the ADL associated set. + void (*g)(); + record(g); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-local-fp-shadows-free-func/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-local-fp-shadows-free-func/audit.h new file mode 100644 index 000000000..46df335ef --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-local-fp-shadows-free-func/audit.h @@ -0,0 +1,11 @@ +#pragma once + +namespace audit { + // A free function named `g` exists in the workspace. Without the local-fp + // guard, a locally-declared `void (*g)()` variable would fall through to + // EMPTY_ADL_ARG and not be treated as a free-function ref — but this test + // specifically verifies that the local fp variable shadows the workspace + // function of the same name and no namespace is contributed. + void g(); + void record(void (*fn)()); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-merge-nonempty-ordinary/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merge-nonempty-ordinary/app.cpp new file mode 100644 index 000000000..3b3628694 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merge-nonempty-ordinary/app.cpp @@ -0,0 +1,11 @@ +#include "data.h" + +namespace app { + void swap(int a, int b); + + void run() { + data::Pair a; + data::Pair b; + swap(a, b); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-merge-nonempty-ordinary/data.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merge-nonempty-ordinary/data.h new file mode 100644 index 000000000..129f476b3 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merge-nonempty-ordinary/data.h @@ -0,0 +1,6 @@ +#pragma once + +namespace data { + struct Pair {}; + void swap(Pair& a, Pair& b); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-merged-narrow-zero/alpha.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merged-narrow-zero/alpha.h new file mode 100644 index 000000000..84b6fb028 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merged-narrow-zero/alpha.h @@ -0,0 +1,6 @@ +#pragma once + +namespace alpha { + struct Token {}; + void probe(Token t); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-merged-narrow-zero/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merged-narrow-zero/app.cpp new file mode 100644 index 000000000..1c0088054 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-merged-narrow-zero/app.cpp @@ -0,0 +1,8 @@ +#include "alpha.h" + +namespace app { + void run() { + alpha::Token t; + probe(t, 42); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-non-function-blocks/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-non-function-blocks/app.cpp new file mode 100644 index 000000000..8a1e1063f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-non-function-blocks/app.cpp @@ -0,0 +1,10 @@ +#include "audit.h" + +namespace app { + int record = 0; + + void run() { + audit::Event e; + record(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-non-function-blocks/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-non-function-blocks/audit.h new file mode 100644 index 000000000..2c9803a3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-non-function-blocks/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-param-not-free-func-ref/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-param-not-free-func-ref/app.cpp new file mode 100644 index 000000000..be2028739 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-param-not-free-func-ref/app.cpp @@ -0,0 +1,14 @@ +#include "utils.h" + +namespace caller { + // `callback` is a plain int parameter, not a function reference. + // Without the fix: `callback` is not found in the compound_statement + // (parameters live in parameter_list) → lookupAdlIdentifierType returns null + // → treated as free-function ref → workspace scan finds utils::callback + // → `utils` added to ADL set → run_with resolves to utils::run_with (false positive). + // With the fix: isIdentifierAFunctionParameter detects `callback` in the + // parameter_list → returns EMPTY_ADL_ARG → no namespace contributed → 0 CALLS edges. + void run(int callback) { + run_with(callback); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-param-not-free-func-ref/utils.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-param-not-free-func-ref/utils.h new file mode 100644 index 000000000..e25ac913f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-param-not-free-func-ref/utils.h @@ -0,0 +1,10 @@ +#pragma once + +namespace utils { + // A function named `callback` exists in the `utils` namespace. Without the + // parameter-list guard, passing a function *parameter* also named `callback` + // would trigger a workspace scan, find utils::callback, contribute `utils` + // to the ADL set, and emit a false-positive CALLS edge to utils::run_with. + void callback(); + void run_with(int n); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-arg-boundary/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-arg-boundary/app.cpp new file mode 100644 index 000000000..3eff3b66c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-arg-boundary/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event* p; + record(p); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-arg-boundary/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-arg-boundary/audit.h new file mode 100644 index 000000000..ca2c149d2 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-arg-boundary/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event* e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-to-pointer/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-to-pointer/app.cpp new file mode 100644 index 000000000..33508836e --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-to-pointer/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event** pp; + record(pp); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-to-pointer/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-to-pointer/audit.h new file mode 100644 index 000000000..2f719362c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-pointer-to-pointer/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event** e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-qualified-variable-arg/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-qualified-variable-arg/app.cpp new file mode 100644 index 000000000..44dcf8618 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-qualified-variable-arg/app.cpp @@ -0,0 +1,14 @@ +#include "data.h" + +namespace caller { + // data::value is a namespace-qualified VARIABLE, not a function. + // ADL must NOT contribute `data` to the associated namespace set — the + // argument type is `int`, which has no associated namespaces in ISO C++. + // GitNexus guards: collectFunctionRefNamespaces verifies a Function/Method + // named `value` exists in `data` before contributing. Since `data::value` + // is a variable (not a function), `data` is NOT added, and process() is + // not resolved via ADL. + void run() { + process(data::value); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-qualified-variable-arg/data.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-qualified-variable-arg/data.h new file mode 100644 index 000000000..37cfefd9d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-qualified-variable-arg/data.h @@ -0,0 +1,6 @@ +#pragma once + +namespace data { + extern int value; + void process(int n); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/app.cpp new file mode 100644 index 000000000..e32733d9b --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/app.cpp @@ -0,0 +1,21 @@ +#include "audit.h" + +namespace app { + void runRef() { + audit::Event e; + audit::Event& s = e; + record(s); + } + + void runConstRef() { + audit::Event e; + const audit::Event& constEventRef = e; + recordConst(constEventRef); + } + + void runPrimitiveRef() { + int n = 0; + int& r = n; + note(r); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/audit.h new file mode 100644 index 000000000..4b4600381 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/audit.h @@ -0,0 +1,5 @@ +#pragma once + +namespace audit { + struct Event {}; +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/record.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/record.h new file mode 100644 index 000000000..590ac5a87 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-reference-arg-boundary/record.h @@ -0,0 +1,8 @@ +#pragma once + +#include "audit.h" + +namespace audit { + void record(Event& e); + void recordConst(const Event& e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/app.cpp new file mode 100644 index 000000000..8a5f57ba9 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/app.cpp @@ -0,0 +1,9 @@ +#include "audit.h" + +namespace app { + void runRvalueRef() { + audit::Event e; + audit::Event&& rr = static_cast(e); + record(rr); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/audit.h new file mode 100644 index 000000000..4b4600381 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/audit.h @@ -0,0 +1,5 @@ +#pragma once + +namespace audit { + struct Event {}; +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/record-rvalue.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/record-rvalue.h new file mode 100644 index 000000000..ae3cf7462 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-rvalue-ref/record-rvalue.h @@ -0,0 +1,7 @@ +#pragma once + +#include "audit.h" + +namespace audit { + void record(Event&& e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-suppressed-parens/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-suppressed-parens/app.cpp new file mode 100644 index 000000000..64b2c6451 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-suppressed-parens/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event e; + (record)(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-suppressed-parens/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-suppressed-parens/audit.h new file mode 100644 index 000000000..2c9803a3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-suppressed-parens/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-template-args/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-template-args/app.cpp new file mode 100644 index 000000000..5673ee229 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-template-args/app.cpp @@ -0,0 +1,23 @@ +#include "audit.h" + +namespace app { + void run() { + std::vector v; + apply(v); + } + + void runNested() { + std::map> m; + applyNested(m); + } + + void runArray() { + std::array a; + applyArray(a); + } + + void runStdConflict() { + std::vector v; + applyStdConflict(v); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-template-args/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-template-args/audit.h new file mode 100644 index 000000000..e59392f89 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-template-args/audit.h @@ -0,0 +1,19 @@ +#pragma once + +#include +#include +#include +#include + +namespace N { + struct T {}; + + void apply(std::vector v); + void applyNested(std::map> m); + void applyArray(std::array a); + void applyStdConflict(std::vector v); +} + +namespace std { + void applyStdConflict(vector v); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-unqualified-ref-collision/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-adl-unqualified-ref-collision/app.cpp new file mode 100644 index 000000000..7512873f3 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-unqualified-ref-collision/app.cpp @@ -0,0 +1,14 @@ +#include "lib.h" + +namespace caller { + void run() { + // Unqualified `worker` — not in local compound_statement scope → treated + // as a potential free-function reference. The workspace scan finds + // worker() in BOTH alpha and beta namespaces, so BOTH are added to the + // associated set. run_with() exists in both namespaces as well, so the + // lookup yields two candidates (alpha::run_with, beta::run_with). + // Merged-narrowing ambiguity suppression in free-call-fallback emits + // zero CALLS edges rather than picking one arbitrarily. + run_with(worker); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-adl-unqualified-ref-collision/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-adl-unqualified-ref-collision/lib.h new file mode 100644 index 000000000..aa1daa331 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-adl-unqualified-ref-collision/lib.h @@ -0,0 +1,12 @@ +#pragma once + +namespace alpha { + // `worker` exists in both alpha and beta namespaces. + void worker(); + void run_with(void (*fn)()); +} + +namespace beta { + void worker(); + void run_with(void (*fn)()); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-cross-file/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-cross-file/caller.cpp new file mode 100644 index 000000000..d60127bfe --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-cross-file/caller.cpp @@ -0,0 +1,5 @@ +void worker(); + +void run() { + worker(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-cross-file/helper.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-cross-file/helper.cpp new file mode 100644 index 000000000..feeef4747 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-cross-file/helper.cpp @@ -0,0 +1,7 @@ +namespace { + void worker() {} +} + +void helper_entry() { + worker(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-same-file-visible/helper.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-same-file-visible/helper.cpp new file mode 100644 index 000000000..3d992bfe5 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-anon-ns-same-file-visible/helper.cpp @@ -0,0 +1,7 @@ +namespace { + void w() {} +} + +void run() { + w(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-include-no-class-leak/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-class-leak/caller.cpp new file mode 100644 index 000000000..8de016602 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-class-leak/caller.cpp @@ -0,0 +1,5 @@ +#include "user.h" + +void run() { + save(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-include-no-class-leak/user.h b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-class-leak/user.h new file mode 100644 index 000000000..089fa6c59 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-class-leak/user.h @@ -0,0 +1,6 @@ +#pragma once + +class User { +public: + void save(); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-include-no-namespace-leak/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-namespace-leak/caller.cpp new file mode 100644 index 000000000..90b1f2aff --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-namespace-leak/caller.cpp @@ -0,0 +1,5 @@ +#include "lib.h" + +void run() { + foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-include-no-namespace-leak/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-namespace-leak/lib.h new file mode 100644 index 000000000..11f71286f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-include-no-namespace-leak/lib.h @@ -0,0 +1,5 @@ +#pragma once + +namespace ns { + void foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-adl-participation/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-adl-participation/app.cpp new file mode 100644 index 000000000..7fc21a0be --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-adl-participation/app.cpp @@ -0,0 +1,8 @@ +#include "audit.h" + +namespace app { + void run() { + audit::Event e; + record(e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-adl-participation/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-adl-participation/audit.h new file mode 100644 index 000000000..9d657461a --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-adl-participation/audit.h @@ -0,0 +1,8 @@ +#pragma once + +namespace audit { + inline namespace v1 { + struct Event {}; + void record(Event e); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous-diff-sigs/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous-diff-sigs/caller.cpp new file mode 100644 index 000000000..fcb416b39 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous-diff-sigs/caller.cpp @@ -0,0 +1,5 @@ +#include "lib.h" + +void run() { + outer::foo(42); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous-diff-sigs/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous-diff-sigs/lib.h new file mode 100644 index 000000000..c0ebbdfac --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous-diff-sigs/lib.h @@ -0,0 +1,10 @@ +#pragma once + +namespace outer { + inline namespace v1 { + void foo(int x); + } + inline namespace v2 { + void foo(double y); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous/caller.cpp new file mode 100644 index 000000000..f2aa44454 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous/caller.cpp @@ -0,0 +1,5 @@ +#include "lib.h" + +void run() { + outer::foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous/lib.h new file mode 100644 index 000000000..54bfb229d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-ambiguous/lib.h @@ -0,0 +1,10 @@ +#pragma once + +namespace outer { + inline namespace v1 { + void foo(); + } + inline namespace v2 { + void foo(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-nested/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-nested/caller.cpp new file mode 100644 index 000000000..f2aa44454 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-nested/caller.cpp @@ -0,0 +1,5 @@ +#include "lib.h" + +void run() { + outer::foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-nested/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-nested/lib.h new file mode 100644 index 000000000..ba85f2aed --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-nested/lib.h @@ -0,0 +1,9 @@ +#pragma once + +namespace outer { + inline namespace v1 { + inline namespace experimental { + void foo(); + } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-unqualified/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-unqualified/caller.cpp new file mode 100644 index 000000000..f2aa44454 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-unqualified/caller.cpp @@ -0,0 +1,5 @@ +#include "lib.h" + +void run() { + outer::foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-unqualified/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-unqualified/lib.h new file mode 100644 index 000000000..e0ffb1eca --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-unqualified/lib.h @@ -0,0 +1,7 @@ +#pragma once + +namespace outer { + inline namespace v1 { + void foo(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-versioned/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-versioned/caller.cpp new file mode 100644 index 000000000..f2aa44454 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-versioned/caller.cpp @@ -0,0 +1,5 @@ +#include "lib.h" + +void run() { + outer::foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-versioned/lib.h b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-versioned/lib.h new file mode 100644 index 000000000..0ff3e61b3 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-inline-namespace-versioned/lib.h @@ -0,0 +1,10 @@ +#pragma once + +namespace outer { + inline namespace v1 { + void foo(); + } + namespace v0 { + void foo(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-namespace-qualified-not-super/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-namespace-qualified-not-super/caller.cpp new file mode 100644 index 000000000..d1edc41c4 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-namespace-qualified-not-super/caller.cpp @@ -0,0 +1,5 @@ +#include "singleton.h" + +void run() { + Singleton::getInstance(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-namespace-qualified-not-super/singleton.h b/gitnexus/test/fixtures/lang-resolution/cpp-namespace-qualified-not-super/singleton.h new file mode 100644 index 000000000..aa2e255e6 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-namespace-qualified-not-super/singleton.h @@ -0,0 +1,6 @@ +#pragma once + +class Singleton { +public: + static Singleton* getInstance(); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/caller.cpp new file mode 100644 index 000000000..2c4ee7f29 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/caller.cpp @@ -0,0 +1,6 @@ +#include "service.h" + +void run() { + S s; + s.f(1); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/service.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/service.cpp new file mode 100644 index 000000000..cd6f080e5 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/service.cpp @@ -0,0 +1,4 @@ +#include "service.h" + +void S::f(int) {} +void S::f(int, int) {} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/service.h b/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/service.h new file mode 100644 index 000000000..66ad00371 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-overload-default-arg-ambiguous/service.h @@ -0,0 +1,7 @@ +#pragma once + +class S { +public: + void f(int); + void f(int, int = 0); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/caller.cpp new file mode 100644 index 000000000..89e62ead1 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/caller.cpp @@ -0,0 +1,6 @@ +#include "service.h" + +void run() { + Service s; + s.process(42); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/service.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/service.cpp new file mode 100644 index 000000000..9bde80f6f --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/service.cpp @@ -0,0 +1,4 @@ +#include "service.h" + +void Service::process(int x) {} +void Service::process(long x) {} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/service.h b/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/service.h new file mode 100644 index 000000000..1e4c5de07 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-overload-int-long/service.h @@ -0,0 +1,7 @@ +#pragma once + +class Service { +public: + void process(int x); + void process(long x); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-qualified-base-call/classes.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-qualified-base-call/classes.h new file mode 100644 index 000000000..1d53b7dfa --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-qualified-base-call/classes.h @@ -0,0 +1,13 @@ +#pragma once + +template +struct Base { + void method(); +}; + +template +struct Derived : Base { + void g() { + Base::method(); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-template-multi-base-list/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-template-multi-base-list/base.h new file mode 100644 index 000000000..30b2f5bd6 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-template-multi-base-list/base.h @@ -0,0 +1,7 @@ +#pragma once + +template +struct A {}; + +template +struct B {}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-template-multi-base-list/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-template-multi-base-list/derived.h new file mode 100644 index 000000000..7fe417b6a --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-template-multi-base-list/derived.h @@ -0,0 +1,6 @@ +#pragma once + +#include "base.h" + +template +struct Derived : A, B {}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-u5-qualified-inline-base-call/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-u5-qualified-inline-base-call/base.h new file mode 100644 index 000000000..de3e84def --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-u5-qualified-inline-base-call/base.h @@ -0,0 +1,12 @@ +#pragma once + +namespace outer { + inline namespace v1 { + template + struct Base { + void f(); + }; + + void free_fn(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-u5-qualified-inline-base-call/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-u5-qualified-inline-base-call/derived.h new file mode 100644 index 000000000..2ff5523a1 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u1-u3-u5-qualified-inline-base-call/derived.h @@ -0,0 +1,11 @@ +#pragma once + +#include "base.h" + +template +struct Derived : outer::v1::Base { + void g() { + outer::v1::Base::f(); + outer::v1::free_fn(); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/audit.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/audit.h new file mode 100644 index 000000000..2c9803a3d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/audit.h @@ -0,0 +1,6 @@ +#pragma once + +namespace audit { + struct Event {}; + void record(Event e); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/base.h new file mode 100644 index 000000000..ccbe5b670 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/base.h @@ -0,0 +1,8 @@ +#pragma once + +#include "audit.h" + +template +struct Base { + void record(audit::Event e); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/derived.h new file mode 100644 index 000000000..ca37c8109 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u2-u3-adl-from-derived/derived.h @@ -0,0 +1,11 @@ +#pragma once + +#include "base.h" + +template +struct Derived : Base { + void g() { + audit::Event e; + record(e); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u3-u5-inline-base/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u3-u5-inline-base/base.h new file mode 100644 index 000000000..e9711ff08 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u3-u5-inline-base/base.h @@ -0,0 +1,10 @@ +#pragma once + +namespace outer { + inline namespace v1 { + template + struct Base { + void f(); + }; + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u3-u5-inline-base/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u3-u5-inline-base/derived.h new file mode 100644 index 000000000..b18febac8 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-phase5-u3-u5-inline-base/derived.h @@ -0,0 +1,10 @@ +#pragma once + +#include "base.h" + +template +struct Derived : outer::v1::Base { + void g() { + f(); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/app.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/app.cpp new file mode 100644 index 000000000..237ce1cae --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/app.cpp @@ -0,0 +1,7 @@ +#include "list_user.h" +#include "list_order.h" + +void callUserSave() { + List list; + list.save(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/list_order.h b/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/list_order.h new file mode 100644 index 000000000..015a16b5b --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/list_order.h @@ -0,0 +1,14 @@ +#pragma once + +struct Order {}; + +template +class List; + +template <> +class List { +public: + void callSave() { save(); } + void save() { persistOrder(); } + void persistOrder() {} +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/list_user.h b/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/list_user.h new file mode 100644 index 000000000..d9ba7fb24 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-template-specialization-disambiguation/list_user.h @@ -0,0 +1,14 @@ +#pragma once + +struct User {}; + +template +class List; + +template <> +class List { +public: + void callSave() { save(); } + void save() { persistUser(); } + void persistUser() {} +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base-ns/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base-ns/base.h new file mode 100644 index 000000000..c9ecf5c22 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base-ns/base.h @@ -0,0 +1,19 @@ +#pragma once + +namespace geom { + +template +struct Base { + void compute(); + int area; +}; + +// Free function inside the same namespace — no ownerId, so the +// class-owned filter does NOT apply to this candidate. It is instead +// suppressed by the namespace-nesting filter (isCppDefGloballyVisible). +// The test therefore exercises a candidate path that is orthogonal to +// the class-owned filter, proving the overall suppression stack is +// robust even when ownerId-based blocking is absent. +void compute(); + +} // namespace geom diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base-ns/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base-ns/derived.h new file mode 100644 index 000000000..9596bcc81 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base-ns/derived.h @@ -0,0 +1,21 @@ +#pragma once + +#include "base.h" + +namespace geom { + +template +struct Derived : Base { + // Unqualified call to compute() inside a template body whose base is + // dependent. Two-phase lookup: the compiler does NOT look into + // Base for this name — so GitNexus must also suppress the edge. + void g() { + compute(); + } + // Unqualified field access — same reasoning applies. + int h() { + return area; + } +}; + +} // namespace geom diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base/base.h new file mode 100644 index 000000000..1c7084ee6 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base/base.h @@ -0,0 +1,7 @@ +#pragma once + +template +struct Base { + void f(); + int i; +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base/derived.h new file mode 100644 index 000000000..fc66c6725 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-dependent-base/derived.h @@ -0,0 +1,13 @@ +#pragma once + +#include "base.h" + +template +struct Derived : Base { + void g() { + f(); + } + int h() { + return i; + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/base.h new file mode 100644 index 000000000..2b7804ba4 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/base.h @@ -0,0 +1,6 @@ +#pragma once + +template +struct Base { + void unused(); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/derived.h new file mode 100644 index 000000000..e3ea61977 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/derived.h @@ -0,0 +1,14 @@ +#pragma once + +#include "base.h" +#include "helpers.h" + +using utils::ns_helper_2; + +template +struct D : Base { + void g() { + utils::ns_helper(); + ns_helper_2(); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/helpers.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/helpers.h new file mode 100644 index 000000000..4bd7a9833 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-namespace-free-call-inside-template/helpers.h @@ -0,0 +1,6 @@ +#pragma once + +namespace utils { + void ns_helper(); + void ns_helper_2(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-non-dependent-base/concrete-base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-non-dependent-base/concrete-base.h new file mode 100644 index 000000000..7b5d1a167 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-non-dependent-base/concrete-base.h @@ -0,0 +1,5 @@ +#pragma once + +struct ConcreteBase { + void f(); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-non-dependent-base/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-non-dependent-base/derived.h new file mode 100644 index 000000000..e0db6269c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-non-dependent-base/derived.h @@ -0,0 +1,10 @@ +#pragma once + +#include "concrete-base.h" + +template +struct Derived : ConcreteBase { + void g() { + f(); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-paired/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-paired/base.h new file mode 100644 index 000000000..84bc1a954 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-paired/base.h @@ -0,0 +1,6 @@ +#pragma once + +template +struct Base { + void f(); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-paired/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-paired/derived.h new file mode 100644 index 000000000..c7cc1a53b --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-paired/derived.h @@ -0,0 +1,14 @@ +#pragma once + +#include "base.h" + +template +struct Derived : Base { + void g_unqualified() { + f(); + } + + void g_this() { + this->f(); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-name-hiding-arity/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-name-hiding-arity/base.h new file mode 100644 index 000000000..84bc1a954 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-name-hiding-arity/base.h @@ -0,0 +1,6 @@ +#pragma once + +template +struct Base { + void f(); +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-name-hiding-arity/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-name-hiding-arity/derived.h new file mode 100644 index 000000000..ad867e820 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-name-hiding-arity/derived.h @@ -0,0 +1,16 @@ +#pragma once + +#include "base.h" + +template +struct Derived : Base { + void f(int); + + void g() { + this->f(); + } + + void g_ok() { + this->f(42); + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-qualified/base.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-qualified/base.h new file mode 100644 index 000000000..286f877a1 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-qualified/base.h @@ -0,0 +1,8 @@ +#pragma once + +template +struct Base { + void f(); + void base_method(); + int i; +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-qualified/derived.h b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-qualified/derived.h new file mode 100644 index 000000000..9b154a429 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-two-phase-this-qualified/derived.h @@ -0,0 +1,16 @@ +#pragma once + +#include "base.h" + +template +struct Derived : Base { + void g() { + this->f(); + } + void k() { + this->base_method(); + } + int h() { + return this->i; + } +}; diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/a.h b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/a.h new file mode 100644 index 000000000..c02e1e19c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/a.h @@ -0,0 +1,5 @@ +#pragma once + +namespace a { + void foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/b.h b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/b.h new file mode 100644 index 000000000..67b75dd79 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/b.h @@ -0,0 +1,5 @@ +#pragma once + +namespace b { + void foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/caller.cpp new file mode 100644 index 000000000..37270861c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-conflict/caller.cpp @@ -0,0 +1,9 @@ +#include "a.h" +#include "b.h" + +using namespace a; +using namespace b; + +void run() { + foo(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/caller.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/caller.cpp new file mode 100644 index 000000000..56737c424 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/caller.cpp @@ -0,0 +1,9 @@ +#include "std-shim.h" + +using namespace std; + +void project_helper(); + +void run() { + project_helper(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/helper.cpp b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/helper.cpp new file mode 100644 index 000000000..010ffb083 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/helper.cpp @@ -0,0 +1 @@ +void project_helper() {} diff --git a/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/std-shim.h b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/std-shim.h new file mode 100644 index 000000000..6055204c6 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/cpp-using-namespace-std-smoke/std-shim.h @@ -0,0 +1,13 @@ +#pragma once + +// Fixture-local std-shaped namespace. Captures the wildcard-leak shape +// without depending on real system-header modeling. The names mirror +// common STL identifiers (cout_write, println) so a regression that +// re-introduces unqualified std:: binding shows up in the assertions +// below — without us having to control whether GitNexus parses real +// system headers. + +namespace std { + void cout_write(); + void println(); +} diff --git a/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/app/Main.java b/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/app/Main.java index e32e3c07e..88c3b71ac 100644 --- a/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/app/Main.java +++ b/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/app/Main.java @@ -1,10 +1,25 @@ package com.example.app; import com.example.util.Logger; +import com.example.util.Formatter; public class Main { public void run() { Logger logger = new Logger(); logger.record("hello", "world", "test"); + + Formatter fmt = new Formatter(); + // 2-arg call: satisfies fixed prefix (level) + 1 vararg + fmt.format(1, "hello"); + // 3-arg call: satisfies fixed prefix (level) + 2 varargs + fmt.format(2, "hello", "world"); + } + + public void badCall() { + Formatter fmt = new Formatter(); + // 0-arg call: does NOT satisfy the required fixed prefix (int level) + // This should be rejected by arity — no CALLS edge to format + fmt.format(); } } + diff --git a/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/util/Formatter.java b/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/util/Formatter.java new file mode 100644 index 000000000..6884acf16 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/java-variadic-resolution/com/example/util/Formatter.java @@ -0,0 +1,8 @@ +package com.example.util; + +public class Formatter { + /** Varargs with a required fixed prefix — 0-arg calls should be rejected. */ + public void format(int level, String... args) { + for (String a : args) System.out.println(level + ": " + a); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/app/Main.java b/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/app/Main.java new file mode 100644 index 000000000..bb4d88597 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/app/Main.java @@ -0,0 +1,10 @@ +package com.example.app; + +import com.example.models.*; + +public class Main { + public void run() { + User user = new User(); + user.save(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/Order.java b/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/Order.java new file mode 100644 index 000000000..2804c749e --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/Order.java @@ -0,0 +1,7 @@ +package com.example.models; + +public class Order { + public void submit() { + System.out.println("submitting order"); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/User.java b/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/User.java new file mode 100644 index 000000000..910f44884 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/User.java @@ -0,0 +1,7 @@ +package com.example.models; + +public class User { + public void save() { + System.out.println("saving user"); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-calls/app/Services/UserService.php b/gitnexus/test/fixtures/lang-resolution/php-calls/app/Services/UserService.php index fa0a1b8be..882e12d64 100644 --- a/gitnexus/test/fixtures/lang-resolution/php-calls/app/Services/UserService.php +++ b/gitnexus/test/fixtures/lang-resolution/php-calls/app/Services/UserService.php @@ -2,10 +2,13 @@ namespace App\Services; -use function App\Utils\OneArg\log; -use function App\Utils\ZeroArg\log as zero_log; +use function App\Utils\OneArg\write_audit; +use function App\Utils\ZeroArg\write_audit as zero_write_audit; function create_user(): string { + // Two visible write_audit candidates (different arities). Arity narrowing + // must pick the 1-arg OneArg version. This validates that visibility + + // arity together correctly disambiguate. return write_audit('hello'); } diff --git a/gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Dynamic.php b/gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Dynamic.php new file mode 100644 index 000000000..4904f3c24 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Dynamic.php @@ -0,0 +1,113 @@ +$method() — dynamic method name via variable_name node. + // Query pattern requires `name: (name)` so this is not captured. + $method = 'dynamicProcess'; + $obj->$method(); + } + + public function memberCallBraceDynamicName(Targets $obj): void + { + // $obj->{$method}() — brace-syntax variant of the above. + $method = 'dynamicBrace'; + $obj->{$method}(); + } + + public function scopedCallDynamicMethodName(): void + { + // ClassName::$method() — dynamic method name on static dispatch. + $method = 'dynamicHandle'; + Targets::$method(); + } + + public function scopedCallVariableClassNameStaticMethod($className): void + { + // $className::method() — class-name is an untyped parameter (no + // type hint, no string-literal assignment that could be picked up + // by a future type-binding heuristic). Receiver IS captured but + // resolution falls through because $className has no class type + // binding in scope. The unresolved-receiver fallback also doesn't + // fire because `dynamicStaticMethod` is unique workspace-wide AND + // exact-arity narrowing in U4 would still match — meaning the + // ONLY thing keeping the edge count at zero today is the absence + // of any type binding for the receiver. + $className::dynamicStaticMethod(); + } + + public function scopedCallDynamicClassAndMethodName(): void + { + // $className::$method() — both dynamic. + $className = 'App\\Services\\Targets'; + $method = 'dynamicScopedDynName'; + $className::$method(); + } + + public function callUserFuncVariableCallable($callable): void + { + // call_user_func($callable, ...) — resolver is structural-only + // and never inspects argument values to infer the callable. + // The literal `call_user_func` itself is an unresolved built-in. + call_user_func($callable); + } + + public function callUserFuncArrayVariable($callable, $args): void + { + // call_user_func_array($callable, $args) — unknown-arity variant. + call_user_func_array($callable, $args); + } + + public function callUserFuncStringCallable(): void + { + // 'Class::method' string-callable form — argument is a string + // literal, never reaches the function: child of function_call_expression. + call_user_func('App\\Services\\Targets::dynamicCallableMethod'); + } + + public function callUserFuncArrayObjectCallable(Targets $obj): void + { + // [$obj, 'method'] array-callable form — array is an argument + // value, not the function: child. + call_user_func([$obj, 'dynamicArrayCallableMethod']); + } + + public function callUserFuncArrayClassNameCallable(): void + { + // ['Class', 'method'] array-callable with class-name string. + call_user_func(['App\\Services\\Targets', 'dynamicArrayClassCallableMethod']); + } + + public function dynamicPropertyRead(Targets $obj): string + { + // $obj->$prop — dynamic property read. No read-access property + // capture pattern exists in query.ts at all (Finding 2). + $prop = 'dynamicProp'; + return $obj->$prop; + } + + public function sanityStaticCall(Targets $obj): void + { + // The fixture's deliberate sanity-check call. THIS one DOES emit + // a CALLS edge — if the assertion that this edge exists ever + // fails, the test infra is broken, not the dynamic-dispatch + // suppression. Without this, every zero-edge assertion above + // would pass even if the pipeline never emitted any edges at all. + $obj->sanityStaticallyNamedTarget(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/OtherTargets.php b/gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/OtherTargets.php new file mode 100644 index 000000000..c8b70a20d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/OtherTargets.php @@ -0,0 +1,16 @@ +record()` MUST resolve to app/Other/User.php::record, +// NOT app/Models/User.php::record. The `saveLocal` method exercises the +// simple-name path as a control — `User` here is the imported App\Models\User. +class Service { + public function save(\App\Other\User $u): void { + $u->record(); + } + + public function saveLocal(User $u): void { + $u->record(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/composer.json b/gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/composer.json new file mode 100644 index 000000000..386b0bd2d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/composer.json @@ -0,0 +1,7 @@ +{ + "autoload": { + "psr-4": { + "App\\": "app/" + } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ChildModel.php b/gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ChildModel.php new file mode 100644 index 000000000..0dff935c9 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ChildModel.php @@ -0,0 +1,10 @@ + hits Case 2 (findClassBindingInScope) in + // receiver-bound-calls.ts. + // Pre-fix bug: MRO walk emits a false CALLS edge to ParentModel::method + // because Case 2 used `continue` on arity mismatch and fell through. + // Post-fix: zero edges (PHP throws ArgumentCountError at runtime). + ChildModel::method(1); + } + + public function callCompatible(): void + { + // Happy path: ChildModel::compat takes 1 arg; matches call site. + ChildModel::compat(1); + } + + public function callNoParent(): void + { + // Orphan::method takes 2 args; called with 1; no parent class exists. + // Pre-fix: same Case 2 bug — the loop exhausts with memberDef cleared, + // BUT with `continue` the loop simply ends after one iteration since + // the chain has only one entry; no edge would have been emitted here + // even pre-fix. Post-fix: same — zero edges. Documents the boundary. + Orphan::method(1); + } + + public function callMostDerivedHappy(): void + { + // Happy path: ChildModel::method takes 2 args; matches call site. + ChildModel::method(1, 2); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/composer.json b/gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/composer.json new file mode 100644 index 000000000..60ede80e5 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/composer.json @@ -0,0 +1,5 @@ +{ + "autoload": { + "psr-4": { "App\\": "app/" } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/composer.json b/gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/composer.json new file mode 100644 index 000000000..3675b0d1c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/composer.json @@ -0,0 +1,8 @@ +{ + "autoload": { + "psr-4": { + "App\\": "src/App/", + "Vendor\\": "src/Vendor/" + } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Caller.php b/gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Caller.php new file mode 100644 index 000000000..6fecabb3c --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Caller.php @@ -0,0 +1,19 @@ +record(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/composer.json b/gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/composer.json new file mode 100644 index 000000000..386b0bd2d --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/composer.json @@ -0,0 +1,7 @@ +{ + "autoload": { + "psr-4": { + "App\\": "app/" + } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Models/Consumer.php b/gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Models/Consumer.php new file mode 100644 index 000000000..86d330173 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Models/Consumer.php @@ -0,0 +1,20 @@ +aMethod(); + } + + public function callDepthTwo(): string { + return $this->bMethod(); + } + + public function callDepthThree(): string { + return $this->deepMethod(); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitA.php b/gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitA.php new file mode 100644 index 000000000..4408b8dfb --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitA.php @@ -0,0 +1,10 @@ += required → edge emitted + * - variadic candidate, argCount < required → NO edge + */ +class Caller +{ + public function callHappyPath($h): void + { + // happyPath(): min=0. argCount=0 → exact match. Edge. + $h->happyPath(); + } + + public function callDefaultExactRequired($h): void + { + // withDefault($a, $b=0): min=1. argCount=1 === min → exact match. Edge. + $h->withDefault('a'); + } + + public function callDefaultBeyondRequired($h): void + { + // withDefault($a, $b=0): min=1, max=2. argCount=2 > min. + // Pre-fix: first-stage narrow accepts (2 <= 2), edge emitted. + // Post-fix: exact-required gate rejects (2 !== 1), no edge. + $h->withDefault('a', 99); + } + + public function callVariadicAtRequired($h): void + { + // variadicLog($level, ...$args): min=1, hasVarArgs. + // argCount=1 === min → edge emitted (variadic relaxed path). + $h->variadicLog('info'); + } + + public function callVariadicBeyondRequired($h): void + { + // variadicLog($level, ...$args): min=1, hasVarArgs. + // argCount=2 > min, variadic → edge emitted. + $h->variadicLog('info', 'arg1'); + } + + public function callVariadicBelowRequired($h): void + { + // variadicLogTwoRequired($a, $b, ...$rest): min=2, hasVarArgs. + // argCount=1 < min → no edge (first-stage rejects). Both pre/post-fix. + $h->variadicLogTwoRequired('only-one'); + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/composer.json b/gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/composer.json new file mode 100644 index 000000000..60ede80e5 --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/composer.json @@ -0,0 +1,5 @@ +{ + "autoload": { + "psr-4": { "App\\": "app/" } + } +} diff --git a/gitnexus/test/fixtures/lang-resolution/php-variadic-arity-minimum/app/Services/Caller.php b/gitnexus/test/fixtures/lang-resolution/php-variadic-arity-minimum/app/Services/Caller.php new file mode 100644 index 000000000..1da29a43a --- /dev/null +++ b/gitnexus/test/fixtures/lang-resolution/php-variadic-arity-minimum/app/Services/Caller.php @@ -0,0 +1,30 @@ +32 767-char inputs through extractors, + * chunkers, or any parse caller need to assert the call routed through + * `parseSourceSafe` rather than `parser.parse(string, ...)` directly. A + * direct call SIGSEGVs on Windows for inputs that size; on Linux/macOS it + * succeeds, so a "no throw" assertion alone silently passes with the + * bypass reintroduced. The spy assertion is what actually catches the + * regression. + * + * Why the test still has to call `vi.mock` with a literal path: vitest's + * hoister static-analyzes the first argument of `vi.mock`, and the path + * varies by directory depth across test files. Everything else — the + * `vi.importActual` round-trip, the spy installation, and the merged + * module shape — lives here. + * + * Why the test still has to dynamic-`import()` this helper inside the + * `vi.mock` factory: `vi.mock` is hoisted above static imports, so the + * factory closure cannot reference statically-imported helpers (they are + * uninitialized at hoist time). The factory body, however, is async and + * runs only when the mocked module is first consumed — by which point + * the helper resolves cleanly via dynamic `import()`. + * + * Usage: + * + * const { parseSourceSafeSpy } = vi.hoisted(() => ({ parseSourceSafeSpy: vi.fn() })); + * + * vi.mock('../../../src/core/tree-sitter/safe-parse.js', async () => { + * const { buildSafeParseMock } = await import('../../helpers/parse-source-safe-mock.js'); + * return buildSafeParseMock(parseSourceSafeSpy); + * }); + * + * it('routes large input through parseSourceSafe', async () => { + * parseSourceSafeSpy.mockClear(); + * // ... call extractor with >40 000-char input ... + * expect(parseSourceSafeSpy).toHaveBeenCalled(); + * }); + */ +export async function buildSafeParseMock( + spy: ReturnType, +): Promise { + const actual = await vi.importActual( + '../../src/core/tree-sitter/safe-parse.js', + ); + spy.mockImplementation(actual.parseSourceSafe); + return { ...actual, parseSourceSafe: spy }; +} diff --git a/gitnexus/test/integration/augmentation.test.ts b/gitnexus/test/integration/augmentation.test.ts index aed09d61f..60c4170fd 100644 --- a/gitnexus/test/integration/augmentation.test.ts +++ b/gitnexus/test/integration/augmentation.test.ts @@ -57,6 +57,7 @@ vi.mock('../../src/storage/repo-manager.js', () => ({ })); let augment: (pattern: string, cwd?: string) => Promise; +let augmentNoFts: (pattern: string, cwd?: string) => Promise; withTestLbugDB( 'augment', @@ -106,6 +107,28 @@ withTestLbugDB( const result = await augment('日本語テスト', handle.dbPath); expect(typeof result).toBe('string'); }); + + // ─── Negative-safety: fallback must stay gated on !ftsAvailable ─── + // + // When FTS is available but happens to return zero BM25 hits, the + // CONTAINS fallback must NOT fire — preserving the original early-return + // semantics. If anyone later loosens the gate to `symbolMatches.length + // === 0` alone, this test fails. + + it('does NOT fire CONTAINS fallback when FTS is available but BM25 returns empty', async () => { + const bm25 = await import('../../src/core/search/bm25-index.js'); + const spy = vi + .spyOn(bm25, 'searchFTSFromLbug') + .mockResolvedValue({ results: [], ftsAvailable: true }); + try { + // 'login' WOULD match a graph node via CONTAINS, but FTS is available + // and empty → fallback gate must hold → result must be ''. + const result = await augment('login', handle.dbPath); + expect(result).toBe(''); + } finally { + spy.mockRestore(); + } + }); }); }, { @@ -131,3 +154,65 @@ withTestLbugDB( }, }, ); + +// ─── FTS-unavailable suite: exercises the CONTAINS fallback branch ──────────── +// +// No ftsIndexes → searchFTSFromLbug returns ftsAvailable: false → fallback fires. +// Same seed data so 'login' still exists as a graph node. + +withTestLbugDB( + 'augment-no-fts', + (handle) => { + describe('augment() — FTS indexes unavailable (CONTAINS fallback)', () => { + it('falls back to CONTAINS query and returns enrichment when FTS is unavailable', async () => { + const result = await augmentNoFts('login', handle.dbPath); + + expect(result.length).toBeGreaterThan(0); + expect(result).toContain('[GitNexus]'); + }); + + it("returns empty string for whitespace-only pattern (CONTAINS '' guard)", async () => { + const result = await augmentNoFts(' ', handle.dbPath); + expect(result).toBe(''); + }); + + it('returns empty string when no nodes match the CONTAINS query', async () => { + const result = await augmentNoFts('nxyz_notfound', handle.dbPath); + expect(result).toBe(''); + }); + + it('returns empty string when fallback CONTAINS query throws', async () => { + const poolAdapter = await import('../../src/core/lbug/pool-adapter.js'); + const spy = vi + .spyOn(poolAdapter, 'executeQuery') + .mockRejectedValue(new Error('simulated DB error')); + try { + const result = await augmentNoFts('login', handle.dbPath); + expect(result).toBe(''); + } finally { + spy.mockRestore(); + } + }); + }); + }, + { + seed: AUGMENT_SEED_DATA, + // Intentionally no ftsIndexes — forces searchFTSFromLbug to return ftsAvailable: false + poolAdapter: true, + afterSetup: async (handle) => { + const { listRegisteredRepos } = await import('../../src/storage/repo-manager.js'); + (listRegisteredRepos as ReturnType).mockResolvedValue([ + { + name: handle.repoId, + path: handle.dbPath, + storagePath: handle.tmpHandle.dbPath, + indexedAt: new Date().toISOString(), + lastCommit: 'abc123', + }, + ]); + + const engine = await import('../../src/core/augmentation/engine.js'); + augmentNoFts = engine.augment; + }, + }, +); diff --git a/gitnexus/test/integration/cli-e2e.test.ts b/gitnexus/test/integration/cli-e2e.test.ts index 8037511bf..99e52c330 100644 --- a/gitnexus/test/integration/cli-e2e.test.ts +++ b/gitnexus/test/integration/cli-e2e.test.ts @@ -36,6 +36,7 @@ const FIXTURE_SRC = path.resolve(testDir, '..', 'fixtures', 'mini-repo'); // still works), `afterAll` rms the parent tmpdir. let MINI_REPO: string; let tmpParent: string; +let suiteGitnexusHome: string; // Absolute file:// URL to tsx loader — needed when spawning CLI with cwd // outside the project tree (bare 'tsx' specifier won't resolve there). @@ -49,6 +50,7 @@ beforeAll(() => { // Copy the fixture into an isolated tmpdir named `mini-repo` so that the // `--repo mini-repo` CLI arg (which matches by basename) still works. tmpParent = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-cli-e2e-')); + suiteGitnexusHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-cli-e2e-home-')); MINI_REPO = path.join(tmpParent, 'mini-repo'); fs.cpSync(FIXTURE_SRC, MINI_REPO, { recursive: true }); @@ -75,21 +77,30 @@ afterAll(() => { if (tmpParent) { fs.rmSync(tmpParent, { recursive: true, force: true }); } + if (suiteGitnexusHome) { + fs.rmSync(suiteGitnexusHome, { recursive: true, force: true }); + } }); +function cliEnv(extraEnv: Record = {}) { + return { + ...process.env, + GITNEXUS_HOME: suiteGitnexusHome, + // Pre-set --max-old-space-size so analyzeCommand's ensureHeap() sees it + // and skips the re-exec. The re-exec drops the tsx loader (--import tsx + // is not in process.argv), causing ERR_UNKNOWN_FILE_EXTENSION on .ts files. + NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), + ...extraEnv, + }; +} + function runCli(command: string, cwd: string, timeoutMs = 15000) { return spawnSync(process.execPath, ['--import', tsxImportUrl, cliEntry, command], { cwd, encoding: 'utf8', timeout: timeoutMs, stdio: ['pipe', 'pipe', 'pipe'], - env: { - ...process.env, - // Pre-set --max-old-space-size so analyzeCommand's ensureHeap() sees it - // and skips the re-exec. The re-exec drops the tsx loader (--import tsx - // is not in process.argv), causing ERR_UNKNOWN_FILE_EXTENSION on .ts files. - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - }, + env: cliEnv(), }); } @@ -103,10 +114,7 @@ function runCliRaw(extraArgs: string[], cwd: string, timeoutMs = 15000) { encoding: 'utf8', timeout: timeoutMs, stdio: ['pipe', 'pipe', 'pipe'], - env: { - ...process.env, - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - }, + env: cliEnv(), }); } @@ -126,11 +134,7 @@ function runCliWithEnv( encoding: 'utf8', timeout: timeoutMs, stdio: ['pipe', 'pipe', 'pipe'], - env: { - ...process.env, - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - ...extraEnv, - }, + env: cliEnv(extraEnv), }); } @@ -919,10 +923,7 @@ describe('CLI end-to-end', () => { encoding: 'utf8', timeout: timeoutMs, stdio: ['pipe', 'pipe', 'pipe'], - env: { - ...process.env, - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - }, + env: cliEnv(), }); } @@ -1042,10 +1043,7 @@ describe('CLI end-to-end', () => { encoding: 'utf8', timeout: 15000, stdio: ['pipe', 'pipe', 'pipe'], - env: { - ...process.env, - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - }, + env: cliEnv(), }, ); if (result.status === null) return; @@ -1159,10 +1157,7 @@ describe('CLI end-to-end', () => { { cwd: MINI_REPO, stdio: ['ignore', 'pipe', 'pipe'], - env: { - ...process.env, - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - }, + env: cliEnv(), }, ); @@ -1212,10 +1207,7 @@ describe('CLI end-to-end', () => { { cwd: MINI_REPO, stdio: ['ignore', 'pipe', 'pipe'], - env: { - ...process.env, - NODE_OPTIONS: `${process.env.NODE_OPTIONS || ''} --max-old-space-size=8192`.trim(), - }, + env: cliEnv(), }, ); diff --git a/gitnexus/test/integration/lbug-close-handle-release.test.ts b/gitnexus/test/integration/lbug-close-handle-release.test.ts index c0a3b8758..65a53bc7d 100644 --- a/gitnexus/test/integration/lbug-close-handle-release.test.ts +++ b/gitnexus/test/integration/lbug-close-handle-release.test.ts @@ -8,9 +8,16 @@ * absorbed by the open-time retry in `lbug-config.ts`. */ import path from 'path'; -import { describe, it } from 'vitest'; +import { describe, expect, it } from 'vitest'; import { createTempDir } from '../helpers/test-db.js'; +/** + * LadybugDB's native Windows file lock can outlive Database.close() for + * same-process close/reopen cycles. Keep true reopen coverage on POSIX and + * cover ordering deterministically in lbug-checkpoint-lifecycle.test.ts. + */ +const itLbugReopen = process.platform === 'win32' ? it.skip : it; + describe('safeClose — close + reopen does not surface lock errors', () => { it('survives 10 sequential open/close/reopen cycles on the same path', async () => { const tmp = await createTempDir('gitnexus-lbug-close-cycle-'); @@ -38,4 +45,38 @@ describe('safeClose — close + reopen does not surface lock errors', () => { await tmp.cleanup(); } }); + + itLbugReopen('flushes WAL when switching between two database paths in one process', async () => { + const repoA = await createTempDir('gitnexus-lbug-switch-a-'); + const repoB = await createTempDir('gitnexus-lbug-switch-b-'); + const dbPathA = path.join(repoA.dbPath, 'lbug'); + const dbPathB = path.join(repoB.dbPath, 'lbug'); + + try { + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + + await adapter.withLbugDb(dbPathA, async () => { + await adapter.executeQuery( + "CREATE (:File {id: 'file:a', name: 'a.ts', filePath: 'a.ts', content: 'repo a'})", + ); + }); + + await adapter.withLbugDb(dbPathB, async () => { + await adapter.executeQuery( + "CREATE (:File {id: 'file:b', name: 'b.ts', filePath: 'b.ts', content: 'repo b'})", + ); + }); + + const rows = await adapter.withLbugDb(dbPathA, async () => + adapter.executeQuery("MATCH (n:File {id: 'file:a'}) RETURN n.filePath AS filePath"), + ); + + expect(rows).toEqual([{ filePath: 'a.ts' }]); + } finally { + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.closeLbug().catch(() => {}); + await repoA.cleanup(); + await repoB.cleanup(); + } + }); }); diff --git a/gitnexus/test/integration/markdown-processor-crlf.test.ts b/gitnexus/test/integration/markdown-processor-crlf.test.ts new file mode 100644 index 000000000..7a3e91a95 --- /dev/null +++ b/gitnexus/test/integration/markdown-processor-crlf.test.ts @@ -0,0 +1,158 @@ +/** + * Regression test for CRLF-encoded markdown heading extraction. + * + * Files with CRLF line endings (Windows-authored markdown) previously + * produced zero Section nodes because `split('\n')` left a trailing `\r` + * on each line, and the heading regex `/^(#{1,6})\s+(.+)$/` (anchored + * with `$`) failed to match `## Heading\r` because `$` only matches at + * end-of-string while `.+` does not consume the trailing `\r`. + * + * Fix: split on `/\r\n|\r|\n/` so all line-ending conventions are + * normalized at split time. See markdown-processor.ts line 39. + */ + +import { describe, it, expect } from 'vitest'; +import { processMarkdown } from '../../src/core/ingestion/markdown-processor.js'; +import { createKnowledgeGraph } from '../../src/core/graph/graph.js'; +import { generateId } from '../../src/lib/utils.js'; +import type { GraphNode } from 'gitnexus-shared'; +import type { KnowledgeGraph } from '../../src/core/graph/types.js'; + +function getMarkdownSections(graph: KnowledgeGraph, filePath: string): GraphNode[] { + return [...graph.iterNodes()] + .filter((n) => n.label === 'Section' && n.properties.filePath === filePath) + .sort( + (a, b) => + ((a.properties.startLine as number | undefined) ?? 0) - + ((b.properties.startLine as number | undefined) ?? 0), + ); +} + +function expectContainsEdge(graph: KnowledgeGraph, sourceId: string, targetId: string) { + const found = [...graph.iterRelationshipsByType('CONTAINS')].some( + (r) => r.sourceId === sourceId && r.targetId === targetId, + ); + expect(found).toBe(true); +} + +function setupGraphWithFile(filePath: string) { + const graph = createKnowledgeGraph(); + const fileNode: GraphNode = { + id: generateId('File', filePath), + label: 'File', + properties: { name: filePath, filePath }, + }; + graph.addNode(fileNode); + return graph; +} + +describe('markdown-processor CRLF tolerance', () => { + it('extracts headings from LF-encoded markdown (baseline)', () => { + const filePath = 'lf.md'; + const graph = setupGraphWithFile(filePath); + const content = '# Title\nbody line 1\n## Sub\nbody line 2\n### SubSub\nmore\n'; + + const stats = processMarkdown(graph, [{ path: filePath, content }], new Set([filePath])); + + expect(stats.sections).toBe(3); + const sections = getMarkdownSections(graph, filePath); + expect(sections.map((s) => s.properties.name)).toEqual(['Title', 'Sub', 'SubSub']); + expect(sections.map((s) => s.properties.level)).toEqual([1, 2, 3]); + expect(sections.map((s) => s.properties.startLine)).toEqual([1, 3, 5]); + expect(sections.map((s) => s.properties.endLine)).toEqual([7, 7, 7]); + for (const s of sections) { + expect(String(s.properties.name)).not.toMatch(/\r/); + } + const fileId = generateId('File', filePath); + expectContainsEdge(graph, fileId, sections[0]!.id); + expectContainsEdge(graph, sections[0]!.id, sections[1]!.id); + expectContainsEdge(graph, sections[1]!.id, sections[2]!.id); + }); + + it('extracts headings from CRLF-encoded markdown (the regression)', () => { + const filePath = 'crlf.md'; + const graph = setupGraphWithFile(filePath); + const content = '# Title\r\nbody line 1\r\n## Sub\r\nbody line 2\r\n### SubSub\r\nmore\r\n'; + + const stats = processMarkdown(graph, [{ path: filePath, content }], new Set([filePath])); + + // Pre-fix: this returned 0 because `## Sub\r` failed the heading regex. + expect(stats.sections).toBe(3); + const sections = getMarkdownSections(graph, filePath); + expect(sections.map((s) => s.properties.name)).toEqual(['Title', 'Sub', 'SubSub']); + expect(sections.map((s) => s.properties.level)).toEqual([1, 2, 3]); + expect(sections.map((s) => s.properties.startLine)).toEqual([1, 3, 5]); + expect(sections.map((s) => s.properties.endLine)).toEqual([7, 7, 7]); + for (const s of sections) { + expect(String(s.properties.name)).not.toMatch(/\r/); + } + const fileId = generateId('File', filePath); + expectContainsEdge(graph, fileId, sections[0]!.id); + expectContainsEdge(graph, sections[0]!.id, sections[1]!.id); + expectContainsEdge(graph, sections[1]!.id, sections[2]!.id); + }); + + it('extracts headings from CR-only-encoded markdown (old Mac OS Classic)', () => { + const filePath = 'cr.md'; + const graph = setupGraphWithFile(filePath); + const content = '# Title\rbody line 1\r## Sub\rbody line 2\r'; + + const stats = processMarkdown(graph, [{ path: filePath, content }], new Set([filePath])); + + expect(stats.sections).toBe(2); + const sections = getMarkdownSections(graph, filePath); + expect(sections.map((s) => s.properties.name)).toEqual(['Title', 'Sub']); + expect(sections.map((s) => s.properties.level)).toEqual([1, 2]); + expect(sections.map((s) => s.properties.startLine)).toEqual([1, 3]); + expect(sections.map((s) => s.properties.endLine)).toEqual([5, 5]); + for (const s of sections) { + expect(String(s.properties.name)).not.toMatch(/\r/); + } + const fileId = generateId('File', filePath); + expectContainsEdge(graph, fileId, sections[0]!.id); + expectContainsEdge(graph, sections[0]!.id, sections[1]!.id); + }); + + it('extracts headings from mixed CRLF + LF markdown', () => { + const filePath = 'mixed.md'; + const graph = setupGraphWithFile(filePath); + const content = '# LF Title\nbody\r\n## CRLF Sub\r\nmore\n### Trailing LF\nend\n'; + + const stats = processMarkdown(graph, [{ path: filePath, content }], new Set([filePath])); + + expect(stats.sections).toBe(3); + const sections = getMarkdownSections(graph, filePath); + expect(sections.map((s) => s.properties.name)).toEqual(['LF Title', 'CRLF Sub', 'Trailing LF']); + expect(sections.map((s) => s.properties.level)).toEqual([1, 2, 3]); + expect(sections.map((s) => s.properties.startLine)).toEqual([1, 3, 5]); + expect(sections.map((s) => s.properties.endLine)).toEqual([7, 7, 7]); + for (const s of sections) { + expect(String(s.properties.name)).not.toMatch(/\r/); + } + const fileId = generateId('File', filePath); + expectContainsEdge(graph, fileId, sections[0]!.id); + expectContainsEdge(graph, sections[0]!.id, sections[1]!.id); + expectContainsEdge(graph, sections[1]!.id, sections[2]!.id); + }); + + it('reports correct startLine and endLine for CRLF content', () => { + const filePath = 'crlf-lines.md'; + const graph = setupGraphWithFile(filePath); + // Lines 1, 3, 5 are headings (1-indexed) + const content = '# T\r\nbody\r\n## Sub\r\nmore\r\n### SubSub\r\ntail\r\n'; + + processMarkdown(graph, [{ path: filePath, content }], new Set([filePath])); + + const sections = getMarkdownSections(graph, filePath); + const titleSection = sections.find((s) => s.properties.name === 'T'); + const subSection = sections.find((s) => s.properties.name === 'Sub'); + const subSubSection = sections.find((s) => s.properties.name === 'SubSub'); + + expect(titleSection?.properties.startLine).toBe(1); + expect(titleSection?.properties.endLine).toBe(7); + expect(subSection?.properties.startLine).toBe(3); + expect(subSection?.properties.endLine).toBe(7); + expect(subSubSection?.properties.startLine).toBe(5); + expect(subSubSection?.properties.endLine).toBe(7); + }); +}); diff --git a/gitnexus/test/integration/resolvers/c.test.ts b/gitnexus/test/integration/resolvers/c.test.ts new file mode 100644 index 000000000..980764b8c --- /dev/null +++ b/gitnexus/test/integration/resolvers/c.test.ts @@ -0,0 +1,111 @@ +/** + * C: struct + include-based imports + function calls across files + */ +import { describe, expect, beforeAll } from 'vitest'; +import path from 'path'; +import { + FIXTURES, + createResolverParityIt, + getRelationships, + getNodesByLabel, + edgeSet, + runPipelineFromRepo, + type PipelineResult, +} from './helpers.js'; + +const it = createResolverParityIt('c'); + +// --------------------------------------------------------------------------- +// C structs + include-based imports + cross-file function calls +// --------------------------------------------------------------------------- + +describe('C struct & include resolution', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'c-structs'), () => {}); + }, 60000); + + it('detects User and Service structs', () => { + const structs = getNodesByLabel(result, 'Struct'); + expect(structs).toContain('User'); + expect(structs).toContain('Service'); + }); + + it('detects functions across all files', () => { + const fns = getNodesByLabel(result, 'Function'); + expect(fns).toContain('main'); + expect(fns).toContain('create_user'); + expect(fns).toContain('free_user'); + expect(fns).toContain('get_user_age'); + expect(fns).toContain('create_service'); + expect(fns).toContain('service_add_user'); + expect(fns).toContain('destroy_service'); + }); + + it('resolves #include imports between .c and .h files', () => { + const imports = getRelationships(result, 'IMPORTS'); + const edges = edgeSet(imports); + // user.c includes user.h + expect(edges).toContain('user.c → user.h'); + // service.h includes user.h + expect(edges).toContain('service.h → user.h'); + // service.c includes service.h + expect(edges).toContain('service.c → service.h'); + // main.c includes service.h + expect(edges).toContain('main.c → service.h'); + }); + + it('emits CALLS edges for cross-file function calls', () => { + const calls = getRelationships(result, 'CALLS'); + const edges = edgeSet(calls); + // main.c calls functions from service + expect(edges).toContain('main → create_service'); + expect(edges).toContain('main → service_add_user'); + expect(edges).toContain('main → destroy_service'); + // service.c calls functions from user + expect(edges).toContain('service_add_user → create_user'); + expect(edges).toContain('service_add_user → free_user'); + expect(edges).toContain('destroy_service → free_user'); + }); +}); + +// --------------------------------------------------------------------------- +// C static function isolation — static functions must NOT leak across files +// --------------------------------------------------------------------------- + +describe('C static function isolation', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'c-static-isolation'), () => {}); + }, 60000); + + it('detects both static and non-static helper functions', () => { + const fns = getNodesByLabel(result, 'Function'); + expect(fns).toContain('helper'); + expect(fns).toContain('public_a'); + expect(fns).toContain('public_b'); + expect(fns).toContain('main'); + }); + + it('caller.c calls b:helper via include, NOT a:static helper', () => { + const calls = getRelationships(result, 'CALLS'); + const edges = edgeSet(calls); + + // caller.c should call public_b (included via b.h) + expect(edges).toContain('main → public_b'); + + // a.c's static helper calls itself locally + expect(edges).toContain('public_a → helper'); + + // caller.c should NOT have a CALLS edge to a.c's static helper. + // Filter edges to only those originating from main → helper to + // verify the correct target file. + const mainToHelper = calls.filter((r) => r.source === 'main' && r.target === 'helper'); + // If a main→helper edge exists, it should point to b.c, not a.c + for (const edge of mainToHelper) { + expect(edge.targetFilePath).not.toContain('a.c'); + } + }); +}); diff --git a/gitnexus/test/integration/resolvers/cpp.test.ts b/gitnexus/test/integration/resolvers/cpp.test.ts index 0839d59f0..de0ad9632 100644 --- a/gitnexus/test/integration/resolvers/cpp.test.ts +++ b/gitnexus/test/integration/resolvers/cpp.test.ts @@ -1,7 +1,7 @@ /** * C++: diamond inheritance + include-based imports + ambiguous #include disambiguation */ -import { describe, it, expect, beforeAll } from 'vitest'; +import { describe, expect, beforeAll } from 'vitest'; import path from 'path'; import { FIXTURES, @@ -11,9 +11,12 @@ import { getNodesByLabelFull, edgeSet, runPipelineFromRepo, + createResolverParityIt, type PipelineResult, } from './helpers.js'; +const it = createResolverParityIt('cpp'); + // --------------------------------------------------------------------------- // Heritage: diamond inheritance + include-based imports // --------------------------------------------------------------------------- @@ -937,10 +940,13 @@ describe('Write access tracking (C++)', () => { it('emits ACCESSES write edges for field assignments', () => { const accesses = getRelationships(result, 'ACCESSES'); const writes = accesses.filter((e) => e.rel.reason === 'write'); - expect(writes.length).toBe(2); - const fieldNames = writes.map((e) => e.target); - expect(fieldNames).toContain('name'); - expect(fieldNames).toContain('address'); + expect(writes.length).toBe(3); + // Per-field exact counts: both `user.name = ...` and `user.name += ...` + // must produce distinct edges (no dedup); single write to `address`. + const nameWrites = writes.filter((e) => e.target === 'name'); + expect(nameWrites.length).toBe(2); + const addrWrites = writes.filter((e) => e.target === 'address'); + expect(addrWrites.length).toBe(1); const sources = writes.map((e) => e.source); expect(sources).toContain('updateUser'); }); @@ -1458,6 +1464,84 @@ describe('C++ template overload cross-file and chain resolution', () => { }); }); +describe('C++ template specialization disambiguation across files', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-template-specialization-disambiguation'), + () => {}, + ); + }, 60000); + + it('emits distinct Class nodes for List and List', () => { + const classes = getNodesByLabelFull(result, 'Class').filter( + (c) => c.name === 'List' && Array.isArray(c.properties.templateArguments), + ); + expect(classes.length).toBe(2); + const fingerprints = new Set(classes.map((c) => c.properties.templateArguments.join(','))); + expect(fingerprints).toEqual(new Set(['User', 'Order'])); + }); + + it('callSave() in each specialization resolves to its own save()', () => { + const calls = getRelationships(result, 'CALLS'); + const saveEdges = calls.filter((c) => c.source === 'callSave' && c.target === 'save'); + expect(saveEdges.length).toBe(2); + + const hasMethod = getRelationships(result, 'HAS_METHOD'); + const ownerFingerprints = new Set(); + for (const edge of saveEdges) { + const sourceOwnerEdge = hasMethod.find((e) => e.rel.targetId === edge.rel.sourceId); + const targetOwnerEdge = hasMethod.find((e) => e.rel.targetId === edge.rel.targetId); + expect(sourceOwnerEdge).toBeDefined(); + expect(targetOwnerEdge).toBeDefined(); + expect(sourceOwnerEdge!.rel.sourceId).toBe(targetOwnerEdge!.rel.sourceId); + const ownerNode = result.graph.getNode(sourceOwnerEdge!.rel.sourceId); + const fp = ownerNode?.properties.templateArguments?.join(','); + if (fp) ownerFingerprints.add(fp); + } + expect(ownerFingerprints).toEqual(new Set(['User', 'Order'])); + }); + + it('save specialization bodies route to their own sibling method', () => { + const calls = getRelationships(result, 'CALLS'); + + const persistUserCalls = calls.filter((c) => c.target === 'persistUser'); + expect(persistUserCalls.length).toBe(1); + const userSaveOwner = getRelationships(result, 'HAS_METHOD').find( + (e) => e.rel.targetId === persistUserCalls[0].rel.sourceId, + ); + expect(userSaveOwner).toBeDefined(); + const userOwnerNode = result.graph.getNode(userSaveOwner!.rel.sourceId); + expect(userOwnerNode?.properties.templateArguments).toEqual(['User']); + + const persistOrderCalls = calls.filter((c) => c.target === 'persistOrder'); + expect(persistOrderCalls.length).toBe(1); + const orderSaveOwner = getRelationships(result, 'HAS_METHOD').find( + (e) => e.rel.targetId === persistOrderCalls[0].rel.sourceId, + ); + expect(orderSaveOwner).toBeDefined(); + const orderOwnerNode = result.graph.getNode(orderSaveOwner!.rel.sourceId); + expect(orderOwnerNode?.properties.templateArguments).toEqual(['Order']); + }); + + it('resolves external List receiver call to List::save', () => { + const calls = getRelationships(result, 'CALLS'); + const edge = calls.find( + (c) => + c.source === 'callUserSave' && c.target === 'save' && c.targetFilePath === 'list_user.h', + ); + expect(edge).toBeDefined(); + + const ownerEdge = getRelationships(result, 'HAS_METHOD').find( + (e) => e.rel.targetId === edge!.rel.targetId, + ); + expect(ownerEdge).toBeDefined(); + const ownerNode = result.graph.getNode(ownerEdge!.rel.sourceId); + expect(ownerNode?.properties.templateArguments).toEqual(['User']); + }); +}); + // ── Phase P: C++ out-of-class method definition + overload disambiguation ─ describe('C++ out-of-class method definition with overloaded declarations', () => { @@ -1582,3 +1666,1358 @@ describe('C++ Derived : A, B — diamond inheritance via leftmost-base MRO (SM-1 expect(methodCall!.source).toBe('run'); }); }); + +// --------------------------------------------------------------------------- +// U1: `#include` must not leak class-owned methods as unqualified bindings +// --------------------------------------------------------------------------- + +describe('C++ include does not leak class methods', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-include-no-class-leak'), () => {}); + }, 60000); + + it('does NOT resolve unqualified save() to User::save via #include', () => { + const calls = getRelationships(result, 'CALLS'); + const leak = calls.filter((c) => c.source === 'run' && c.target === 'save'); + expect(leak.length).toBe(0); + }); + + it('preserves the file-level #include IMPORTS edge', () => { + const imports = getRelationships(result, 'IMPORTS'); + expect(imports.length).toBe(1); + expect(imports[0].targetFilePath).toBe('user.h'); + }); +}); + +// --------------------------------------------------------------------------- +// U1: `#include` must not leak namespace-nested symbols as unqualified bindings +// --------------------------------------------------------------------------- + +describe('C++ include does not leak namespace members', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-include-no-namespace-leak'), + () => {}, + ); + }, 60000); + + it('does NOT resolve unqualified foo() to ns::foo via #include', () => { + const calls = getRelationships(result, 'CALLS'); + const leak = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + expect(leak.length).toBe(0); + }); + + it('preserves the file-level #include IMPORTS edge', () => { + const imports = getRelationships(result, 'IMPORTS'); + expect(imports.length).toBe(1); + expect(imports[0].targetFilePath).toBe('lib.h'); + }); +}); + +// --------------------------------------------------------------------------- +// U1: anonymous-namespace symbols remain visible within their declaring TU +// (positive companion to the cross-file exclusion test below) +// --------------------------------------------------------------------------- + +describe('C++ anonymous namespace symbols visible in same TU', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-anon-ns-same-file-visible'), + () => {}, + ); + }, 60000); + + it('resolves run() -> w() within the same TU', () => { + const calls = getRelationships(result, 'CALLS'); + const wCalls = calls.filter((c) => c.source === 'run' && c.target === 'w'); + expect(wCalls.length).toBe(1); + }); +}); + +// --------------------------------------------------------------------------- +// U2: integer-width overload ambiguity suppresses CALLS edge entirely +// (PR #1520 review follow-up plan U2; Claude review Finding 5) +// --------------------------------------------------------------------------- + +describe('C++ ambiguous integer-width overloads', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-overload-int-long'), () => {}); + }, 60000); + + it('emits zero CALLS edges when process(int)/process(long) collide after normalization', () => { + const calls = getRelationships(result, 'CALLS'); + const processCalls = calls.filter((c) => c.source === 'run' && c.target === 'process'); + // Exact .toBe(0): any non-zero count is a regression. count=1 = arbitrary + // pick (the bug U2 fixes); count=2+ would require an ambiguous-edge model + // GitNexus does not have. The resolver must suppress entirely. + expect(processCalls.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// U3: anonymous-namespace symbols MUST NOT leak across translation units +// (full-pipeline integration test; unit-level coverage exists separately) +// PR #1520 review follow-up plan U3 / Claude review Finding 7 +// --------------------------------------------------------------------------- + +describe('C++ anonymous namespace cross-file exclusion (integration)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-anon-ns-cross-file'), () => {}); + }, 60000); + + it('caller.cpp::run -> worker does NOT target helper.cpp anonymous-namespace worker', () => { + const calls = getRelationships(result, 'CALLS'); + const crossFileLeak = calls.filter( + (c) => + c.source === 'run' && c.target === 'worker' && c.targetFilePath?.includes('helper.cpp'), + ); + expect(crossFileLeak.length).toBe(0); + }); + + it('helper.cpp::helper_entry still resolves its OWN anonymous-namespace worker (positive guard)', () => { + const calls = getRelationships(result, 'CALLS'); + const sameFileResolve = calls.filter( + (c) => + c.source === 'helper_entry' && + c.target === 'worker' && + c.targetFilePath?.includes('helper.cpp'), + ); + // Pairs with the negative test above so a "no edges at all" regression + // doesn't make the cross-file leak check pass vacuously. + expect(sameFileResolve.length).toBe(1); + }); +}); + +// State-isolation guard: re-run the same fixture and assert identical +// results. Proves `clearFileLocalNames()` (called from the cpp resolver's +// `loadResolutionConfig`) is exercised by `runPipelineFromRepo` and +// that module-level `fileLocalNames` state doesn't bleed across runs. +describe('C++ anonymous namespace state-isolation guard', () => { + it('second run of the same fixture produces identical worker-cross-file edge count', async () => { + const fixture = path.join(FIXTURES, 'cpp-anon-ns-cross-file'); + const r1 = await runPipelineFromRepo(fixture, () => {}); + const r2 = await runPipelineFromRepo(fixture, () => {}); + const countLeak = (r: PipelineResult): number => + getRelationships(r, 'CALLS').filter( + (c) => + c.source === 'run' && c.target === 'worker' && c.targetFilePath?.includes('helper.cpp'), + ).length; + expect(countLeak(r1)).toBe(0); + expect(countLeak(r2)).toBe(0); + }, 120000); +}); + +// --------------------------------------------------------------------------- +// U4: `using namespace` with conflicting names from two namespaces +// The resolver MUST emit zero CALLS edges — emitting one is arbitrary +// pick; emitting two requires an ambiguous-target edge model GitNexus +// does not have. +// Depends on U1 (without scope-aware filtering, `a::foo` and `b::foo` +// would already be in the importer's wildcard binding set as simple +// `foo` and this test would pass for the wrong reason). +// PR #1520 review follow-up plan U4 / Claude review Finding 7 +// --------------------------------------------------------------------------- + +describe('C++ using-namespace with conflicting names', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-using-namespace-conflict'), + () => {}, + ); + }, 60000); + + it('emits zero CALLS edges for ambiguous foo() bound via two using-namespace declarations', () => { + const calls = getRelationships(result, 'CALLS'); + const fooCalls = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + expect(fooCalls.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// U5: `using namespace std` MUST NOT leak shim STL symbols into unqualified +// bindings. Uses a fixture-local `namespace std { ... }` shim rather than +// real — captures the wildcard-leak shape deterministically +// without depending on system-header modeling stability. +// PR #1520 review follow-up plan U5 / Claude review Finding 7 +// --------------------------------------------------------------------------- + +describe('C++ using-namespace std smoke test', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-using-namespace-std-smoke'), + () => {}, + ); + }, 60000); + + it('resolves the project call (positive guard against vacuous pass)', () => { + const calls = getRelationships(result, 'CALLS'); + const projectCalls = calls.filter((c) => c.source === 'run' && c.target === 'project_helper'); + expect(projectCalls.length).toBe(1); + }); + + it('does NOT leak unqualified bindings for shim STL symbols', () => { + const calls = getRelationships(result, 'CALLS'); + const stlLeaks = calls.filter( + (c) => c.source === 'run' && (c.target === 'cout_write' || c.target === 'println'), + ); + expect(stlLeaks.length).toBe(0); + }); + + it('emits no CALLS or ACCESSES edges from run() into std-shim.h', () => { + const calls = getRelationships(result, 'CALLS'); + const accesses = getRelationships(result, 'ACCESSES'); + const intoShim = [...calls, ...accesses].filter( + (e) => e.source === 'run' && e.targetFilePath?.includes('std-shim.h'), + ); + expect(intoShim.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// U1 (follow-up plan 2026-05-13-001): namespace-qualified or class-qualified +// calls from outside that class MUST NOT be classified as super-receiver calls. +// The `isSuperReceiverInContext` hook consults the caller's MRO. +// --------------------------------------------------------------------------- + +describe('C++ namespace-qualified call is not a super receiver', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-namespace-qualified-not-super'), + () => {}, + ); + }, 60000); + + it('resolves Singleton::getInstance() from a free function (not as super call)', () => { + const calls = getRelationships(result, 'CALLS'); + const getInstanceCalls = calls.filter((c) => c.source === 'run' && c.target === 'getInstance'); + // Exactly 1: routed through the normal qualified-call path, NOT the super + // branch. Before the U1 fix the regex `/^[A-Z]\w*::/` matched Singleton::, + // entered the super branch with no enclosing class, and dropped the edge. + expect(getInstanceCalls.length).toBe(1); + expect(getInstanceCalls[0].targetFilePath).toContain('singleton.h'); + }); +}); + +// --------------------------------------------------------------------------- +// U4 (follow-up plan 2026-05-13-001): default-argument overload ambiguity. +// `void f(int); void f(int, int = 0); f(1);` is ambiguous per ISO C++. The +// OVERLOAD_AMBIGUOUS sentinel from plan 2026-05-12-002 U2 should detect +// this case via isOverloadAmbiguousAfterNormalization. +// --------------------------------------------------------------------------- + +describe('C++ default-argument overload ambiguity', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-overload-default-arg-ambiguous'), + () => {}, + ); + }, 60000); + + it('s.f(1) emits zero CALLS edges when f(int) and f(int, int=0) both match', () => { + const calls = getRelationships(result, 'CALLS'); + const fCalls = calls.filter((c) => c.source === 'run' && c.target === 'f'); + // Exact .toBe(0): count=1 means arbitrary pick (the bug); count=2+ would + // require an ambiguous-target edge model GitNexus does not have. The + // resolver must suppress entirely. Standard C++ rejects the call as + // ambiguous (GCC/Clang both diagnose). + expect(fCalls.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// U3 (follow-up plan 2026-05-13-001): two-phase template lookup. +// Inside a class template body, unqualified calls MUST NOT bind to members +// of a dependent base class. Only `this->name()` or `Base::name()` forms +// should resolve. +// --------------------------------------------------------------------------- + +describe('C++ two-phase template lookup — dependent base suppression', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-two-phase-dependent-base'), + () => {}, + ); + }, 60000); + + it('Derived::g() -> f() does NOT bind to Base::f (dependent base)', () => { + const calls = getRelationships(result, 'CALLS'); + const leaks = calls.filter((c) => c.source === 'g' && c.target === 'f'); + expect(leaks.length).toBe(0); + }); + + it('Derived::h() -> i does NOT bind to Base::i (dependent base)', () => { + const accesses = getRelationships(result, 'ACCESSES'); + const leaks = accesses.filter((c) => c.source === 'h' && c.target === 'i'); + expect(leaks.length).toBe(0); + }); +}); + +describe('C++ two-phase template lookup — positive this-qualified calls', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-two-phase-this-qualified'), + () => {}, + ); + }, 60000); + + it('Derived::g() -> this->f() resolves to f (1 edge)', () => { + const calls = getRelationships(result, 'CALLS'); + const thisCalls = calls.filter((c) => c.source === 'g' && c.target === 'f'); + expect(thisCalls.length).toBe(1); + expect(thisCalls[0].targetFilePath).toContain('base.h'); + }); + + it('Derived::k() -> this->base_method() resolves via EXTENDS chain (1 edge)', () => { + const calls = getRelationships(result, 'CALLS'); + const inheritedCalls = calls.filter((c) => c.source === 'k' && c.target === 'base_method'); + expect(inheritedCalls.length).toBe(1); + expect(inheritedCalls[0].targetFilePath).toContain('base.h'); + }); +}); + +describe('C++ two-phase template lookup — paired unqualified + this-qualified in one fixture', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-two-phase-paired'), () => {}); + }, 60000); + + it('Derived::g_unqualified() -> f() does NOT bind to Base::f', () => { + const calls = getRelationships(result, 'CALLS'); + const leaks = calls.filter((c) => c.source === 'g_unqualified' && c.target === 'f'); + expect(leaks.length).toBe(0); + }); + + it('Derived::g_this() -> this->f() resolves to Base::f (1 edge)', () => { + const calls = getRelationships(result, 'CALLS'); + const resolved = calls.filter((c) => c.source === 'g_this' && c.target === 'f'); + expect(resolved.length).toBe(1); + expect(resolved[0].targetFilePath).toContain('base.h'); + }); +}); + +describe('C++ two-phase template lookup — namespace calls inside template body', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-two-phase-namespace-free-call-inside-template'), + () => {}, + ); + }, 60000); + + it('D::g() -> utils::ns_helper() resolves (1 edge)', () => { + const calls = getRelationships(result, 'CALLS'); + const qualifiedCalls = calls.filter((c) => c.source === 'g' && c.target === 'ns_helper'); + expect(qualifiedCalls.length).toBe(1); + expect(qualifiedCalls[0].targetFilePath).toContain('helpers.h'); + }); + + it('D::g() -> ns_helper_2() resolves after using-declaration (1 edge)', () => { + const calls = getRelationships(result, 'CALLS'); + const usingCalls = calls.filter((c) => c.source === 'g' && c.target === 'ns_helper_2'); + expect(usingCalls.length).toBe(1); + expect(usingCalls[0].targetFilePath).toContain('helpers.h'); + }); +}); + +describe('C++ two-phase template lookup — this-> name-hiding arity mismatch', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-two-phase-this-name-hiding-arity'), + () => {}, + ); + }, 60000); + + it('Derived::g() -> this->f() emits zero CALLS edges when only hidden derived overload is arity-incompatible', () => { + const calls = getRelationships(result, 'CALLS'); + const fCalls = calls.filter((c) => c.source === 'g' && c.target === 'f'); + expect(fCalls.length).toBe(0); + }); + + it('Derived::g_ok() -> this->f(42) resolves to derived overload (1 edge)', () => { + const calls = getRelationships(result, 'CALLS'); + const fCalls = calls.filter((c) => c.source === 'g_ok' && c.target === 'f'); + expect(fCalls.length).toBe(1); + expect(fCalls[0].targetFilePath).toContain('derived.h'); + }); +}); + +// --------------------------------------------------------------------------- +// U3 cross-file namespace variant: Base lives in a different file AND +// inside a namespace. The fixture also contains a free function with the +// same name inside the namespace — that candidate has no ownerId, so the +// class-owned filter does NOT apply to it; it is instead suppressed by the +// namespace-nesting filter. Both candidates must still yield zero edges. +// --------------------------------------------------------------------------- + +describe('C++ two-phase template lookup — cross-file namespace variant', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-two-phase-dependent-base-ns'), + () => {}, + ); + }, 60000); + + it('geom::Derived::g() -> compute() does NOT bind to geom::Base::compute (cross-file dependent base, class-owned)', () => { + const calls = getRelationships(result, 'CALLS'); + const leaks = calls.filter((c) => c.source === 'g' && c.target === 'compute'); + expect(leaks.length).toBe(0); + }); + + it('geom::Derived::h() -> area does NOT bind to geom::Base::area (cross-file dependent base, class-owned)', () => { + const accesses = getRelationships(result, 'ACCESSES'); + const leaks = accesses.filter((c) => c.source === 'h' && c.target === 'area'); + expect(leaks.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// U2 (follow-up plan 2026-05-13-001): argument-dependent (Koenig) lookup. +// Free-function calls with class-typed arguments must consider candidates +// declared in the argument's enclosing namespace (associated namespace). +// V1 boundary: only direct enclosing-namespace closure for value class- +// typed args; pointer/reference args and template specializations with +// explicit type arguments included. Function pointers and base-class +// associated namespaces remain excluded. +// --------------------------------------------------------------------------- + +describe('C++ ADL — basic associated-namespace closure', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-basic'), () => {}); + }, 60000); + + it('record(e) where e is audit::Event resolves to audit::record via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // Exactly 1: ordinary lookup is empty (no `using` statement, no local + // declaration), ADL surfaces audit::record because audit::Event's + // associated namespace is `audit`. The CALLS edge should target the + // declaration in audit.h. + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); +}); + +describe('C++ ADL — merges with non-empty ordinary lookup', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-merge-nonempty-ordinary'), + () => {}, + ); + }, 60000); + + it('swap(a, b) prefers data::swap(Pair&, Pair&) over app::swap(int, int)', () => { + const calls = getRelationships(result, 'CALLS'); + const swapCalls = calls.filter((c) => c.source === 'run' && c.target === 'swap'); + expect(swapCalls.length).toBe(1); + expect(swapCalls[0].targetFilePath).toContain('data.h'); + }); +}); + +describe('C++ ADL — base-class associated namespaces', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-base-associated-namespaces'), + () => {}, + ); + }, 60000); + + it('resolves log(d) to base_lib::log via ADL when Derived inherits from base_lib::Base', () => { + const calls = getRelationships(result, 'CALLS'); + const logCalls = calls.filter((c) => c.source === 'run_single' && c.target === 'log'); + expect(logCalls.length).toBe(1); + expect(logCalls[0].targetFilePath).toContain('base_lib.h'); + const targetNode = result.graph.getNode(logCalls[0].rel.targetId); + expect(logCalls[0].rel.targetId).toBe('Function:base_lib.h:log'); + expect(targetNode?.properties.parameterTypes).toEqual(['Base']); + }); + + it('resolves trace(m) via full MRO walk when MultiLevel inherits via middle_lib::Mid -> base_lib::Root', () => { + const calls = getRelationships(result, 'CALLS'); + const traceCalls = calls.filter((c) => c.source === 'run_multi' && c.target === 'trace'); + expect(traceCalls.length).toBe(1); + expect(traceCalls[0].targetFilePath).toContain('base_lib.h'); + const targetNode = result.graph.getNode(traceCalls[0].rel.targetId); + expect(traceCalls[0].rel.targetId).toBe('Function:base_lib.h:trace'); + expect(targetNode?.properties.parameterTypes).toEqual(['Root']); + }); + + it('diamond inheritance contributes base namespace once (no duplicate/crash)', () => { + const calls = getRelationships(result, 'CALLS'); + const pingCalls = calls.filter((c) => c.source === 'run_diamond' && c.target === 'ping'); + expect(pingCalls.length).toBe(1); + expect(pingCalls[0].targetFilePath).toContain('base_lib.h'); + const targetNode = result.graph.getNode(pingCalls[0].rel.targetId); + expect(pingCalls[0].rel.targetId).toBe('Function:base_lib.h:ping'); + expect(targetNode?.properties.parameterTypes).toEqual(['DiamondBase']); + }); +}); + +describe('C++ ADL — base-class namespace MRO with simple-name class collisions', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-base-associated-namespaces-collision'), + () => {}, + ); + }, 60000); + + it('does NOT emit CALLS for collide(t) when class-name lookup is ambiguous', () => { + const calls = getRelationships(result, 'CALLS'); + const collideCalls = calls.filter((c) => c.source === 'run' && c.target === 'collide'); + expect(collideCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — base-class namespace mapping skips anonymous/unresolved bases', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-base-associated-namespaces-negative'), + () => {}, + ); + }, 60000); + + it('hidden_probe(d) still resolves via ordinary lookup when declaration is visible', () => { + const calls = getRelationships(result, 'CALLS'); + const hiddenProbeCalls = calls.filter( + (c) => c.source === 'run_hidden' && c.target === 'hidden_probe', + ); + expect(hiddenProbeCalls.length).toBe(1); + expect(hiddenProbeCalls[0].targetFilePath).toContain('base_lib.h'); + }); + + it('unresolved_probe(d) emits zero CALLS when base class cannot be resolved', () => { + const calls = getRelationships(result, 'CALLS'); + const unresolvedProbeCalls = calls.filter( + (c) => c.source === 'run_missing' && c.target === 'unresolved_probe', + ); + expect(unresolvedProbeCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — parenthesized name suppresses ADL', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-suppressed-parens'), () => {}); + }, 60000); + + it('(record)(e) emits zero CALLS edges — ADL is suppressed by parentheses', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // Exact .toBe(0): ISO C++ [basic.lookup.argdep]/3.1 specifies that the + // parenthesized form `(f)(x)` forces ordinary lookup only — ADL must + // NOT fire. Without ordinary-lookup candidates (no `using`, no local + // declaration), the call goes unresolved. + expect(recordCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — pointer arg unwrapping', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-pointer-arg-boundary'), + () => {}, + ); + }, 60000); + + it('record(p) where p is audit::Event* resolves to audit::record via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); +}); + +describe('C++ ADL — reference arg unwrapping', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-reference-arg-boundary'), + () => {}, + ); + }, 60000); + + it('record(s) where s is audit::Event& resolves to audit::record via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'runRef' && c.target === 'record'); + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('record.h'); + }); + + it('recordConst(cs) where cs is const audit::Event& resolves via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter( + (c) => c.source === 'runConstRef' && c.target === 'recordConst', + ); + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('record.h'); + }); + + it('note(r) where r is int& emits zero CALLS edges (primitive ref)', () => { + const calls = getRelationships(result, 'CALLS'); + const noteCalls = calls.filter((c) => c.source === 'runPrimitiveRef' && c.target === 'note'); + expect(noteCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — rvalue reference args participate', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-rvalue-ref'), () => {}); + }, 60000); + + it('record(rr) where rr is audit::Event&& resolves to audit::record via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'runRvalueRef' && c.target === 'record'); + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('record-rvalue.h'); + }); +}); + +describe('C++ ADL — function pointer args do not participate', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-function-pointer-arg'), + () => {}, + ); + }, 60000); + + it('record(g) where g is void (*)() emits zero CALLS edges', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + expect(recordCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — preceding function-pointer declarations do not block class args', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-function-pointer-before-class-arg'), + () => {}, + ); + }, 60000); + + it('record(e) still resolves via ADL when an earlier declaration is void (*)()', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); +}); + +describe('C++ ADL — class-returning function pointer args do not participate', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-function-pointer-class-return-arg'), + () => {}, + ); + }, 60000); + + it('record(factory) where factory is audit::Event (*)() emits zero CALLS edges', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + expect(recordCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — pointer-to-pointer args participate', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-pointer-to-pointer'), () => {}); + }, 60000); + + it('record(pp) where pp is audit::Event** resolves to audit::record via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); +}); + +describe('C++ ADL — template specialization args contribute associated namespaces', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-template-args'), () => {}); + }, 60000); + + it('apply(v) where v is std::vector resolves to N::apply via ADL template-arg namespace', () => { + const calls = getRelationships(result, 'CALLS'); + const applyCalls = calls.filter((c) => c.source === 'run' && c.target === 'apply'); + expect(applyCalls.length).toBe(1); + expect(applyCalls[0].targetFilePath).toContain('audit.h'); + }); + + it('applyNested(m) where m is std::map> resolves via nested template-arg namespace', () => { + const calls = getRelationships(result, 'CALLS'); + const applyCalls = calls.filter((c) => c.source === 'runNested' && c.target === 'applyNested'); + expect(applyCalls.length).toBe(1); + expect(applyCalls[0].targetFilePath).toContain('audit.h'); + }); + + it('applyArray(a) where a is std::array resolves to N::applyArray (non-type arg ignored)', () => { + const calls = getRelationships(result, 'CALLS'); + const applyCalls = calls.filter((c) => c.source === 'runArray' && c.target === 'applyArray'); + expect(applyCalls.length).toBe(1); + expect(applyCalls[0].targetFilePath).toContain('audit.h'); + }); + + it('applyStdConflict(v) is suppressed when ADL surfaces both N and std candidates', () => { + const calls = getRelationships(result, 'CALLS'); + const applyCalls = calls.filter( + (c) => c.source === 'runStdConflict' && c.target === 'applyStdConflict', + ); + expect(applyCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — int/long-collision overloads suppress via OVERLOAD_AMBIGUOUS', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-ambiguous'), () => {}); + }, 60000); + + it('process(t, 42) emits zero CALLS edges when ADL surfaces process(Token,int)/process(Token,long) (collide after C++ int normalization)', () => { + const calls = getRelationships(result, 'CALLS'); + const processCalls = calls.filter((c) => c.source === 'run' && c.target === 'process'); + // Exact .toBe(0): both alpha::process(Token, int) and + // alpha::process(Token, long) are surfaced via ADL (alpha::Token's + // associated namespace). C++ arity-metadata normalizes int/long to + // 'int', so both candidates have parameterTypes ['Token', 'int']. + // narrowOverloadCandidates can't disambiguate (arg-types are + // ['', 'int']), and isOverloadAmbiguousAfterNormalization detects + // the collision in merged ordinary+ADL narrowing, so fallback suppresses. + // count=1 is the bug (arbitrary first-pick); count=2 would require + // an ambiguous-target edge model GitNexus does not have. + expect(processCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — merged narrowing to zero suppresses global fallback', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-merged-narrow-zero'), () => {}); + }, 60000); + + it('probe(t, 42) emits zero CALLS when ADL contributes only arity-mismatched candidates', () => { + const calls = getRelationships(result, 'CALLS'); + const probeCalls = calls.filter((c) => c.source === 'run' && c.target === 'probe'); + // ADL surfaces alpha::probe(Token), but call arity is 2 (`probe(t, 42)`), + // so merged overload narrowing yields zero survivors. The site is treated + // as handled and must NOT fall through to global simple-name fallback. + expect(probeCalls.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// ADL V2 — ISO C++ `[basic.lookup.argdep]` §2: enum types contribute their +// enclosing namespace to the associated set, just like class types. +// --------------------------------------------------------------------------- + +describe('C++ ADL — enum-typed argument contributes enclosing namespace', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-enum-arg'), () => {}); + }, 60000); + + it('serialize(ch) where ch is color::Channel resolves to color::serialize via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const serializeCalls = calls.filter((c) => c.source === 'run' && c.target === 'serialize'); + // Exactly 1: ordinary lookup in app::run finds nothing for `serialize`. + // ADL surfaces color::serialize because color::Channel's enclosing + // namespace is `color`. Before the enum gap fix, this was 0. + expect(serializeCalls.length).toBe(1); + expect(serializeCalls[0].targetFilePath).toContain('color.h'); + }); +}); + +// --------------------------------------------------------------------------- +// ADL V2 — ISO C++ `[basic.lookup.argdep]` §2: "hidden friend" functions +// declared inside a class body are visible via ADL. They are not namespace- +// scope declarations (owned by the class scope in tree-sitter-cpp), so they +// require scanning associated class scopes in addition to namespace scopes. +// --------------------------------------------------------------------------- + +describe('C++ ADL — hidden friend function visible via ADL', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-hidden-friend'), () => {}); + }, 60000); + + it('process(f) where f is lib::Foo resolves to hidden friend process(Foo&) via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const processCalls = calls.filter((c) => c.source === 'run' && c.target === 'process'); + // Exactly 1: process(Foo&) is a hidden friend declared inside Foo's + // class body. Ordinary namespace-scope lookup won't find it — only ADL + // scanning the associated class's ownedDefs can surface it. + expect(processCalls.length).toBe(1); + expect(processCalls[0].targetFilePath).toContain('lib.h'); + }); +}); + +// --------------------------------------------------------------------------- +// ADL V2 — ISO C++ `[basic.lookup.unqual]` §7: non-function ordinary lookup +// result blocks ADL. If the name resolves to a variable/class/enum in scope, +// ADL does not fire even if class-typed arguments are present. +// --------------------------------------------------------------------------- + +describe('C++ ADL — non-function ordinary lookup suppresses ADL', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-non-function-blocks'), + () => {}, + ); + }, 60000); + + it('record(e) emits zero CALLS when a variable named record exists in scope', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // ISO C++: `int record = 0;` in namespace app means ordinary lookup + // finds a non-function entity. ADL should be suppressed — even though + // `e` is audit::Event, audit::record should NOT be discovered. + expect(recordCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — inner callable + outer non-callable: ADL not suppressed', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-inner-callable-outer-noncallable'), + () => {}, + ); + }, 60000); + + it('swap(a,b) resolves to data::swap when inner scope has callable swap and outer has variable', () => { + const calls = getRelationships(result, 'CALLS'); + const swapCalls = calls.filter((c) => c.source === 'run' && c.target === 'swap'); + // Ordinary lookup finds `inner::swap(int,int)` at the nearest scope. + // The outer `app::swap` (variable) does NOT suppress ADL because + // ordinary lookup stopped at the inner scope. ADL contributes + // data::swap(Pair&,Pair&) which wins via argTypes narrowing. + expect(swapCalls.length).toBe(1); + expect(swapCalls[0].targetFilePath).toContain('data.h'); + }); +}); + +describe('C++ ADL — block-scope function declaration suppresses ADL', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-block-scope-decl-blocks'), + () => {}, + ); + }, 60000); + + it('record(e) emits zero CALLS when a block-scope function declaration exists', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // ISO C++ [basic.lookup.argdep]: a block-scope function declaration + // (not via using-declaration) suppresses ADL — even though `e` is + // audit::Event, audit::record should NOT be discovered. + expect(recordCalls.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// ADL V2 — free-function reference args contribute their namespace. +// +// GitNexus approximation (not strict ISO C++ ADL): when a qualified_identifier +// like `utils::worker` is passed as an argument, GitNexus contributes the +// enclosing namespace (`utils`) to the associated set, provided a Function or +// Method named `worker` is found in the `utils` namespace at resolution time. +// Under ISO C++ [basic.lookup.argdep] the associated entities for a function-type +// argument come from the parameter types and return type of the overload set — +// NOT the function's enclosing namespace. For `void worker()`, the standard- +// compliant associated set is empty. The approximation captures the dominant +// real-world pattern (pass a utility function → find its sibling) at the cost +// of potential false positives when an unrelated function with the same simple +// name exists in the same namespace (bounded by the workspace-function lookup). +// --------------------------------------------------------------------------- + +describe('C++ ADL — qualified free-function reference contributes its namespace', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'cpp-adl-free-func-ref'), () => {}); + }, 60000); + + it('with_callback(utils::worker) resolves to utils::with_callback via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const cbCalls = calls.filter((c) => c.source === 'run' && c.target === 'with_callback'); + // Ordinary lookup inside caller::run finds nothing (no `using`, no local + // declaration). utils::worker is a qualified_identifier argument, so ADL + // contributes `utils` to the associated-namespace set. utils::with_callback + // is then discovered as the sole candidate. + expect(cbCalls.length).toBe(1); + expect(cbCalls[0].targetFilePath).toContain('utils.h'); + }); +}); + +describe('C++ ADL — overloaded free-function reference does not crash', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-free-func-ref-overloaded'), + () => {}, + ); + }, 60000); + + it('with_callback(utils::worker) with overloaded utils::worker still resolves utils::with_callback via ADL', () => { + const calls = getRelationships(result, 'CALLS'); + const cbCalls = calls.filter((c) => c.source === 'run' && c.target === 'with_callback'); + // utils::worker has two overloads (worker() and worker(int)). V1 + // simplification: contribute the namespace if ANY overload exists in the + // workspace, regardless of which one would be selected. The namespace + // `utils` is still added, and utils::with_callback is discovered. + expect(cbCalls.length).toBe(1); + expect(cbCalls[0].targetFilePath).toContain('utils.h'); + }); +}); + +describe('C++ ADL — namespace-qualified variable arg does NOT contribute namespace', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-qualified-variable-arg'), + () => {}, + ); + }, 60000); + + it('process(data::value) emits zero CALLS edges — data::value is a variable, not a function', () => { + const calls = getRelationships(result, 'CALLS'); + const processCalls = calls.filter((c) => c.source === 'run' && c.target === 'process'); + // data::value is a namespace-qualified integer variable. tree-sitter-cpp + // produces a qualified_identifier AST node regardless of whether `value` + // denotes a function, variable, enum, or static member. The GitNexus guard + // in collectFunctionRefNamespaces verifies that a Function/Method named + // `value` exists in the `data` namespace before contributing it. Since + // `data::value` is an int variable, `data` is never added to the associated + // set, so data::process is never found as an ADL candidate. + expect(processCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — function parameter does NOT trigger free-function-ref ADL', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-param-not-free-func-ref'), + () => {}, + ); + }, 60000); + + it('run_with(callback) emits zero CALLS edges when callback is a parameter, not a function reference', () => { + const calls = getRelationships(result, 'CALLS'); + const runWithCalls = calls.filter((c) => c.source === 'run' && c.target === 'run_with'); + // `callback` is an int parameter of `caller::run`. Function parameters + // live in the parameter_list, not in the compound_statement, so the + // local-scope declaration scan would not find it and would return null — + // previously misclassifying it as an unqualified free-function reference. + // The workspace contains utils::callback(), so the scan would find it and + // contribute `utils` to the ADL set, emitting a false-positive CALLS edge + // to utils::run_with. isIdentifierAFunctionParameter now catches this and + // returns EMPTY_ADL_ARG, preventing the workspace scan entirely. + expect(runWithCalls.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// U5 (follow-up plan 2026-05-13-001): inline namespace transitive walking. +// `inline namespace v1 { ... }` makes its members reachable through the +// enclosing namespace's qualified lookup as if declared directly there +// (ISO C++ `[namespace.def]/p4`). Adds a C++-specific +// `resolveQualifiedReceiverMember` hook on the ScopeResolver contract. +// --------------------------------------------------------------------------- + +describe('C++ ADL — local function-pointer var shadows same-named free function', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-local-fp-shadows-free-func'), + () => {}, + ); + }, 60000); + + it('record(g) emits zero CALLS edges even though audit::g() exists in the workspace', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // `g` is a locally-declared `void (*g)()` variable. `audit::g()` also + // exists in the workspace. Without the foundAsLocalFunctionPointer guard, + // `g` would not be detected in the compound_statement (it IS there, but + // as a function-pointer declarator), and the workspace scan would find + // audit::g, contribute `audit` to the ADL set, and emit a false-positive + // CALLS edge to audit::record. The guard correctly returns EMPTY_ADL_ARG, + // so no namespace is contributed and no edge is emitted. + expect(recordCalls.length).toBe(0); + }); +}); + +describe('C++ ADL — unqualified free-function ref with namespace collision', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-unqualified-ref-collision'), + () => {}, + ); + }, 60000); + + it('run_with(worker) emits zero CALLS edges when worker exists in two namespaces', () => { + const calls = getRelationships(result, 'CALLS'); + const runWithCalls = calls.filter((c) => c.source === 'run' && c.target === 'run_with'); + // Unqualified `worker` → workspace scan finds alpha::worker and beta::worker. + // Both alpha and beta are added to the associated set. run_with() exists in + // both namespaces → two candidates → merged narrowing suppression → + // zero CALLS edges (suppressed rather than arbitrary pick). + expect(runWithCalls.length).toBe(0); + }); +}); + +describe('C++ inline namespace — outer::foo resolves to inline child', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-inline-namespace-unqualified'), + () => {}, + ); + }, 60000); + + it('outer::foo() resolves to outer::v1::foo via inline-namespace transitive walking', () => { + const calls = getRelationships(result, 'CALLS'); + const fooCalls = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + // Exactly 1: the inline-namespace exemption lets `outer::foo()` reach + // the declaration in `outer::v1::foo()`. Without U5 the call would be + // unresolved (count = 0). + expect(fooCalls.length).toBe(1); + expect(fooCalls[0].targetFilePath).toContain('lib.h'); + }); +}); + +describe('C++ inline namespace — versioned (v1 inline, v0 not)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-inline-namespace-versioned'), + () => {}, + ); + }, 60000); + + it('outer::foo() resolves to outer::v1::foo (inline child), NOT outer::v0::foo', () => { + const calls = getRelationships(result, 'CALLS'); + const fooCalls = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + // Exactly 1: only inline-namespace children are reachable through the + // enclosing namespace's qualified lookup. `v0` is NOT inline so its + // `foo` is NOT visible as `outer::foo`. + expect(fooCalls.length).toBe(1); + expect(fooCalls[0].targetFilePath).toContain('lib.h'); + }); +}); + +describe('C++ inline namespace — ambiguous same-name across inline children (#1564)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-inline-namespace-ambiguous'), + () => {}, + ); + }, 60000); + + it('outer::foo() emits zero CALLS edges when v1 and v2 both declare foo', () => { + const calls = getRelationships(result, 'CALLS'); + const fooCalls = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + // ISO C++ leaves this ambiguous — both inline namespace children declare + // the same name. The resolver must suppress rather than pick arbitrarily. + expect(fooCalls.length).toBe(0); + }); +}); + +describe('C++ inline namespace — ambiguous distinct signatures (conservative suppress)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-inline-namespace-ambiguous-diff-sigs'), + () => {}, + ); + }, 60000); + + it('outer::foo(42) emits zero CALLS edges when v1 declares foo(int) and v2 declares foo(double)', () => { + const calls = getRelationships(result, 'CALLS'); + const fooCalls = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + // Even though the two overloads have distinct signatures and a compiler + // could disambiguate via argument types, the `resolveQualifiedReceiverMember` + // hook lacks call-site arity/argument-type information, so multi-hit cases + // are conservatively suppressed. Documents the limitation noted in + // inline-namespaces.ts (Finding 1 of Claude review on #1600). + expect(fooCalls.length).toBe(0); + }); +}); + +describe('C++ inline namespace — nested (STL __1-style)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-inline-namespace-nested'), + () => {}, + ); + }, 60000); + + it('outer::foo() resolves through two transitive inline namespaces (v1 then experimental)', () => { + const calls = getRelationships(result, 'CALLS'); + const fooCalls = calls.filter((c) => c.source === 'run' && c.target === 'foo'); + // Exactly 1: the resolver descends inline namespaces depth-first, so + // `outer::foo` reaches `outer::v1::experimental::foo` through two + // transitive inline-namespace hops. Mirrors libc++ `std::__1::vector` + // / libstdc++ `std::__cxx11` qualified-call shape. + expect(fooCalls.length).toBe(1); + expect(fooCalls[0].targetFilePath).toContain('lib.h'); + }); +}); + +describe('C++ inline namespace — ADL participation', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-inline-namespace-adl-participation'), + () => {}, + ); + }, 60000); + + it('ADL surfaces audit::v1::record through inline-namespace transitive walking', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // Exactly 1: `audit::Event e;` resolves Event's enclosing namespace + // to `audit` (the inline child `v1` is transparent — see U2's + // computeNamespaceQName walking through the inline scope). ADL then + // surfaces every callable named `record` in any namespace scope + // matching qname 'audit' across files. Since inline namespaces are + // exempted from the non-globally-visible filter, the `record` + // declared inside `inline namespace v1` is reachable. count=0 + // would be the bug — ADL failing to walk inline children. + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); +}); + +describe('C++ ADL — inline namespace expansion in associated set', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-adl-inline-ns-expansion'), + () => {}, + ); + }, 60000); + + it('record(e) resolves to audit::v1::record when Event is in outer audit and record is in inline v1 (arity-disambiguated from other::record(int))', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'run' && c.target === 'record'); + // ISO C++: inline namespaces are transparent — candidates in + // `audit::v1` are visible as if declared at `audit` level. With a + // competing `other::record(int)` (different arity), the merged + // ordinary+ADL overload narrowing must select `audit::v1::record(Event)` + // since it's the only arity-matching candidate for `record(e)`. + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); +}); + +// --------------------------------------------------------------------------- +// Phase 5 (follow-up plan 2026-05-13-001): cross-unit composition tests. +// Lock in correct interaction between U1 (super-receiver context), U2 (ADL), +// U3 (two-phase lookup), and U5 (inline namespaces). +// --------------------------------------------------------------------------- + +describe('C++ Phase 5 U1×U3 — qualified Base::method() inside template body', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-phase5-u1-u3-qualified-base-call'), + () => {}, + ); + }, 60000); + + it('emits EXTENDS edge: Derived → Base for template base Base', () => { + const extends_ = getRelationships(result, 'EXTENDS'); + expect(edgeSet(extends_)).toContain('Derived → Base'); + }); + + it('Base::method() resolves to Base::method inside template body', () => { + const calls = getRelationships(result, 'CALLS'); + const methodCalls = calls.filter((c) => c.source === 'g' && c.target === 'method'); + expect(methodCalls.length).toBe(1); + expect(methodCalls[0].targetFilePath).toContain('classes.h'); + }); +}); + +describe('C++ Phase 5 U1×U3 — template multi-base list', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-phase5-u1-u3-template-multi-base-list'), + () => {}, + ); + }, 60000); + + it('emits EXTENDS edges: Derived → A, Derived → B for template multi-base list', () => { + const extends_ = getRelationships(result, 'EXTENDS'); + expect(extends_.length).toBe(2); + expect(edgeSet(extends_)).toEqual(['Derived → A', 'Derived → B']); + }); +}); + +describe('C++ Phase 5 U2×U3 — ADL routes around dependent-base shadow', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-phase5-u2-u3-adl-from-derived'), + () => {}, + ); + }, 60000); + + it('record(e) inside Derived::g() resolves via ADL to audit::record (not Base::record)', () => { + const calls = getRelationships(result, 'CALLS'); + const recordCalls = calls.filter((c) => c.source === 'g' && c.target === 'record'); + // Exactly 1: Base::record is class-owned so the global free-call + // fallback's `isFileLocalDef` blocks it (and U3's two-phase + // suppression also fires for unqualified calls inside template + // body when the candidate is a dependent-base member). ADL then + // surfaces audit::record via `audit::Event`'s associated namespace. + // The two-phase + ADL composition leaves exactly one CALLS edge — + // to audit::record in audit.h. + expect(recordCalls.length).toBe(1); + expect(recordCalls[0].targetFilePath).toContain('audit.h'); + }); + + it('record(e) does NOT bind to Base::record (class-owned dependent-base member)', () => { + const calls = getRelationships(result, 'CALLS'); + const baseRecordLeaks = calls.filter( + (c) => c.source === 'g' && c.target === 'record' && c.targetFilePath?.includes('base.h'), + ); + expect(baseRecordLeaks.length).toBe(0); + }); +}); + +describe('C++ Phase 5 U3×U5 — template Derived : outer::v1::Base (inline)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-phase5-u3-u5-inline-base'), + () => {}, + ); + }, 60000); + + it('unqualified f() inside Derived::g() does NOT bind to outer::v1::Base::f (dependent base across inline namespace)', () => { + const calls = getRelationships(result, 'CALLS'); + const fLeaks = calls.filter((c) => c.source === 'g' && c.target === 'f'); + // Exact .toBe(0): same suppression rationale as the plain U3 fixture + // (`cpp-two-phase-dependent-base`) — `f()` is unqualified, Base is a + // dependent base, and Base::f is class-owned so the global free-call + // fallback's `isFileLocalDef` blocks it. The inline-namespace wrapper + // doesn't change the suppression behavior: dependent-base detection + // walks the heritage's simple name (`Base`) regardless of the + // qualifying namespace path. + expect(fLeaks.length).toBe(0); + }); +}); + +describe('C++ Phase 5 U1×U3×U5 — qualified outer::v1::Base::f() inside template body', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'cpp-phase5-u1-u3-u5-qualified-inline-base-call'), + () => {}, + ); + }, 60000); + + it('emits EXTENDS edge: Derived → Base for qualified template base outer::v1::Base', () => { + const extends_ = getRelationships(result, 'EXTENDS'); + expect(edgeSet(extends_)).toContain('Derived → Base'); + }); + + it('outer::v1::Base::f() resolves to Base::f inside template body', () => { + const calls = getRelationships(result, 'CALLS'); + const fCalls = calls.filter((c) => c.source === 'g' && c.target === 'f'); + expect(fCalls.length).toBe(1); + expect(fCalls[0].targetFilePath).toContain('base.h'); + }); + + it('outer::v1::free_fn() resolves as a namespace free function, not a super-receiver method', () => { + const calls = getRelationships(result, 'CALLS'); + const freeCalls = calls.filter((c) => c.source === 'g' && c.target === 'free_fn'); + expect(freeCalls.length).toBe(1); + expect(freeCalls[0].targetLabel).toBe('Function'); + expect(freeCalls[0].rel.reason).toBe('import-resolved'); + }); +}); diff --git a/gitnexus/test/integration/resolvers/helpers.ts b/gitnexus/test/integration/resolvers/helpers.ts index e92526b19..ae2a75f04 100644 --- a/gitnexus/test/integration/resolvers/helpers.ts +++ b/gitnexus/test/integration/resolvers/helpers.ts @@ -9,6 +9,18 @@ import type { PipelineResult } from '../../../src/types/pipeline.js'; import type { GraphRelationship } from 'gitnexus-shared'; const LEGACY_RESOLVER_PARITY_EXPECTED_FAILURES: Readonly>> = { + c: new Set([ + // The legacy DAG path does not resolve the main → create_service call + // because the function prototype in the .h file and the definition in + // the .c file create a dedup ambiguity. The registry-primary path + // resolves it via scope-based wildcard import binding. + 'emits CALLS edges for cross-file function calls', + // The legacy DAG path does not resolve cross-file calls through + // #include → prototype chains. The scope-based path resolves + // caller.c → b.h → public_b via wildcard import binding + + // isFileLocalDef filtering of static functions. + 'caller.c calls b:helper via include, NOT a:static helper', + ]), csharp: new Set([ 'emits the using-import edge App/Program.cs -> Models/User.cs through the scope-resolution path', // Generic type-argument USES edges are emitted by the registry-primary @@ -22,6 +34,52 @@ const LEGACY_RESOLVER_PARITY_EXPECTED_FAILURES: Readonlymethod()` precedence inside a class that composes a trait AND + // extends a parent both defining the same method requires the augmented + // trait-aware MRO (trait shadows parent). The legacy DAG has no + // trait-aware MRO, so it fails to bind the call to the trait. Scope- + // resolver-only correctness win (commit af9af4a9 U3). + '$this->record() still resolves to Auditable::record (trait shadows parent)', + // Fully-qualified type-hint resolution (`\App\Other\User $u` parameter) + // routes through the scope-resolver's bindingAugmentations channel + // populated by `populatePhpNamespaceSiblings` Step 3b. The legacy DAG + // resolves receiver types via simple-name workspace lookup and has no + // namespace-prefixed binding channel, so it cannot distinguish the FQN + // target from a same-simple-name class reachable via `use`. Scope- + // resolver-only correctness win (Codex PR #1497 review, finding 1). + '\\App\\Other\\User parameter resolves $u->record() to app/Other/User.php (NOT app/Models/User.php)', + // MRO arity-mismatch on class-name receivers (`Child::method(1)` where + // Child::method takes 2 args and Parent::method takes 1): the legacy + // DAG has no arity narrowing on Case 2 (class-name) MRO walk, so it + // emits a false CALLS edge to Parent::method on fallthrough. Scope- + // resolver-only correctness win (PR #1497 review Image 1 / U1). + 'arity-incompatible most-derived override does NOT fall through to ParentModel::method', + // Class-name receiver with single-class arity mismatch (no parent in + // the MRO chain): legacy resolves the method by name without arity + // gating, so it emits a CALLS edge even when arity is definitively + // incompatible. The scope-resolver's `narrowOverloadCandidates` check + // in `receiver-bound-calls.ts` Case 2 rejects this post-fix. Scope- + // resolver-only correctness win (PR #1497 / U1). + 'arity-incompatible class with no parent emits zero CALLS edges (regression check)', + // `phpEmitUnresolvedReceiverEdges` exact-required-arity gate (PR + // #1497 / U4): the legacy DAG has no equivalent unresolved-receiver + // fallback hook, so it resolves these untyped-receiver sites via a + // different code path that over-emits for default-parameter and + // variadic-required-mismatch shapes. Scope-resolver-only correctness + // wins; backporting to legacy is out of scope. + 'argCount > required (2>1) on candidate with default param emits NO edge post-fix', + 'variadic candidate, argCount < required (1<2) emits NO edge', + ]), python: new Set([ // Suffix-fallback lex tiebreak depends on the registry-primary // resolver's deterministic sort. The legacy resolver returns the @@ -32,6 +90,120 @@ const LEGACY_RESOLVER_PARITY_EXPECTED_FAILURES: Readonly([ + // The legacy DAG path has no scope-aware filtering on the global + // free-call fallback, so `#include`d headers still leak class + // methods (`User::save`) and namespace members (`ns::foo`) as + // resolution targets for unqualified calls. The scope-resolver + // path filters via `populateCppNonGloballyVisible` + + // `isFileLocalDef`. Scope-resolver-only correctness win + // (PR #1520 review follow-up plan U1); backporting to legacy is + // out of scope. + 'does NOT resolve unqualified save() to User::save via #include', + 'does NOT resolve unqualified foo() to ns::foo via #include', + // The legacy DAG path lacks the OVERLOAD_AMBIGUOUS suppression + // wired through `pickOverload` + `isOverloadAmbiguousAfterNormalization`, + // so it arbitrarily picks the first overload when `f(int)` and + // `f(long)` collide after C++ integer-width normalization. Scope- + // resolver-only correctness win (PR #1520 review follow-up plan U2 / + // Claude review Finding 5); backporting to legacy is out of scope. + 'emits zero CALLS edges when process(int)/process(long) collide after normalization', + // The legacy DAG path resolves `using namespace a; using namespace b; foo()` + // by walking the workspace registry by simple name and binding to + // the first match — same shape as the integer-width collision, just + // with namespace-resolution as the ambiguity source. Scope-resolver- + // only correctness win (PR #1520 review follow-up plan U4 / Claude + // review Finding 7); backporting to legacy is out of scope. + 'emits zero CALLS edges for ambiguous foo() bound via two using-namespace declarations', + // The legacy DAG path lacks two-phase template lookup. Unqualified + // calls inside a class template body bind to dependent-base members + // there, producing CALLS edges the compiler would reject (ISO C++ + // two-phase name lookup). Scope-resolver-only correctness win + // (PR #1520 review follow-up plan 2026-05-13-001 U3); backporting + // is out of scope. + 'Derived::g() -> f() does NOT bind to Base::f (dependent base)', + // The legacy DAG path does not apply merged ordinary+ADL narrowing + // with ambiguity suppression. + // When ADL surfaces multiple overloads that collide after C++ + // int/long normalization, legacy picks the first match arbitrarily. + // The scope-resolver path suppresses in free-call-fallback after + // merged-candidate overload narrowing. Scope-resolver-only + // correctness win (PR #1520 review follow-up plan + // 2026-05-13-001 U2); backporting is out of scope. + 'process(t, 42) emits zero CALLS edges when ADL surfaces process(Token,int)/process(Token,long) (collide after C++ int normalization)', + // Legacy DAG path does not merge ordinary and ADL candidate sets for + // non-empty ordinary lookup, so it misses ADL's better-match overload. + 'swap(a, b) prefers data::swap(Pair&, Pair&) over app::swap(int, int)', + // The legacy DAG path has no qualified namespace-member resolver + // and no inline-namespace awareness. For the versioned fixture + // (`outer::v1::foo` inline, `outer::v0::foo` not), the registry- + // primary path resolves `outer::foo()` to v1 via the inline + // exemption; legacy can't see EITHER and emits zero edges. The + // unqualified / nested fixtures coincidentally resolve in legacy + // because their global free-call fallback picks the unique simple- + // name match; the versioned fixture has two `foo`s and legacy can't + // disambiguate. Scope-resolver-only correctness win (PR #1520 + // review follow-up plan 2026-05-13-001 U5); backporting is out of + // scope. + 'outer::foo() resolves to outer::v1::foo (inline child), NOT outer::v0::foo', + // Phase 5 cross-unit composition tests assert no false positives + // for compositions where the legacy DAG over-resolves. The legacy + // path has no template-arg-stripping qualified-receiver logic and + // no two-phase dependent-base suppression, so it produces CALLS + // edges where the registry-primary path correctly suppresses. + // Scope-resolver-only correctness wins (PR #1520 review follow-up + // plan 2026-05-13-001 Phase 5); backporting is out of scope. + 'emits EXTENDS edge: Derived → Base for template base Base', + 'emits EXTENDS edges: Derived → A, Derived → B for template multi-base list', + 'Base::method() resolves to Base::method inside template body', + 'unqualified f() inside Derived::g() does NOT bind to outer::v1::Base::f (dependent base across inline namespace)', + 'emits EXTENDS edge: Derived → Base for qualified template base outer::v1::Base', + 'outer::v1::Base::f() resolves to Base::f inside template body', + 'outer::v1::free_fn() resolves as a namespace free function, not a super-receiver method', + // Template specialization owner identity currently relies on + // class-template fingerprints in the registry-primary graph bridge. + // Legacy DAG collapses specializations to the simple class name. + 'emits distinct Class nodes for List and List', + 'callSave() in each specialization resolves to its own save()', + 'save specialization bodies route to their own sibling method', + // PR #1590 follow-up: explicit `this->` resolution in template class + // bodies and paired two-phase assertions are scope-resolver-only. + // Legacy DAG lacks this receiver-bound template semantics and + // dependent-base suppression parity for these shapes. + 'Derived::g() -> this->f() resolves to f (1 edge)', + 'Derived::k() -> this->base_method() resolves via EXTENDS chain (1 edge)', + 'Derived::g_unqualified() -> f() does NOT bind to Base::f', + 'Derived::g_this() -> this->f() resolves to Base::f (1 edge)', + 'Derived::g() -> this->f() emits zero CALLS edges when only hidden derived overload is arity-incompatible', + // The legacy DAG path has no inline-namespace same-name ambiguity + // detection. When two inline children declare the same name, the + // legacy path picks an arbitrary match. The scope-resolver returns + // 'ambiguous' and suppresses edge emission. Scope-resolver-only + // correctness win (#1564); backporting to legacy is out of scope. + 'outer::foo() emits zero CALLS edges when v1 and v2 both declare foo', + // Distinct-signature inline-namespace ambiguity: `foo(int)` in v1 and + // `foo(double)` in v2. The scope-resolver conservatively suppresses + // because `resolveQualifiedReceiverMember` lacks call-site argument + // types. Legacy DAG has no inline-namespace resolver. Scope-resolver- + // only correctness win (#1600 / Claude review Finding 1). + 'outer::foo(42) emits zero CALLS edges when v1 declares foo(int) and v2 declares foo(double)', + // PR #1598: ADL free-function reference arg negative fixtures rely on + // scope-resolver-only correctness. The legacy DAG falls back to + // `pickUniqueGlobalCallable` which resolves the callee by simple-name + // workspace lookup, ignoring argument analysis. These fixtures expect + // zero CALLS edges (the registry-primary path correctly avoids a false- + // positive), but the legacy path emits one edge via the global fallback. + // Scope-resolver-only correctness wins; backporting is out of scope. + 'process(data::value) emits zero CALLS edges \u2014 data::value is a variable, not a function', + 'run_with(callback) emits zero CALLS edges when callback is a parameter, not a function reference', + // PR #1599 adversarial review findings: nearest-scope ADL blocker + // semantics and block-scope function declaration ADL suppression are + // scope-resolver-only. The legacy DAG has no scope-aware ADL blocker + // detection; it falls back to `pickUniqueGlobalCallable`. Scope- + // resolver-only correctness wins; backporting is out of scope. + 'swap(a,b) resolves to data::swap when inner scope has callable swap and outer has variable', + 'record(e) emits zero CALLS when a block-scope function declaration exists', + ]), }; type ResolverParityEnv = Readonly>; diff --git a/gitnexus/test/integration/resolvers/java.test.ts b/gitnexus/test/integration/resolvers/java.test.ts index d9bae90bf..8a813525b 100644 --- a/gitnexus/test/integration/resolvers/java.test.ts +++ b/gitnexus/test/integration/resolvers/java.test.ts @@ -1,11 +1,12 @@ /** * Java: class extends + implements multiple interfaces + ambiguous package disambiguation */ -import { describe, it, expect, beforeAll } from 'vitest'; +import { describe, expect, beforeAll } from 'vitest'; import path from 'path'; import { FIXTURES, CROSS_FILE_FIXTURES, + createResolverParityIt, getRelationships, getNodesByLabel, getNodesByLabelFull, @@ -14,6 +15,8 @@ import { type PipelineResult, } from './helpers.js'; +const it = createResolverParityIt('java'); + // --------------------------------------------------------------------------- // Heritage: class extends + implements multiple interfaces // --------------------------------------------------------------------------- @@ -438,6 +441,54 @@ describe('Java variadic call resolution', () => { } expect(allDangling).toEqual([]); }); + + it('resolves 2-arg call to fixed-prefix varargs method format(int, String...) in Formatter.java', () => { + const calls = getRelationships(result, 'CALLS'); + const fmtCall = calls.find((c) => c.target === 'format' && c.source === 'run'); + expect(fmtCall).toBeDefined(); + expect(fmtCall!.targetFilePath).toBe('com/example/util/Formatter.java'); + }); + + it('0-arg call to format(int, String...) still resolves in legacy mode (arity rejection is registry-only)', () => { + // In REGISTRY_PRIMARY_JAVA=1 mode, `requiredParameterCount = 1` causes + // `javaArityCompatibility` to return 'incompatible' for 0-arg calls, + // preventing the CALLS edge. In default (legacy) mode, arity is not + // enforced so the edge is created. This test documents the legacy + // behavior; the negative assertion is a flip-blocker for registry-primary. + const calls = getRelationships(result, 'CALLS'); + const zeroArgFmtCall = calls.find((c) => c.target === 'format' && c.source === 'badCall'); + expect(zeroArgFmtCall).toBeDefined(); + }); +}); + +// --------------------------------------------------------------------------- +// Wildcard import: `import com.example.models.*` resolves to a package file +// --------------------------------------------------------------------------- + +describe('Java wildcard import resolution', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'java-wildcard-import'), () => {}); + }, 60000); + + it('parses wildcard import without errors and creates graph nodes', () => { + // The wildcard import (`import com.example.models.*`) exercises the + // directoryChild branch in resolveJavaImportTarget. Even if no IMPORTS + // edge is created (nondeterministic file selection — documented flip + // blocker), the graph must contain valid nodes for all classes. + const classes = getNodesByLabel(result, 'Class'); + expect(classes).toContain('Main'); + expect(classes).toContain('User'); + expect(classes).toContain('Order'); + }); + + it('resolves user.save() call via wildcard-imported User', () => { + const calls = getRelationships(result, 'CALLS'); + const saveCall = calls.find((c) => c.target === 'save' && c.source === 'run'); + expect(saveCall).toBeDefined(); + expect(saveCall!.targetFilePath).toBe('com/example/models/User.java'); + }); }); // --------------------------------------------------------------------------- diff --git a/gitnexus/test/integration/resolvers/php.test.ts b/gitnexus/test/integration/resolvers/php.test.ts index e120d92f4..336e5dee2 100644 --- a/gitnexus/test/integration/resolvers/php.test.ts +++ b/gitnexus/test/integration/resolvers/php.test.ts @@ -1,11 +1,12 @@ /** * PHP: PSR-4 imports, extends, implements, trait use, enums, calls + ambiguous disambiguation */ -import { describe, it, expect, beforeAll } from 'vitest'; +import { describe, expect, beforeAll } from 'vitest'; import path from 'path'; import { FIXTURES, CROSS_FILE_FIXTURES, + createResolverParityIt, getRelationships, getNodesByLabel, getNodesByLabelFull, @@ -14,6 +15,12 @@ import { type PipelineResult, } from './helpers.js'; +// Wrap vitest's `it` so legacy-DAG-only divergences (commit af9af4a9 U1/U3) +// are skipped under REGISTRY_PRIMARY_PHP=0. The skip list lives in +// helpers.ts:LEGACY_RESOLVER_PARITY_EXPECTED_FAILURES.php — sibling pattern +// to csharp/typescript/python. +const it = createResolverParityIt('php'); + // --------------------------------------------------------------------------- // Heritage: PSR-4 imports, extends, implements, trait use, enums, calls // --------------------------------------------------------------------------- @@ -91,6 +98,10 @@ describe('PHP heritage & import resolution', () => { expect(targets).toContain('label'); }); + // save($entity: mixed) calls $entity->getId() — the receiver is typed `mixed` + // so there is no TypeRef in scope. The scope-resolver `emitUnresolvedReceiverEdges` + // hook (PHP-wired) recovers this case via workspace-wide unique-name lookup, + // matching the legacy DAG behavior. it('emits CALLS edge: save → getId', () => { const calls = getRelationships(result, 'CALLS').filter( (e) => e.source === 'save' && e.target === 'getId', @@ -439,6 +450,161 @@ describe('PHP variadic call resolution', () => { }); }); +// --------------------------------------------------------------------------- +// Variadic arity minimum: required-arg count must be enforced for variadic +// functions. f(int $req, ...$rest) called as f() is an ArgumentCountError at +// PHP runtime and must NOT emit a CALLS edge from the resolver. +// --------------------------------------------------------------------------- + +describe('PHP variadic arity minimum (U1)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-variadic-arity-minimum'), () => {}); + }, 60000); + + const callsFrom = (source: string, target: string) => + getRelationships(result, 'CALLS').filter((c) => c.source === source && c.target === target); + + it('emits CALLS edge for record(level, ...msgs) with arity 4 (happy path)', () => { + expect(callsFrom('callValidRecord', 'record').length).toBe(1); + }); + + it('emits CALLS edge for record(level) with only the required arg (arity 1)', () => { + expect(callsFrom('callValidRecordMin', 'record').length).toBe(1); + }); + + it('does NOT emit CALLS edge for record() with zero args (below required=1)', () => { + expect(callsFrom('callTooFewRecord', 'record').length).toBe(0); + }); + + it('emits CALLS edge for format() — pure variadic, required=0', () => { + expect(callsFrom('callPureVariadic', 'format').length).toBe(1); + }); + + it('emits CALLS edge for pad("x") — required+optional+variadic, only required given', () => { + expect(callsFrom('callPadMin', 'pad').length).toBe(1); + }); + + it('does NOT emit CALLS edge for pad() with zero args (below required=1)', () => { + expect(callsFrom('callPadTooFew', 'pad').length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// Transitive trait MRO: trait A uses B uses C — Consumer using A must see C's +// methods. Current depth-2 expansion in buildPhpMro silently drops methods +// from 3+ level chains. +// --------------------------------------------------------------------------- + +describe('PHP transitive trait MRO (U2)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-transitive-traits'), () => {}); + }, 60000); + + const callsFrom = (source: string, target: string) => + getRelationships(result, 'CALLS').filter((c) => c.source === source && c.target === target); + + it('detects 3 traits and 1 class', () => { + expect(getNodesByLabel(result, 'Trait')).toEqual(['TraitA', 'TraitB', 'TraitC']); + expect(getNodesByLabel(result, 'Class')).toContain('Consumer'); + }); + + it('depth-1: $this->aMethod() resolves to TraitA::aMethod', () => { + expect(callsFrom('callDepthOne', 'aMethod').length).toBe(1); + }); + + it('depth-2: $this->bMethod() resolves to TraitB::bMethod (TraitA uses TraitB)', () => { + expect(callsFrom('callDepthTwo', 'bMethod').length).toBe(1); + }); + + it('depth-3: $this->deepMethod() resolves to TraitC::deepMethod (TraitA → TraitB → TraitC)', () => { + expect(callsFrom('callDepthThree', 'deepMethod').length).toBe(1); + }); +}); + +// --------------------------------------------------------------------------- +// parent:: bypasses traits. When a class composes a trait AND extends a parent +// that both define the same method name, parent::method() must resolve to the +// parent class (PHP semantics), NOT the trait. $this->method() still goes to +// the trait (PHP's own-class > trait > parent precedence). +// --------------------------------------------------------------------------- + +describe('PHP parent:: bypasses traits (U3)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-parent-vs-trait'), () => {}); + }, 60000); + + const callsFromTo = (source: string, target: string, file: string) => + getRelationships(result, 'CALLS').filter( + (c) => c.source === source && c.target === target && c.targetFilePath === file, + ); + + it('parent::record() resolves to Base::record, NOT Auditable::record', () => { + expect(callsFromTo('callViaParent', 'record', 'app/Base.php').length).toBe(1); + expect(callsFromTo('callViaParent', 'record', 'app/Auditable.php').length).toBe(0); + }); + + it('$this->record() still resolves to Auditable::record (trait shadows parent)', () => { + expect(callsFromTo('callViaThis', 'record', 'app/Auditable.php').length).toBe(1); + expect(callsFromTo('callViaThis', 'record', 'app/Base.php').length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// Namespace-aware free-call fallback. PHP's `pickUniqueGlobalCallable` must +// reject cross-namespace candidates that the caller can't reach without an +// explicit `use function` import. Same-namespace and globally-imported calls +// still emit edges. +// --------------------------------------------------------------------------- + +describe('PHP namespace-aware free-call fallback (U4)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'php-namespace-fallback-isolation'), + () => {}, + ); + }, 60000); + + const callsFromTo = (source: string, target: string, file?: string) => + getRelationships(result, 'CALLS').filter( + (c) => + c.source === source && + c.target === target && + (file === undefined || c.targetFilePath === file), + ); + + it('rejects cross-namespace candidate when caller has no use-function import', () => { + // callNoImport (in \App) calls format('x'). Workspace has \App\Utils\format/1 + // and \Vendor\Utils\format/2. Caller is in \App — NOT same namespace as + // either candidate, and no `use function` for `format` is in scope. + // Expected: NO CALLS edge. + expect(callsFromTo('callNoImport', 'format').length).toBe(0); + }); + + it('resolves same-namespace free call (caller in App\\Utils → App\\Utils\\format)', () => { + expect(callsFromTo('callSameNamespace', 'format', 'src/App/Utils/Format.php').length).toBe(1); + }); + + it('resolves use-function-imported alias (vendorFormat → Vendor\\Utils\\format)', () => { + // `use function Vendor\Utils\format as vendorFormat;`. Caller in \App calls + // vendorFormat('x', 80) — the import target is reachable. The CALLS edge + // may surface against either the alias name (`vendorFormat`) or the + // canonical function name (`format` in the vendor file) depending on + // dedup ordering; either way, exactly one edge total. + expect( + callsFromTo('callImported', 'vendorFormat').length + + callsFromTo('callImported', 'format', 'src/Vendor/Utils/Format.php').length, + ).toBe(1); + }); +}); + // --------------------------------------------------------------------------- // Local shadow: same-file definition takes priority over imported name // --------------------------------------------------------------------------- @@ -1807,3 +1973,325 @@ describe('PHP Child extends ParentClass — inherited method resolution (SM-9)', expect(parentMethodCall!.source).toBe('run'); }); }); + +// --------------------------------------------------------------------------- +// Fully-qualified type-hint resolution (Codex PR #1497 review, finding 1). +// +// Two `User` classes coexist in the workspace: `App\Models\User` and +// `App\Other\User`. A service file imports the simple-name `User` from +// App\Models, but uses a fully-qualified `\App\Other\User` in a parameter +// annotation. PHP runtime semantics: the leading `\` is an absolute namespace +// path; the parameter is always `App\Other\User`, even when the simple +// `User` is bound to a different class by `use`. +// +// Pre-fix: `normalizePhpType` strips the qualifier so the TypeRef carries +// only `User`, then `findClassBindingInScope` walks the scope chain and +// resolves to the imported `App\Models\User` — emitting a CALLS edge to the +// wrong class. Post-fix: qualified form survives on `rawName`, the +// QualifiedNameIndex fallback (or a PHP-specific qualified lookup) routes +// the call to App\Other\User::record. +// --------------------------------------------------------------------------- + +describe('PHP fully-qualified type-hint resolution (Codex #1497)', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-fqn-cross-namespace'), () => {}); + }, 60000); + + const callsFromTo = (source: string, target: string, file: string) => + getRelationships(result, 'CALLS').filter( + (c) => c.source === source && c.target === target && c.targetFilePath === file, + ); + + it('detects both User classes in distinct namespaces', () => { + expect(getNodesByLabel(result, 'Class')).toContain('User'); + // Exactly two User entries — one per namespace. + const userClasses = getNodesByLabelFull(result, 'Class').filter((n) => n.name === 'User'); + expect(userClasses.length).toBe(2); + const userFiles = userClasses.map((c) => c.properties.filePath as string).sort(); + expect( + userFiles.some((f) => f.includes('Models/User.php') || f.includes('Models\\User.php')), + ).toBe(true); + expect( + userFiles.some((f) => f.includes('Other/User.php') || f.includes('Other\\User.php')), + ).toBe(true); + }); + + it('\\App\\Other\\User parameter resolves $u->record() to app/Other/User.php (NOT app/Models/User.php)', () => { + // The bug Codex flagged: FQN parameter collapses to simple `User`, then + // resolves to the imported `App\Models\User` instead of the explicit + // `\App\Other\User` named in the annotation. Post-fix: exactly one edge, + // pointing to the FQN target. + expect(callsFromTo('save', 'record', 'app/Other/User.php').length).toBe(1); + expect(callsFromTo('save', 'record', 'app/Models/User.php').length).toBe(0); + }); + + it('simple-name `User $u` parameter resolves to the imported App\\Models\\User (control case)', () => { + // Sanity check that unqualified type-hint resolution still works via the + // `use App\Models\User;` import. Without this control, U2's normalizer + // change could regress the simple-name path and we'd miss it. + expect(callsFromTo('saveLocal', 'record', 'app/Models/User.php').length).toBe(1); + expect(callsFromTo('saveLocal', 'record', 'app/Other/User.php').length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// MRO arity-mismatch: most-derived override with incompatible arity must NOT +// fall through to an arity-compatible ancestor (PHP throws ArgumentCountError +// at runtime). See receiver-bound-calls.ts Case 2. +// --------------------------------------------------------------------------- + +describe('PHP MRO arity-mismatch fallthrough', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-mro-arity-mismatch'), () => {}); + }, 60000); + + const callsFromTo = (source: string, target: string, targetFilePath: string) => + getRelationships(result, 'CALLS').filter( + (c) => c.source === source && c.target === target && c.targetFilePath === targetFilePath, + ); + + it('detects ParentModel, ChildModel, Orphan, and Caller classes', () => { + expect(getNodesByLabel(result, 'Class')).toEqual([ + 'Caller', + 'ChildModel', + 'Orphan', + 'ParentModel', + ]); + }); + + it('arity-incompatible most-derived override does NOT fall through to ParentModel::method', () => { + // Pre-fix bug: `$child->method(1)` with ChildModel::method(int,int) and + // ParentModel::method(int) would emit a false CALLS edge to ParentModel::method. + // Post-fix: zero CALLS edges from callIncompatible for this site. + expect(callsFromTo('callIncompatible', 'method', 'app/Models/ParentModel.php').length).toBe(0); + expect(callsFromTo('callIncompatible', 'method', 'app/Models/ChildModel.php').length).toBe(0); + }); + + it('arity-compatible most-derived override emits exactly one CALLS edge to ChildModel::compat', () => { + // Happy path: ChildModel::compat(int) matches the call site $child->compat(1). + expect(callsFromTo('callCompatible', 'compat', 'app/Models/ChildModel.php').length).toBe(1); + expect(callsFromTo('callCompatible', 'compat', 'app/Models/ParentModel.php').length).toBe(0); + }); + + it('arity-incompatible class with no parent emits zero CALLS edges (regression check)', () => { + // Orphan::method(int,int) called with one arg, no parent class — must remain + // unresolved both before and after the fix. + expect(callsFromTo('callNoParent', 'method', 'app/Models/Orphan.php').length).toBe(0); + }); + + it('arity-compatible most-derived call still resolves to ChildModel::method (happy path)', () => { + // Ensure the fix did not break compatible-arity resolution. + expect(callsFromTo('callMostDerivedHappy', 'method', 'app/Models/ChildModel.php').length).toBe( + 1, + ); + expect(callsFromTo('callMostDerivedHappy', 'method', 'app/Models/ParentModel.php').length).toBe( + 0, + ); + }); +}); + +// --------------------------------------------------------------------------- +// @declaration.variable double-match dedup on typed properties. +// Pre-fix, the catch-all property pattern in query.ts (no `type:` constraint) +// also matched typed property declarations and emitted a stray Variable def +// alongside the legitimate Property def. captures.ts now pre-scans rawMatches +// for @declaration.property anchors and suppresses the duplicate. +// --------------------------------------------------------------------------- + +describe('PHP typed-property double-match dedup', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-typed-property-dedup'), () => {}); + }, 60000); + + it('detects the Mixed class', () => { + expect(getNodesByLabel(result, 'Class')).toContain('Mixed'); + }); + + it('emits exactly one Property def for the typed property `$repo`', () => { + const properties = getNodesByLabel(result, 'Property'); + expect(properties.filter((n) => n === 'repo').length).toBe(1); + }); + + it('emits exactly one Property def for the constructor-promoted typed `$promotedRepo`', () => { + const properties = getNodesByLabel(result, 'Property'); + expect(properties.filter((n) => n === 'promotedRepo').length).toBe(1); + }); + + it('emits zero stray Variable defs for typed property and promoted typed parameter', () => { + // Pre-fix: a Variable def named `$repo` and `$promotedRepo` (no `$` strip) + // would slip through the catch-all pattern. Post-fix: zero. + const variables = getNodesByLabel(result, 'Variable'); + expect(variables.filter((n) => n === '$repo' || n === 'repo').length).toBe(0); + expect(variables.filter((n) => n === '$promotedRepo' || n === 'promotedRepo').length).toBe(0); + }); + + it('untyped property `$id` still emits its catch-all Property def (regression check)', () => { + // The untyped catch-all @declaration.variable pattern is the legitimate + // path for `public $id;`. Make sure the cross-match dedup does not + // over-suppress untyped declarations — they have no @declaration.property + // sibling, so their anchor is not in the typedPropertyAnchorIds set. + const properties = getNodesByLabel(result, 'Property'); + expect(properties.filter((n) => n === 'id').length).toBe(1); + }); + + it('no `$`-prefixed Property or Variable defs leak from typed declarations', () => { + // The catch-all branch does NOT run the `$`-strip normalization, so any + // def it produces for a typed property carries a `$`-prefixed name — + // a known receiver-binding lookup pollution vector. Post-fix the + // catch-all is suppressed for typed property_declaration anchors, so + // no `$repo` / `$promotedRepo` def should appear at any label. + for (const n of result.graph.iterNodes()) { + const name = String(n.properties.name); + if (name === '$repo' || name === '$promotedRepo') { + throw new Error(`leaked $-prefixed def: ${n.label}|${name}|${n.id}`); + } + } + }); +}); + +// --------------------------------------------------------------------------- +// Dynamic PHP constructs MUST NOT capture as resolvable references. +// Findings 1-7 of the PR #1497 adversarial review confirmed via grammar +// inspection that $obj->$method(), call_user_func(...), array/string +// callables, and dynamic property reads produce zero captures. This suite +// locks that invariant in regression so a future query.ts edit cannot +// silently relax `name: (name)` to `name: (_)` and reintroduce false- +// positive edges. +// --------------------------------------------------------------------------- + +describe('PHP dynamic dispatch — negative regression suite', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo(path.join(FIXTURES, 'php-dynamic-calls'), () => {}); + }, 60000); + + const callsFromDynamicTo = (target: string) => + getRelationships(result, 'CALLS').filter( + (c) => + c.target === target && + // Source is some method on `Dynamic` (the file under test). + c.sourceFilePath === 'app/Services/Dynamic.php', + ); + + it('detects the Dynamic and Targets classes', () => { + expect(getNodesByLabel(result, 'Class')).toContain('Dynamic'); + expect(getNodesByLabel(result, 'Class')).toContain('Targets'); + }); + + it('sanity check: non-dynamic call DOES emit an edge', () => { + // Without this, every zero-edge assertion below would pass even if the + // pipeline emitted no CALLS edges at all. + expect(callsFromDynamicTo('sanityStaticallyNamedTarget').length).toBe(1); + }); + + it('$obj->$method() emits no CALLS edge to dynamicProcess', () => { + expect(callsFromDynamicTo('dynamicProcess').length).toBe(0); + }); + + it('$obj->{$method}() emits no CALLS edge to dynamicBrace', () => { + expect(callsFromDynamicTo('dynamicBrace').length).toBe(0); + }); + + it('Class::$method() emits no CALLS edge to dynamicHandle', () => { + expect(callsFromDynamicTo('dynamicHandle').length).toBe(0); + }); + + it('$className::method() with untyped variable receiver emits no CALLS edge', () => { + // Two attractor classes (Targets and OtherTargets) both expose + // dynamicStaticMethod so the unresolved-receiver fallback (Finding 8 / + // U4) cannot fire — that isolates this assertion to the dynamic- + // dispatch suppression at the query / receiver-bound-calls layer. + expect(callsFromDynamicTo('dynamicStaticMethod').length).toBe(0); + }); + + it('$className::$method() with dynamic class and method names emits no CALLS edge', () => { + expect(callsFromDynamicTo('dynamicScopedDynName').length).toBe(0); + }); + + it('call_user_func / call_user_func_array string and array callables emit no CALLS edges', () => { + // call_user_func itself is a built-in with no workspace def, so the + // free-call to it is unresolved — no edge to `call_user_func`. + expect(callsFromDynamicTo('call_user_func').length).toBe(0); + expect(callsFromDynamicTo('call_user_func_array').length).toBe(0); + // None of the named targets reachable only via the callable argument + // should pick up a false-positive edge. + expect(callsFromDynamicTo('dynamicCallableMethod').length).toBe(0); + expect(callsFromDynamicTo('dynamicArrayCallableMethod').length).toBe(0); + expect(callsFromDynamicTo('dynamicArrayClassCallableMethod').length).toBe(0); + }); + + it('dynamic property read ($obj->$prop) emits no read-edge to dynamicProp', () => { + // No read-access property capture pattern exists in query.ts at all + // (Finding 2). Verify no CALLS / READS / write edge targets `dynamicProp`. + expect(callsFromDynamicTo('dynamicProp').length).toBe(0); + const reads = getRelationships(result, 'READS').filter( + (r) => r.target === 'dynamicProp' && r.sourceFilePath === 'app/Services/Dynamic.php', + ); + expect(reads.length).toBe(0); + }); +}); + +// --------------------------------------------------------------------------- +// phpEmitUnresolvedReceiverEdges exact-required-arity gate (Finding 8 / U4). +// The 0.6-confidence fallback for untyped receivers now requires argCount +// to exactly match the candidate's required parameter count for fixed- +// arity candidates. Variadic candidates keep the relaxed argCount >= +// required semantics. +// --------------------------------------------------------------------------- + +describe('PHP unresolved-receiver fallback exact-required-arity gate', () => { + let result: PipelineResult; + + beforeAll(async () => { + result = await runPipelineFromRepo( + path.join(FIXTURES, 'php-unresolved-receiver-arity'), + () => {}, + ); + }, 60000); + + const fallbackEdgeFromTo = (source: string, target: string) => + getRelationships(result, 'CALLS').filter( + (c) => + c.source === source && c.target === target && c.targetFilePath === 'app/Models/Handler.php', + ); + + it('detects Handler and Caller classes', () => { + expect(getNodesByLabel(result, 'Class')).toContain('Handler'); + expect(getNodesByLabel(result, 'Class')).toContain('Caller'); + }); + + it('happy path: argCount === required (0===0) emits 0.6 fallback edge', () => { + expect(fallbackEdgeFromTo('callHappyPath', 'happyPath').length).toBe(1); + }); + + it('argCount === required (1===1) on candidate with default param still emits edge', () => { + expect(fallbackEdgeFromTo('callDefaultExactRequired', 'withDefault').length).toBe(1); + }); + + it('argCount > required (2>1) on candidate with default param emits NO edge post-fix', () => { + // Pre-fix: first-stage narrowOverloadCandidates accepted (1 <= 2 <= 2). + // Post-fix: exact-required gate rejects (2 !== 1). + expect(fallbackEdgeFromTo('callDefaultBeyondRequired', 'withDefault').length).toBe(0); + }); + + it('variadic candidate, argCount === required (1===1) emits edge', () => { + expect(fallbackEdgeFromTo('callVariadicAtRequired', 'variadicLog').length).toBe(1); + }); + + it('variadic candidate, argCount > required (2>1) emits edge (relaxed)', () => { + expect(fallbackEdgeFromTo('callVariadicBeyondRequired', 'variadicLog').length).toBe(1); + }); + + it('variadic candidate, argCount < required (1<2) emits NO edge', () => { + expect(fallbackEdgeFromTo('callVariadicBelowRequired', 'variadicLogTwoRequired').length).toBe( + 0, + ); + }); +}); diff --git a/gitnexus/test/integration/resolvers/typescript-esm-js-extension.test.ts b/gitnexus/test/integration/resolvers/typescript-esm-js-extension.test.ts new file mode 100644 index 000000000..476082563 --- /dev/null +++ b/gitnexus/test/integration/resolvers/typescript-esm-js-extension.test.ts @@ -0,0 +1,62 @@ +/** + * Integration test: TypeScript ESM .js extension imports produce CALLS edges. + * + * Verifies the full pipeline: .js import → resolveImportPath strips .js → + * resolves to .ts → scope-resolver emits CALLS edge. + */ +import { describe, it, expect, beforeAll, afterAll } from 'vitest'; +import path from 'path'; +import fs from 'node:fs'; +import os from 'node:os'; +import { getRelationships, runPipelineFromRepo, type PipelineResult } from './helpers.js'; + +function writeFixtureRepo(root: string, files: Record): void { + for (const [relPath, content] of Object.entries(files)) { + const fullPath = path.join(root, relPath); + fs.mkdirSync(path.dirname(fullPath), { recursive: true }); + fs.writeFileSync(fullPath, content, 'utf8'); + } +} + +describe('TypeScript ESM .js extension → CALLS edges', () => { + let result: PipelineResult; + let repoDir: string | undefined; + + beforeAll(async () => { + repoDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-ts-esm-js-ext-')); + writeFixtureRepo(repoDir, { + 'src/utils.ts': ` +export function estimateTokens(text: string): number { + return Math.ceil(text.length / 4); +} +`, + 'src/index.ts': ` +import { estimateTokens } from './utils.js'; + +export function processText(text: string): number { + return estimateTokens(text); +} +`, + }); + result = await runPipelineFromRepo(repoDir, () => {}); + }, 60000); + + afterAll(() => { + if (repoDir !== undefined) fs.rmSync(repoDir, { recursive: true, force: true }); + }); + + it('emits CALLS edge from processText → estimateTokens via .js import', () => { + const calls = getRelationships(result, 'CALLS'); + const edge = calls.find((c) => c.source === 'processText' && c.target === 'estimateTokens'); + expect(edge).toBeDefined(); + expect(edge!.targetFilePath).toBe('src/utils.ts'); + }); + + it('emits IMPORTS edge from index.ts → utils.ts', () => { + const imports = getRelationships(result, 'IMPORTS'); + const edge = imports.find( + (e) => e.sourceFilePath === 'src/index.ts' && e.targetFilePath === 'src/utils.ts', + ); + expect(edge).toBeDefined(); + }); +}); diff --git a/gitnexus/test/integration/worker-pool.test.ts b/gitnexus/test/integration/worker-pool.test.ts index 845c1cfba..7fba8ebf5 100644 --- a/gitnexus/test/integration/worker-pool.test.ts +++ b/gitnexus/test/integration/worker-pool.test.ts @@ -354,7 +354,7 @@ describe('worker pool integration', () => { try { await expect(pool.dispatch([{ path: 'crash.ts', content: '' }])).rejects.toThrow( - /simulated startup crash|exited with code/, + /simulated startup crash|exited with code|idle timeout/, ); const warnRecords = cap.records().filter((r) => Number(r.level) >= 40 /* warn or above */); expect(warnRecords.length).toBeGreaterThan(0); diff --git a/gitnexus/test/unit/ai-context.test.ts b/gitnexus/test/unit/ai-context.test.ts index bbaecb932..68dee21dd 100644 --- a/gitnexus/test/unit/ai-context.test.ts +++ b/gitnexus/test/unit/ai-context.test.ts @@ -45,6 +45,54 @@ describe('generateAIContextFiles', () => { expect(content).toContain('TestProject'); }); + it('omits volatile counts when noStats option is set (#1477)', async () => { + // Distinct subdir per case so we can assert on a clean slate. + const subDir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-no-stats-test-')); + const subStorage = path.join(subDir, '.gitnexus'); + await fs.mkdir(subStorage, { recursive: true }); + try { + // Stats values picked to be unmistakable if they leak through. + const stats = { nodes: 12345, edges: 67890, processes: 99 }; + await generateAIContextFiles(subDir, subStorage, 'NoStatsProject', stats, undefined, { + noStats: true, + }); + + for (const f of ['CLAUDE.md', 'AGENTS.md']) { + const content = await fs.readFile(path.join(subDir, f), 'utf-8'); + expect(content).toContain('NoStatsProject'); + // The "(N symbols, N relationships, N execution flows)" + // phrase MUST NOT appear when noStats=true. + expect(content).not.toMatch( + /\(\d+\s+symbols,\s+\d+\s+relationships,\s+\d+\s+execution flows\)/, + ); + // And the distinctive numbers must not leak via any other path. + expect(content).not.toContain('12345'); + expect(content).not.toContain('67890'); + } + } finally { + await fs.rm(subDir, { recursive: true, force: true }); + } + }); + + it('preserves volatile counts when noStats is not set (default)', async () => { + const subDir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-with-stats-test-')); + const subStorage = path.join(subDir, '.gitnexus'); + await fs.mkdir(subStorage, { recursive: true }); + try { + const stats = { nodes: 12345, edges: 67890, processes: 99 }; + await generateAIContextFiles(subDir, subStorage, 'WithStatsProject', stats); + for (const f of ['CLAUDE.md', 'AGENTS.md']) { + const content = await fs.readFile(path.join(subDir, f), 'utf-8'); + expect(content).toContain('WithStatsProject'); + expect(content).toMatch( + /\(12345\s+symbols,\s+67890\s+relationships,\s+99\s+execution flows\)/, + ); + } + } finally { + await fs.rm(subDir, { recursive: true, force: true }); + } + }); + it('keeps the load-bearing repo-specific sections in the CLAUDE.md block (#856)', async () => { // The trimmed block must still contain everything that is genuinely // unique per repo or load-bearing for the agent: the freshness warning, @@ -123,9 +171,81 @@ describe('generateAIContextFiles', () => { expect(starts).toBe(1); }); + it('preserves custom section when gitnexus:keep is present', async () => { + const claudeMdPath = path.join(tmpDir, 'CLAUDE.md'); + + // Write a custom lean section with keep marker + const customContent = `# My Project + +Some project docs here. + + + +# GitNexus — Code Knowledge Graph + +Indexed as **TestProject** (50 symbols, 100 relationships, 5 execution flows). MCP tools. + +| Tool | Use for | +|------|---------| +| query | Find flows | + +Resources: gitnexus://repo/TestProject/context + +`; + await fs.writeFile(claudeMdPath, customContent, 'utf-8'); + + // Run analyze with new stats — should only update the stats line + const stats = { nodes: 999, edges: 1234, processes: 42 }; + await generateAIContextFiles(tmpDir, storagePath, 'TestProject', stats); + + const result = await fs.readFile(claudeMdPath, 'utf-8'); + + // Stats should be updated + expect(result).toContain('999 symbols'); + expect(result).toContain('1234 relationships'); + expect(result).toContain('42 execution flows'); + expect(result).toContain('. MCP tools.'); + + // Custom layout should be preserved (not replaced with verbose template) + expect(result).toContain(''); + expect(result).toContain('Code Knowledge Graph'); + expect(result).toContain('| query | Find flows |'); + + // Verbose template sections should NOT be present + expect(result).not.toContain('## Always Do'); + expect(result).not.toContain('## Never Do'); + expect(result).not.toContain('## When Debugging'); + + // Non-GitNexus content should be preserved + expect(result).toContain('# My Project'); + expect(result).toContain('Some project docs here.'); + }); + + it('replaces section when no keep marker is present', async () => { + const agentsPath = path.join(tmpDir, 'AGENTS.md'); + + // Write a section WITHOUT keep marker + const content = ` +# GitNexus — Code Intelligence + +Old content here. + +`; + await fs.writeFile(agentsPath, content, 'utf-8'); + + const stats = { nodes: 100, edges: 200, processes: 10 }; + await generateAIContextFiles(tmpDir, storagePath, 'TestProject', stats); + + const result = await fs.readFile(agentsPath, 'utf-8'); + + // Should have the full verbose template + expect(result).toContain('## Always Do'); + expect(result).not.toContain('Old content here'); + }); + it('installs skills files', async () => { const stats = { nodes: 10 }; - const result = await generateAIContextFiles(tmpDir, storagePath, 'TestProject', stats); + await generateAIContextFiles(tmpDir, storagePath, 'TestProject', stats); // Should have installed skill files const skillsDir = path.join(tmpDir, '.claude', 'skills', 'gitnexus'); @@ -137,6 +257,101 @@ describe('generateAIContextFiles', () => { } }); + it('does not create .claude/skills/gitnexus/ when skipSkills is true (#742)', async () => { + // Regression guard for #742. The --skip-skills flag must prevent + // installSkills() from writing the 6 standard skill dirs into the + // analyzed repo. Per-test tmpdir so we start from a known-clean + // slate — the shared tmpDir from beforeAll may already contain + // .claude/skills/gitnexus/ from an earlier test. + const skipDir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-ai-ctx-skip-skills-')); + const skipStorage = path.join(skipDir, '.gitnexus'); + await fs.mkdir(skipStorage, { recursive: true }); + try { + const stats = { nodes: 50, edges: 100, processes: 5 }; + const result = await generateAIContextFiles( + skipDir, + skipStorage, + 'TestProject', + stats, + undefined, + { skipSkills: true }, + ); + + expect(result.files).toContain('.claude/skills/gitnexus/ (skipped via --skip-skills)'); + await expect( + fs.access(path.join(skipDir, '.claude', 'skills', 'gitnexus')), + ).rejects.toThrow(); + } finally { + await fs.rm(skipDir, { recursive: true, force: true }); + } + }); + + it('writes nothing when both skipAgentsMd and skipSkills are true (--index-only, #742)', async () => { + // Regression guard for #742. analyzeCommand() resolves --index-only + // into BOTH skipAgentsMd=true and skipSkills=true. This test pins + // the resolved-flag combination so a future regression that drops + // either guard fails here. Per-test tmpdir for the same reason as + // the skipSkills test above. + const idxDir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-ai-ctx-index-only-')); + const idxStorage = path.join(idxDir, '.gitnexus'); + await fs.mkdir(idxStorage, { recursive: true }); + try { + const stats = { nodes: 50, edges: 100, processes: 5 }; + const result = await generateAIContextFiles( + idxDir, + idxStorage, + 'TestProject', + stats, + undefined, + { skipAgentsMd: true, skipSkills: true }, + ); + + expect(result.files).toContain('AGENTS.md (skipped via --skip-agents-md)'); + expect(result.files).toContain('CLAUDE.md (skipped via --skip-agents-md)'); + expect(result.files).toContain('.claude/skills/gitnexus/ (skipped via --skip-skills)'); + + await expect(fs.access(path.join(idxDir, 'AGENTS.md'))).rejects.toThrow(); + await expect(fs.access(path.join(idxDir, 'CLAUDE.md'))).rejects.toThrow(); + await expect(fs.access(path.join(idxDir, '.claude', 'skills', 'gitnexus'))).rejects.toThrow(); + } finally { + await fs.rm(idxDir, { recursive: true, force: true }); + } + }); + + it('omits standard skill references from AGENTS.md/CLAUDE.md when skipSkills is true (#742)', async () => { + // The skills routing table in AGENTS.md/CLAUDE.md points agents at + // .claude/skills/gitnexus/*/SKILL.md files installed by installSkills(). + // When --skip-skills suppresses that install but AGENTS.md/CLAUDE.md + // are still written, the routing table must NOT name files that don't + // exist — otherwise every agent load incurs 6 failed reads and the + // routing instructions are worthless. Per-test tmpdir so the assertions + // are not contaminated by a CLAUDE.md from an earlier test. + const noStdDir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-ai-ctx-no-std-skills-')); + const noStdStorage = path.join(noStdDir, '.gitnexus'); + await fs.mkdir(noStdStorage, { recursive: true }); + try { + const stats = { nodes: 50, edges: 100, processes: 5 }; + await generateAIContextFiles(noStdDir, noStdStorage, 'TestProject', stats, undefined, { + skipSkills: true, + }); + + const content = await fs.readFile(path.join(noStdDir, 'CLAUDE.md'), 'utf-8'); + expect(content).not.toContain('gitnexus-exploring/SKILL.md'); + expect(content).not.toContain('gitnexus-impact-analysis/SKILL.md'); + expect(content).not.toContain('gitnexus-debugging/SKILL.md'); + expect(content).not.toContain('gitnexus-refactoring/SKILL.md'); + expect(content).not.toContain('gitnexus-guide/SKILL.md'); + expect(content).not.toContain('gitnexus-cli/SKILL.md'); + // The load-bearing imperative sections must still ship — only the + // routing rows are conditional. + expect(content).toContain('## Always Do'); + expect(content).toContain('## Never Do'); + expect(content).toContain('gitnexus://repo/TestProject/context'); + } finally { + await fs.rm(noStdDir, { recursive: true, force: true }); + } + }); + it('preserves manual AGENTS.md and CLAUDE.md edits when skipAgentsMd is enabled', async () => { const stats = { nodes: 42, edges: 84, processes: 3 }; const agentsPath = path.join(tmpDir, 'AGENTS.md'); @@ -276,4 +491,240 @@ describe('generateAIContextFiles', () => { await fs.rm(crlfDir, { recursive: true, force: true }); } }); + + // ────────────────────────────────────────────────────────────────── + // Keep-marker edge cases (added to address PR #1508 review findings) + // ────────────────────────────────────────────────────────────────── + + it('keep marker OUTSIDE the GitNexus section has no effect (#1508 review F5)', async () => { + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-scope-')); + try { + const claudePath = path.join(dir, 'CLAUDE.md'); + // Keep marker appears in user prose BEFORE the GitNexus section. + // The keep-path must NOT be triggered — full template replacement + // is the correct behavior here, because the marker is not inside + // the generated block. + const fileWithOutOfBandMarker = `# My Project + +A note about markers: they only apply inside the +GitNexus block below, not in prose like this. + + +Old verbose stub here. + +`; + await fs.writeFile(claudePath, fileWithOutOfBandMarker, 'utf-8'); + + const stats = { nodes: 50, edges: 100, processes: 5 }; + await generateAIContextFiles(dir, path.join(dir, '.gitnexus'), 'TestProject', stats); + + const result = await fs.readFile(claudePath, 'utf-8'); + // Section MUST have been fully replaced — keep marker outside section ignored + expect(result).toContain('## Always Do'); + expect(result).not.toContain('Old verbose stub here.'); + // User's prose with the marker reference is preserved untouched + expect(result).toContain('A note about markers'); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); + + it('AGENTS.md keep path preserves custom layout (#1508 review F5)', async () => { + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-agents-')); + try { + const agentsPath = path.join(dir, 'AGENTS.md'); + const customAgents = `# AGENTS instructions + +Project-specific agent guidance. + + + +# GitNexus context for AGENTS + +Indexed as **AgentsTest** (10 symbols, 20 relationships, 1 execution flows). + +Use 'query' for finding flows, 'context' for symbol details. + +`; + await fs.writeFile(agentsPath, customAgents, 'utf-8'); + + const stats = { nodes: 777, edges: 888, processes: 9 }; + await generateAIContextFiles(dir, path.join(dir, '.gitnexus'), 'AgentsTest', stats); + + const result = await fs.readFile(agentsPath, 'utf-8'); + // Stats updated + expect(result).toContain('777 symbols'); + expect(result).toContain('888 relationships'); + expect(result).toContain('9 execution flows'); + // Custom layout preserved + expect(result).toContain('# GitNexus context for AGENTS'); + expect(result).toContain("Use 'query' for finding flows"); + // Verbose template NOT injected + expect(result).not.toContain('## Always Do'); + // Non-GitNexus content preserved + expect(result).toContain('# AGENTS instructions'); + expect(result).toContain('Project-specific agent guidance.'); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); + + it('idempotent: second run with keep marker produces byte-identical output (#1508 review F5)', async () => { + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-idem-')); + try { + const claudePath = path.join(dir, 'CLAUDE.md'); + const seed = `# Project + + + +Indexed as **Idem** (1 symbols, 2 relationships, 3 execution flows). Custom. + +`; + await fs.writeFile(claudePath, seed, 'utf-8'); + + const stats = { nodes: 99, edges: 100, processes: 7 }; + await generateAIContextFiles(dir, path.join(dir, '.gitnexus'), 'Idem', stats); + const afterFirst = await fs.readFile(claudePath, 'utf-8'); + + await generateAIContextFiles(dir, path.join(dir, '.gitnexus'), 'Idem', stats); + const afterSecond = await fs.readFile(claudePath, 'utf-8'); + + expect(afterSecond).toBe(afterFirst); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); + + it('CRLF file with keep marker: stats line updates without corrupting content (#1508 review F5)', async () => { + // upsertGitNexusSection writes with .trim() + '\n', so the saved file uses LF + // line endings throughout — CRLF in the seed input is not preserved. + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-crlf-')); + try { + const claudePath = path.join(dir, 'CLAUDE.md'); + const crlfContent = + '# Project\r\n' + + '\r\n' + + '\r\n' + + '\r\n' + + 'Indexed as **CRLFTest** (5 symbols, 6 relationships, 7 execution flows). Custom CRLF.\r\n' + + '\r\n'; + await fs.writeFile(claudePath, crlfContent, 'utf-8'); + + const stats = { nodes: 50, edges: 60, processes: 7 }; + await generateAIContextFiles(dir, path.join(dir, '.gitnexus'), 'CRLFTest', stats); + + const result = await fs.readFile(claudePath, 'utf-8'); + // Stats updated correctly + expect(result).toContain('50 symbols'); + expect(result).toContain('60 relationships'); + // Custom prose preserved + expect(result).toContain('Custom CRLF'); + // No verbose template injected + expect(result).not.toContain('## Always Do'); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); + + it('noStats + keep marker: stats line update is NOT corrupted by Always-Do tuple text (#1508 review F3)', async () => { + // Regression guard: with the old fallback regex `\(([^)]+)\)`, when + // noStats=true suppressed the canonical stats line from generated + // content, the fallback matched the FIRST parenthesized text in the + // template, which was `({target: "symbolName", direction: "upstream"})` + // from the Always Do bullet — silently writing that as the stats line. + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-nostats-')); + try { + const claudePath = path.join(dir, 'CLAUDE.md'); + const seed = ` + +Indexed as **NoStatsTest** (1 symbols, 1 relationships, 1 execution flows). Custom. + +`; + await fs.writeFile(claudePath, seed, 'utf-8'); + + const stats = { nodes: 42, edges: 84, processes: 3 }; + await generateAIContextFiles( + dir, + path.join(dir, '.gitnexus'), + 'NoStatsTest', + stats, + undefined, + { noStats: true }, + ); + + const result = await fs.readFile(claudePath, 'utf-8'); + // Stats line MUST NOT have been corrupted with the Always-Do tuple text + expect(result).not.toMatch(/\(\{target:/); + expect(result).not.toMatch(/direction:\s*"upstream"/); + // Stats line should reflect a sensible numeric update (passed stats) + expect(result).toContain('42 symbols'); + // Custom prose still preserved + expect(result).toContain('Custom.'); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); + + it("returns 'preserved' (not 'updated') when keep marker is present but no stats line matches (#1508 review F1)", async () => { + // Regression guard for the misleading-return-value bug: previously the + // function returned 'updated' without writing when the keep-section had + // no recognizable stats line, causing CLI output to claim files were + // updated when they were not. + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-noline-')); + try { + const claudePath = path.join(dir, 'CLAUDE.md'); + // Custom keep-section with NO "Indexed as ..." or "indexed by GitNexus as ..." line + const seed = `# Project + + + +# GitNexus block (custom, no stats line) + +This block intentionally omits the standard stats line. + +`; + await fs.writeFile(claudePath, seed, 'utf-8'); + + const stats = { nodes: 100, edges: 200, processes: 10 }; + const result = await generateAIContextFiles( + dir, + path.join(dir, '.gitnexus'), + 'NoLineTest', + stats, + ); + + // The result manifest should reflect 'preserved', not 'updated' + expect(result.files).toContain('CLAUDE.md (preserved)'); + // File on disk is unchanged + const onDisk = await fs.readFile(claudePath, 'utf-8'); + expect(onDisk).toBe(seed); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); + + it('project name with markdown-sensitive punctuation lands intact in stats line (#1508 review F5)', async () => { + const dir = await fs.mkdtemp(path.join(os.tmpdir(), 'gn-keep-punct-')); + try { + const claudePath = path.join(dir, 'CLAUDE.md'); + const seed = ` + +Indexed as **placeholder** (1 symbols, 1 relationships, 1 execution flows). Custom. + +`; + await fs.writeFile(claudePath, seed, 'utf-8'); + + // Name with hyphens, dot, and slash — exactly what dp-web4/some-repo + // style names look like + const trickyName = 'dp-web4/some-repo.v2'; + const stats = { nodes: 5, edges: 10, processes: 1 }; + await generateAIContextFiles(dir, path.join(dir, '.gitnexus'), trickyName, stats); + + const result = await fs.readFile(claudePath, 'utf-8'); + // The full name appears in the bold of the stats line, intact + expect(result).toContain(`Indexed as **${trickyName}** (5 symbols`); + } finally { + await fs.rm(dir, { recursive: true, force: true }); + } + }); }); diff --git a/gitnexus/test/unit/analyze-community-skills-gate.test.ts b/gitnexus/test/unit/analyze-community-skills-gate.test.ts new file mode 100644 index 000000000..35eaa5c77 --- /dev/null +++ b/gitnexus/test/unit/analyze-community-skills-gate.test.ts @@ -0,0 +1,27 @@ +import { describe, it, expect } from 'vitest'; +import { shouldGenerateCommunitySkillFiles } from '../../src/cli/analyze.js'; + +describe('shouldGenerateCommunitySkillFiles (#742 / PR 1485)', () => { + it('is false when --index-only is set even if --skills and pipelineResult are present', () => { + expect(shouldGenerateCommunitySkillFiles({ skills: true, indexOnly: true }, { ok: true })).toBe( + false, + ); + }); + + it('is false when pipelineResult is missing', () => { + expect(shouldGenerateCommunitySkillFiles({ skills: true, indexOnly: false }, null)).toBe(false); + expect(shouldGenerateCommunitySkillFiles({ skills: true }, undefined)).toBe(false); + }); + + it('is true when --skills is set, pipeline exists, and not index-only', () => { + expect( + shouldGenerateCommunitySkillFiles({ skills: true, indexOnly: false }, { communities: [] }), + ).toBe(true); + expect(shouldGenerateCommunitySkillFiles({ skills: true }, { x: 1 })).toBe(true); + }); + + it('is false when --skills is omitted', () => { + expect(shouldGenerateCommunitySkillFiles({ indexOnly: false }, { x: 1 })).toBe(false); + expect(shouldGenerateCommunitySkillFiles(undefined, { x: 1 })).toBe(false); + }); +}); diff --git a/gitnexus/test/unit/analyze-no-stats-bridge.test.ts b/gitnexus/test/unit/analyze-no-stats-bridge.test.ts new file mode 100644 index 000000000..f941141ef --- /dev/null +++ b/gitnexus/test/unit/analyze-no-stats-bridge.test.ts @@ -0,0 +1,140 @@ +import { beforeEach, describe, expect, it, vi } from 'vitest'; + +const { runFullAnalysisMock, generateAIContextFilesMock, generateSkillFilesMock } = vi.hoisted( + () => { + const runFullAnalysisMock = vi.fn(); + const generateAIContextFilesMock = vi.fn(async () => ({ files: [] as string[] })); + const generateSkillFilesMock = vi.fn(async () => ({ + skills: [{ name: 'c', label: 'Community', symbolCount: 1, fileCount: 1 }], + outputPath: '/repo/.claude/skills/generated', + })); + return { runFullAnalysisMock, generateAIContextFilesMock, generateSkillFilesMock }; + }, +); + +vi.mock('../../src/core/run-analyze.js', () => ({ + runFullAnalysis: runFullAnalysisMock, +})); + +vi.mock('../../src/cli/ai-context.js', () => ({ + generateAIContextFiles: generateAIContextFilesMock, +})); + +vi.mock('../../src/cli/skill-gen.js', () => ({ + generateSkillFiles: generateSkillFilesMock, +})); + +vi.mock('../../src/core/lbug/lbug-adapter.js', () => ({ + closeLbug: vi.fn(async () => undefined), +})); + +vi.mock('../../src/storage/repo-manager.js', () => ({ + getStoragePaths: vi.fn(() => ({ storagePath: '.gitnexus', lbugPath: '.gitnexus/lbug' })), + getGlobalRegistryPath: vi.fn(() => 'registry.json'), + RegistryNameCollisionError: class RegistryNameCollisionError extends Error {}, + AnalysisNotFinalizedError: class AnalysisNotFinalizedError extends Error {}, + assertAnalysisFinalized: vi.fn(async () => undefined), +})); + +vi.mock('../../src/storage/git.js', () => ({ + getGitRoot: vi.fn(() => '/repo'), + hasGitDir: vi.fn(() => true), +})); + +vi.mock('../../src/core/ingestion/utils/max-file-size.js', () => ({ + getMaxFileSizeBannerMessage: vi.fn(() => null), +})); + +describe('analyzeCommand commander → runFullAnalysis noStats bridge (#1477)', () => { + beforeEach(() => { + vi.resetModules(); + runFullAnalysisMock.mockReset(); + runFullAnalysisMock.mockResolvedValue({ + repoName: 'repo', + repoPath: '/repo', + stats: {}, + alreadyUpToDate: true, + }); + generateAIContextFilesMock.mockReset(); + generateAIContextFilesMock.mockResolvedValue({ files: [] }); + generateSkillFilesMock.mockReset(); + generateSkillFilesMock.mockResolvedValue({ + skills: [{ name: 'c', label: 'Community', symbolCount: 1, fileCount: 1 }], + outputPath: '/repo/.claude/skills/generated', + }); + process.exitCode = undefined; + process.env.NODE_OPTIONS = `${process.env.NODE_OPTIONS ?? ''} --max-old-space-size=8192`.trim(); + }); + + it('maps commander-shaped stats:false to noStats:true (equivalent to --no-stats)', async () => { + const { analyzeCommand } = await import('../../src/cli/analyze.js'); + + await analyzeCommand(undefined, { stats: false }); + + expect(runFullAnalysisMock).toHaveBeenCalledTimes(1); + const opts = runFullAnalysisMock.mock.calls[0][1]; + expect(opts.noStats).toBe(true); + }); + + it('maps omitted stats to noStats:false (default-on preserved)', async () => { + const { analyzeCommand } = await import('../../src/cli/analyze.js'); + + await analyzeCommand(undefined, {}); + + const opts = runFullAnalysisMock.mock.calls[0][1]; + expect(opts.noStats).toBe(false); + }); + + it('maps explicit stats:true to noStats:false', async () => { + const { analyzeCommand } = await import('../../src/cli/analyze.js'); + + await analyzeCommand(undefined, { stats: true }); + + const opts = runFullAnalysisMock.mock.calls[0][1]; + expect(opts.noStats).toBe(false); + }); + + it('still maps stats:false to noStats:true when skipAgentsMd is set', async () => { + const { analyzeCommand } = await import('../../src/cli/analyze.js'); + + await analyzeCommand(undefined, { stats: false, skipAgentsMd: true }); + + const opts = runFullAnalysisMock.mock.calls[0][1]; + expect(opts.noStats).toBe(true); + expect(opts.skipAgentsMd).toBe(true); + }); + + it('passes stats:false as noStats to generateAIContextFiles on the --skills regeneration path (#1477)', async () => { + runFullAnalysisMock.mockResolvedValueOnce({ + repoName: 'repo', + repoPath: '/repo', + stats: { + files: 1, + nodes: 10, + edges: 20, + communities: 0, + processes: 5, + }, + alreadyUpToDate: false, + pipelineResult: { communityResult: undefined }, + }); + + const exitSpy = vi.spyOn(process, 'exit').mockImplementation(() => undefined as never); + try { + const { analyzeCommand } = await import('../../src/cli/analyze.js'); + + await analyzeCommand(undefined, { skills: true, stats: false }); + + expect(generateSkillFilesMock).toHaveBeenCalledTimes(1); + expect(generateAIContextFilesMock).toHaveBeenCalledTimes(1); + const aiCtxOpts = generateAIContextFilesMock.mock.calls[0]![5]; + expect(aiCtxOpts).toEqual({ + skipAgentsMd: undefined, + skipSkills: undefined, + noStats: true, + }); + } finally { + exitSpy.mockRestore(); + } + }); +}); diff --git a/gitnexus/test/unit/ast-utils.test.ts b/gitnexus/test/unit/ast-utils.test.ts index f736d7e77..481ebc740 100644 --- a/gitnexus/test/unit/ast-utils.test.ts +++ b/gitnexus/test/unit/ast-utils.test.ts @@ -1,10 +1,11 @@ import { beforeEach, describe, expect, it, vi } from 'vitest'; -const { createParserForLanguage, getLanguageFromFilename } = vi.hoisted(() => ({ +const { createParserForLanguage, getLanguageFromFilename, parseSourceSafeSpy } = vi.hoisted(() => ({ createParserForLanguage: vi.fn(), getLanguageFromFilename: vi.fn((filePath: string) => filePath.endsWith('.py') ? 'python' : 'typescript', ), + parseSourceSafeSpy: vi.fn(), })); vi.mock('../../src/core/tree-sitter/parser-loader.js', () => ({ @@ -15,6 +16,11 @@ vi.mock('../../src/core/tree-sitter/parser-loader.js', () => ({ ), })); +vi.mock('../../src/core/tree-sitter/safe-parse.js', async () => { + const { buildSafeParseMock } = await import('../helpers/parse-source-safe-mock.js'); + return buildSafeParseMock(parseSourceSafeSpy); +}); + vi.mock('gitnexus-shared', () => ({ getLanguageFromFilename, })); @@ -72,4 +78,25 @@ describe('ensureAndParse', () => { expect(tsParse).toHaveBeenCalledTimes(2); expect(tsxParse).toHaveBeenCalledTimes(1); }); + + // Windows SIGSEGV regression: ensureAndParse must route through parseSourceSafe + // so >32 767-char inputs do not crash the process. Direct parser.parse(content) + // on strings that size SIGSEGVs on Windows; the spy assertion is what catches + // a bypass since parser.parse(40 000 chars) succeeds on Linux/macOS. + it('routes >32 767-char input through parseSourceSafe', async () => { + parseSourceSafeSpy.mockClear(); + + const fakeParse = vi.fn().mockReturnValue({ rootNode: { type: 'module' } }); + createParserForLanguage.mockResolvedValue({ parse: fakeParse }); + + const { ensureAndParse } = await import('../../src/core/embeddings/ast-utils.js'); + + const largeInput = 'const x = 1;\n'.repeat(4000); // ~52 000 chars + expect(largeInput.length).toBeGreaterThan(40_000); + + const result = await ensureAndParse(largeInput, 'big.ts'); + + expect(parseSourceSafeSpy).toHaveBeenCalled(); + expect(result).not.toBeNull(); + }); }); diff --git a/gitnexus/test/unit/calltool-dispatch.test.ts b/gitnexus/test/unit/calltool-dispatch.test.ts index 45e1b71d2..8a9a1a629 100644 --- a/gitnexus/test/unit/calltool-dispatch.test.ts +++ b/gitnexus/test/unit/calltool-dispatch.test.ts @@ -216,6 +216,19 @@ describe('LocalBackend.callTool', () => { expect(result).not.toHaveProperty('warning'); }); + it('does not crash when searchFTSFromLbug throws (#1489)', async () => { + const { searchFTSFromLbug } = await import('../../src/core/search/bm25-index.js'); + vi.mocked(searchFTSFromLbug).mockRejectedValueOnce(new Error('bm25Results is not iterable')); + (executeParameterized as any).mockResolvedValue([]); + + const result = await backend.callTool('query', { query: 'auth' }); + + // Should still return a valid result shape (semantic-only fallback) + expect(result).toHaveProperty('processes'); + expect(result).toHaveProperty('definitions'); + expect(result).not.toHaveProperty('error'); + }); + it('skips vector index query when VECTOR is unsupported by the platform', async () => { const cap = _captureLogger(); platformMocks.isVectorExtensionSupportedByPlatform.mockReturnValue(false); diff --git a/gitnexus/test/unit/cursor-hook.test.ts b/gitnexus/test/unit/cursor-hook.test.ts new file mode 100644 index 000000000..e64979895 --- /dev/null +++ b/gitnexus/test/unit/cursor-hook.test.ts @@ -0,0 +1,636 @@ +/** + * Regression Tests: Cursor postToolUse Hook + * + * Tests the hook script at gitnexus-cursor-integration/hooks/gitnexus-hook.cjs + * which runs as a Cursor 2.4 postToolUse hook. + * + * Covers: + * - extractPattern: pattern extraction from Grep/Read/Shell tool inputs + * - findGitNexusDir: .gitnexus directory discovery (shared with Claude hook) + * - cwd validation: rejects relative paths + * - shell injection: verifies no `shell: true` in spawnSync calls + * - cross-platform: Windows .cmd extension handling + * - output shape: top-level `additional_context` (NOT Claude's `hookSpecificOutput.additionalContext`) + * - hooks.json wiring matches the script's actual handlers + * + * Cursor hooks reach the augment CLI only when cwd is inside an indexed + * repo, so behavior tests stick to early-exit paths to avoid spawning + * `npx gitnexus`. + */ +import { describe, it, expect, beforeAll, afterAll } from 'vitest'; +import { spawnSync } from 'child_process'; +import fs from 'fs'; +import path from 'path'; +import os from 'os'; +import { runHook } from '../utils/hook-test-helpers.js'; + +// ─── Path to the Cursor hook + manifest ───────────────────────────── + +const CURSOR_HOOK = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-cursor-integration', + 'hooks', + 'gitnexus-hook.cjs', +); +const CURSOR_HOOK_LOCK = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-cursor-integration', + 'hooks', + 'hook-lock.cjs', +); +const CURSOR_HOOKS_JSON = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-cursor-integration', + 'hooks', + 'hooks.json', +); + +// ─── Cursor-specific output parser ────────────────────────────────── +// Cursor postToolUse output shape: { "additional_context": "..." } + +function parseCursorOutput(stdout: string): { additional_context?: string } | null { + if (!stdout.trim()) return null; + try { + return JSON.parse(stdout.trim()); + } catch { + return null; + } +} + +// ─── Test fixtures ────────────────────────────────────────────────── + +let tmpDir: string; +// Separate fixture for the concurrency guard tests: this one has a real +// `.gitnexus/` so the hook reaches acquireHookSlot. The base tmpDir above +// deliberately has no .gitnexus so unrelated early-exit tests stay cheap. +let guardTmpDir: string; +let guardGitNexusDir: string; + +beforeAll(() => { + tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-cursor-hook-test-')); + spawnSync('git', ['init'], { cwd: tmpDir, stdio: 'pipe' }); + spawnSync('git', ['config', 'user.email', 'test@test.com'], { cwd: tmpDir, stdio: 'pipe' }); + spawnSync('git', ['config', 'user.name', 'Test'], { cwd: tmpDir, stdio: 'pipe' }); + + guardTmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-cursor-hook-guard-')); + guardGitNexusDir = path.join(guardTmpDir, '.gitnexus'); + fs.mkdirSync(guardGitNexusDir, { recursive: true }); + spawnSync('git', ['init'], { cwd: guardTmpDir, stdio: 'pipe' }); + spawnSync('git', ['config', 'user.email', 'test@test.com'], { + cwd: guardTmpDir, + stdio: 'pipe', + }); + spawnSync('git', ['config', 'user.name', 'Test'], { cwd: guardTmpDir, stdio: 'pipe' }); + fs.writeFileSync(path.join(guardTmpDir, 'dummy.txt'), 'hello'); + spawnSync('git', ['add', '.'], { cwd: guardTmpDir, stdio: 'pipe' }); + spawnSync('git', ['commit', '-m', 'init'], { cwd: guardTmpDir, stdio: 'pipe' }); +}); + +afterAll(() => { + fs.rmSync(tmpDir, { recursive: true, force: true }); + fs.rmSync(guardTmpDir, { recursive: true, force: true }); +}); + +// ─── Manifest + hook file presence ─────────────────────────────────── + +describe('Cursor integration files', () => { + it('hook script exists', () => { + expect(fs.existsSync(CURSOR_HOOK)).toBe(true); + }); + + it('hooks.json exists', () => { + expect(fs.existsSync(CURSOR_HOOKS_JSON)).toBe(true); + }); + + it('legacy augment-shell.sh has been removed', () => { + const legacy = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-cursor-integration', + 'hooks', + 'augment-shell.sh', + ); + expect(fs.existsSync(legacy)).toBe(false); + }); +}); + +// ─── hooks.json wiring ────────────────────────────────────────────── + +describe('hooks.json wiring', () => { + const manifest = JSON.parse(fs.readFileSync(CURSOR_HOOKS_JSON, 'utf-8')); + + it('declares version 1', () => { + expect(manifest.version).toBe(1); + }); + + it('registers a postToolUse hook (not legacy beforeShellExecution)', () => { + expect(manifest.hooks.postToolUse).toBeDefined(); + expect(Array.isArray(manifest.hooks.postToolUse)).toBe(true); + expect(manifest.hooks.beforeShellExecution).toBeUndefined(); + }); + + it('matches Shell, Read, and Grep tools', () => { + const matcher: string = manifest.hooks.postToolUse[0].matcher; + expect(matcher).toMatch(/Shell/); + expect(matcher).toMatch(/Read/); + expect(matcher).toMatch(/Grep/); + }); + + it('points command at the new Node hook', () => { + const command: string = manifest.hooks.postToolUse[0].command; + expect(command).toContain('gitnexus-hook.cjs'); + expect(command).not.toContain('augment-shell.sh'); + }); + + it('declares timeout in seconds (not milliseconds)', () => { + // Cursor's `timeout` field is in seconds per + // https://cursor.com/docs/agent/hooks. Regression guard: a value of + // 1000+ here would be a >16-minute timeout, almost certainly a ms/s mixup. + const timeout: number = manifest.hooks.postToolUse[0].timeout; + expect(typeof timeout).toBe('number'); + expect(timeout).toBeGreaterThan(0); + expect(timeout).toBeLessThan(120); + }); +}); + +// ─── Source code regressions ──────────────────────────────────────── + +describe('Cursor hook source regressions', () => { + const source = fs.readFileSync(CURSOR_HOOK, 'utf-8'); + + it('does not pass shell: true to spawnSync', () => { + const lines = source.split('\n'); + for (let i = 0; i < lines.length; i++) { + const line = lines[i]; + if (line.trim().startsWith('//') || line.trim().startsWith('*')) continue; + if (/shell:\s*(true|isWin)/.test(line)) { + throw new Error(`Cursor hook line ${i + 1} has shell injection risk: ${line.trim()}`); + } + } + }); + + it('uses npx.cmd for Windows', () => { + expect(source).toContain('npx.cmd'); + }); + + it('validates cwd is an absolute path', () => { + expect(source).toMatch(/path\.isAbsolute\(cwd\)/); + }); + + it('truncates debug error messages to 200 chars', () => { + expect(source).toContain('.slice(0, 200)'); + }); + + it('emits Cursor-shape additional_context (not Claude hookSpecificOutput)', () => { + expect(source).toContain('additional_context'); + expect(source).not.toContain('hookSpecificOutput'); + expect(source).not.toContain('hookEventName'); + }); + + it('rejects patterns shorter than 3 chars', () => { + expect(source).toMatch(/length\s*>=\s*3/); + }); + + it('passes pattern after end-of-options marker (--)', () => { + // Regression for #200 — augment patterns starting with `-` would + // otherwise be parsed as CLI flags by the gitnexus CLI. + expect(source).toMatch(/'augment',\s*'--',\s*pattern/); + }); + + it('gates on a non-global .gitnexus directory before invoking the CLI', () => { + expect(source).toContain('findGitNexusDir'); + expect(source).toContain('isGlobalRegistryDir'); + }); + + it('handles linked git worktrees via git rev-parse --git-common-dir', () => { + expect(source).toContain('--git-common-dir'); + }); +}); + +// ─── extractPattern coverage (source-level) ───────────────────────── + +describe('Cursor hook extractPattern coverage', () => { + const source = fs.readFileSync(CURSOR_HOOK, 'utf-8'); + + it("handles 'grep' tool (Cursor matcher: Grep)", () => { + expect(source).toMatch(/t === 'grep'/); + }); + + it('probes a wide alias set for Grep query field (Cursor contract not formally specified)', () => { + // Cursor 2.4 docs at https://cursor.com/docs/agent/hooks list the + // matchers but not the per-tool tool_input field names. If Cursor + // changes the contract, we want the hook to still extract *something* + // — these aliases plus the longest-string fallback give us coverage. + for (const alias of ['query', 'pattern', 'regex', 'q', 'search', 'searchQuery']) { + expect(source).toContain(`toolInput.${alias}`); + } + expect(source).toContain('pickLongestStringValue'); + }); + + it("handles 'read' tool (Cursor matcher: Read)", () => { + expect(source).toMatch(/t === 'read'/); + for (const alias of ['target_file', 'file_path', 'filePath', 'path', 'file']) { + expect(source).toContain(`toolInput.${alias}`); + } + }); + + it("handles 'shell' tool (Cursor matcher: Shell)", () => { + expect(source).toMatch(/t === 'shell'/); + expect(source).toMatch(/\\brg\\b\|\\bgrep\\b/); + }); + + it('logs raw payload to stderr when GITNEXUS_DEBUG is set (for contract diagnostics)', () => { + expect(source).toContain('GITNEXUS_DEBUG'); + expect(source).toContain('GitNexus Cursor hook stdin:'); + }); +}); + +// ─── Behavior: graceful no-op paths (no augment CLI invocation) ───── + +describe('Cursor hook behavior — early-exit paths', () => { + it('exits cleanly on empty stdin', () => { + const result = spawnSync(process.execPath, [CURSOR_HOOK], { + input: '', + encoding: 'utf-8', + timeout: 10000, + stdio: ['pipe', 'pipe', 'pipe'], + }); + expect(result.status).toBe(0); + expect(result.stdout.trim()).toBe(''); + }); + + it('exits cleanly on invalid JSON stdin', () => { + const result = spawnSync(process.execPath, [CURSOR_HOOK], { + input: 'not json at all', + encoding: 'utf-8', + timeout: 10000, + stdio: ['pipe', 'pipe', 'pipe'], + }); + expect(result.status).toBe(0); + expect(result.stdout.trim()).toBe(''); + }); + + it('produces no output when cwd is relative', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Grep', + tool_input: { query: 'validateUser' }, + cwd: 'relative/path', + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('produces no output when cwd has no .gitnexus dir', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Grep', + tool_input: { query: 'validateUser' }, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('produces no output for unknown tool names', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'TotallyMadeUpTool', + tool_input: { foo: 'bar' }, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('produces no output for Shell commands without rg/grep', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Shell', + tool_input: { command: 'ls -la' }, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('produces no output for Grep with a 2-char query', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Grep', + tool_input: { query: 'is' }, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('produces no output for Read whose basename has no identifier chars', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Read', + tool_input: { target_file: '/tmp/--.md' }, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('produces no output for Read with no file path', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Read', + tool_input: {}, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + }); + + it('treats tool_name case-insensitively (Grep vs grep)', () => { + // Both should reach the same handler — and both should early-exit silently + // because tmpDir has no .gitnexus. + for (const toolName of ['Grep', 'grep', 'GREP']) { + const result = runHook(CURSOR_HOOK, { + tool_name: toolName, + tool_input: { query: 'validateUser' }, + cwd: tmpDir, + }); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + } + }); +}); + +// ─── Behavior: GITNEXUS_DEBUG payload logging ──────────────────────── + +describe('Cursor hook debug logging', () => { + it('echoes the payload to stderr only when GITNEXUS_DEBUG is set', () => { + const payload = { + tool_name: 'Grep', + tool_input: { query: 'validateUser' }, + cwd: tmpDir, + }; + + // GITNEXUS_DEBUG unset → stderr quiet. + const quiet = spawnSync(process.execPath, [CURSOR_HOOK], { + input: JSON.stringify(payload), + encoding: 'utf-8', + timeout: 10000, + stdio: ['pipe', 'pipe', 'pipe'], + env: { ...process.env, GITNEXUS_DEBUG: '' }, + }); + expect(quiet.status).toBe(0); + expect(quiet.stderr).not.toContain('GitNexus Cursor hook stdin'); + + // GITNEXUS_DEBUG=1 → payload echoed to stderr (stdout still empty for + // unindexed cwd, so the hook output contract is preserved). + const verbose = spawnSync(process.execPath, [CURSOR_HOOK], { + input: JSON.stringify(payload), + encoding: 'utf-8', + timeout: 10000, + stdio: ['pipe', 'pipe', 'pipe'], + env: { ...process.env, GITNEXUS_DEBUG: '1' }, + }); + expect(verbose.status).toBe(0); + expect(verbose.stderr).toContain('GitNexus Cursor hook stdin'); + expect(verbose.stderr).toContain('"tool_name":"Grep"'); + expect(verbose.stdout.trim()).toBe(''); + }); +}); + +// ─── Source code regression: concurrency guard (#1486) ───────────── + +describe('Cursor hook concurrency guard', () => { + const source = fs.readFileSync(CURSOR_HOOK, 'utf-8'); + const lockSource = fs.readFileSync(CURSOR_HOOK_LOCK, 'utf-8'); + + it('loads acquireHookSlot helper module', () => { + expect(source).toContain('acquireHookSlot'); + expect(source).toContain('hook-lock.cjs'); + }); + + it('helper defines acquireHookSlot with MAX_INFLIGHT constant', () => { + expect(lockSource).toContain('function acquireHookSlot'); + expect(lockSource).toContain('HOOK_LOCK_MAX_INFLIGHT'); + }); + + it('calls acquireHookSlot in main() and releases via finally', () => { + // The Cursor hook uses a flat main() dispatcher rather than a separate + // handlePreToolUse — assert the guard call + finally release wiring is + // present so a future refactor cannot accidentally skip it. + expect(source).toContain('acquireHookSlot('); + expect(source).toMatch(/finally\s*\{[^}]*release\(\)/s); + }); + + it('uses atomic fixed-name slot files (hard cap, not soft TOCTOU cap)', () => { + expect(lockSource).toMatch(/slot-\$\{slot\}\.lock|`slot-/); + const slotFn = lockSource.slice( + lockSource.indexOf('function acquireHookSlot'), + lockSource.indexOf('function', lockSource.indexOf('function acquireHookSlot') + 1), + ); + expect(slotFn).not.toContain('readdirSync'); + }); + + it('fails closed when lock dir cannot be created', () => { + // Regression: see hooks.test.ts. The mkdirSync catch must return null + // (skip augment) rather than `() => {}` (proceed unguarded), so that + // a read-only or cross-user `.gitnexus/` cannot reintroduce #1486. + const slotFn = lockSource.slice( + lockSource.indexOf('function acquireHookSlot'), + lockSource.indexOf('function', lockSource.indexOf('function acquireHookSlot') + 1), + ); + const mkdirCatch = slotFn.slice( + slotFn.indexOf('fs.mkdirSync(lockDir'), + slotFn.indexOf('const myPidStr'), + ); + expect(mkdirCatch).toContain('return null'); + expect(mkdirCatch).not.toMatch(/return\s*\(\s*\)\s*=>\s*\{\s*\}/); + }); + + // Note: the 10-concurrent-spawner burst test that validates `wx` + // (O_CREAT|O_EXCL) under simultaneous contention lives in + // hooks.test.ts. The Cursor hook uses byte-for-byte the same + // acquireHookSlot, so duplicating the burst test here would only test + // the OS primitive, not Cursor-specific wiring. The source-level checks + // above guarantee the Cursor hook keeps calling that same algorithm. +}); + +// ─── Integration: concurrency guard skips when slots are full ────── + +describe('Cursor hook concurrency guard (integration)', () => { + it('exits silently when all MAX_INFLIGHT slots hold live pids', async () => { + const { spawn } = await import('child_process'); + const lockDir = path.join(guardGitNexusDir, '.hook-locks'); + fs.mkdirSync(lockDir, { recursive: true }); + + const sleepers = [0, 1, 2].map(() => + spawn(process.execPath, ['-e', 'setTimeout(()=>{},60000)'], { + stdio: 'ignore', + detached: false, + }), + ); + const writtenLocks: string[] = []; + try { + for (let i = 0; i < sleepers.length; i++) { + const p = path.join(lockDir, `slot-${i}.lock`); + fs.writeFileSync(p, String(sleepers[i].pid)); + writtenLocks.push(p); + } + + const result = runHook(CURSOR_HOOK, { + tool_name: 'Grep', + tool_input: { query: 'validateUser' }, + cwd: guardTmpDir, + }); + + expect(result.stdout.trim()).toBe(''); + for (let i = 0; i < sleepers.length; i++) { + const p = path.join(lockDir, `slot-${i}.lock`); + expect(fs.existsSync(p)).toBe(true); + expect(fs.readFileSync(p, 'utf-8').trim()).toBe(String(sleepers[i].pid)); + } + } finally { + for (const child of sleepers) { + try { + child.kill(); + } catch { + /* ignore */ + } + } + for (const p of writtenLocks) { + try { + fs.unlinkSync(p); + } catch { + /* ignore */ + } + } + try { + fs.rmdirSync(lockDir); + } catch { + /* ignore */ + } + } + }); + + it('reclaims a slot held by a dead pid', () => { + const lockDir = path.join(guardGitNexusDir, '.hook-locks'); + fs.mkdirSync(lockDir, { recursive: true }); + const deadPid = 2_147_483_640; + const stalePath = path.join(lockDir, 'slot-0.lock'); + try { + fs.writeFileSync(stalePath, String(deadPid)); + expect(fs.readFileSync(stalePath, 'utf-8').trim()).toBe(String(deadPid)); + + runHook(CURSOR_HOOK, { + tool_name: 'Grep', + tool_input: { query: 'validateUser' }, + cwd: guardTmpDir, + }); + + // The hook reclaimed and then released slot-0 — either gone (released) + // or no longer owned by the dead pid. + if (fs.existsSync(stalePath)) { + expect(fs.readFileSync(stalePath, 'utf-8').trim()).not.toBe(String(deadPid)); + } + } finally { + try { + fs.unlinkSync(stalePath); + } catch { + /* already pruned */ + } + try { + fs.rmdirSync(lockDir); + } catch { + /* ignore */ + } + } + }); +}); + +// ─── Documented contract behavior (extractPattern via the live hook) ─ + +describe('Shell quoted-pattern parser limitations (documented)', () => { + // The Shell parser cannot reconstruct shell quoting. These tests pin the + // current behavior so a future "fix" doesn't silently change extraction + // — and so users diagnosing a noisy/missed pattern can find the behavior + // documented in tests. + // + // We can't observe the extracted pattern directly without an indexed + // repo, but we *can* confirm the hook reaches the augment-call path + // (vs. early-exiting) by checking exit status + clean stdout for cases + // where parseRgGrepPattern would yield a >=3-char token. + + it('quoted multi-word `rg "User Service"` extracts the first word only', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Shell', + tool_input: { command: 'rg "User Service" src/' }, + cwd: tmpDir, // no .gitnexus → exits early after extract + }); + expect(result.status).toBe(0); + expect(result.stdout.trim()).toBe(''); + }); + + it('single-token quoted `rg "validateUser"` works as expected', () => { + const result = runHook(CURSOR_HOOK, { + tool_name: 'Shell', + tool_input: { command: 'rg "validateUser"' }, + cwd: tmpDir, + }); + expect(result.status).toBe(0); + expect(result.stdout.trim()).toBe(''); + }); +}); + +// ─── Install docs ───────────────────────────────────────────────────── + +describe('Cursor integration install docs', () => { + const integrationReadme = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-cursor-integration', + 'README.md', + ); + + it('install README exists', () => { + expect(fs.existsSync(integrationReadme)).toBe(true); + }); + + it('install README documents the hook install path', () => { + const body = fs.readFileSync(integrationReadme, 'utf-8'); + expect(body).toContain('.cursor/hooks.json'); + expect(body).toContain('hooks/gitnexus-hook.cjs'); + expect(body).toContain('hooks/hook-lock.cjs'); + expect(body).toContain('Hook install'); + }); + + it('install README documents GITNEXUS_DEBUG for payload diagnostics', () => { + const body = fs.readFileSync(integrationReadme, 'utf-8'); + expect(body).toContain('GITNEXUS_DEBUG'); + }); +}); + +// ─── Output parser sanity (synthetic JSON) ────────────────────────── + +describe('parseCursorOutput', () => { + it('parses a well-formed { additional_context } payload', () => { + const parsed = parseCursorOutput('{"additional_context":"hello"}'); + expect(parsed).not.toBeNull(); + expect(parsed?.additional_context).toBe('hello'); + }); + + it('returns null on empty stdout', () => { + expect(parseCursorOutput('')).toBeNull(); + expect(parseCursorOutput(' \n')).toBeNull(); + }); + + it('returns null on malformed JSON', () => { + expect(parseCursorOutput('not json')).toBeNull(); + }); +}); diff --git a/gitnexus/test/unit/esm-extension-resolution.test.ts b/gitnexus/test/unit/esm-extension-resolution.test.ts new file mode 100644 index 000000000..794888049 --- /dev/null +++ b/gitnexus/test/unit/esm-extension-resolution.test.ts @@ -0,0 +1,226 @@ +/** + * Unit tests for TypeScript ESM .js extension resolution. + * + * TypeScript ESM requires imports to use .js extensions even when source + * files are .ts. The resolver must map .js → .ts (and .jsx → .tsx, + * .mjs → .mts, .cjs → .cts) when the literal .js file does not exist. + */ + +import { describe, it, expect } from 'vitest'; +import { resolveImportPath } from '../../src/core/ingestion/import-resolvers/standard.js'; +import { stripJsExtension } from '../../src/core/ingestion/import-resolvers/standard.js'; +import { buildSuffixIndex } from '../../src/core/ingestion/import-resolvers/utils.js'; +import { SupportedLanguages } from 'gitnexus-shared'; + +function makeCtx(files: string[]) { + // Match production normalization: only replace backslashes with forward slashes + const normalized = files.map((f) => f.replace(/\\/g, '/')); + const allFilesSet = new Set(files); + const index = buildSuffixIndex(normalized, files); + const cache = new Map(); + return { files, normalized, allFilesSet, index, cache }; +} + +function resolve( + currentFile: string, + importPath: string, + language: SupportedLanguages, + ctx: ReturnType, +): string | null { + return resolveImportPath( + currentFile, + importPath, + ctx.allFilesSet, + ctx.files, + ctx.normalized, + ctx.cache, + language, + null, + ctx.index, + ); +} + +describe('TypeScript ESM .js extension resolution', () => { + it('resolves ./utils.js to ./utils.ts when .js does not exist', () => { + const ctx = makeCtx(['src/index.ts', 'src/utils.ts']); + const result = resolve('src/index.ts', './utils.js', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/utils.ts'); + }); + + it('resolves ./component.jsx to ./component.tsx', () => { + const ctx = makeCtx(['src/app.ts', 'src/component.tsx']); + const result = resolve('src/app.ts', './component.jsx', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/component.tsx'); + }); + + it('resolves ./config.mjs to ./config.mts', () => { + const ctx = makeCtx(['src/index.ts', 'src/config.mts']); + const result = resolve('src/index.ts', './config.mjs', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/config.mts'); + }); + + it('resolves ./legacy.cjs to ./legacy.cts', () => { + const ctx = makeCtx(['src/index.ts', 'src/legacy.cts']); + const result = resolve('src/index.ts', './legacy.cjs', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/legacy.cts'); + }); + + it('prefers actual .js file when it exists', () => { + const ctx = makeCtx(['src/index.ts', 'src/utils.js', 'src/utils.ts']); + const result = resolve('src/index.ts', './utils.js', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/utils.js'); + }); + + it('resolves relative path with ../ and .js extension', () => { + const ctx = makeCtx(['src/helpers/token.ts', 'src/core/engine.ts']); + const result = resolve( + 'src/core/engine.ts', + '../helpers/token.js', + SupportedLanguages.TypeScript, + ctx, + ); + expect(result).toBe('src/helpers/token.ts'); + }); + + it('works for JavaScript language too', () => { + const ctx = makeCtx(['src/index.js', 'src/utils.ts']); + const result = resolve('src/index.js', './utils.js', SupportedLanguages.JavaScript, ctx); + expect(result).toBe('src/utils.ts'); + }); + + it('does NOT apply ESM fallback for non-TS/JS languages', () => { + const ctx = makeCtx(['src/main.py', 'src/utils.ts']); + const result = resolve('src/main.py', './utils.js', SupportedLanguages.Python, ctx); + expect(result).toBeNull(); + }); + + it('returns null when neither .js nor .ts exists', () => { + const ctx = makeCtx(['src/index.ts']); + const result = resolve('src/index.ts', './missing.js', SupportedLanguages.TypeScript, ctx); + expect(result).toBeNull(); + }); +}); + +describe('ESM extension resolution — .mjs/.cjs with competing siblings', () => { + it('resolves ./config.mjs to .ts when only .ts exists (no .mts)', () => { + const ctx = makeCtx(['src/index.ts', 'src/config.ts']); + const result = resolve('src/index.ts', './config.mjs', SupportedLanguages.TypeScript, ctx); + // .ts wins because EXTENSIONS order tries .ts before .mts + expect(result).toBe('src/config.ts'); + }); + + it('resolves ./config.mjs to .mts when both .ts and .mts exist', () => { + // Note: EXTENSIONS order is .tsx, .ts, .mts, .cts — so .ts wins over .mts. + // This is intentional for a source-analysis tool: we resolve to the first + // matching source file. In practice, having both config.ts and config.mts + // in the same directory is extremely rare. + const ctx = makeCtx(['src/index.ts', 'src/config.ts', 'src/config.mts']); + const result = resolve('src/index.ts', './config.mjs', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/config.ts'); + }); + + it('resolves ./config.cjs to .cts when only .cts exists', () => { + const ctx = makeCtx(['src/index.ts', 'src/config.cts']); + const result = resolve('src/index.ts', './config.cjs', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/config.cts'); + }); +}); + +describe('ESM extension resolution — directory index boundary', () => { + it('resolves ./dir.js to dir/index.ts when dir/ exists (bundler-mode)', () => { + // After stripping .js from "dir.js" → "dir", tryResolveWithExtensions probes + // "/index.ts" suffix. This matches bundler-mode behavior where bare directory + // imports resolve to index files. Intentional for source-analysis compatibility. + const ctx = makeCtx(['src/index.ts', 'src/dir/index.ts']); + const result = resolve('src/index.ts', './dir.js', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/dir/index.ts'); + }); + + it('resolves ./dir/index.js to dir/index.ts', () => { + const ctx = makeCtx(['src/index.ts', 'src/dir/index.ts']); + const result = resolve('src/index.ts', './dir/index.js', SupportedLanguages.TypeScript, ctx); + expect(result).toBe('src/dir/index.ts'); + }); +}); + +describe('stripJsExtension', () => { + it('strips .js', () => expect(stripJsExtension('foo/bar.js')).toBe('foo/bar')); + it('strips .jsx', () => expect(stripJsExtension('foo/bar.jsx')).toBe('foo/bar')); + it('strips .mjs', () => expect(stripJsExtension('foo/bar.mjs')).toBe('foo/bar')); + it('strips .cjs', () => expect(stripJsExtension('foo/bar.cjs')).toBe('foo/bar')); + it('returns null for .ts', () => expect(stripJsExtension('foo/bar.ts')).toBeNull()); + it('returns null for no extension', () => expect(stripJsExtension('foo/bar')).toBeNull()); +}); + +describe('ESM extension resolution — path aliases with .js extensions', () => { + const aliasAtToSrc = new Map([['@/', 'src/']]); + const aliasTildeToSrc = new Map([['~/', 'src/']]); + + function resolveWithAlias( + currentFile: string, + importPath: string, + ctx: ReturnType, + aliases: Map, + baseUrl = '.', + ): string | null { + return resolveImportPath( + currentFile, + importPath, + ctx.allFilesSet, + ctx.files, + ctx.normalized, + ctx.cache, + SupportedLanguages.TypeScript, + { aliases, baseUrl }, + ctx.index, + ); + } + + it('resolves @/utils.js to src/utils.ts via alias', () => { + const ctx = makeCtx(['src/index.ts', 'src/utils.ts']); + const result = resolveWithAlias('src/index.ts', '@/utils.js', ctx, aliasAtToSrc, '.'); + expect(result).toBe('src/utils.ts'); + }); + + it('resolves @/component.jsx to src/component.tsx via alias', () => { + const ctx = makeCtx(['src/index.ts', 'src/component.tsx']); + const result = resolveWithAlias('src/index.ts', '@/component.jsx', ctx, aliasAtToSrc, '.'); + expect(result).toBe('src/component.tsx'); + }); + + it('resolves @/config.mjs to src/config.mts via alias', () => { + const ctx = makeCtx(['src/index.ts', 'src/config.mts']); + const result = resolveWithAlias('src/index.ts', '@/config.mjs', ctx, aliasAtToSrc, '.'); + expect(result).toBe('src/config.mts'); + }); + + it('resolves @/legacy.cjs to src/legacy.cts via alias', () => { + const ctx = makeCtx(['src/index.ts', 'src/legacy.cts']); + const result = resolveWithAlias('src/index.ts', '@/legacy.cjs', ctx, aliasAtToSrc, '.'); + expect(result).toBe('src/legacy.cts'); + }); + + it('prefers actual .js file over TS fallback in alias resolution', () => { + const ctx = makeCtx(['src/index.ts', 'src/utils.js', 'src/utils.ts']); + const result = resolveWithAlias('src/index.ts', '@/utils.js', ctx, aliasAtToSrc, '.'); + expect(result).toBe('src/utils.js'); + }); + + it('resolves alias with baseUrl prefix', () => { + const ctx = makeCtx(['app/src/index.ts', 'app/src/helpers/token.ts']); + const result = resolveWithAlias( + 'app/src/index.ts', + '~/helpers/token.js', + ctx, + aliasTildeToSrc, + 'app', + ); + expect(result).toBe('app/src/helpers/token.ts'); + }); + + it('returns null when alias .js import has no matching source', () => { + const ctx = makeCtx(['src/index.ts']); + const result = resolveWithAlias('src/index.ts', '@/missing.js', ctx, aliasAtToSrc, '.'); + expect(result).toBeNull(); + }); +}); diff --git a/gitnexus/test/unit/git-clone.test.ts b/gitnexus/test/unit/git-clone.test.ts index 18ac8e9d6..88832aa83 100644 --- a/gitnexus/test/unit/git-clone.test.ts +++ b/gitnexus/test/unit/git-clone.test.ts @@ -7,12 +7,12 @@ import { buildCloneArgs, normalizeGitUrlForCompare, assertRemoteMatchesRequestedUrl, - getRemoteOriginUrl, } from '../../src/server/git-clone.js'; import path from 'node:path'; import os from 'node:os'; import fs from 'node:fs/promises'; import { spawn } from 'node:child_process'; +import { getRemoteOriginUrl } from '../../src/storage/git.js'; describe('git-clone', () => { describe('extractRepoName', () => { @@ -50,17 +50,6 @@ describe('git-clone', () => { expect(() => extractRepoName('https://example.com/foo:.')).toThrow('valid repository name'); }); - it('rejects URLs with shell metacharacters in the last segment', () => { - // The split on /[/:]/ does not split on backslashes or other shell chars, - // so a name like `repo;rm -rf /` would slip through without the pattern. - expect(() => extractRepoName('https://example.com/foo:repo;rm')).toThrow( - 'valid repository name', - ); - expect(() => extractRepoName('https://example.com/foo:repo$x')).toThrow( - 'valid repository name', - ); - }); - it('rejects empty input', () => { expect(() => extractRepoName('')).toThrow('valid repository name'); }); @@ -77,6 +66,31 @@ describe('git-clone', () => { // multiple seconds on 10k slashes). expect(elapsedMs).toBeLessThan(500); }); + + it('strips leading dashes to prevent argument injection', () => { + expect(extractRepoName('https://github.com/user/--upload-pack=payload.git')).toBe( + 'upload-pack_payload', + ); + expect(extractRepoName('https://github.com/user/-repo')).toBe('repo'); + }); + + it('sanitizes unsafe directory characters', () => { + // sanitizeRepoName turns into _tag_ + expect(extractRepoName('https://github.com/user/repo.git')).toBe('repo_tag_'); + }); + + it('sanitizes shell metacharacters in URL segments', () => { + // The split on /[/:]/ does not split on backslashes or other shell chars, + // so a name like `repo;rm -rf /` would slip through without the pattern. + // After fix/sanitize-repo-name, these are sanitized to underscores. + expect(extractRepoName('https://example.com/foo:repo;rm')).toBe('repo_rm'); + expect(extractRepoName('https://example.com/foo:repo$x')).toBe('repo_x'); + }); + + it('sanitizes whitespace and backslashes', () => { + expect(extractRepoName('https://example.com/foo:repo name')).toBe('repo_name'); + expect(extractRepoName('https://example.com/foo:repo\\name')).toBe('repo_name'); + }); }); describe('getCloneDir', () => { @@ -209,7 +223,7 @@ describe('git-clone', () => { it('blocks NAT64 with embedded RFC1918 addresses', () => { // The startsWith('64:ff9b:') check covers any embedded IPv4. These - // explicit RFC1918 cases document SSRF coverage for the full private + // explicit RFC1918 architectures document SSRF coverage for the full private // IPv4 surface — not just loopback and cloud metadata. expect(() => validateGitUrl('http://[64:ff9b::a00:1]/repo.git')).toThrow('private/internal'); // 10.0.0.1 expect(() => validateGitUrl('http://[64:ff9b::ac10:1]/repo.git')).toThrow('private/internal'); // 172.16.0.1 diff --git a/gitnexus/test/unit/git.test.ts b/gitnexus/test/unit/git.test.ts index af339ce69..1bebf4143 100644 --- a/gitnexus/test/unit/git.test.ts +++ b/gitnexus/test/unit/git.test.ts @@ -8,6 +8,8 @@ import { getCurrentCommit, getGitRoot, findGitRootByDotGit, + parseRepoNameFromUrl, + sanitizeRepoName, } from '../../src/storage/git.js'; // Mock child_process.execSync @@ -164,4 +166,61 @@ describe('git utilities', () => { } }); }); + + describe('sanitizeRepoName', () => { + it('strips leading dashes', () => { + expect(sanitizeRepoName('--repo')).toBe('repo'); + }); + + it('replaces unsafe characters with underscores', () => { + expect(sanitizeRepoName('repo')).toBe('repo_tag_'); + expect(sanitizeRepoName('repo:name')).toBe('repo_name'); + expect(sanitizeRepoName('repo"quoted"')).toBe('repo_quoted_'); + }); + + it('blocks path traversal segments', () => { + expect(sanitizeRepoName('.')).toBe('unknown'); + expect(sanitizeRepoName('..')).toBe('unknown'); + }); + + it('blocks Windows reserved names', () => { + expect(sanitizeRepoName('CON')).toBe('unknown'); + expect(sanitizeRepoName('prn')).toBe('unknown'); + expect(sanitizeRepoName('AUX')).toBe('unknown'); + expect(sanitizeRepoName('NUL')).toBe('unknown'); + expect(sanitizeRepoName('COM1')).toBe('unknown'); + expect(sanitizeRepoName('LPT9')).toBe('unknown'); + + // Reserved names with extensions + expect(sanitizeRepoName('CON.txt')).toBe('unknown'); + expect(sanitizeRepoName('NUL.tar.gz')).toBe('unknown'); + expect(sanitizeRepoName('AUX.local')).toBe('unknown'); + }); + + it('returns unknown for empty or invalid input', () => { + expect(sanitizeRepoName('')).toBe('unknown'); + expect(sanitizeRepoName('---')).toBe('unknown'); + }); + }); + + describe('parseRepoNameFromUrl', () => { + it('extracts and sanitizes name from HTTPS URL', () => { + expect(parseRepoNameFromUrl('https://github.com/user/my-repo.git')).toBe('my-repo'); + expect(parseRepoNameFromUrl('https://github.com/user/--payload.git')).toBe('payload'); + }); + + it('extracts and sanitizes name from SSH URL', () => { + expect(parseRepoNameFromUrl('git@github.com:user/my-repo.git')).toBe('my-repo'); + expect(parseRepoNameFromUrl('git@github.com:--payload.git')).toBe('payload'); + }); + + it('returns null for all-dash inputs (prevents registry collision)', () => { + expect(parseRepoNameFromUrl('https://github.com/user/---.git')).toBeNull(); + }); + + it('returns null for empty URL', () => { + expect(parseRepoNameFromUrl('')).toBeNull(); + expect(parseRepoNameFromUrl(null)).toBeNull(); + }); + }); }); diff --git a/gitnexus/test/unit/group/grpc-extractor.test.ts b/gitnexus/test/unit/group/grpc-extractor.test.ts index b128c6ddf..127dd6ab9 100644 --- a/gitnexus/test/unit/group/grpc-extractor.test.ts +++ b/gitnexus/test/unit/group/grpc-extractor.test.ts @@ -1,8 +1,15 @@ -import { describe, it, expect, beforeEach, afterEach } from 'vitest'; +import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; import * as fs from 'node:fs'; import fsp from 'node:fs/promises'; import * as path from 'node:path'; import * as os from 'node:os'; + +const { parseSourceSafeSpy } = vi.hoisted(() => ({ parseSourceSafeSpy: vi.fn() })); + +vi.mock('../../../src/core/tree-sitter/safe-parse.js', async () => { + const { buildSafeParseMock } = await import('../../helpers/parse-source-safe-mock.js'); + return buildSafeParseMock(parseSourceSafeSpy); +}); import { GrpcExtractor, buildProtoMap, @@ -677,6 +684,33 @@ stub = leaked_pb2_grpc.LeakedServiceStub(channel)`, ).toBe(false); }); }); + + describe('Windows SIGSEGV regression — large input must route through parseSourceSafe', () => { + it('routes >32 767-char source file through parseSourceSafe (not direct parser.parse)', async () => { + parseSourceSafeSpy.mockClear(); + + // Synthesize a >40 000-char source file in a language whose grpc plugin + // is always available (Go has no optional grammar — the Go plugin is + // unconditionally wired in grpc-patterns/index.ts). Direct + // parser.parse(content) on an input this size SIGSEGVs the process on + // Windows; parseSourceSafe routes through the chunked-callback path and + // works on every platform. The spy assertion is what catches the + // regression — a "no throw" assertion alone is satisfied by the bypass + // on Linux/macOS where parser.parse(40 000 chars) succeeds. + const padding = Array.from( + { length: 600 }, + (_, i) => `func helper${i}() string { return "padding-${i}-aaaaaaaaaaaaaaaaaaaaaa" }\n`, + ).join(''); + const largeGo = `package big\n\n${padding}\n`; + expect(largeGo.length).toBeGreaterThan(40_000); + + writeFile('server/big.go', largeGo); + + await extractor.extract(null, tmpDir, makeRepo(tmpDir)); + + expect(parseSourceSafeSpy).toHaveBeenCalled(); + }); + }); }); describe('buildProtoMap', () => { diff --git a/gitnexus/test/unit/group/http-route-extractor.test.ts b/gitnexus/test/unit/group/http-route-extractor.test.ts index 69d3da2fa..aa648a71d 100644 --- a/gitnexus/test/unit/group/http-route-extractor.test.ts +++ b/gitnexus/test/unit/group/http-route-extractor.test.ts @@ -1,17 +1,25 @@ -import { describe, it, expect, beforeEach, afterEach } from 'vitest'; +import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; import * as fs from 'node:fs'; import * as path from 'node:path'; import * as os from 'node:os'; + +const { parseSourceSafeSpy } = vi.hoisted(() => ({ parseSourceSafeSpy: vi.fn() })); + +vi.mock('../../../src/core/tree-sitter/safe-parse.js', async () => { + const { buildSafeParseMock } = await import('../../helpers/parse-source-safe-mock.js'); + return buildSafeParseMock(parseSourceSafeSpy); +}); + import { HttpRouteExtractor } from '../../../src/core/group/extractors/http-route-extractor.js'; import type { RepoHandle } from '../../../src/core/group/types.js'; describe('HttpRouteExtractor', () => { - const tmpDir = path.join(os.tmpdir(), `gitnexus-http-extract-${Date.now()}`); + let tmpDir: string; let extractor: HttpRouteExtractor; beforeEach(() => { extractor = new HttpRouteExtractor(); - fs.mkdirSync(tmpDir, { recursive: true }); + tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-http-extract-')); }); afterEach(() => { @@ -428,6 +436,74 @@ def create_order(): consumers.find((c) => c.contractId === 'http::POST::/api/orders/{param}'), ).toBeDefined(); }); + it('extracts Python httpx.AsyncClient calls assigned to attributes or aliases', async () => { + const dir = path.join(tmpDir, 'python-httpx-consumer'); + fs.mkdirSync(path.join(dir, 'src'), { recursive: true }); + fs.writeFileSync( + path.join(dir, 'src', 'client.py'), + ` +import httpx + +module_client = httpx.AsyncClient(base_url="https://svc.local") + +class TopicClient: + def __init__(self): + self._client = httpx.AsyncClient(base_url="https://svc.local") + + async def list_topics(self): + return await self._client.get("/topic") + + async def publish(self): + return await self._client.request("POST", "/questions/import") + + async def delete_topic(self): + return await self._client.delete("/topic") + +async def check_duplicate(): + async with httpx.AsyncClient() as client: + data = {} + data.get("/nope") + service.request("POST", "/nope") + return await client.post("https://svc.local/questions/duplicate-check") + +def unrelated_scope_collision(): + client = acquire_cache_client() + return client.get("/ignored-same-name") + +def module_scope_shadow_collision(): + client = acquire_cache_client() + return client.get("/ignored-module-same-name") + +module_client.get("/module-topic") +`, + ); + + const contracts = await extractor.extract(null, dir, makeRepo(dir)); + const consumers = contracts.filter((c) => c.role === 'consumer'); + + const expected = [ + 'http::GET::/topic', + 'http::POST::/questions/import', + 'http::DELETE::/topic', + 'http::POST::/questions/duplicate-check', + 'http::GET::/module-topic', + ]; + + for (const contractId of expected) { + const consumer = consumers.find((c) => c.contractId === contractId); + expect(consumer).toBeDefined(); + expect(consumer?.meta.framework).toBe('python-httpx'); + } + + expect(consumers.find((c) => c.contractId === 'http::GET::/nope')).toBeUndefined(); + expect(consumers.find((c) => c.contractId === 'http::POST::/nope')).toBeUndefined(); + expect( + consumers.find((c) => c.contractId === 'http::GET::/ignored-same-name'), + ).toBeUndefined(); + expect( + consumers.find((c) => c.contractId === 'http::GET::/ignored-module-same-name'), + ).toBeUndefined(); + }); it('extracts Java RestTemplate, WebClient and OkHttp calls', async () => { const dir = path.join(tmpDir, 'java-consumer'); @@ -815,4 +891,34 @@ export default r; expect(contracts.some((c) => c.symbolRef?.filePath?.startsWith('mentor_env/'))).toBe(false); }); }); + + describe('Windows SIGSEGV regression — large input must route through parseSourceSafe', () => { + it('routes >32 767-char source file through parseSourceSafe (not direct parser.parse)', async () => { + parseSourceSafeSpy.mockClear(); + + // >40 000-char Java controller file. Direct parser.parse(content) on + // an input this size SIGSEGVs the process on Windows. The spy assertion + // is what catches the regression — a "no throw" assertion alone is + // satisfied by the bypass on Linux/macOS where parser.parse(40 000 chars) + // succeeds. + const padding = Array.from( + { length: 600 }, + (_, i) => ` public String helper${i}() { return "padding-${i}-aaaaaaaaaaaaaaaaaaa"; }\n`, + ).join(''); + const largeJava = `package com.example;\n\n@RestController\npublic class BigController {\n${padding}}\n`; + expect(largeJava.length).toBeGreaterThan(40_000); + + // Use mkdtempSync rather than a fixed subdir name: satisfies CodeQL's + // js/insecure-temporary-file rule by generating a unique random suffix + // instead of relying on the parent tmpDir's predictable Date.now() name. + const dir = fs.mkdtempSync(path.join(tmpDir, 'large-input-')); + fs.mkdirSync(path.join(dir, 'src/controller'), { recursive: true }); + fs.writeFileSync(path.join(dir, 'src/controller/BigController.java'), largeJava); + + const mockDbExecutor = async (_query: string) => []; + await extractor.extract(mockDbExecutor, dir, makeRepo(dir)); + + expect(parseSourceSafeSpy).toHaveBeenCalled(); + }); + }); }); diff --git a/gitnexus/test/unit/group/include-extractor.test.ts b/gitnexus/test/unit/group/include-extractor.test.ts index 3956cd5f2..321773518 100644 --- a/gitnexus/test/unit/group/include-extractor.test.ts +++ b/gitnexus/test/unit/group/include-extractor.test.ts @@ -1,7 +1,15 @@ -import { describe, it, expect, beforeEach, afterEach } from 'vitest'; +import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; import * as fs from 'node:fs'; import * as path from 'node:path'; import * as os from 'node:os'; + +const { parseSourceSafeSpy } = vi.hoisted(() => ({ parseSourceSafeSpy: vi.fn() })); + +vi.mock('../../../src/core/tree-sitter/safe-parse.js', async () => { + const { buildSafeParseMock } = await import('../../helpers/parse-source-safe-mock.js'); + return buildSafeParseMock(parseSourceSafeSpy); +}); + import { IncludeExtractor } from '../../../src/core/group/extractors/include-extractor.js'; import type { RepoHandle } from '../../../src/core/group/types.js'; import { normalizeContractId } from '../../../src/core/group/matching.js'; @@ -560,4 +568,35 @@ int auto_main() { return 0; }`, } }); }); + + describe('Windows SIGSEGV regression — large input must route through parseSourceSafe', () => { + it('routes >32 767-char header file through parseSourceSafe (not direct parser.parse)', async () => { + parseSourceSafeSpy.mockClear(); + + // Bump the file-size cap so the >40 000-char file isn't filtered before + // it ever reaches the parser. Direct parser.parse(content) on a string + // this size SIGSEGVs the process on Windows. The spy assertion catches + // the regression — a "no throw" assertion alone is satisfied by the + // bypass on Linux/macOS where parser.parse(40 000 chars) succeeds. + const previousLimit = process.env.GITNEXUS_MAX_FILE_SIZE; + process.env.GITNEXUS_MAX_FILE_SIZE = '512'; + try { + const includes = Array.from( + { length: 1500 }, + (_, i) => `#include "lib/header_${i}.h"\n`, + ).join(''); + const largeHeader = `#pragma once\n${includes}\nstruct Big {};\n`; + expect(largeHeader.length).toBeGreaterThan(40_000); + + writeFile('big/big.cpp', largeHeader); + + await extractor.extract(null, tmpDir, makeRepo(tmpDir)); + + expect(parseSourceSafeSpy).toHaveBeenCalled(); + } finally { + if (previousLimit === undefined) delete process.env.GITNEXUS_MAX_FILE_SIZE; + else process.env.GITNEXUS_MAX_FILE_SIZE = previousLimit; + } + }); + }); }); diff --git a/gitnexus/test/unit/group/thrift-extractor.test.ts b/gitnexus/test/unit/group/thrift-extractor.test.ts index ca7045543..fa33b0e49 100644 --- a/gitnexus/test/unit/group/thrift-extractor.test.ts +++ b/gitnexus/test/unit/group/thrift-extractor.test.ts @@ -1,8 +1,16 @@ -import { describe, it, expect, beforeEach, afterEach } from 'vitest'; +import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; import * as fs from 'node:fs'; import fsp from 'node:fs/promises'; import * as path from 'node:path'; import * as os from 'node:os'; + +const { parseSourceSafeSpy } = vi.hoisted(() => ({ parseSourceSafeSpy: vi.fn() })); + +vi.mock('../../../src/core/tree-sitter/safe-parse.js', async () => { + const { buildSafeParseMock } = await import('../../helpers/parse-source-safe-mock.js'); + return buildSafeParseMock(parseSourceSafeSpy); +}); + import { ThriftExtractor, buildThriftContext, @@ -580,6 +588,39 @@ class PaymentWorkflow { expect(contracts).toEqual([]); }); + + describe('Windows SIGSEGV regression — large input must route through parseSourceSafe', () => { + it('routes >32 767-char source file through parseSourceSafe (not direct parser.parse)', async () => { + parseSourceSafeSpy.mockClear(); + + // Need a base .thrift file so buildThriftContext finds at least one + // service to scan; without it the source-scan loop short-circuits. + writeFile( + 'idl/order.thrift', + `namespace java billing.v1 +service OrderService { + PlaceOrderResponse PlaceOrder(1: PlaceOrderRequest request) +}`, + ); + + // >40 000-char Java client file. Direct parser.parse(content) on a + // string this size SIGSEGVs the process on Windows. The spy assertion + // catches the regression — a "no throw" assertion alone is satisfied + // by the bypass on Linux/macOS where parser.parse(40 000 chars) succeeds. + const padding = Array.from( + { length: 600 }, + (_, i) => ` public String helper${i}() { return "padding-${i}-aaaaaaaaaaaaaaaaaaa"; }\n`, + ).join(''); + const largeJava = `package com.example;\n\nimport billing.v1.OrderService;\n\npublic class BigClient {\n private OrderService.Iface client;\n${padding}}\n`; + expect(largeJava.length).toBeGreaterThan(40_000); + + writeFile('src/main/java/com/example/BigClient.java', largeJava); + + await extractor.extract(null, tmpDir, makeRepo(tmpDir)); + + expect(parseSourceSafeSpy).toHaveBeenCalled(); + }); + }); }); describe('buildThriftContext', () => { diff --git a/gitnexus/test/unit/hf-env.test.ts b/gitnexus/test/unit/hf-env.test.ts index fa8f23bd3..5999b34a2 100644 --- a/gitnexus/test/unit/hf-env.test.ts +++ b/gitnexus/test/unit/hf-env.test.ts @@ -1,12 +1,12 @@ import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; import os from 'node:os'; import { join } from 'node:path'; +import { CircuitBreaker } from 'gitnexus-shared'; import { applyHfEnvOverrides, isNetworkFetchError, isHfDownloadFailure, isHfCircuitOpenError, - HfDownloadCircuitBreaker, withDownloadTimeout, withHfDownloadRetry, CIRCUIT_OPEN_TAG, @@ -154,85 +154,13 @@ describe('isHfDownloadFailure', () => { }); }); -describe('HfDownloadCircuitBreaker', () => { - it('starts in closed state', () => { - const cb = new HfDownloadCircuitBreaker(); - expect(cb.isOpen()).toBe(false); - expect(cb.state).toBe('closed'); - }); - - it('opens after reaching the failure threshold', () => { - const cb = new HfDownloadCircuitBreaker(3); - cb.recordFailure(); - cb.recordFailure(); - expect(cb.isOpen()).toBe(false); - cb.recordFailure(); // threshold reached - expect(cb.isOpen()).toBe(true); - expect(cb.state).toBe('open'); - }); - - it('closes on recordSuccess after being open', () => { - const cb = new HfDownloadCircuitBreaker(1); - cb.recordFailure(); - expect(cb.isOpen()).toBe(true); - cb.recordSuccess(); - expect(cb.isOpen()).toBe(false); - expect(cb.state).toBe('closed'); - }); - - it('transitions to half-open after the reset timeout', () => { - vi.useFakeTimers(); - try { - const cb = new HfDownloadCircuitBreaker(1, 100 /* 100ms */); - cb.recordFailure(); - expect(cb.isOpen()).toBe(true); - vi.advanceTimersByTime(200); - expect(cb.isOpen()).toBe(false); - expect(cb.state).toBe('half-open'); - } finally { - vi.useRealTimers(); - } - }); - - it('reset() restores closed state', () => { - const cb = new HfDownloadCircuitBreaker(1); - cb.recordFailure(); - expect(cb.isOpen()).toBe(true); - cb.reset(); - expect(cb.isOpen()).toBe(false); - expect(cb.state).toBe('closed'); - }); - - it('re-opens when a failure is recorded in half-open state', () => { - vi.useFakeTimers(); - try { - const cb = new HfDownloadCircuitBreaker(1, 100 /* 100ms */); - cb.recordFailure(); // opens the circuit - vi.advanceTimersByTime(200); // advance past reset timeout - expect(cb.state).toBe('half-open'); // getter transitions _state to half-open - cb.recordFailure(); // failure in half-open → re-opens - expect(cb.isOpen()).toBe(true); - expect(cb.state).toBe('open'); - } finally { - vi.useRealTimers(); - } - }); - - it('closes the circuit when success is recorded in half-open state', () => { - vi.useFakeTimers(); - try { - const cb = new HfDownloadCircuitBreaker(1, 100 /* 100ms */); - cb.recordFailure(); // opens the circuit - vi.advanceTimersByTime(200); // advance past reset timeout - expect(cb.state).toBe('half-open'); - cb.recordSuccess(); // success in half-open → closes - expect(cb.isOpen()).toBe(false); - expect(cb.state).toBe('closed'); - } finally { - vi.useRealTimers(); - } - }); -}); +// CircuitBreaker state-machine tests live in +// `gitnexus/test/unit/integrations/circuit-breaker.test.ts` — that suite +// already covers the closed/open/half-open transitions, recordSuccess/ +// recordFailure semantics, half-open probe gating, and configurable +// thresholds. No need to duplicate here; this file's remaining tests +// focus on HF-specific composition (withHfDownloadRetry, env-var +// overrides, error classification). describe('withDownloadTimeout', () => { it('resolves when fn completes before the timeout', async () => { @@ -262,7 +190,7 @@ describe('withDownloadTimeout', () => { describe('withHfDownloadRetry', () => { it('returns the result on first success', async () => { const fn = vi.fn().mockResolvedValue('ok'); - const cb = new HfDownloadCircuitBreaker(); + const cb = new CircuitBreaker(); const result = await withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 }); expect(result).toBe('ok'); expect(fn).toHaveBeenCalledTimes(1); @@ -270,7 +198,7 @@ describe('withHfDownloadRetry', () => { it('retries on network errors and succeeds on second attempt', async () => { const fn = vi.fn().mockRejectedValueOnce(new Error('fetch failed')).mockResolvedValue('ok'); - const cb = new HfDownloadCircuitBreaker(); + const cb = new CircuitBreaker(); const result = await withHfDownloadRetry(fn, { circuit: cb, maxAttempts: 3, @@ -282,7 +210,7 @@ describe('withHfDownloadRetry', () => { it('throws the last network error after all attempts are exhausted', async () => { const fn = vi.fn().mockRejectedValue(new Error('ECONNREFUSED 127.0.0.1:443')); - const cb = new HfDownloadCircuitBreaker(99 /* high threshold */); + const cb = new CircuitBreaker({ failureThreshold: 99 }); await expect( withHfDownloadRetry(fn, { circuit: cb, maxAttempts: 3, baseDelayMs: 0 }), ).rejects.toThrow('ECONNREFUSED'); @@ -291,7 +219,7 @@ describe('withHfDownloadRetry', () => { it('does not retry non-network errors', async () => { const fn = vi.fn().mockRejectedValue(new Error('Failed to initialize CUDA backend')); - const cb = new HfDownloadCircuitBreaker(); + const cb = new CircuitBreaker(); await expect( withHfDownloadRetry(fn, { circuit: cb, maxAttempts: 3, baseDelayMs: 0 }), ).rejects.toThrow('Failed to initialize CUDA backend'); @@ -300,7 +228,7 @@ describe('withHfDownloadRetry', () => { it('fails immediately when the circuit is already open', async () => { const fn = vi.fn().mockResolvedValue('ok'); - const cb = new HfDownloadCircuitBreaker(1); + const cb = new CircuitBreaker({ failureThreshold: 1 }); cb.recordFailure(); // open the circuit await expect(withHfDownloadRetry(fn, { circuit: cb })).rejects.toThrow(CIRCUIT_OPEN_TAG); expect(fn).not.toHaveBeenCalled(); @@ -308,12 +236,12 @@ describe('withHfDownloadRetry', () => { it('opens the circuit after failureThreshold failures and throws a circuit-open error', async () => { const fn = vi.fn().mockRejectedValue(new Error('ENOTFOUND huggingface.co')); - const cb = new HfDownloadCircuitBreaker(2 /* threshold */, 60_000); + const cb = new CircuitBreaker({ failureThreshold: 2, cooldownMs: 60_000 }); // First call: 2 attempts, threshold=2 → circuit opens on 2nd failure await expect( withHfDownloadRetry(fn, { circuit: cb, maxAttempts: 2, baseDelayMs: 0 }), ).rejects.toThrow(CIRCUIT_OPEN_TAG); - expect(cb.isOpen()).toBe(true); + expect(cb.getState()).toBe('open'); }); it('calls onRetry with correct arguments on each retry', async () => { @@ -322,7 +250,7 @@ describe('withHfDownloadRetry', () => { .mockRejectedValueOnce(new Error('fetch failed')) .mockRejectedValueOnce(new Error('fetch failed')) .mockResolvedValue('ok'); - const cb = new HfDownloadCircuitBreaker(99); + const cb = new CircuitBreaker({ failureThreshold: 99 }); const onRetry = vi.fn(); await withHfDownloadRetry(fn, { circuit: cb, maxAttempts: 3, baseDelayMs: 0, onRetry }); expect(onRetry).toHaveBeenCalledTimes(2); @@ -342,11 +270,11 @@ describe('withHfDownloadRetry', () => { it('resets the circuit on success', async () => { const fn = vi.fn().mockResolvedValue('value'); - const cb = new HfDownloadCircuitBreaker(5); + const cb = new CircuitBreaker({ failureThreshold: 5 }); cb.recordFailure(); cb.recordFailure(); // 2 failures, circuit still closed await withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 }); - expect(cb.state).toBe('closed'); + expect(cb.getState()).toBe('closed'); }); }); @@ -371,7 +299,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS=1 gives exactly 1 attempt', async () => { process.env.HF_MAX_ATTEMPTS = '1'; const fn = vi.fn().mockRejectedValue(new Error('ECONNREFUSED 127.0.0.1:443')); - const cb = new HfDownloadCircuitBreaker(99_999 /* high threshold */); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'ECONNREFUSED', ); @@ -381,7 +309,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS=2 gives exactly 2 attempts', async () => { process.env.HF_MAX_ATTEMPTS = '2'; const fn = vi.fn().mockRejectedValue(new Error('ENOTFOUND huggingface.co')); - const cb = new HfDownloadCircuitBreaker(99_999); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'ENOTFOUND', ); @@ -391,7 +319,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS=abc falls back to the built-in default', async () => { process.env.HF_MAX_ATTEMPTS = 'abc'; const fn = vi.fn().mockRejectedValue(new Error('fetch failed')); - const cb = new HfDownloadCircuitBreaker(99_999); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'fetch failed', ); @@ -401,7 +329,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS=0 falls back to the built-in default', async () => { process.env.HF_MAX_ATTEMPTS = '0'; const fn = vi.fn().mockRejectedValue(new Error('fetch failed')); - const cb = new HfDownloadCircuitBreaker(99_999); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'fetch failed', ); @@ -411,7 +339,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS=-1 falls back to the built-in default', async () => { process.env.HF_MAX_ATTEMPTS = '-1'; const fn = vi.fn().mockRejectedValue(new Error('fetch failed')); - const cb = new HfDownloadCircuitBreaker(99_999); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'fetch failed', ); @@ -421,7 +349,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS is clamped to HF_MAX_ATTEMPTS_CAP', async () => { process.env.HF_MAX_ATTEMPTS = '9999'; const fn = vi.fn().mockRejectedValue(new Error('fetch failed')); - const cb = new HfDownloadCircuitBreaker(99_999 /* very high threshold */); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'fetch failed', ); @@ -431,7 +359,7 @@ describe('withHfDownloadRetry env overrides', () => { it('HF_MAX_ATTEMPTS=2.9 is floored to 2', async () => { process.env.HF_MAX_ATTEMPTS = '2.9'; const fn = vi.fn().mockRejectedValue(new Error('fetch failed')); - const cb = new HfDownloadCircuitBreaker(99_999); + const cb = new CircuitBreaker({ failureThreshold: 99_999 }); await expect(withHfDownloadRetry(fn, { circuit: cb, baseDelayMs: 0 })).rejects.toThrow( 'fetch failed', ); @@ -443,7 +371,7 @@ describe('withHfDownloadRetry env overrides', () => { try { process.env.HF_DOWNLOAD_TIMEOUT_MS = '50'; const neverResolves = () => new Promise(() => {}); - const cb = new HfDownloadCircuitBreaker(99); + const cb = new CircuitBreaker({ failureThreshold: 99 }); const promise = withHfDownloadRetry(neverResolves, { circuit: cb, maxAttempts: 1 }); vi.advanceTimersByTime(100); await expect(promise).rejects.toThrow('ETIMEDOUT'); @@ -458,7 +386,7 @@ describe('withHfDownloadRetry env overrides', () => { // we just verify that the env var rejection causes options.timeoutMs to be // the default constant (not -1) by confirming the resolved value is used. const fn = vi.fn().mockResolvedValue('ok'); - const cb = new HfDownloadCircuitBreaker(99); + const cb = new CircuitBreaker({ failureThreshold: 99 }); // Provide explicit timeoutMs to avoid the default 5-minute wait const result = await withHfDownloadRetry(fn, { circuit: cb, timeoutMs: 100 }); expect(result).toBe('ok'); @@ -470,7 +398,7 @@ describe('withHfDownloadRetry env overrides', () => { // Set an env value exceeding the 30-minute cap process.env.HF_DOWNLOAD_TIMEOUT_MS = String(HF_MAX_TIMEOUT_MS + 60_000); const neverResolves = () => new Promise(() => {}); - const cb = new HfDownloadCircuitBreaker(99); + const cb = new CircuitBreaker({ failureThreshold: 99 }); const promise = withHfDownloadRetry(neverResolves, { circuit: cb, maxAttempts: 1 }); // Advance just past the 30-minute cap vi.advanceTimersByTime(HF_MAX_TIMEOUT_MS + 1); @@ -483,7 +411,7 @@ describe('withHfDownloadRetry env overrides', () => { it('explicit options override env vars', async () => { process.env.HF_MAX_ATTEMPTS = '5'; const fn = vi.fn().mockRejectedValue(new Error('fetch failed')); - const cb = new HfDownloadCircuitBreaker(99); + const cb = new CircuitBreaker({ failureThreshold: 99 }); // explicit maxAttempts: 2 must win over HF_MAX_ATTEMPTS=5 await expect( withHfDownloadRetry(fn, { circuit: cb, maxAttempts: 2, baseDelayMs: 0 }), diff --git a/gitnexus/test/unit/hooks.test.ts b/gitnexus/test/unit/hooks.test.ts index da19da002..a0ef2b8cb 100644 --- a/gitnexus/test/unit/hooks.test.ts +++ b/gitnexus/test/unit/hooks.test.ts @@ -12,6 +12,7 @@ * - shell injection: verifies no shell: true in spawnSync calls * - dispatch map: correct handler routing * - cross-platform: Windows .cmd extension handling + * - cross-platform: DB lock probe (Linux /proc, Unix lsof, Windows RM) * * Since the hooks are CJS scripts that call main() on load, we test them * by spawning them as child processes with controlled stdin JSON. @@ -26,6 +27,7 @@ import { runHook, parseHookOutput } from '../utils/hook-test-helpers.js'; // ─── Paths to both hook variants ──────────────────────────────────── const CJS_HOOK = path.resolve(__dirname, '..', '..', 'hooks', 'claude', 'gitnexus-hook.cjs'); +const CJS_HOOK_LOCK = path.resolve(__dirname, '..', '..', 'hooks', 'claude', 'hook-lock.cjs'); const PLUGIN_HOOK = path.resolve( __dirname, '..', @@ -35,6 +37,32 @@ const PLUGIN_HOOK = path.resolve( 'hooks', 'gitnexus-hook.js', ); +const PLUGIN_HOOK_LOCK = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-claude-plugin', + 'hooks', + 'hook-lock.js', +); +const CJS_HOOK_DB_PROBE = path.resolve( + __dirname, + '..', + '..', + 'hooks', + 'claude', + 'hook-db-lock-probe.cjs', +); +const PLUGIN_HOOK_DB_PROBE = path.resolve( + __dirname, + '..', + '..', + '..', + 'gitnexus-claude-plugin', + 'hooks', + 'hook-db-lock-probe.cjs', +); // ─── Test fixtures: temporary .gitnexus directory ─────────────────── @@ -99,6 +127,62 @@ function createGlobalRegistry(homeDir: string, marker: 'both' | 'registry' | 're } } +function writeExecutable(filePath: string, content: string) { + fs.writeFileSync(filePath, content, { mode: 0o755 }); +} + +function createHookToolDir(options: { + gitnexusStderr?: string; + gitnexusMarkerPath?: string; + lsofOutput?: string; + lsofOutputLines?: string[]; + psOutput?: string; + psOutputByPid?: Record; + lsofSleepMs?: number; +}) { + const binDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-hook-bin-')); + const gitnexusStderr = JSON.stringify(options.gitnexusStderr ?? ''); + const markerPath = JSON.stringify(options.gitnexusMarkerPath ?? ''); + + const fakeGitNexus = `#!/usr/bin/env node\nconst fs = require('fs');\nconst marker = ${markerPath};\nif (marker) fs.writeFileSync(marker, 'called');\nprocess.stderr.write(${gitnexusStderr});\n`; + writeExecutable(path.join(binDir, 'gitnexus'), fakeGitNexus); + writeExecutable(path.join(binDir, 'gitnexus-cli.js'), fakeGitNexus); + + const lsofOutput = + options.lsofOutputLines != null + ? options.lsofOutputLines.join('\n') + (options.lsofOutputLines.length ? '\n' : '') + : (options.lsofOutput ?? ''); + const lsofBody = + options.lsofSleepMs != null + ? `#!/usr/bin/env node\nsetTimeout(() => {}, ${Number(options.lsofSleepMs)});\n` + : `#!/usr/bin/env node\nprocess.stdout.write(${JSON.stringify(lsofOutput)});\nprocess.exit(0);\n`; + writeExecutable(path.join(binDir, 'lsof'), lsofBody); + + const psBody = + options.psOutputByPid != null + ? `#!/usr/bin/env node +const byPid = ${JSON.stringify(options.psOutputByPid)}; +const args = process.argv; +const p = args[args.indexOf('-p') + 1]; +process.stdout.write(byPid[p] ?? ''); +process.exit(0); +` + : `#!/usr/bin/env node\nprocess.stdout.write(${JSON.stringify(options.psOutput ?? '')});\nprocess.exit(0);\n`; + writeExecutable(path.join(binDir, 'ps'), psBody); + + return binDir; +} + +function hookEnv(binDir: string) { + return { + ...process.env, + PATH: `${binDir}${path.delimiter}${process.env.PATH || ''}`, + GITNEXUS_HOOK_CLI_PATH: path.join(binDir, 'gitnexus-cli.js'), + GITNEXUS_HOOK_LSOF_PATH: path.join(binDir, 'lsof'), + GITNEXUS_HOOK_PS_PATH: path.join(binDir, 'ps'), + }; +} + // ─── Both hook files should exist ─────────────────────────────────── describe('Hook files exist', () => { @@ -294,6 +378,720 @@ describe('Git mutation regex', () => { } }); +// ─── Source code regression: PreToolUse concurrency guard (#1486) ── + +describe('PreToolUse concurrency guard', () => { + for (const [label, hookPath, lockPath] of [ + ['CJS', CJS_HOOK, CJS_HOOK_LOCK], + ['Plugin', PLUGIN_HOOK, PLUGIN_HOOK_LOCK], + ] as const) { + it(`${label} hook loads acquireHookSlot helper`, () => { + const source = fs.readFileSync(hookPath, 'utf-8'); + expect(source).toContain('acquireHookSlot'); + expect(source).toContain('hook-lock'); + }); + + it(`${label} helper defines acquireHookSlot`, () => { + const source = fs.readFileSync(lockPath, 'utf-8'); + expect(source).toContain('function acquireHookSlot'); + expect(source).toContain('HOOK_LOCK_MAX_INFLIGHT'); + }); + + it(`${label} hook calls acquireHookSlot in handlePreToolUse`, () => { + const source = fs.readFileSync(hookPath, 'utf-8'); + const preBody = source.slice( + source.indexOf('function handlePreToolUse'), + source.indexOf('function handlePostToolUse'), + ); + expect(preBody).toContain('acquireHookSlot('); + expect(preBody).toMatch(/release\(\)/); + }); + + it(`${label} hook uses atomic fixed-name slot files (hard cap)`, () => { + // Regression for the TOCTOU soft-cap: an earlier revision counted + // entries then wrote a per-pid lock, which let simultaneous bursts + // exceed MAX_INFLIGHT. The hard-cap version writes to fixed-name + // slot-N.lock paths so O_CREAT|O_EXCL is atomic across processes. + const source = fs.readFileSync(lockPath, 'utf-8'); + expect(source).toMatch(/slot-\$\{slot\}\.lock|`slot-/); + // And no longer reads the lock dir to count active hooks. + const slotFn = source.slice( + source.indexOf('function acquireHookSlot'), + source.indexOf('function', source.indexOf('function acquireHookSlot') + 1), + ); + expect(slotFn).not.toContain('readdirSync'); + }); + + it(`${label} hook fails closed when lock dir cannot be created`, () => { + // Regression: an earlier revision returned `() => {}` (truthy no-op) on + // mkdirSync failure, which left callers — `if (!release) return;` — to + // proceed unguarded and reintroduce the #1486 fan-out on read-only or + // cross-user `.gitnexus/` setups. The guard must fail closed (null). + const source = fs.readFileSync(lockPath, 'utf-8'); + const slotFn = source.slice( + source.indexOf('function acquireHookSlot'), + source.indexOf('function', source.indexOf('function acquireHookSlot') + 1), + ); + const mkdirCatch = slotFn.slice( + slotFn.indexOf('fs.mkdirSync(lockDir'), + slotFn.indexOf('const myPidStr'), + ); + expect(mkdirCatch).toContain('return null'); + expect(mkdirCatch).not.toMatch(/return\s*\(\s*\)\s*=>\s*\{\s*\}/); + }); + } +}); + +// ─── Integration: concurrency guard skips when slots are full ────── + +describe('PreToolUse concurrency guard (integration)', () => { + for (const [label, hookPath] of [ + ['CJS', CJS_HOOK], + ['Plugin', PLUGIN_HOOK], + ] as const) { + it(`${label}: hook exits silently when all MAX_INFLIGHT slots hold live pids`, async () => { + const { spawn } = await import('child_process'); + const lockDir = path.join(gitNexusDir, '.hook-locks'); + fs.mkdirSync(lockDir, { recursive: true }); + + // Spawn 3 long-sleeping node child processes to use as live PIDs. + const sleepers = [0, 1, 2].map(() => + spawn(process.execPath, ['-e', 'setTimeout(()=>{},60000)'], { + stdio: 'ignore', + detached: false, + }), + ); + const writtenLocks: string[] = []; + try { + for (let i = 0; i < sleepers.length; i++) { + // Slot files are named slot-N.lock; content is the owning PID. + const p = path.join(lockDir, `slot-${i}.lock`); + fs.writeFileSync(p, String(sleepers[i].pid)); + writtenLocks.push(p); + } + + const result = runHook(hookPath, { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }); + + expect(result.stdout.trim()).toBe(''); + // Sentinel slot files survive; the hook bailed before claiming any of them. + for (let i = 0; i < sleepers.length; i++) { + const p = path.join(lockDir, `slot-${i}.lock`); + expect(fs.existsSync(p)).toBe(true); + // Owner unchanged. + expect(fs.readFileSync(p, 'utf-8').trim()).toBe(String(sleepers[i].pid)); + } + } finally { + for (const child of sleepers) { + try { + child.kill(); + } catch { + /* ignore */ + } + } + for (const p of writtenLocks) { + try { + fs.unlinkSync(p); + } catch { + /* ignore */ + } + } + try { + fs.rmdirSync(lockDir); + } catch { + /* ignore */ + } + } + }); + + it(`${label}: hook reclaims a slot held by a dead pid`, () => { + const lockDir = path.join(gitNexusDir, '.hook-locks'); + fs.mkdirSync(lockDir, { recursive: true }); + // PID 1 exists on every POSIX system (init); on Windows process.kill(1,0) + // throws. Use a definitely-dead PID instead: a very large number unlikely + // to be assigned. + const deadPid = 2_147_483_640; + const stalePath = path.join(lockDir, 'slot-0.lock'); + try { + fs.writeFileSync(stalePath, String(deadPid)); + expect(fs.readFileSync(stalePath, 'utf-8').trim()).toBe(String(deadPid)); + + runHook(hookPath, { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }); + + // The hook reclaimed and then released slot-0 — either the file is + // gone (released) or its content is something other than the dead PID. + if (fs.existsSync(stalePath)) { + expect(fs.readFileSync(stalePath, 'utf-8').trim()).not.toBe(String(deadPid)); + } + } finally { + try { + fs.unlinkSync(stalePath); + } catch { + /* already pruned */ + } + try { + fs.rmdirSync(lockDir); + } catch { + /* ignore */ + } + } + }); + + it(`${label}: hook does not exceed MAX_INFLIGHT under simultaneous bursts (hard cap)`, async () => { + // Spawn many hook processes concurrently and assert that at most + // MAX_INFLIGHT (3) slot files end up populated by live pids. The + // O_CREAT|O_EXCL slot scheme makes this a hard cap, not the soft cap + // that the count-then-claim approach gives. + const { spawn } = await import('child_process'); + const lockDir = path.join(gitNexusDir, '.hook-locks'); + // Clean any leftover slot files. + try { + for (const f of fs.readdirSync(lockDir)) fs.unlinkSync(path.join(lockDir, f)); + } catch { + /* dir may not exist yet */ + } + fs.mkdirSync(lockDir, { recursive: true }); + + // We use child workers that just claim a slot via the same algorithm + // and then sleep, so we can observe the on-disk state under contention + // without spawning the real gitnexus augment CLI. + const claimerScript = ` + const fs = require('fs'); const path = require('path'); + const lockDir = ${JSON.stringify(lockDir)}; + const MAX = 3; + const STALE = 30000; + const myPid = String(process.pid); + function tryAcquire() { + for (let slot = 0; slot < MAX; slot++) { + const p = path.join(lockDir, 'slot-' + slot + '.lock'); + for (let a = 0; a < 2; a++) { + try { fs.writeFileSync(p, myPid, { flag: 'wx' }); return p; } + catch { + let stat; try { stat = fs.statSync(p); } catch { continue; } + let live = false; + try { + const s = fs.readFileSync(p, 'utf-8').trim(); + if (s === '') live = true; + else { const o = Number.parseInt(s, 10); + if (Number.isFinite(o) && o > 0) { try { process.kill(o, 0); live = true; } catch {} } + } + } catch {} + if (live && Date.now() - stat.mtimeMs > STALE) live = false; + if (live) break; + try { fs.unlinkSync(p); } catch {} + } + } + } + return null; + } + const claimed = tryAcquire(); + if (claimed) { + process.stdout.write('CLAIMED:' + claimed + '\\n'); + setTimeout(() => {}, 5000); + } else { + process.stdout.write('SKIPPED\\n'); + } + `; + + const N = 10; + const claimers = Array.from({ length: N }, () => + spawn(process.execPath, ['-e', claimerScript], { + stdio: ['ignore', 'pipe', 'ignore'], + detached: false, + }), + ); + try { + // Wait until every claimer has printed its decision. + const decisions = await Promise.all( + claimers.map( + (c) => + new Promise((resolve) => { + let buf = ''; + c.stdout!.on('data', (d) => { + buf += d.toString(); + if (buf.includes('\n')) resolve(buf.split('\n')[0]); + }); + c.on('exit', () => resolve(buf.split('\n')[0] || 'EXIT')); + }), + ), + ); + const claimedCount = decisions.filter((d) => d.startsWith('CLAIMED:')).length; + const skippedCount = decisions.filter((d) => d === 'SKIPPED').length; + + // HARD CAP: never more than 3 winners, regardless of how many bursts. + expect(claimedCount).toBeLessThanOrEqual(3); + // And the remainder must have all explicitly skipped. + expect(claimedCount + skippedCount).toBe(N); + + // On-disk state matches. + const liveSlots = fs + .readdirSync(lockDir) + .filter((f) => /^slot-\d+\.lock$/.test(f)) + .filter((f) => { + try { + const o = Number.parseInt(fs.readFileSync(path.join(lockDir, f), 'utf-8').trim(), 10); + return Number.isFinite(o) && o > 0; + } catch { + return false; + } + }); + expect(liveSlots.length).toBeLessThanOrEqual(3); + } finally { + for (const c of claimers) { + try { + c.kill(); + } catch { + /* ignore */ + } + } + try { + for (const f of fs.readdirSync(lockDir)) fs.unlinkSync(path.join(lockDir, f)); + } catch { + /* ignore */ + } + try { + fs.rmdirSync(lockDir); + } catch { + /* ignore */ + } + } + }); + } +}); + +// ─── Source: cross-platform DB lock probe module (#1493) ───────────── + +describe('Cross-platform DB lock probe (source)', () => { + for (const [label, hookPath, probePath] of [ + ['CJS', CJS_HOOK, CJS_HOOK_DB_PROBE], + ['Plugin', PLUGIN_HOOK, PLUGIN_HOOK_DB_PROBE], + ] as const) { + it(`${label} probe file exists`, () => { + expect(fs.existsSync(probePath)).toBe(true); + }); + + it(`${label} hook requires hook-db-lock-probe.cjs`, () => { + const source = fs.readFileSync(hookPath, 'utf-8'); + expect(source).toContain("require('./hook-db-lock-probe.cjs')"); + }); + + it(`${label} probe covers Linux /proc, Unix lsof, and Windows Restart Manager`, () => { + const p = fs.readFileSync(probePath, 'utf-8'); + expect(p).toContain('win-rm-list-json.ps1'); + expect(p).toContain('/proc/'); + expect(p).toContain('linuxProcScanFindGitNexusServer'); + expect(p).toContain('unixLsofPsFindGitNexusServer'); + expect(p).toContain('hasGitNexusServerOwnerWindows'); + expect(p).toContain('GITNEXUS_HOOK_LSOF_PATH'); + expect(p).toContain('GITNEXUS_HOOK_POWERSHELL_PATH'); + expect(p).toContain('GITNEXUS_HOOK_LINUX_PROC_BUDGET_MS'); + }); + } +}); + +// ─── Integration: PreToolUse augmentation filtering (#1492) ───────── + +describe('PreToolUse augmentation filtering (integration)', () => { + for (const [label, hookPath] of [ + ['CJS', CJS_HOOK], + ['Plugin', PLUGIN_HOOK], + ] as const) { + it(`${label}: emits valid GitNexus augmentation context`, () => { + const binDir = createHookToolDir({ + gitnexusStderr: '[GitNexus] 1 related symbol found:\n\nvalidateUser (src/auth.ts)\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + + const output = parseHookOutput(result.stdout); + expect(output).not.toBeNull(); + expect(output!.hookEventName).toBe('PreToolUse'); + expect(output!.additionalContext).toContain('[GitNexus] 1 related symbol found'); + } finally { + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: suppresses LadybugDB lock warnings from augment stderr`, () => { + const markerPath = path.join(os.tmpdir(), 'gn-hook-lockwarn-' + process.pid + '-' + label); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + gitnexusStderr: + 'GitNexus: FTS extension load failed: IO exception: Could not set lock on file : /tmp/repo/.gitnexus/lbug\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + + expect(result.stdout.trim()).toBe(''); + expect(fs.existsSync(markerPath)).toBe(true); + + // Finding #18: when GITNEXUS_DEBUG=1 is set, the discarded prefix is + // recoverable on the hook's stderr (not silently dropped). + const debugResult = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: { ...hookEnv(binDir), GITNEXUS_DEBUG: '1' } }, + ); + expect(debugResult.stderr).toContain('augment stderr discarded prefix'); + expect(debugResult.stderr).toContain('Could not set lock on file'); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it.skipIf(process.platform === 'win32')( + `${label}: skips augment when a GitNexus MCP process owns the repo DB`, + () => { + const markerPath = path.join(os.tmpdir(), `gitnexus-hook-called-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + lsofOutput: '12345\n', + psOutput: 'node /tmp/node_modules/.bin/gitnexus mcp\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + expect(result.stderr).toContain('[GitNexus] augment skipped'); + expect(fs.existsSync(markerPath)).toBe(false); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }, + ); + } +}); + +describe.skipIf(process.platform === 'win32')( + 'Ladybug DB owner guard — production-shaped ps + failure modes (#1493)', + () => { + for (const [label, hookPath] of [ + ['CJS', CJS_HOOK], + ['Plugin', PLUGIN_HOOK], + ] as const) { + it(`${label}: skips augment for real node_modules/gitnexus ps line (npx child)`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-prodps-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + lsofOutput: '99901\n', + psOutput: 'node /tmp/node_modules/gitnexus/dist/cli/index.js mcp\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + expect(result.stderr).toContain('[GitNexus] augment skipped'); + expect(fs.existsSync(markerPath)).toBe(false); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: npx parent command line is NOT treated as GitNexus server owner`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-npx-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + gitnexusStderr: '[GitNexus] 1 related symbol found:\n\nvalidateUser (src/auth.ts)\n', + lsofOutput: '99902\n', + psOutput: 'npx -y gitnexus@latest mcp\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + const output = parseHookOutput(result.stdout); + expect(output).not.toBeNull(); + expect(fs.existsSync(markerPath)).toBe(true); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: skips augment for gitnexus serve child`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-serve-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + lsofOutput: '99903\n', + psOutput: 'node /repo/node_modules/gitnexus/dist/cli/index.js serve\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + expect(result.stderr).toContain('[GitNexus] augment skipped'); + expect(fs.existsSync(markerPath)).toBe(false); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: ENOENT lsof → augment still runs (fail-open)`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-enoent-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + gitnexusStderr: '[GitNexus] 1 related symbol found:\n\nvalidateUser (src/auth.ts)\n', + lsofOutput: '', + psOutput: '', + }); + try { + const env = { + ...hookEnv(binDir), + GITNEXUS_HOOK_LSOF_PATH: path.join(binDir, '__missing_lsof__'), + }; + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env }, + ); + const output = parseHookOutput(result.stdout); + expect(output).not.toBeNull(); + expect(fs.existsSync(markerPath)).toBe(true); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: ETIMEDOUT lsof → augment skipped (fail-closed)`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-etime-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + lsofSleepMs: 5000, + psOutput: '', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + expect(result.stderr).toContain('[GitNexus] augment skipped'); + expect(fs.existsSync(markerPath)).toBe(false); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: non-GitNexus ps line → augment runs`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-other-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + gitnexusStderr: '[GitNexus] 1 related symbol found:\n\nvalidateUser (src/auth.ts)\n', + lsofOutput: '99904\n', + psOutput: '/usr/bin/bash -l\n', + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + const output = parseHookOutput(result.stdout); + expect(output).not.toBeNull(); + expect(fs.existsSync(markerPath)).toBe(true); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: multiple PIDs — skip if any ps line is GitNexus MCP`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-multi-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + gitnexusStderr: '[GitNexus] 1 related symbol found:\n\nvalidateUser (src/auth.ts)\n', + lsofOutputLines: ['111', '222'], + psOutputByPid: { + '111': 'vim /tmp/x\n', + '222': 'node /x/node_modules/gitnexus/dist/cli/index.js mcp\n', + }, + }); + try { + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env: hookEnv(binDir) }, + ); + expect(result.stdout.trim()).toBe(''); + expect(result.status).toBe(0); + expect(result.stderr).toContain('[GitNexus] augment skipped'); + expect(fs.existsSync(markerPath)).toBe(false); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + + it(`${label}: ps ENOENT → augment runs (ignore that PID)`, () => { + const markerPath = path.join(os.tmpdir(), `gn-hook-pseno-${process.pid}-${label}`); + const lbugPath = path.join(gitNexusDir, 'lbug'); + fs.writeFileSync(lbugPath, ''); + fs.rmSync(markerPath, { force: true }); + const binDir = createHookToolDir({ + gitnexusMarkerPath: markerPath, + gitnexusStderr: '[GitNexus] 1 related symbol found:\n\nvalidateUser (src/auth.ts)\n', + lsofOutput: '99905\n', + psOutput: '', + }); + try { + const env = { + ...hookEnv(binDir), + GITNEXUS_HOOK_PS_PATH: path.join(binDir, '__missing_ps__'), + }; + const result = runHook( + hookPath, + { + hook_event_name: 'PreToolUse', + tool_name: 'Grep', + tool_input: { pattern: 'validateUser' }, + cwd: tmpDir, + }, + undefined, + { env }, + ); + const output = parseHookOutput(result.stdout); + expect(output).not.toBeNull(); + expect(fs.existsSync(markerPath)).toBe(true); + } finally { + fs.rmSync(markerPath, { force: true }); + fs.rmSync(binDir, { recursive: true, force: true }); + } + }); + } + }, +); + // ─── Integration: PostToolUse staleness detection ─────────────────── describe('PostToolUse staleness detection (integration)', () => { diff --git a/gitnexus/test/unit/http-embedder.test.ts b/gitnexus/test/unit/http-embedder.test.ts index 0dea77758..4ac683095 100644 --- a/gitnexus/test/unit/http-embedder.test.ts +++ b/gitnexus/test/unit/http-embedder.test.ts @@ -96,6 +96,73 @@ describe('HTTP embedding backend', () => { expect(result.length).toBe(384); }); + it('omits dimensions from request body when GITNEXUS_EMBEDDING_DIMS is unset', async () => { + process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; + process.env.GITNEXUS_EMBEDDING_MODEL = 'test-model'; + // GITNEXUS_EMBEDDING_DIMS intentionally unset + + vi.stubGlobal( + 'fetch', + vi.fn().mockResolvedValue({ + ok: true, + json: async () => ({ data: [{ embedding: mockVec }] }), + }), + ); + + const { embedText } = await import('../../src/core/embeddings/embedder.js'); + await embedText('test text'); + + const body = JSON.parse((fetch as any).mock.calls[0][1].body); + // Backends that reject unknown fields must see the pre-existing + // request shape. The field must be absent, not `undefined`. + expect('dimensions' in body).toBe(false); + }); + + it('forwards GITNEXUS_EMBEDDING_DIMS as dimensions in request body', async () => { + process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; + process.env.GITNEXUS_EMBEDDING_MODEL = 'text-embedding-3-large'; + process.env.GITNEXUS_EMBEDDING_DIMS = '1024'; + + const vec1024 = Array.from({ length: 1024 }, (_, i) => i / 1024); + vi.stubGlobal( + 'fetch', + vi.fn().mockResolvedValue({ + ok: true, + json: async () => ({ data: [{ embedding: vec1024 }] }), + }), + ); + + const { embedText } = await import('../../src/core/embeddings/embedder.js'); + const result = await embedText('test text'); + + const body = JSON.parse((fetch as any).mock.calls[0][1].body); + expect(body.dimensions).toBe(1024); + expect(body.model).toBe('text-embedding-3-large'); + expect(result.length).toBe(1024); + }); + + it('forwards dimensions on the single-query path', async () => { + process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; + process.env.GITNEXUS_EMBEDDING_MODEL = 'text-embedding-3-large'; + process.env.GITNEXUS_EMBEDDING_DIMS = '512'; + + const vec512 = Array.from({ length: 512 }, (_, i) => i / 512); + vi.stubGlobal( + 'fetch', + vi.fn().mockResolvedValue({ + ok: true, + json: async () => ({ data: [{ embedding: vec512 }] }), + }), + ); + + const mod = await import('../../src/mcp/core/embedder.js'); + const result = await mod.embedQuery('query text'); + + const body = JSON.parse((fetch as any).mock.calls[0][1].body); + expect(body.dimensions).toBe(512); + expect(result.length).toBe(512); + }); + it('retries on server error', async () => { process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; process.env.GITNEXUS_EMBEDDING_MODEL = 'test-model'; @@ -191,6 +258,51 @@ describe('HTTP embedding backend', () => { expect(results).toHaveLength(70); }); + it('forwards dimensions in every batch when splitting large inputs', async () => { + process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; + process.env.GITNEXUS_EMBEDDING_MODEL = 'test-model'; + process.env.GITNEXUS_EMBEDDING_DIMS = '512'; + + const vec512 = Array.from({ length: 512 }, (_, i) => i / 512); + const makeResp = (n: number) => ({ + ok: true, + json: async () => ({ data: Array.from({ length: n }, () => ({ embedding: vec512 })) }), + }); + vi.stubGlobal( + 'fetch', + vi.fn().mockResolvedValueOnce(makeResp(64)).mockResolvedValueOnce(makeResp(6)), + ); + + const { embedBatch } = await import('../../src/core/embeddings/embedder.js'); + const results = await embedBatch(Array.from({ length: 70 }, (_, i) => `text ${i}`)); + + expect(fetch).toHaveBeenCalledTimes(2); + expect(results).toHaveLength(70); + + // Verify dimensions is sent in BOTH batch requests + const body0 = JSON.parse((fetch as any).mock.calls[0][1].body); + const body1 = JSON.parse((fetch as any).mock.calls[1][1].body); + expect(body0.dimensions).toBe(512); + expect(body1.dimensions).toBe(512); + }); + + it('rejects non-numeric GITNEXUS_EMBEDDING_DIMS values', async () => { + process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; + process.env.GITNEXUS_EMBEDDING_MODEL = 'test-model'; + process.env.GITNEXUS_EMBEDDING_DIMS = '1024abc'; + + vi.stubGlobal( + 'fetch', + vi.fn().mockResolvedValue({ + ok: true, + json: async () => ({ data: [{ embedding: mockVec }] }), + }), + ); + + const { embedText } = await import('../../src/core/embeddings/embedder.js'); + await expect(embedText('test')).rejects.toThrow('must be a positive integer'); + }); + it('rejects initEmbedder when using HTTP backend', async () => { process.env.GITNEXUS_EMBEDDING_URL = 'http://test:8080/v1'; process.env.GITNEXUS_EMBEDDING_MODEL = 'test-model'; diff --git a/gitnexus/test/unit/hybrid-search.test.ts b/gitnexus/test/unit/hybrid-search.test.ts index ee2a4499b..813f78aa7 100644 --- a/gitnexus/test/unit/hybrid-search.test.ts +++ b/gitnexus/test/unit/hybrid-search.test.ts @@ -1,5 +1,5 @@ /** - * P1 Unit Tests: Hybrid Search (mergeWithRRF) + * P1 Unit Tests: Hybrid Search (mergeWithRRF + hybridSearch) * * Tests: mergeWithRRF from hybrid-search.ts * - BM25-only merge @@ -7,12 +7,20 @@ * - Combined ranking * - Limit parameter * - Empty inputs + * - Undefined/null inputs (#1489) + * + * Tests: hybridSearch fallback when FTS unavailable (#1489) */ -import { describe, it, expect } from 'vitest'; -import { mergeWithRRF } from '../../src/core/search/hybrid-search.js'; +import { describe, it, expect, vi } from 'vitest'; +import { mergeWithRRF, hybridSearch } from '../../src/core/search/hybrid-search.js'; import type { BM25SearchResult } from '../../src/core/search/bm25-index.js'; import type { SemanticSearchResult } from '../../src/core/embeddings/types.js'; +vi.mock('../../src/core/search/bm25-index.js', async (importOriginal) => { + const actual = (await importOriginal()) as any; + return { ...actual, searchFTSFromLbug: vi.fn() }; +}); + let bm25Rank = 0; function makeBM25(filePath: string, score: number): BM25SearchResult { return { filePath, score, rank: ++bm25Rank }; @@ -123,4 +131,72 @@ describe('mergeWithRRF', () => { expect(result[0].bm25Score).toBe(15); expect(result[0].semanticScore).toBeCloseTo(0.7); // 1 - distance }); + + // Regression: #1489 — bm25Results is not iterable when FTS unavailable + it('does not crash when bm25Results is undefined (#1489)', () => { + const semantic: SemanticSearchResult[] = [makeSemantic('src/a.ts', 0.1)]; + // Force undefined to simulate the crash path where FTS returns unexpected shape + const result = mergeWithRRF(undefined as any, semantic); + expect(result).toHaveLength(1); + expect(result[0].filePath).toBe('src/a.ts'); + expect(result[0].sources).toEqual(['semantic']); + }); + + it('does not crash when semanticResults is undefined (#1489)', () => { + const bm25: BM25SearchResult[] = [makeBM25('src/a.ts', 10)]; + const result = mergeWithRRF(bm25, undefined as any); + expect(result).toHaveLength(1); + expect(result[0].filePath).toBe('src/a.ts'); + expect(result[0].sources).toEqual(['bm25']); + }); + + it('does not crash when both inputs are undefined (#1489)', () => { + const result = mergeWithRRF(undefined as any, undefined as any); + expect(result).toHaveLength(0); + }); +}); + +// Regression: #1489 — hybridSearch must not crash when FTS is unavailable +describe('hybridSearch — FTS failure fallback (#1489)', () => { + it('falls back to semantic-only when searchFTSFromLbug throws', async () => { + const { searchFTSFromLbug } = await import('../../src/core/search/bm25-index.js'); + vi.mocked(searchFTSFromLbug).mockRejectedValueOnce(new Error('bm25Results is not iterable')); + + const mockExecuteQuery = vi.fn().mockResolvedValue([]); + const mockSemanticSearch = vi + .fn() + .mockResolvedValue([makeSemantic('src/semantic-hit.ts', 0.15)]); + + const results = await hybridSearch('test query', 10, mockExecuteQuery, mockSemanticSearch); + expect(results).toHaveLength(1); + expect(results[0].filePath).toBe('src/semantic-hit.ts'); + expect(results[0].sources).toEqual(['semantic']); + }); + + it('returns empty when both FTS and semantic return nothing', async () => { + const { searchFTSFromLbug } = await import('../../src/core/search/bm25-index.js'); + vi.mocked(searchFTSFromLbug).mockRejectedValueOnce(new Error('FTS unavailable')); + + const mockExecuteQuery = vi.fn().mockResolvedValue([]); + const mockSemanticSearch = vi.fn().mockResolvedValue([]); + + const results = await hybridSearch('test query', 10, mockExecuteQuery, mockSemanticSearch); + expect(results).toHaveLength(0); + }); + + it('works normally when FTS succeeds', async () => { + const { searchFTSFromLbug } = await import('../../src/core/search/bm25-index.js'); + vi.mocked(searchFTSFromLbug).mockResolvedValueOnce({ + results: [{ filePath: 'src/fts-hit.ts', score: 5, rank: 1 }], + ftsAvailable: true, + }); + + const mockExecuteQuery = vi.fn().mockResolvedValue([]); + const mockSemanticSearch = vi.fn().mockResolvedValue([]); + + const results = await hybridSearch('test query', 10, mockExecuteQuery, mockSemanticSearch); + expect(results).toHaveLength(1); + expect(results[0].filePath).toBe('src/fts-hit.ts'); + expect(results[0].sources).toEqual(['bm25']); + }); }); diff --git a/gitnexus/test/unit/incremental-file-hash.test.ts b/gitnexus/test/unit/incremental-file-hash.test.ts new file mode 100644 index 000000000..0f59dfb09 --- /dev/null +++ b/gitnexus/test/unit/incremental-file-hash.test.ts @@ -0,0 +1,124 @@ +import { describe, it, expect } from 'vitest'; +import { mkdtemp, writeFile, rm } from 'fs/promises'; +import { tmpdir } from 'os'; +import path from 'path'; +import { computeFileHash, computeFileHashes, diffFileHashes } from '../../src/storage/file-hash.js'; + +describe('diffFileHashes', () => { + it('classifies files into changed / added / deleted / toWrite', () => { + const stored = { a: 'h-a', b: 'h-b', c: 'h-c' }; + const current = new Map([ + ['a', 'h-a'], // unchanged + ['b', 'h-b-NEW'], // changed + ['d', 'h-d'], // added + // 'c' is gone → deleted + ]); + const diff = diffFileHashes(current, stored); + expect(diff.changed).toEqual(['b']); + expect(diff.added).toEqual(['d']); + expect(diff.deleted).toEqual(['c']); + // toWrite is the union of changed ∪ added (rows to be (re)written) + expect(diff.toWrite.sort()).toEqual(['b', 'd']); + }); + + it('treats no stored map as "everything is added"', () => { + const current = new Map([ + ['x', 'h1'], + ['y', 'h2'], + ]); + const diff = diffFileHashes(current, undefined); + expect(diff.added.sort()).toEqual(['x', 'y']); + expect(diff.changed).toEqual([]); + expect(diff.deleted).toEqual([]); + expect(diff.toWrite.sort()).toEqual(['x', 'y']); + }); + + it('returns sorted arrays for stable cross-platform comparison', () => { + const stored = { z: 'h', a: 'h', m: 'h' }; + const current = new Map([ + ['z', 'h2'], + ['a', 'h2'], + ['m', 'h2'], + ]); + const diff = diffFileHashes(current, stored); + expect(diff.changed).toEqual(['a', 'm', 'z']); + expect(diff.toWrite).toEqual(['a', 'm', 'z']); + }); + + it('handles empty current map (all stored files become deleted)', () => { + const stored = { a: 'h1', b: 'h2' }; + const diff = diffFileHashes(new Map(), stored); + expect(diff.deleted).toEqual(['a', 'b']); + expect(diff.changed).toEqual([]); + expect(diff.added).toEqual([]); + }); +}); + +describe('computeFileHash', () => { + it('produces a stable SHA-256 hex digest', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-fh-')); + try { + const f = path.join(dir, 'a.txt'); + await writeFile(f, 'hello world\n', 'utf-8'); + const h1 = await computeFileHash(f); + const h2 = await computeFileHash(f); + expect(h1).toBe(h2); + expect(h1).toMatch(/^[a-f0-9]{64}$/); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); + + it('returns null on missing file (caller treats as "no signature")', async () => { + const h = await computeFileHash('/definitely/does/not/exist/here.xyz'); + expect(h).toBeNull(); + }); + + it('different content → different hash', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-fh-')); + try { + const a = path.join(dir, 'a.txt'); + const b = path.join(dir, 'b.txt'); + await writeFile(a, 'hello', 'utf-8'); + await writeFile(b, 'goodbye', 'utf-8'); + const ha = await computeFileHash(a); + const hb = await computeFileHash(b); + expect(ha).not.toBeNull(); + expect(hb).not.toBeNull(); + expect(ha).not.toBe(hb); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); +}); + +describe('computeFileHashes', () => { + it('hashes a small batch of files in parallel', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-fh-')); + try { + await writeFile(path.join(dir, 'one.txt'), 'A', 'utf-8'); + await writeFile(path.join(dir, 'two.txt'), 'B', 'utf-8'); + await writeFile(path.join(dir, 'three.txt'), 'C', 'utf-8'); + const map = await computeFileHashes(dir, ['one.txt', 'two.txt', 'three.txt']); + expect(map.size).toBe(3); + expect(map.get('one.txt')).toMatch(/^[a-f0-9]{64}$/); + // All distinct since contents differ + const hashes = [...map.values()]; + expect(new Set(hashes).size).toBe(3); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); + + it('omits files that fail to read (no entry in result)', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-fh-')); + try { + await writeFile(path.join(dir, 'real.txt'), 'X', 'utf-8'); + const map = await computeFileHashes(dir, ['real.txt', 'phantom.txt']); + expect(map.has('real.txt')).toBe(true); + expect(map.has('phantom.txt')).toBe(false); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); +}); diff --git a/gitnexus/test/unit/incremental-orchestration.test.ts b/gitnexus/test/unit/incremental-orchestration.test.ts new file mode 100644 index 000000000..3d0d244af --- /dev/null +++ b/gitnexus/test/unit/incremental-orchestration.test.ts @@ -0,0 +1,263 @@ +/** + * Integration coverage for the `runFullAnalysis` incremental-orchestration + * wiring (Claude PR-review Finding 2). + * + * These tests exercise the *real runtime path* — they call + * `runFullAnalysis` against a real on-disk git repo backed by a real + * LadybugDB at `/.gitnexus/`, and assert behaviours that pure + * unit tests on `diffFileHashes` / `extractChangedSubgraph` cannot + * catch: + * + * - the `isIncremental` decision (post-pipeline eligibility check) + * - `incrementalInProgress` dirty-flag set-before-mutation and + * clear-on-success + * - the importer-closure expansion (1-hop reached via the writable + * set, transitive reachable via bounded BFS) + * - the "forced full rebuild on dirty-flag-from-prior-crash" path + * + * Each test creates a temporary git repo, runs the analyzer, and asserts + * on the resulting `meta.json` and graph state. Cleanup is best-effort + * (Windows LadybugDB handle release can lag; `cleanupTempDir` retries). + */ + +import { execSync } from 'child_process'; +import { writeFile, readFile, copyFile, mkdir } from 'fs/promises'; +import path from 'path'; +import { fileURLToPath } from 'url'; +import { describe, it, expect } from 'vitest'; +import { + getStoragePaths, + saveMeta, + loadMeta, + INCREMENTAL_SCHEMA_VERSION, + type RepoMeta, +} from '../../src/storage/repo-manager.js'; +import { createTempDir } from '../helpers/test-db.js'; + +const HERE = path.dirname(fileURLToPath(import.meta.url)); +const FIXTURE_SRC = path.resolve(HERE, '..', 'fixtures', 'mini-repo', 'src'); + +/** + * Copy the mini-repo fixture into a fresh git-initialized temp directory. + * Returns the temp handle so the caller owns cleanup. + */ +async function setupMiniRepo(): Promise<{ dbPath: string; cleanup: () => Promise }> { + const tmp = await createTempDir('gitnexus-incr-orch-'); + const dest = path.join(tmp.dbPath, 'src'); + await mkdir(dest, { recursive: true }); + // Copy mini-repo fixture files + const names = [ + 'index.ts', + 'handler.ts', + 'validator.ts', + 'formatter.ts', + 'middleware.ts', + 'logger.ts', + 'db.ts', + ]; + for (const n of names) { + await copyFile(path.join(FIXTURE_SRC, n), path.join(dest, n)); + } + execSync('git init', { cwd: tmp.dbPath, stdio: 'pipe' }); + execSync('git -c user.name=test -c user.email=t@t -c commit.gpgsign=false add -A', { + cwd: tmp.dbPath, + stdio: 'pipe', + }); + execSync('git -c user.name=test -c user.email=t@t -c commit.gpgsign=false commit -q -m initial', { + cwd: tmp.dbPath, + stdio: 'pipe', + }); + return tmp; +} + +describe('runFullAnalysis — incremental orchestration', () => { + it('first run populates fileHashes + schemaVersion and clears incrementalInProgress on success', async () => { + const repo = await setupMiniRepo(); + try { + const { runFullAnalysis } = await import('../../src/core/run-analyze.js'); + await runFullAnalysis(repo.dbPath, { skipAgentsMd: true }, { onProgress: () => {} }); + + const { storagePath } = getStoragePaths(repo.dbPath); + const meta = await loadMeta(storagePath); + expect(meta).not.toBeNull(); + expect(meta!.schemaVersion).toBe(INCREMENTAL_SCHEMA_VERSION); + expect(meta!.fileHashes).toBeDefined(); + expect(Object.keys(meta!.fileHashes ?? {}).length).toBeGreaterThan(0); + // Dirty flag MUST be cleared after a successful run. + expect(meta!.incrementalInProgress).toBeUndefined(); + } finally { + await repo.cleanup(); + } + }, 180_000); + + it('second run on unchanged state takes the alreadyUpToDate fast path', async () => { + const repo = await setupMiniRepo(); + try { + const { runFullAnalysis } = await import('../../src/core/run-analyze.js'); + const first = await runFullAnalysis( + repo.dbPath, + { skipAgentsMd: true }, + { onProgress: () => {} }, + ); + expect(first.alreadyUpToDate).toBeUndefined(); + + const second = await runFullAnalysis( + repo.dbPath, + { skipAgentsMd: true }, + { onProgress: () => {} }, + ); + // lastCommit==HEAD && working tree clean (mod GitNexus output) → + // early-return fast path. + expect(second.alreadyUpToDate).toBe(true); + } finally { + await repo.cleanup(); + } + }, 300_000); + + it('second run after a comment-only edit takes the incremental path, clears the dirty flag, and preserves graph stats exactly', async () => { + const repo = await setupMiniRepo(); + try { + const { runFullAnalysis } = await import('../../src/core/run-analyze.js'); + await runFullAnalysis(repo.dbPath, { skipAgentsMd: true }, { onProgress: () => {} }); + const { storagePath } = getStoragePaths(repo.dbPath); + const firstMeta = await loadMeta(storagePath); + + // Modify a source file with a COMMENT-ONLY edit — by construction + // this changes the content hash (driving the incremental code path) + // without changing any symbol, scope binding, call edge, import, + // or community membership. Therefore every graph-stat invariant + // (files / nodes / edges / communities / processes) MUST be + // bit-identical to the first run. Anything else is a regression. + const target = path.join(repo.dbPath, 'src', 'logger.ts'); + const before = await readFile(target, 'utf-8'); + await writeFile(target, before + '\n// touched by test\n', 'utf-8'); + + const second = await runFullAnalysis( + repo.dbPath, + { skipAgentsMd: true }, + { onProgress: () => {} }, + ); + // The early-return alreadyUpToDate path must NOT fire (the dirty + // tree should kick the run through to incremental writeback). + expect(second.alreadyUpToDate).toBeUndefined(); + + const secondMeta = await loadMeta(storagePath); + expect(secondMeta).not.toBeNull(); + // Dirty flag must be cleared on success. + expect(secondMeta!.incrementalInProgress).toBeUndefined(); + // fileHashes[logger.ts] must have rotated to the new content. + expect(secondMeta!.fileHashes?.['src/logger.ts']).toBeDefined(); + expect(secondMeta!.fileHashes?.['src/logger.ts']).not.toBe( + firstMeta!.fileHashes?.['src/logger.ts'], + ); + // Exact-equality stats invariant. DoD §2.7: avoid bounds-only + // assertions that would mask a regression dropping half the graph. + expect(secondMeta!.stats?.files).toBe(firstMeta!.stats?.files); + expect(secondMeta!.stats?.nodes).toBe(firstMeta!.stats?.nodes); + expect(secondMeta!.stats?.edges).toBe(firstMeta!.stats?.edges); + expect(secondMeta!.stats?.communities).toBe(firstMeta!.stats?.communities); + expect(secondMeta!.stats?.processes).toBe(firstMeta!.stats?.processes); + } finally { + await repo.cleanup(); + } + }, 300_000); + + it('incremental output is byte-equivalent to a full rebuild (incremental ≡ --force on the same repo state)', async () => { + // The central correctness contract of this PR: an incremental run + // and a full rebuild from the same repo state must produce identical + // graph stats. We exercise it end-to-end: + // + // 1. setup mini-repo + run analyze (populates the index) + // 2. edit one source file (comment-only — same graph) + // 3. run incremental analyze → record secondMeta + // 4. run analyze --force from the same state → record forceMeta + // 5. assert every stats invariant is exactly equal. + // + // Steps 3 and 4 share the same on-disk file contents, so any + // divergence is purely an artifact of the writeback strategy. If + // any invariant differs, the PR's load-bearing claim is violated. + const repo = await setupMiniRepo(); + try { + const { runFullAnalysis } = await import('../../src/core/run-analyze.js'); + + // Step 1: initial index. + await runFullAnalysis(repo.dbPath, { skipAgentsMd: true }, { onProgress: () => {} }); + + // Step 2: comment-only edit, same as the test above. + const target = path.join(repo.dbPath, 'src', 'logger.ts'); + const original = await readFile(target, 'utf-8'); + await writeFile(target, original + '\n// equivalence test touch\n', 'utf-8'); + + // Step 3: incremental writeback for the edited file. + const incremental = await runFullAnalysis( + repo.dbPath, + { skipAgentsMd: true }, + { onProgress: () => {} }, + ); + expect(incremental.alreadyUpToDate).toBeUndefined(); + const { storagePath } = getStoragePaths(repo.dbPath); + const secondMeta = await loadMeta(storagePath); + expect(secondMeta).not.toBeNull(); + + // Step 4: force a full rebuild from the SAME on-disk file state. + const forced = await runFullAnalysis( + repo.dbPath, + { skipAgentsMd: true, force: true }, + { onProgress: () => {} }, + ); + expect(forced.alreadyUpToDate).toBeUndefined(); + const forceMeta = await loadMeta(storagePath); + expect(forceMeta).not.toBeNull(); + + // Step 5: exact-equality across every stat. `toEqual` would also + // work but `toBe` per-field makes a failure pinpoint the field. + expect(secondMeta!.stats?.files).toBe(forceMeta!.stats?.files); + expect(secondMeta!.stats?.nodes).toBe(forceMeta!.stats?.nodes); + expect(secondMeta!.stats?.edges).toBe(forceMeta!.stats?.edges); + expect(secondMeta!.stats?.communities).toBe(forceMeta!.stats?.communities); + expect(secondMeta!.stats?.processes).toBe(forceMeta!.stats?.processes); + } finally { + await repo.cleanup(); + } + }, 600_000); + + it('a stale incrementalInProgress flag at startup forces a full rebuild that clears it', async () => { + const repo = await setupMiniRepo(); + try { + const { runFullAnalysis } = await import('../../src/core/run-analyze.js'); + // First run lays down a normal index. + await runFullAnalysis(repo.dbPath, { skipAgentsMd: true }, { onProgress: () => {} }); + + // Manually corrupt meta.json with a stale dirty flag — simulates + // a crashed previous incremental run. + const { storagePath } = getStoragePaths(repo.dbPath); + const meta = await loadMeta(storagePath); + expect(meta).not.toBeNull(); + const tampered: RepoMeta = { + ...meta!, + incrementalInProgress: { + startedAt: Date.now() - 60_000, + toWriteCount: 3, + }, + }; + await saveMeta(storagePath, tampered); + + // Next run must detect the flag, force a full rebuild (which + // overwrites meta), and clear the flag. + const recovered = await runFullAnalysis( + repo.dbPath, + { skipAgentsMd: true }, + { onProgress: () => {} }, + ); + // A full rebuild was taken — the alreadyUpToDate fast path + // explicitly cannot fire because the dirty-flag check rewrote + // `options.force` to true. + expect(recovered.alreadyUpToDate).toBeUndefined(); + + const after = await loadMeta(storagePath); + expect(after!.incrementalInProgress).toBeUndefined(); + } finally { + await repo.cleanup(); + } + }, 300_000); +}); diff --git a/gitnexus/test/unit/incremental-parse-cache.test.ts b/gitnexus/test/unit/incremental-parse-cache.test.ts new file mode 100644 index 000000000..757b9cf3a --- /dev/null +++ b/gitnexus/test/unit/incremental-parse-cache.test.ts @@ -0,0 +1,243 @@ +import { describe, it, expect } from 'vitest'; +import { mkdtemp, rm } from 'fs/promises'; +import { tmpdir } from 'os'; +import path from 'path'; +import { + PARSE_CACHE_VERSION, + computeChunkHash, + fileContentHash, + loadParseCache, + saveParseCache, + pruneCache, + type ParseCache, +} from '../../src/storage/parse-cache.js'; +import type { ParseWorkerResult } from '../../src/core/ingestion/workers/parse-worker.js'; + +const minimalResult = (overrides: Partial = {}): ParseWorkerResult => ({ + nodes: [], + relationships: [], + symbols: [], + imports: [], + calls: [], + assignments: [], + heritage: [], + routes: [], + fetchCalls: [], + decoratorRoutes: [], + toolDefs: [], + ormQueries: [], + constructorBindings: [], + fileScopeBindings: [], + parsedFiles: [], + skippedLanguages: {}, + fileCount: 0, + ...overrides, +}); + +describe('computeChunkHash', () => { + it('produces a stable hex hash for a fixed set of (filePath, contentHash) entries', () => { + const entries = [ + { filePath: 'a.ts', contentHash: 'h-a' }, + { filePath: 'b.ts', contentHash: 'h-b' }, + { filePath: 'c.ts', contentHash: 'h-c' }, + ]; + const h1 = computeChunkHash(entries); + const h2 = computeChunkHash(entries); + expect(h1).toBe(h2); + expect(h1).toMatch(/^[a-f0-9]{64}$/); + }); + + it('is order-independent (same files in different order → same hash)', () => { + const order1 = [ + { filePath: 'a.ts', contentHash: 'h-a' }, + { filePath: 'b.ts', contentHash: 'h-b' }, + ]; + const order2 = [ + { filePath: 'b.ts', contentHash: 'h-b' }, + { filePath: 'a.ts', contentHash: 'h-a' }, + ]; + expect(computeChunkHash(order1)).toBe(computeChunkHash(order2)); + }); + + it('changes when any file content changes', () => { + const before = [ + { filePath: 'a.ts', contentHash: 'h-a' }, + { filePath: 'b.ts', contentHash: 'h-b' }, + ]; + const after = [ + { filePath: 'a.ts', contentHash: 'h-a' }, + { filePath: 'b.ts', contentHash: 'h-b-NEW' }, // b.ts content changed + ]; + expect(computeChunkHash(before)).not.toBe(computeChunkHash(after)); + }); + + it('changes when chunk membership changes (file added or removed)', () => { + const small = [ + { filePath: 'a.ts', contentHash: 'h-a' }, + { filePath: 'b.ts', contentHash: 'h-b' }, + ]; + const bigger = [...small, { filePath: 'c.ts', contentHash: 'h-c' }]; + expect(computeChunkHash(small)).not.toBe(computeChunkHash(bigger)); + }); +}); + +describe('fileContentHash', () => { + it('hashes a string deterministically', () => { + expect(fileContentHash('hello')).toBe(fileContentHash('hello')); + expect(fileContentHash('hello')).not.toBe(fileContentHash('hello!')); + expect(fileContentHash('hello')).toMatch(/^[a-f0-9]{64}$/); + }); + + it('handles Buffer input identical to its string form', () => { + const s = 'sentinel'; + expect(fileContentHash(Buffer.from(s))).toBe(fileContentHash(s)); + }); +}); + +describe('PARSE_CACHE_VERSION', () => { + it('embeds the gitnexus package version (so upgrades invalidate the cache)', () => { + // Looks like "1+1.6.4" — schema bump prefix + actual gitnexus version + expect(PARSE_CACHE_VERSION).toMatch(/^\d+\+\d+\.\d+\.\d+/); + }); +}); + +describe('pruneCache', () => { + it('drops entries whose hashes are not in the used-set', () => { + const cache: ParseCache = { + version: PARSE_CACHE_VERSION, + entries: new Map([ + ['hash-A', [minimalResult()]], + ['hash-B', [minimalResult()]], + ['hash-C', [minimalResult()]], + ]), + usedKeys: new Set(['hash-A']), + }; + const removed = pruneCache(cache, cache.usedKeys); + expect(removed).toBe(2); + expect([...cache.entries.keys()].sort()).toEqual(['hash-A']); + }); + + it('returns 0 when every entry is in use', () => { + const cache: ParseCache = { + version: PARSE_CACHE_VERSION, + entries: new Map([ + ['hash-A', [minimalResult()]], + ['hash-B', [minimalResult()]], + ]), + usedKeys: new Set(['hash-A', 'hash-B']), + }; + expect(pruneCache(cache, cache.usedKeys)).toBe(0); + expect(cache.entries.size).toBe(2); + }); +}); + +describe('loadParseCache / saveParseCache (round-trip)', () => { + it('round-trips an empty cache', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-')); + try { + const cache: ParseCache = { + version: PARSE_CACHE_VERSION, + entries: new Map(), + usedKeys: new Set(), + }; + await saveParseCache(dir, cache); + const loaded = await loadParseCache(dir); + expect(loaded.version).toBe(PARSE_CACHE_VERSION); + expect(loaded.entries.size).toBe(0); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); + + it('returns an empty cache when the file is missing', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-')); + try { + const loaded = await loadParseCache(dir); + expect(loaded.entries.size).toBe(0); + expect(loaded.usedKeys.size).toBe(0); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); + + it('returns an empty cache on version mismatch (next-run regen)', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-')); + try { + // Write a cache file with a different version directly + const fs = await import('fs/promises'); + await fs.writeFile( + path.join(dir, 'parse-cache.json'), + JSON.stringify({ version: 'foreign-99', entries: { h: [] } }), + 'utf-8', + ); + const loaded = await loadParseCache(dir); + expect(loaded.entries.size).toBe(0); // mismatch → empty + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); + + it('returns an empty cache on corrupt JSON', async () => { + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-')); + try { + const fs = await import('fs/promises'); + await fs.writeFile(path.join(dir, 'parse-cache.json'), '{not-json', 'utf-8'); + const loaded = await loadParseCache(dir); + expect(loaded.entries.size).toBe(0); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); + + it('round-trips Map and Set values through the JSON replacer/reviver', async () => { + // ParsedFile.scopes[*].typeBindings is a ReadonlyMap. + // Without the replacer/reviver pair, JSON.stringify collapses Maps to + // {} and downstream code that does .get() / iterates entries crashes + // with "is not iterable". This test pins the round-trip behaviour. + const dir = await mkdtemp(path.join(tmpdir(), 'gnx-pc-')); + try { + const innerMap = new Map([ + ['k1', 'v1'], + ['k2', 'v2'], + ]); + const innerSet = new Set(['s1', 's2']); + // Stash the live Map/Set inside a synthetic ParseWorkerResult — we + // only need the serializer to traverse them. Casting to bypass the + // strict shape isn't a problem here: this test is about JSON + // round-tripping of arbitrary nested Map/Set values, not full + // ParseWorkerResult contents. + const fake = minimalResult({ + parsedFiles: [ + { + filePath: 't.ts', + // Cast through unknown to satisfy the readonly Scope shape + // while still smuggling a live Map into the serializer's + // traversal path — see comment block above. + scopes: [{ id: 's1', typeBindings: innerMap, extras: innerSet }], + } as unknown as ParseWorkerResult['parsedFiles'][number], + ], + }); + + const cache: ParseCache = { + version: PARSE_CACHE_VERSION, + entries: new Map([['chunk-h', [fake]]]), + usedKeys: new Set(['chunk-h']), + }; + await saveParseCache(dir, cache); + const loaded = await loadParseCache(dir); + const reloaded = loaded.entries.get('chunk-h')?.[0]; + expect(reloaded).toBeDefined(); + const scope = (reloaded as ParseWorkerResult).parsedFiles[0]?.scopes[0] as unknown as { + typeBindings?: unknown; + extras?: unknown; + }; + expect(scope.typeBindings).toBeInstanceOf(Map); + expect((scope.typeBindings as Map).get('k1')).toBe('v1'); + expect((scope.typeBindings as Map).size).toBe(2); + expect(scope.extras).toBeInstanceOf(Set); + expect((scope.extras as Set).has('s2')).toBe(true); + } finally { + await rm(dir, { recursive: true, force: true }); + } + }); +}); diff --git a/gitnexus/test/unit/incremental-shadow-candidates.test.ts b/gitnexus/test/unit/incremental-shadow-candidates.test.ts new file mode 100644 index 000000000..207cc0b3c --- /dev/null +++ b/gitnexus/test/unit/incremental-shadow-candidates.test.ts @@ -0,0 +1,75 @@ +import { describe, it, expect } from 'vitest'; +import { shadowCandidatesFor } from '../../src/core/incremental/shadow-candidates.js'; + +describe('shadowCandidatesFor', () => { + it('returns an empty list when the input has no recognised module extension', () => { + expect(shadowCandidatesFor('README.md')).toEqual([]); + expect(shadowCandidatesFor('src/foo')).toEqual([]); + expect(shadowCandidatesFor('binary.so')).toEqual([]); + }); + + it('enumerates same-basename / different-extension candidates (pattern a)', () => { + const out = shadowCandidatesFor('src/foo/bar.ts'); + // All non-.ts module extensions on the same path should appear. + expect(out).toContain('src/foo/bar.tsx'); + expect(out).toContain('src/foo/bar.js'); + expect(out).toContain('src/foo/bar.jsx'); + expect(out).toContain('src/foo/bar.mjs'); + expect(out).toContain('src/foo/bar.cjs'); + expect(out).toContain('src/foo/bar.d.ts'); + // ...but NOT the same .ts (you can't shadow yourself). + expect(out).not.toContain('src/foo/bar.ts'); + }); + + it('enumerates directory-style index candidates (pattern b) for both path separators', () => { + const out = shadowCandidatesFor('src/foo/bar.ts'); + // POSIX form + expect(out).toContain('src/foo/bar/index.ts'); + expect(out).toContain('src/foo/bar/index.tsx'); + expect(out).toContain('src/foo/bar/index.js'); + // Windows form + expect(out).toContain('src/foo/bar\\index.ts'); + expect(out).toContain('src/foo/bar\\index.js'); + }); + + it('enumerates bare-file shadows when the added file is a directory index (pattern c)', () => { + const out = shadowCandidatesFor('src/foo/index.ts'); + // Adding foo/index.ts can shadow foo.{ext} (rare but real — converting + // a single-file module into a directory module). + expect(out).toContain('src/foo.ts'); + expect(out).toContain('src/foo.tsx'); + expect(out).toContain('src/foo.js'); + expect(out).toContain('src/foo.jsx'); + expect(out).toContain('src/foo.mjs'); + expect(out).toContain('src/foo.cjs'); + }); + + it('also handles the Windows-separator form of `foo\\index.ts`', () => { + const out = shadowCandidatesFor('src\\foo\\index.ts'); + expect(out).toContain('src\\foo.ts'); + expect(out).toContain('src\\foo.tsx'); + expect(out).toContain('src\\foo.js'); + }); + + it('handles `.d.ts` as a single extension token (not `.ts`)', () => { + // The longest-match scan in shadowCandidatesFor puts `.d.ts` first. + // For `foo.d.ts`, the noExt portion is "foo" (not "foo.d"), so the + // pattern (a) candidates should be the non-.d.ts module variants. + const out = shadowCandidatesFor('types/foo.d.ts'); + expect(out).toContain('types/foo.ts'); + expect(out).toContain('types/foo.tsx'); + expect(out).toContain('types/foo.js'); + // Not the .d.ts itself. + expect(out).not.toContain('types/foo.d.ts'); + }); + + it('deduplicates output (no candidate appears twice)', () => { + const out = shadowCandidatesFor('src/foo/bar.ts'); + expect(out.length).toBe(new Set(out).size); + }); + + it('never includes the input path itself', () => { + const input = 'src/foo/bar.ts'; + expect(shadowCandidatesFor(input)).not.toContain(input); + }); +}); diff --git a/gitnexus/test/unit/incremental-subgraph-extract.test.ts b/gitnexus/test/unit/incremental-subgraph-extract.test.ts new file mode 100644 index 000000000..dc720fd9e --- /dev/null +++ b/gitnexus/test/unit/incremental-subgraph-extract.test.ts @@ -0,0 +1,169 @@ +/** + * Tests for incremental DB writeback subgraph extraction. + * + * Locks the Finding 1 fix (PR #1479 review): cross-file edges between + * two unchanged files MUST land in the writeback subgraph when a third + * (changed) file alters their cross-file resolution. The pre-fix + * behaviour silently dropped those edges, leaving stale rows in the DB. + * + * These tests use synthetic graphs constructed via createKnowledgeGraph + * directly — they don't run the parser, so they're cheap and stable. + */ + +import { describe, it, expect } from 'vitest'; +import type { GraphNode, GraphRelationship } from 'gitnexus-shared'; +import { createKnowledgeGraph } from '../../src/core/graph/graph.js'; +import { + extractChangedSubgraph, + computeEffectiveWriteSet, +} from '../../src/core/incremental/subgraph-extract.js'; + +const makeFileNode = (id: string, filePath: string, label = 'Function'): GraphNode => + ({ + id, + label, + properties: { filePath, name: id }, + }) as unknown as GraphNode; + +const makeWideNode = (id: string, label: 'Community' | 'Process'): GraphNode => + ({ + id, + label, + properties: {}, + }) as unknown as GraphNode; + +const makeRel = ( + id: string, + sourceId: string, + targetId: string, + type = 'CALLS', +): GraphRelationship => + ({ + id, + sourceId, + targetId, + type, + properties: {}, + }) as unknown as GraphRelationship; + +describe('extractChangedSubgraph', () => { + it('includes nodes whose filePath is in the explicit toWriteSet', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('a', '/repo/a.ts')); + g.addNode(makeFileNode('c', '/repo/c.ts')); + + const sub = extractChangedSubgraph(g, new Set(['/repo/c.ts'])); + + expect(sub.nodes.map((n) => n.id).sort()).toEqual(['c']); + }); + + it('always includes graph-wide nodes (Community, Process)', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('a', '/repo/a.ts')); + g.addNode(makeWideNode('comm-1', 'Community')); + g.addNode(makeWideNode('proc-1', 'Process')); + + const sub = extractChangedSubgraph(g, new Set([])); // no files changed + + expect(sub.nodes.map((n) => n.id).sort()).toEqual(['comm-1', 'proc-1']); + }); + + it('includes a relationship when at least one endpoint is writable', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('a:fn', '/repo/a.ts')); + g.addNode(makeFileNode('c:fn', '/repo/c.ts')); + g.addRelationship(makeRel('e1', 'a:fn', 'c:fn', 'CALLS')); + + // toWriteSet already includes A (the orchestrator expanded it via + // computeEffectiveWriteSet) — both endpoints writable, edge fires. + const sub = extractChangedSubgraph(g, new Set(['/repo/a.ts', '/repo/c.ts'])); + + expect(sub.nodes.map((n) => n.id).sort()).toEqual(['a:fn', 'c:fn']); + expect(sub.relationships.map((r) => r.id)).toEqual(['e1']); + }); + + it('skips a relationship entirely between unchanged files', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('x:fn', '/repo/x.ts')); + g.addNode(makeFileNode('y:fn', '/repo/y.ts')); + g.addRelationship(makeRel('e1', 'x:fn', 'y:fn', 'CALLS')); + + const sub = extractChangedSubgraph(g, new Set(['/repo/c.ts'])); + + expect(sub.nodes).toEqual([]); + expect(sub.relationships).toEqual([]); + }); +}); + +describe('computeEffectiveWriteSet (Finding 1)', () => { + it('barrel re-export — expands the writable set to the consumer file', () => { + // Scenario: file C (a barrel) used to re-export from B; now re-exports + // from D. File A is unchanged byte-wise but its CALLS to foo() now + // resolve to D instead of B. Both A and D are unchanged at the file + // level — but A's edges have shifted. + // + // Pre-fix: toWriteSet={C} → A's nodes not deleted, A→D edge not + // inserted (neither endpoint writable). DB ends up with + // stale A→B and missing A→D. + // Post-fix: the new graph has A→C (A still imports the barrel), so + // A crosses the writable boundary and joins the effective + // write set. deleteNodesForFile(A) then clears the stale + // rows and the subgraph carries the new A→D edge. + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('a:fn', '/repo/a.ts')); + g.addNode(makeFileNode('b:fn', '/repo/b.ts')); + g.addNode(makeFileNode('c:re-export', '/repo/c.ts')); + g.addNode(makeFileNode('d:fn', '/repo/d.ts')); + g.addRelationship(makeRel('e1', 'a:fn', 'c:re-export', 'IMPORTS')); + g.addRelationship(makeRel('e2', 'a:fn', 'd:fn', 'CALLS')); + + const effective = computeEffectiveWriteSet(g, new Set(['/repo/c.ts'])); + + expect([...effective].sort()).toEqual(['/repo/a.ts', '/repo/c.ts']); + }); + + it('picks up edges pointing INTO the changed file (symmetric case)', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('b:fn', '/repo/b.ts')); + g.addNode(makeFileNode('c:fn', '/repo/c.ts')); + g.addRelationship(makeRel('e1', 'b:fn', 'c:fn', 'CALLS')); + + const effective = computeEffectiveWriteSet(g, new Set(['/repo/c.ts'])); + + expect([...effective].sort()).toEqual(['/repo/b.ts', '/repo/c.ts']); + }); + + it('does not expand when no edge crosses the writable boundary', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('x:fn', '/repo/x.ts')); + g.addNode(makeFileNode('y:fn', '/repo/y.ts')); + g.addRelationship(makeRel('e1', 'x:fn', 'y:fn', 'CALLS')); + + const effective = computeEffectiveWriteSet(g, new Set(['/repo/c.ts'])); + + expect([...effective].sort()).toEqual(['/repo/c.ts']); + }); + + it('ignores edges to graph-wide nodes (no filePath)', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('a:fn', '/repo/a.ts')); + g.addNode(makeWideNode('comm-1', 'Community')); + g.addRelationship(makeRel('e1', 'a:fn', 'comm-1', 'BELONGS_TO')); + + const effective = computeEffectiveWriteSet(g, new Set(['/repo/a.ts'])); + + expect([...effective].sort()).toEqual(['/repo/a.ts']); + }); + + it('does not mutate the input set', () => { + const g = createKnowledgeGraph(); + g.addNode(makeFileNode('a:fn', '/repo/a.ts')); + g.addNode(makeFileNode('c:fn', '/repo/c.ts')); + g.addRelationship(makeRel('e1', 'a:fn', 'c:fn', 'CALLS')); + + const input = new Set(['/repo/c.ts']); + computeEffectiveWriteSet(g, input); + + expect([...input]).toEqual(['/repo/c.ts']); + }); +}); diff --git a/gitnexus/test/unit/integrations/circuit-breaker.test.ts b/gitnexus/test/unit/integrations/circuit-breaker.test.ts new file mode 100644 index 000000000..4f08cd4f8 --- /dev/null +++ b/gitnexus/test/unit/integrations/circuit-breaker.test.ts @@ -0,0 +1,395 @@ +import { describe, it, expect, beforeEach } from 'vitest'; +import { CircuitBreaker, CircuitOpenError, getBreaker } from 'gitnexus-shared'; +import { __resetBreakerRegistry__ } from 'gitnexus-shared/test-helpers'; + +describe('CircuitBreaker', () => { + beforeEach(() => __resetBreakerRegistry__()); + + function makeClock(start = 1_700_000_000_000) { + let t = start; + return { + now: () => t, + advance: (ms: number) => { + t += ms; + }, + }; + } + + it('runs through check/recordSuccess in closed state', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 3, cooldownMs: 30_000, now: clock.now }); + expect(b.getState()).toBe('closed'); + b.check(); // does not throw + b.recordSuccess(); + expect(b.getState()).toBe('closed'); + expect(b.getConsecutiveFailures()).toBe(0); + }); + + it('stays closed below the failure threshold', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 3, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + b.recordFailure(); + expect(b.getState()).toBe('closed'); + expect(b.getConsecutiveFailures()).toBe(2); + }); + + it('opens after failureThreshold consecutive failures and check throws', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 3, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + b.recordFailure(); + b.recordFailure(); + expect(b.getState()).toBe('open'); + expect(() => b.check()).toThrow(CircuitOpenError); + }); + + it('CircuitOpenError.retryAfterMs decreases as time advances', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught?.retryAfterMs).toBe(30_000); + + clock.advance(10_000); + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught?.retryAfterMs).toBe(20_000); + }); + + it('transitions Open -> Half-Open after cooldown elapses (via check)', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + expect(b.getState()).toBe('open'); + clock.advance(31_000); + b.check(); // should not throw + // After check, internal state is half-open (next call probes). + expect(b.getConsecutiveFailures()).toBe(1); // unchanged until next outcome + }); + + it('half-open + recordSuccess -> closed and counter reset', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + b.check(); + b.recordSuccess(); + expect(b.getState()).toBe('closed'); + expect(b.getConsecutiveFailures()).toBe(0); + }); + + it('half-open + recordFailure -> open with fresh openedAt', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + const firstOpen = clock.now(); + clock.advance(31_000); // cooldown expired + b.check(); // half-open + b.recordFailure(); + // Open with fresh timestamp — full cooldown again. + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught).toBeInstanceOf(CircuitOpenError); + expect(caught?.retryAfterMs).toBe(30_000); + // Sanity: not the original openedAt (would be negative remaining). + expect(clock.now()).toBeGreaterThan(firstOpen); + }); + + it('recordSuccess from closed state with prior partial failures resets counter', () => { + const b = new CircuitBreaker({ failureThreshold: 5 }); + b.recordFailure(); + b.recordFailure(); + expect(b.getConsecutiveFailures()).toBe(2); + b.recordSuccess(); + expect(b.getConsecutiveFailures()).toBe(0); + expect(b.getState()).toBe('closed'); + }); + + describe('recordNeutral (U1)', () => { + it('is a no-op from closed state with zero prior failures', () => { + const b = new CircuitBreaker({ failureThreshold: 3 }); + b.recordNeutral(); + expect(b.getState()).toBe('closed'); + expect(b.getConsecutiveFailures()).toBe(0); + }); + + it('preserves partial-failure progress (does not reset counter)', () => { + const b = new CircuitBreaker({ failureThreshold: 3 }); + b.recordFailure(); + b.recordFailure(); + b.recordNeutral(); + expect(b.getConsecutiveFailures()).toBe(2); + expect(b.getState()).toBe('closed'); + // Real third failure still trips the breaker — neutrals didn't + // erase the running count toward the threshold. + b.recordFailure(); + expect(b.getState()).toBe('open'); + }); + + it('does not reset openedAt or transition out of open state', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + expect(b.getState()).toBe('open'); + b.recordNeutral(); + // Still open; cooldown clock unchanged. + expect(() => b.check()).toThrow(CircuitOpenError); + }); + + it('leaves half-open state alone (next true outcome decides)', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + b.check(); // half-open + b.recordNeutral(); + // Still half-open; a subsequent recordFailure flips to open. + b.recordFailure(); + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught).toBeInstanceOf(CircuitOpenError); + }); + + it('integration: 2 failures + 5 neutrals + 1 failure → opens on third real failure', () => { + const b = new CircuitBreaker({ failureThreshold: 3 }); + b.recordFailure(); + b.recordFailure(); + for (let i = 0; i < 5; i++) b.recordNeutral(); + expect(b.getConsecutiveFailures()).toBe(2); + expect(b.getState()).toBe('closed'); + b.recordFailure(); + expect(b.getState()).toBe('open'); + }); + }); + + describe('half-open probe permit gate (U1)', () => { + it('admits exactly one caller after cooldown; subsequent check() throws halfOpenRetryAfterMs', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ + failureThreshold: 1, + cooldownMs: 30_000, + halfOpenRetryAfterMs: 1_000, + now: clock.now, + }); + b.recordFailure(); + clock.advance(31_000); + + // Caller A: gets the probe permit. + b.check(); + expect(b.isProbeInFlight()).toBe(true); + + // Caller B: blocked. + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught).toBeInstanceOf(CircuitOpenError); + expect(caught?.retryAfterMs).toBe(1_000); + + // Caller A's recordSuccess clears the breaker. + b.recordSuccess(); + expect(b.isProbeInFlight()).toBe(false); + expect(b.getState()).toBe('closed'); + + // Caller C: succeeds in closed state. + b.check(); + expect(b.getState()).toBe('closed'); + }); + + it('recordFailure on probe re-opens with fresh cooldown (NOT halfOpenRetryAfterMs)', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ + failureThreshold: 1, + cooldownMs: 30_000, + halfOpenRetryAfterMs: 1_000, + now: clock.now, + }); + b.recordFailure(); + clock.advance(31_000); + + b.check(); // A: probe + expect(() => b.check()).toThrow(CircuitOpenError); // B: blocked + + b.recordFailure(); // A reports failure → reopens with fresh openedAt + + // C: should see the fresh cooldown remaining, not the probe-in-flight 1s default. + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught).toBeInstanceOf(CircuitOpenError); + // Fresh openedAt = current clock; cooldown is 30s; retryAfter ≈ 30s. + expect(caught?.retryAfterMs).toBe(30_000); + }); + + it('recordNeutral releases the probe permit but leaves state half-open', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + + b.check(); // A: probe + expect(b.isProbeInFlight()).toBe(true); + + b.recordNeutral(); // A: neutral — permit released, state untouched + expect(b.isProbeInFlight()).toBe(false); + expect(b.getState()).toBe('half-open'); + + // B: succeeds (becomes the new probe), no longer blocked. + b.check(); + expect(b.isProbeInFlight()).toBe(true); + + // B's recordSuccess clears the breaker. + b.recordSuccess(); + expect(b.getState()).toBe('closed'); + }); + + it('three sequential probes via neutrals: A → A.neutral → B → B.neutral → C', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + const initialFailures = b.getConsecutiveFailures(); + clock.advance(31_000); + + for (let i = 0; i < 3; i++) { + b.check(); + b.recordNeutral(); + } + // Counter unchanged; state still half-open; permit released. + expect(b.getConsecutiveFailures()).toBe(initialFailures); + expect(b.getState()).toBe('half-open'); + expect(b.isProbeInFlight()).toBe(false); + }); + + it('5 same-tick sequential callers: exactly one passes, the other 4 throw', () => { + // `check()` is synchronous — these calls execute on a single + // microtask in declaration order. The first mutates probeInFlight + // = true; the next four observe the mutation and throw. This + // tests mutation ordering, not true concurrency (the actual + // interleaved-async-microtask scenario lives in U2). + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + + const results: Array<'pass' | 'throw'> = []; + for (let i = 0; i < 5; i++) { + try { + b.check(); + results.push('pass'); + } catch { + results.push('throw'); + } + } + expect(results.filter((r) => r === 'pass').length).toBe(1); + expect(results.filter((r) => r === 'throw').length).toBe(4); + }); + + it('probe permit consumed; clock advances another full cooldown without record*; still throws', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + + b.check(); // probe permit consumed + clock.advance(60_000); // another full cooldown elapses, no record* + + // Half-open semantics: wait for an outcome, not a timer. The + // permit-consumed state doesn't auto-resolve on time. + expect(() => b.check()).toThrow(CircuitOpenError); + }); + + it('halfOpenRetryAfterMs default is 1000 when not configured', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + b.check(); + + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught?.retryAfterMs).toBe(1_000); + }); + + it('halfOpenRetryAfterMs is configurable for long-running protected ops', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ + failureThreshold: 1, + cooldownMs: 30_000, + halfOpenRetryAfterMs: 10_000, // LLM-streaming-friendly + now: clock.now, + }); + b.recordFailure(); + clock.advance(31_000); + b.check(); + + let caught: CircuitOpenError | null = null; + try { + b.check(); + } catch (err) { + caught = err as CircuitOpenError; + } + expect(caught?.retryAfterMs).toBe(10_000); + }); + + it('getState() is a pure read — does not consume the probe permit', () => { + const clock = makeClock(); + const b = new CircuitBreaker({ failureThreshold: 1, cooldownMs: 30_000, now: clock.now }); + b.recordFailure(); + clock.advance(31_000); + + // Test calls getState() to inspect — must not consume the permit. + expect(b.getState()).toBe('half-open'); + expect(b.isProbeInFlight()).toBe(false); + // First check() still gets the permit. + b.check(); + expect(b.isProbeInFlight()).toBe(true); + }); + }); + + describe('getBreaker registry', () => { + it('returns the same instance for the same key', () => { + const a = getBreaker('endpoint-a'); + const b = getBreaker('endpoint-a'); + expect(a).toBe(b); + }); + + it('returns different instances for different keys', () => { + const a = getBreaker('endpoint-a'); + const b = getBreaker('endpoint-b'); + expect(a).not.toBe(b); + }); + + it('__resetBreakerRegistry__ clears all instances', () => { + const a = getBreaker('endpoint-a'); + __resetBreakerRegistry__(); + const a2 = getBreaker('endpoint-a'); + expect(a2).not.toBe(a); + }); + }); +}); diff --git a/gitnexus/test/unit/integrations/resilient-fetch.test.ts b/gitnexus/test/unit/integrations/resilient-fetch.test.ts new file mode 100644 index 000000000..05299c0ba --- /dev/null +++ b/gitnexus/test/unit/integrations/resilient-fetch.test.ts @@ -0,0 +1,558 @@ +import { describe, it, expect, beforeEach, vi } from 'vitest'; +import { + CircuitBreaker, + CircuitOpenError, + parseRetryAfter, + resilientFetch, + ResilientFetchExhaustedError, + RETRY_AFTER_CAP_MS, +} from 'gitnexus-shared'; +import { __resetBreakerRegistry__, classifyOutcome } from 'gitnexus-shared/test-helpers'; + +describe('parseRetryAfter', () => { + it('parses delta-seconds form', () => { + expect(parseRetryAfter('30')).toBe(30_000); + expect(parseRetryAfter('0')).toBe(0); + }); + it('returns null on negative or non-numeric garbage', () => { + expect(parseRetryAfter(null)).toBeNull(); + expect(parseRetryAfter('')).toBeNull(); + expect(parseRetryAfter(' ')).toBeNull(); + expect(parseRetryAfter('not-a-number')).toBeNull(); + }); + it('parses HTTP-date form against an injected clock', () => { + const now = () => Date.parse('Wed, 21 Oct 2025 07:28:00 GMT'); + expect(parseRetryAfter('Wed, 21 Oct 2025 07:28:30 GMT', now)).toBe(30_000); + }); + it('returns 0 (not negative) on past HTTP-date', () => { + const now = () => Date.parse('Wed, 21 Oct 2025 08:00:00 GMT'); + expect(parseRetryAfter('Wed, 21 Oct 2025 07:28:00 GMT', now)).toBe(0); + }); +}); + +describe('classifyOutcome', () => { + const now = () => 1_700_000_000_000; + + it('classifies 2xx as success', () => { + const resp = new Response(null, { status: 204 }); + const out = classifyOutcome({ kind: 'response', resp }, now); + expect(out.kind).toBe('success'); + }); + it('classifies 5xx as retryable-status without afterMs', () => { + const resp = new Response(null, { status: 503 }); + const out = classifyOutcome({ kind: 'response', resp }, now); + expect(out.kind).toBe('retryable-status'); + if (out.kind === 'retryable-status') expect(out.afterMs).toBeUndefined(); + }); + it('classifies 429 with Retry-After (capped) as retryable-status', () => { + const resp = new Response(null, { status: 429, headers: { 'Retry-After': '99999' } }); + const out = classifyOutcome({ kind: 'response', resp }, now); + expect(out.kind).toBe('retryable-status'); + if (out.kind === 'retryable-status') expect(out.afterMs).toBe(RETRY_AFTER_CAP_MS); + }); + it('classifies 429 from a header-less fetch mock without throwing', () => { + // Tests sometimes stub `fetch` with a plain `{ ok, status }` object + // (e.g. http-embedder.test.ts). Real `Response` always carries + // `Headers`, but the helper must not crash when the stub does not. + // Falls through to exponential-backoff retry like a 429 with no + // Retry-After header. + const resp = { ok: false, status: 429 } as unknown as Response; + const out = classifyOutcome({ kind: 'response', resp }, now); + expect(out.kind).toBe('retryable-status'); + if (out.kind === 'retryable-status') expect(out.afterMs).toBeUndefined(); + }); + it('classifies 401/403/404/422 as terminal-client', () => { + for (const status of [401, 403, 404, 422, 400]) { + const resp = new Response(null, { status }); + const out = classifyOutcome({ kind: 'response', resp }, now); + expect(out.kind).toBe('terminal-client'); + } + }); + it('classifies TimeoutError as terminal-network', () => { + const err = new DOMException('aborted', 'TimeoutError'); + const out = classifyOutcome({ kind: 'error', err }, now); + expect(out.kind).toBe('terminal-network'); + }); + it('classifies generic network throw as retryable-network', () => { + const err = new TypeError('fetch failed'); + const out = classifyOutcome({ kind: 'error', err }, now); + expect(out.kind).toBe('retryable-network'); + }); +}); + +describe('resilientFetch', () => { + const URL_STR = 'https://example.test/api/dispatch'; + + beforeEach(() => __resetBreakerRegistry__()); + + function jsonResp(status: number, headers?: Record): Response { + return new Response(null, { status, headers }); + } + + function makeBreaker(opts: Partial[0]> = {}) { + let t = 1_700_000_000_000; + const breaker = new CircuitBreaker({ + failureThreshold: 3, + cooldownMs: 30_000, + key: 'test', + now: () => t, + ...opts, + }); + return { breaker, advance: (ms: number) => (t += ms) }; + } + + it('204 returns immediately, no retries, breaker stays closed', async () => { + const fetchImpl = vi.fn(async () => jsonResp(204)); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + const resp = await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep }, + }); + expect(resp.status).toBe(204); + expect(fetchImpl).toHaveBeenCalledTimes(1); + expect(sleep).not.toHaveBeenCalled(); + expect(breaker.getState()).toBe('closed'); + expect(breaker.getConsecutiveFailures()).toBe(0); + }); + + it('one 503 then 204 → retried once, returns 204, breaker stays closed', async () => { + let n = 0; + const fetchImpl = vi.fn(async () => { + n += 1; + return n === 1 ? jsonResp(503) : jsonResp(204); + }); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + const resp = await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep, random: () => 0.5, baseDelayMs: 100, capDelayMs: 1000 }, + }); + expect(resp.status).toBe(204); + expect(fetchImpl).toHaveBeenCalledTimes(2); + expect(sleep).toHaveBeenCalledTimes(1); + expect(breaker.getConsecutiveFailures()).toBe(0); + }); + + it('429 with Retry-After honored (capped at RETRY_AFTER_CAP_MS)', async () => { + let n = 0; + const fetchImpl = vi.fn(async () => { + n += 1; + return n === 1 ? jsonResp(429, { 'Retry-After': '1' }) : jsonResp(204); + }); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep }, + }); + expect(sleep).toHaveBeenCalledWith(1000); // 1s + }); + + it('429 with absurd Retry-After is capped to RETRY_AFTER_CAP_MS', async () => { + let n = 0; + const fetchImpl = vi.fn(async () => { + n += 1; + return n === 1 ? jsonResp(429, { 'Retry-After': '99999' }) : jsonResp(204); + }); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep, capDelayMs: 999_999 }, // ensure cap comes from RETRY_AFTER_CAP_MS, not retry config + }); + expect(sleep).toHaveBeenCalledWith(RETRY_AFTER_CAP_MS); + }); + + it('429 without Retry-After falls back to exponential-backoff delay', async () => { + let n = 0; + const fetchImpl = vi.fn(async () => { + n += 1; + return n === 1 ? jsonResp(429) : jsonResp(204); + }); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep, baseDelayMs: 100, capDelayMs: 1000, random: () => 0.5 }, + }); + // attempt 0: full-jitter upper = min(1000, 100*1) = 100; floor(0.5*100) = 50 + expect(sleep).toHaveBeenCalledWith(50); + }); + + it('401 returned as Response, no retry, breaker not incremented', async () => { + const fetchImpl = vi.fn(async () => jsonResp(401)); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + const resp = await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep }, + }); + expect(resp.status).toBe(401); + expect(fetchImpl).toHaveBeenCalledTimes(1); + expect(breaker.getConsecutiveFailures()).toBe(0); + }); + + it('422 returned as Response, no retry', async () => { + const fetchImpl = vi.fn(async () => jsonResp(422)); + const { breaker } = makeBreaker(); + const resp = await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {} }, + }); + expect(resp.status).toBe(422); + expect(fetchImpl).toHaveBeenCalledTimes(1); + }); + + it('TimeoutError rethrown immediately, no retry, breaker not incremented', async () => { + const fetchImpl = vi.fn(async () => { + throw new DOMException('aborted', 'TimeoutError'); + }); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep }, + }), + ).rejects.toThrow(DOMException); + expect(fetchImpl).toHaveBeenCalledTimes(1); + expect(sleep).not.toHaveBeenCalled(); + expect(breaker.getConsecutiveFailures()).toBe(0); + }); + + it('three consecutive 503 throws ResilientFetchExhaustedError; breaker increments by 1', async () => { + const fetchImpl = vi.fn(async () => jsonResp(503)); + const sleep = vi.fn(async () => {}); + const { breaker } = makeBreaker(); + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep, maxAttempts: 3 }, + }), + ).rejects.toBeInstanceOf(ResilientFetchExhaustedError); + expect(fetchImpl).toHaveBeenCalledTimes(3); + expect(breaker.getConsecutiveFailures()).toBe(1); + }); + + it('after three exhausted 503 batches, breaker opens and fails fast', async () => { + const fetchImpl = vi.fn(async () => jsonResp(503)); + const { breaker } = makeBreaker({ failureThreshold: 3, cooldownMs: 60_000 }); + for (let i = 0; i < 3; i++) { + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 3 }, + }), + ).rejects.toBeInstanceOf(ResilientFetchExhaustedError); + } + expect(breaker.getState()).toBe('open'); + // 4th call: breaker open, no fetch invoked. + const fetchCallsBefore = fetchImpl.mock.calls.length; + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 3 }, + }), + ).rejects.toBeInstanceOf(CircuitOpenError); + expect(fetchImpl.mock.calls.length).toBe(fetchCallsBefore); + }); + + it('retryable-network error retries, breaker counts only on exhaustion', async () => { + const fetchImpl = vi.fn(async () => { + throw new TypeError('fetch failed'); + }); + const { breaker } = makeBreaker(); + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 3 }, + }), + ).rejects.toBeInstanceOf(TypeError); + expect(fetchImpl).toHaveBeenCalledTimes(3); + expect(breaker.getConsecutiveFailures()).toBe(1); + }); + + describe('U2: terminal outcomes route through recordNeutral', () => { + it('401 does not erase prior partial-failure progress on the breaker', async () => { + const { breaker } = makeBreaker(); + // Pre-seed the breaker with 2 failures (still closed; threshold 3). + breaker.recordFailure(); + breaker.recordFailure(); + expect(breaker.getConsecutiveFailures()).toBe(2); + + const fetchImpl = vi.fn(async () => jsonResp(401)); + await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {} }, + }); + + // Counter MUST stay at 2 — under the old behaviour recordSuccess + // would have reset to 0 and the next 5xx batch would have started + // from scratch instead of tipping over the threshold. + expect(breaker.getConsecutiveFailures()).toBe(2); + expect(breaker.getState()).toBe('closed'); + }); + + it('TimeoutError does not erase prior partial-failure progress', async () => { + const { breaker } = makeBreaker(); + breaker.recordFailure(); + breaker.recordFailure(); + + const fetchImpl = vi.fn(async () => { + throw new DOMException('aborted by timeout', 'TimeoutError'); + }); + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {} }, + }), + ).rejects.toBeInstanceOf(DOMException); + + expect(breaker.getConsecutiveFailures()).toBe(2); + }); + + it('external AbortError is terminal: no retry, breaker untouched', async () => { + const { breaker } = makeBreaker(); + breaker.recordFailure(); + + const fetchImpl = vi.fn(async () => { + throw new DOMException('aborted by caller', 'AbortError'); + }); + const sleep = vi.fn(async () => {}); + + await expect( + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep, maxAttempts: 3 }, + }), + ).rejects.toMatchObject({ name: 'AbortError' }); + + expect(fetchImpl).toHaveBeenCalledTimes(1); + expect(sleep).not.toHaveBeenCalled(); + // Counter unchanged — neither incremented (no failure) nor reset + // (no synthetic success). + expect(breaker.getConsecutiveFailures()).toBe(1); + }); + + it('interleaved 5xx + 401 + 5xx + 401 + 5xx opens breaker on third real failure', async () => { + const { breaker } = makeBreaker({ failureThreshold: 3 }); + const sequence = [503, 401, 503, 401, 503]; + let i = 0; + const fetchImpl = vi.fn(async () => jsonResp(sequence[i++])); + + // Each call uses maxAttempts:1 so each surfaces a single response + // (5xx → ResilientFetchExhaustedError; 4xx → returned Response). + const driveOne = () => + resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + + await expect(driveOne()).rejects.toBeInstanceOf(ResilientFetchExhaustedError); // 5xx fail #1 + await driveOne(); // 401 neutral + await expect(driveOne()).rejects.toBeInstanceOf(ResilientFetchExhaustedError); // 5xx fail #2 + await driveOne(); // 401 neutral + await expect(driveOne()).rejects.toBeInstanceOf(ResilientFetchExhaustedError); // 5xx fail #3 → opens + + expect(breaker.getState()).toBe('open'); + expect(fetchImpl).toHaveBeenCalledTimes(5); + }); + }); + + describe('half-open single-probe gating (U2)', () => { + /** Test helper: a fetch mock whose Response is controlled by the test. */ + function deferredFetch(): { + promise: Promise; + resolve: (resp: Response) => void; + reject: (err: unknown) => void; + } { + let resolve!: (resp: Response) => void; + let reject!: (err: unknown) => void; + const promise = new Promise((res, rej) => { + resolve = res; + reject = rej; + }); + return { promise, resolve, reject }; + } + + /** Builds a clock-injected breaker pre-opened with cooldown elapsed. */ + function preOpenedBreaker(opts: { cooldownMs: number; halfOpenRetryAfterMs?: number }): { + breaker: CircuitBreaker; + advance: (ms: number) => void; + } { + let t = 1_700_000_000_000; + const breaker = new CircuitBreaker({ + failureThreshold: 1, + cooldownMs: opts.cooldownMs, + halfOpenRetryAfterMs: opts.halfOpenRetryAfterMs ?? 1_000, + key: 'test', + now: () => t, + }); + breaker.recordFailure(); + t += opts.cooldownMs + 1; // cooldown elapsed + return { breaker, advance: (ms) => (t += ms) }; + } + + it('happy: 3 concurrent calls — exactly 1 hits fetch, others throw CircuitOpenError', async () => { + const { breaker } = preOpenedBreaker({ cooldownMs: 10 }); + const deferred = deferredFetch(); + const fetchImpl = vi.fn(() => deferred.promise); + + // Synchronous portion of each `resilientFetch` runs eagerly up to + // the first await, so by the time r2/r3 are constructed the probe + // permit is already consumed by r1 and they reject synchronously. + const r1 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + const r2 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + const r3 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + + // Resolve the probe with 200; r1 should now settle. + deferred.resolve(new Response(null, { status: 200 })); + + const results = await Promise.allSettled([r1, r2, r3]); + + expect(results[0].status).toBe('fulfilled'); + if (results[0].status === 'fulfilled') { + expect(results[0].value.status).toBe(200); + } + expect(results[1].status).toBe('rejected'); + if (results[1].status === 'rejected') { + expect(results[1].reason).toBeInstanceOf(CircuitOpenError); + } + expect(results[2].status).toBe('rejected'); + if (results[2].status === 'rejected') { + expect(results[2].reason).toBeInstanceOf(CircuitOpenError); + } + + // Only ONE underlying fetch was invoked. + expect(fetchImpl).toHaveBeenCalledTimes(1); + // Breaker closed after the probe's success. + expect(breaker.getState()).toBe('closed'); + }); + + it('error: probe gets 503 — exhausted error; subsequent caller sees fresh full cooldown', async () => { + const { breaker } = preOpenedBreaker({ cooldownMs: 10_000, halfOpenRetryAfterMs: 1_000 }); + const deferred = deferredFetch(); + const fetchImpl = vi.fn(() => deferred.promise); + + const r1 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + const r2 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + const r3 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + + // Probe fails with 503 → exhausted (maxAttempts: 1) → recordFailure → reopen. + deferred.resolve(new Response(null, { status: 503 })); + + const results = await Promise.allSettled([r1, r2, r3]); + + expect(results[0].status).toBe('rejected'); + if (results[0].status === 'rejected') { + expect(results[0].reason).toBeInstanceOf(ResilientFetchExhaustedError); + } + expect(results[1].status).toBe('rejected'); + if (results[1].status === 'rejected') { + expect(results[1].reason).toBeInstanceOf(CircuitOpenError); + // Blocked-while-half-open used the halfOpenRetryAfterMs default. + expect((results[1].reason as CircuitOpenError).retryAfterMs).toBe(1_000); + } + + // Breaker has re-opened with a fresh openedAt. + expect(breaker.getState()).toBe('open'); + + // r4: should see the fresh full cooldown, NOT the probe-in-flight 1000ms. + let r4Caught: CircuitOpenError | null = null; + try { + await resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + } catch (err) { + r4Caught = err as CircuitOpenError; + } + expect(r4Caught).toBeInstanceOf(CircuitOpenError); + expect(r4Caught?.retryAfterMs).toBe(10_000); + }); + + it('cancellation: probe AbortError releases permit; next caller becomes new probe', async () => { + const { breaker } = preOpenedBreaker({ cooldownMs: 10_000 }); + const deferred1 = deferredFetch(); + const deferred2 = deferredFetch(); + let callIdx = 0; + const fetchImpl = vi.fn(() => (callIdx++ === 0 ? deferred1.promise : deferred2.promise)); + + // r1 admitted as the probe; r2 blocked while r1 still in flight. + const r1 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + const r2 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + await expect(r2).rejects.toBeInstanceOf(CircuitOpenError); + + // Cancel the probe — `AbortError` routes through terminal-network → + // `recordNeutral` → permit released, state stays half-open. + deferred1.reject(new DOMException('aborted by caller', 'AbortError')); + await expect(r1).rejects.toMatchObject({ name: 'AbortError' }); + + expect(breaker.isProbeInFlight()).toBe(false); + expect(breaker.getState()).toBe('half-open'); + + // r3: now succeeds and becomes the new probe. + const r3 = resilientFetch(URL_STR, undefined, { + fetchImpl: fetchImpl as unknown as typeof fetch, + breaker, + retry: { sleep: async () => {}, maxAttempts: 1 }, + }); + deferred2.resolve(new Response(null, { status: 200 })); + const r3Resp = await r3; + expect(r3Resp.status).toBe(200); + expect(breaker.getState()).toBe('closed'); + // Two fetches total: the cancelled probe + the recovery probe. + expect(fetchImpl).toHaveBeenCalledTimes(2); + }); + }); +}); diff --git a/gitnexus/test/unit/integrations/retry.test.ts b/gitnexus/test/unit/integrations/retry.test.ts new file mode 100644 index 000000000..2dd4f4cf3 --- /dev/null +++ b/gitnexus/test/unit/integrations/retry.test.ts @@ -0,0 +1,128 @@ +import { describe, it, expect, vi } from 'vitest'; +import { computeBackoffMs, withRetry, type RetryOptions } from 'gitnexus-shared'; + +describe('computeBackoffMs', () => { + it('returns afterMs (capped) when caller supplies it', () => { + expect(computeBackoffMs(0, 500, 5000, 1500, () => 0.5)).toBe(1500); + expect(computeBackoffMs(0, 500, 5000, 99_999, () => 0.5)).toBe(5000); + expect(computeBackoffMs(0, 500, 5000, 0, () => 0.5)).toBe(0); + expect(computeBackoffMs(0, 500, 5000, -1, () => 0.5)).toBe(0); + }); + + it('full-jitter delay falls within [0, min(cap, base * 2^attempt)]', () => { + // attempt 0: upper = min(5000, 500 * 1) = 500 + expect(computeBackoffMs(0, 500, 5000, undefined, () => 0)).toBe(0); + expect(computeBackoffMs(0, 500, 5000, undefined, () => 0.999)).toBeLessThan(500); + // attempt 1: upper = min(5000, 500 * 2) = 1000 + expect(computeBackoffMs(1, 500, 5000, undefined, () => 0.5)).toBe(500); + // attempt 4: 500 * 16 = 8000, capped at 5000 + expect(computeBackoffMs(4, 500, 5000, undefined, () => 0.5)).toBe(2500); + expect(computeBackoffMs(4, 500, 5000, undefined, () => 0.999)).toBeLessThan(5000); + }); +}); + +describe('withRetry', () => { + function makeOpts(overrides: Partial = {}): RetryOptions { + return { + maxAttempts: 3, + baseDelayMs: 10, + capDelayMs: 100, + isRetryable: () => ({ retry: true }), + sleep: vi.fn(async () => {}), + random: () => 0.5, + ...overrides, + }; + } + + it('returns immediately when fn succeeds first try', async () => { + const sleep = vi.fn(async () => {}); + const fn = vi.fn(async () => 'ok'); + const result = await withRetry(fn, makeOpts({ sleep })); + expect(result).toBe('ok'); + expect(fn).toHaveBeenCalledTimes(1); + expect(sleep).not.toHaveBeenCalled(); + }); + + it('retries when isRetryable returns retry:true and second call succeeds', async () => { + const sleep = vi.fn(async () => {}); + let calls = 0; + const fn = async () => { + calls += 1; + if (calls === 1) throw new Error('boom'); + return 'ok'; + }; + const result = await withRetry(fn, makeOpts({ sleep })); + expect(result).toBe('ok'); + expect(calls).toBe(2); + expect(sleep).toHaveBeenCalledTimes(1); + }); + + it('honors afterMs returned by isRetryable', async () => { + const sleep = vi.fn(async () => {}); + let calls = 0; + const fn = async () => { + calls += 1; + if (calls === 1) throw new Error('throttle'); + return 'ok'; + }; + await withRetry( + fn, + makeOpts({ + sleep, + isRetryable: () => ({ retry: true, afterMs: 1500 }), + capDelayMs: 5000, + }), + ); + expect(sleep).toHaveBeenCalledWith(1500); + }); + + it('caps afterMs at capDelayMs', async () => { + const sleep = vi.fn(async () => {}); + let calls = 0; + const fn = async () => { + calls += 1; + if (calls === 1) throw new Error('throttle'); + return 'ok'; + }; + await withRetry( + fn, + makeOpts({ + sleep, + isRetryable: () => ({ retry: true, afterMs: 10_000 }), + capDelayMs: 3000, + }), + ); + expect(sleep).toHaveBeenCalledWith(3000); + }); + + it('rethrows immediately when isRetryable returns retry:false', async () => { + const sleep = vi.fn(async () => {}); + const fn = vi.fn(async () => { + throw new Error('terminal'); + }); + await expect( + withRetry(fn, makeOpts({ sleep, isRetryable: () => ({ retry: false }) })), + ).rejects.toThrow('terminal'); + expect(fn).toHaveBeenCalledTimes(1); + expect(sleep).not.toHaveBeenCalled(); + }); + + it('throws the last error when maxAttempts exhausted', async () => { + const sleep = vi.fn(async () => {}); + let calls = 0; + const fn = async () => { + calls += 1; + throw new Error(`boom-${calls}`); + }; + await expect(withRetry(fn, makeOpts({ sleep, maxAttempts: 3 }))).rejects.toThrow('boom-3'); + expect(calls).toBe(3); + // 3 attempts → 2 sleeps between them; final attempt does not sleep. + expect(sleep).toHaveBeenCalledTimes(2); + }); + + it('rejects maxAttempts < 1', async () => { + await expect(withRetry(async () => 'ok', makeOpts({ maxAttempts: 0 }))).rejects.toThrow( + /maxAttempts must be >= 1/, + ); + }); +}); diff --git a/gitnexus/test/unit/lbug-checkpoint-lifecycle.test.ts b/gitnexus/test/unit/lbug-checkpoint-lifecycle.test.ts new file mode 100644 index 000000000..3e9ffe8f6 --- /dev/null +++ b/gitnexus/test/unit/lbug-checkpoint-lifecycle.test.ts @@ -0,0 +1,420 @@ +import { afterEach, describe, expect, it, vi } from 'vitest'; + +describe('lbug adapter CHECKPOINT lifecycle', () => { + afterEach(() => { + vi.doUnmock('../../src/core/lbug/lbug-config.js'); + vi.doUnmock('../../src/core/lbug/extension-loader.js'); + vi.resetModules(); + vi.clearAllMocks(); + }); + + it('drains and closes CHECKPOINT result before closing connection and database handles', async () => { + vi.resetModules(); + + const events: string[] = []; + const checkpointResult = { + getAll: vi.fn(async () => { + events.push('checkpoint:getAll'); + return []; + }), + close: vi.fn(() => { + events.push('checkpoint:close'); + }), + }; + const genericResult = { + getAll: vi.fn(async () => []), + close: vi.fn(), + }; + const conn = { + query: vi.fn(async (sql: string) => { + if (sql === 'CHECKPOINT') { + events.push('checkpoint:query'); + return checkpointResult; + } + return genericResult; + }), + close: vi.fn(async () => { + events.push('conn:close'); + }), + }; + const db = { + close: vi.fn(async () => { + events.push('db:close'); + }), + }; + + vi.doMock('../../src/core/lbug/lbug-config.js', () => ({ + openLbugConnection: vi.fn(async () => ({ db, conn })), + closeLbugConnection: vi.fn(async () => {}), + isDbBusyError: vi.fn((err: unknown) => String(err).toLowerCase().includes('lock')), + isOpenRetryExhausted: vi.fn(() => false), + waitForWindowsHandleRelease: vi.fn(async () => true), + })); + vi.doMock('../../src/core/lbug/extension-loader.js', () => ({ + extensionManager: { + ensure: vi.fn(async () => true), + getCapabilities: vi.fn(() => []), + reset: vi.fn(), + }, + })); + + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.initLbug('/tmp/gitnexus-lbug-checkpoint-lifecycle/lbug'); + + events.length = 0; + await adapter.closeLbug(); + + expect(events).toEqual([ + 'checkpoint:query', + 'checkpoint:getAll', + 'checkpoint:close', + 'conn:close', + 'db:close', + ]); + }); + + it('closes normal query results after reading rows', async () => { + vi.resetModules(); + + const events: string[] = []; + const queryResult = { + getAll: vi.fn(async () => { + events.push('query:getAll'); + return [{ id: 'file:a' }]; + }), + close: vi.fn(() => { + events.push('query:close'); + }), + }; + const genericResult = { + getAll: vi.fn(async () => []), + close: vi.fn(), + }; + const conn = { + query: vi.fn(async (sql: string) => { + if (sql === 'MATCH (n:File) RETURN n.id AS id') { + events.push('query:run'); + return queryResult; + } + return genericResult; + }), + close: vi.fn(async () => {}), + }; + const db = { + close: vi.fn(async () => {}), + }; + + vi.doMock('../../src/core/lbug/lbug-config.js', () => ({ + openLbugConnection: vi.fn(async () => ({ db, conn })), + closeLbugConnection: vi.fn(async () => {}), + isDbBusyError: vi.fn((err: unknown) => String(err).toLowerCase().includes('lock')), + isOpenRetryExhausted: vi.fn(() => false), + waitForWindowsHandleRelease: vi.fn(async () => true), + })); + vi.doMock('../../src/core/lbug/extension-loader.js', () => ({ + extensionManager: { + ensure: vi.fn(async () => true), + getCapabilities: vi.fn(() => []), + reset: vi.fn(), + }, + })); + + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.initLbug('/tmp/gitnexus-lbug-query-lifecycle/lbug'); + + events.length = 0; + await expect(adapter.executeQuery('MATCH (n:File) RETURN n.id AS id')).resolves.toEqual([ + { id: 'file:a' }, + ]); + + expect(events).toEqual(['query:run', 'query:getAll', 'query:close']); + + await adapter.closeLbug(); + }); + + it('treats synchronous query result close errors as best-effort cleanup', async () => { + vi.resetModules(); + + const queryResult = { + getAll: vi.fn(async () => [{ id: 'file:a' }]), + close: vi.fn(() => { + throw new Error('close failed'); + }), + }; + const genericResult = { + getAll: vi.fn(async () => []), + close: vi.fn(), + }; + const conn = { + query: vi.fn(async (sql: string) => { + if (sql === 'MATCH (n:File) RETURN n.id AS id') { + return queryResult; + } + return genericResult; + }), + close: vi.fn(async () => {}), + }; + const db = { + close: vi.fn(async () => {}), + }; + + vi.doMock('../../src/core/lbug/lbug-config.js', () => ({ + openLbugConnection: vi.fn(async () => ({ db, conn })), + closeLbugConnection: vi.fn(async () => {}), + isDbBusyError: vi.fn((err: unknown) => String(err).toLowerCase().includes('lock')), + isOpenRetryExhausted: vi.fn(() => false), + waitForWindowsHandleRelease: vi.fn(async () => true), + })); + vi.doMock('../../src/core/lbug/extension-loader.js', () => ({ + extensionManager: { + ensure: vi.fn(async () => true), + getCapabilities: vi.fn(() => []), + reset: vi.fn(), + }, + })); + + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.initLbug('/tmp/gitnexus-lbug-sync-close-lifecycle/lbug'); + + await expect(adapter.executeQuery('MATCH (n:File) RETURN n.id AS id')).resolves.toEqual([ + { id: 'file:a' }, + ]); + expect(queryResult.close).toHaveBeenCalledOnce(); + + await adapter.closeLbug(); + }); + + it('closes later query results when an earlier array result fails to read', async () => { + vi.resetModules(); + + const events: string[] = []; + const firstResult = { + getAll: vi.fn(async () => { + events.push('first:getAll'); + throw new Error('read failed'); + }), + close: vi.fn(() => { + events.push('first:close'); + }), + }; + const secondResult = { + getAll: vi.fn(async () => { + events.push('second:getAll'); + return []; + }), + close: vi.fn(() => { + events.push('second:close'); + }), + }; + const genericResult = { + getAll: vi.fn(async () => []), + close: vi.fn(), + }; + const conn = { + query: vi.fn(async (sql: string) => { + if (sql === 'MATCH (n:File) RETURN n.id AS id') { + return [firstResult, secondResult]; + } + return genericResult; + }), + close: vi.fn(async () => {}), + }; + const db = { + close: vi.fn(async () => {}), + }; + + vi.doMock('../../src/core/lbug/lbug-config.js', () => ({ + openLbugConnection: vi.fn(async () => ({ db, conn })), + closeLbugConnection: vi.fn(async () => {}), + isDbBusyError: vi.fn((err: unknown) => String(err).toLowerCase().includes('lock')), + isOpenRetryExhausted: vi.fn(() => false), + waitForWindowsHandleRelease: vi.fn(async () => true), + })); + vi.doMock('../../src/core/lbug/extension-loader.js', () => ({ + extensionManager: { + ensure: vi.fn(async () => true), + getCapabilities: vi.fn(() => []), + reset: vi.fn(), + }, + })); + + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.initLbug('/tmp/gitnexus-lbug-array-error-lifecycle/lbug'); + + await expect(adapter.executeQuery('MATCH (n:File) RETURN n.id AS id')).rejects.toThrow( + 'read failed', + ); + expect(events).toEqual(['first:getAll', 'first:close', 'second:getAll', 'second:close']); + + await adapter.closeLbug(); + }); + + it('closes non-first stream query results when LadybugDB returns an array', async () => { + vi.resetModules(); + + const events: string[] = []; + const firstResult = { + hasNext: vi + .fn() + .mockImplementationOnce(() => { + events.push('first:hasNext:true'); + return true; + }) + .mockImplementationOnce(() => { + events.push('first:hasNext:false'); + return false; + }), + getNext: vi.fn(async () => { + events.push('first:getNext'); + return { id: 'file:a' }; + }), + getAll: vi.fn(async () => { + events.push('first:getAll'); + return []; + }), + close: vi.fn(() => { + events.push('first:close'); + }), + }; + const secondResult = { + getAll: vi.fn(async () => { + events.push('second:getAll'); + return []; + }), + close: vi.fn(() => { + events.push('second:close'); + }), + }; + const genericResult = { + getAll: vi.fn(async () => []), + close: vi.fn(), + }; + const conn = { + query: vi.fn(async (sql: string) => { + if (sql === 'MATCH (n:File) RETURN n.id AS id') { + events.push('stream:query'); + return [firstResult, secondResult]; + } + return genericResult; + }), + close: vi.fn(async () => {}), + }; + const db = { + close: vi.fn(async () => {}), + }; + + vi.doMock('../../src/core/lbug/lbug-config.js', () => ({ + openLbugConnection: vi.fn(async () => ({ db, conn })), + closeLbugConnection: vi.fn(async () => {}), + isDbBusyError: vi.fn((err: unknown) => String(err).toLowerCase().includes('lock')), + isOpenRetryExhausted: vi.fn(() => false), + waitForWindowsHandleRelease: vi.fn(async () => true), + })); + vi.doMock('../../src/core/lbug/extension-loader.js', () => ({ + extensionManager: { + ensure: vi.fn(async () => true), + getCapabilities: vi.fn(() => []), + reset: vi.fn(), + }, + })); + + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.initLbug('/tmp/gitnexus-lbug-stream-lifecycle/lbug'); + + const rows: unknown[] = []; + events.length = 0; + await expect( + adapter.streamQuery('MATCH (n:File) RETURN n.id AS id', (row) => { + rows.push(row); + }), + ).resolves.toBe(1); + + expect(rows).toEqual([{ id: 'file:a' }]); + expect(events).toEqual([ + 'stream:query', + 'first:hasNext:true', + 'first:getNext', + 'first:hasNext:false', + 'first:getAll', + 'first:close', + 'second:getAll', + 'second:close', + ]); + + await adapter.closeLbug(); + }); + + it('drains stream query results when row handling fails before the result is exhausted', async () => { + vi.resetModules(); + + const events: string[] = []; + const queryResult = { + hasNext: vi.fn(() => { + events.push('stream:hasNext'); + return true; + }), + getNext: vi.fn(async () => { + events.push('stream:getNext'); + return { id: 'file:a' }; + }), + getAll: vi.fn(async () => { + events.push('stream:getAll'); + return [{ id: 'file:b' }]; + }), + close: vi.fn(() => { + events.push('stream:close'); + }), + }; + const genericResult = { + getAll: vi.fn(async () => []), + close: vi.fn(), + }; + const conn = { + query: vi.fn(async (sql: string) => { + if (sql === 'MATCH (n:File) RETURN n.id AS id') { + events.push('stream:query'); + return queryResult; + } + return genericResult; + }), + close: vi.fn(async () => {}), + }; + const db = { + close: vi.fn(async () => {}), + }; + + vi.doMock('../../src/core/lbug/lbug-config.js', () => ({ + openLbugConnection: vi.fn(async () => ({ db, conn })), + closeLbugConnection: vi.fn(async () => {}), + isDbBusyError: vi.fn((err: unknown) => String(err).toLowerCase().includes('lock')), + isOpenRetryExhausted: vi.fn(() => false), + waitForWindowsHandleRelease: vi.fn(async () => true), + })); + vi.doMock('../../src/core/lbug/extension-loader.js', () => ({ + extensionManager: { + ensure: vi.fn(async () => true), + getCapabilities: vi.fn(() => []), + reset: vi.fn(), + }, + })); + + const adapter = await import('../../src/core/lbug/lbug-adapter.js'); + await adapter.initLbug('/tmp/gitnexus-lbug-stream-error-lifecycle/lbug'); + + await expect( + adapter.streamQuery('MATCH (n:File) RETURN n.id AS id', () => { + throw new Error('client disconnected'); + }), + ).rejects.toThrow('client disconnected'); + + expect(events).toEqual([ + 'stream:query', + 'stream:hasNext', + 'stream:getNext', + 'stream:getAll', + 'stream:close', + ]); + + await adapter.closeLbug(); + }); +}); diff --git a/gitnexus/test/unit/lbug-checkpoint.test.ts b/gitnexus/test/unit/lbug-checkpoint.test.ts index 5b68ee9bd..5b9603997 100644 --- a/gitnexus/test/unit/lbug-checkpoint.test.ts +++ b/gitnexus/test/unit/lbug-checkpoint.test.ts @@ -58,6 +58,14 @@ describe('flushWAL / safeClose — consolidation guard (#1376)', () => { expect(matches.length).toBe(1); }); + it('flushWAL drains and closes the CHECKPOINT result before returning', () => { + const flushBody = adapterSource.slice( + adapterSource.indexOf('export const flushWAL'), + adapterSource.indexOf('export const safeClose'), + ); + expect(flushBody).toMatch(/await drainQueryResult\(checkpointResult\)/); + }); + it('conn.close() only appears inside safeClose (with eslint-disable)', () => { // Every conn.close() in the adapter must live inside safeClose, guarded // by the eslint-disable comment. Count occurrences to catch leaks. diff --git a/gitnexus/test/unit/registry-primary-flag.test.ts b/gitnexus/test/unit/registry-primary-flag.test.ts index 5f688c732..e800bd14a 100644 --- a/gitnexus/test/unit/registry-primary-flag.test.ts +++ b/gitnexus/test/unit/registry-primary-flag.test.ts @@ -127,8 +127,10 @@ describe('isRegistryPrimary', () => { it('handles the CPlusPlus → REGISTRY_PRIMARY_CPP mapping correctly', () => { process.env['REGISTRY_PRIMARY_CPP'] = 'true'; expect(isRegistryPrimary(SupportedLanguages.CPlusPlus)).toBe(true); - // Negative: the TS-key-style name is NOT read. - delete process.env['REGISTRY_PRIMARY_CPP']; + // Negative: the TS-key-style name is NOT read. CPlusPlus is now in + // MIGRATED_LANGUAGES, so we must explicitly opt it out via the + // canonical env var to verify the wrong-name var has no effect. + process.env['REGISTRY_PRIMARY_CPP'] = 'false'; process.env['REGISTRY_PRIMARY_CPLUSPLUS'] = 'true'; expect(isRegistryPrimary(SupportedLanguages.CPlusPlus)).toBe(false); }); @@ -148,16 +150,21 @@ describe('primaryLanguages', () => { it('returns exactly the flipped languages (env opts in unmigrated, opts out migrated)', () => { // Migrated languages are default-on; each must be opted out here when - // testing explicit env overrides. Java (unmigrated) opts in; Go stays off. - process.env['REGISTRY_PRIMARY_PYTHON'] = 'false'; - process.env['REGISTRY_PRIMARY_CSHARP'] = 'false'; - process.env['REGISTRY_PRIMARY_TYPESCRIPT'] = 'false'; - process.env['REGISTRY_PRIMARY_GO'] = 'false'; + // testing explicit env overrides. Java (unmigrated) opts in. + // Opt out every member of MIGRATED_LANGUAGES dynamically so this test + // does not have to be updated each time a new language ships its + // Ring 3 migration (C++ and PHP joined the set in their respective + // Ring 3 migrations; future Ring 3 additions land here without test churn). + for (const lang of MIGRATED_LANGUAGES) { + process.env[envVarNameFor(lang)] = 'false'; + } process.env['REGISTRY_PRIMARY_JAVA'] = '1'; const enabled = primaryLanguages(); expect(enabled.has(SupportedLanguages.Python)).toBe(false); expect(enabled.has(SupportedLanguages.CSharp)).toBe(false); expect(enabled.has(SupportedLanguages.Go)).toBe(false); + expect(enabled.has(SupportedLanguages.CPlusPlus)).toBe(false); + expect(enabled.has(SupportedLanguages.PHP)).toBe(false); expect(enabled.has(SupportedLanguages.Java)).toBe(true); // Only Java is on: migrated defaults overridden off, Java explicitly on. expect(enabled.size).toBe(1); diff --git a/gitnexus/test/unit/repo-manager-ensure-ignore-readonly.test.ts b/gitnexus/test/unit/repo-manager-ensure-ignore-readonly.test.ts new file mode 100644 index 000000000..8e49a01f3 --- /dev/null +++ b/gitnexus/test/unit/repo-manager-ensure-ignore-readonly.test.ts @@ -0,0 +1,113 @@ +/** + * Read-only / permission-denied write paths for ensureGitNexusIgnored (#1549, PR #1550). + * Separate from repo-manager.test.ts: Vitest cannot vi.spyOn ESM namespace exports of + * fs/promises; a delegating vi.mock is required for cross-platform mock rejects. + */ +import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; +import path from 'path'; + +const fswCtx = vi.hoisted(() => ({ + writeFileMock: vi.fn(), + realWrite: null as ((...args: unknown[]) => Promise) | null, +})); + +vi.mock('fs/promises', async (importOriginal) => { + const actual = await importOriginal(); + const d = actual.default; + fswCtx.realWrite = d.writeFile.bind(d); + fswCtx.writeFileMock.mockImplementation((...args) => fswCtx.realWrite!(...args)); + return { + default: new Proxy(d, { + get(target, prop) { + if (prop === 'writeFile') return fswCtx.writeFileMock; + const v = Reflect.get(target, prop, target) as unknown; + return typeof v === 'function' ? (v as (...args: unknown[]) => unknown).bind(target) : v; + }, + }), + }; +}); + +import fs from 'fs/promises'; +import { ensureGitNexusIgnored } from '../../src/storage/repo-manager.js'; +import { _captureLogger } from '../../src/core/logger.js'; +import { createTempDir } from '../helpers/test-db.js'; + +const samePath = (a: string, b: string) => path.normalize(a) === path.normalize(b); + +describe('ensureGitNexusIgnored — mocked writeFile (EROFS / EACCES / EPERM)', () => { + let tmpRepo: Awaited>; + + beforeEach(async () => { + tmpRepo = await createTempDir('gitnexus-ro-ignore-mock-'); + fswCtx.writeFileMock.mockClear(); + fswCtx.writeFileMock.mockImplementation((...args) => fswCtx.realWrite!(...args)); + }); + + afterEach(async () => { + await tmpRepo.cleanup(); + }); + + it.each(['EROFS', 'EACCES', 'EPERM'] as const)( + 'tolerates %s on .git/info/exclude write and logs a warn', + async (code) => { + const gitignorePath = path.join(tmpRepo.dbPath, '.gitnexus', '.gitignore'); + await fs.mkdir(path.dirname(gitignorePath), { recursive: true }); + await fs.writeFile(gitignorePath, '*\n', 'utf-8'); + + const excludePath = path.join(tmpRepo.dbPath, '.git', 'info', 'exclude'); + await fs.mkdir(path.dirname(excludePath), { recursive: true }); + await fs.writeFile(excludePath, '# empty\n', 'utf-8'); + + const cap = _captureLogger(); + fswCtx.writeFileMock.mockRejectedValueOnce(Object.assign(new Error('mock ro'), { code })); + + try { + await expect(ensureGitNexusIgnored(tmpRepo.dbPath)).resolves.not.toThrow(); + expect(fswCtx.writeFileMock).toHaveBeenCalled(); + expect( + cap + .records() + .some( + (r) => + r.level === 40 && + r.code === code && + typeof r.path === 'string' && + samePath(String(r.path), excludePath) && + String(r.msg ?? '').includes('.git/info/exclude'), + ), + ).toBe(true); + } finally { + cap.restore(); + } + }, + ); + + it.each(['EROFS', 'EACCES', 'EPERM'] as const)( + 'tolerates %s on .gitnexus/.gitignore write and logs a warn', + async (code) => { + const cap = _captureLogger(); + const gitignorePath = path.join(tmpRepo.dbPath, '.gitnexus', '.gitignore'); + + fswCtx.writeFileMock.mockRejectedValueOnce(Object.assign(new Error('mock ro'), { code })); + + try { + await expect(ensureGitNexusIgnored(tmpRepo.dbPath)).resolves.not.toThrow(); + expect(fswCtx.writeFileMock).toHaveBeenCalled(); + expect( + cap + .records() + .some( + (r) => + r.level === 40 && + r.code === code && + typeof r.path === 'string' && + samePath(String(r.path), gitignorePath) && + String(r.msg ?? '').includes('.gitnexus/.gitignore'), + ), + ).toBe(true); + } finally { + cap.restore(); + } + }, + ); +}); diff --git a/gitnexus/test/unit/repo-manager.test.ts b/gitnexus/test/unit/repo-manager.test.ts index bbd0fd50e..d3dd65a27 100644 --- a/gitnexus/test/unit/repo-manager.test.ts +++ b/gitnexus/test/unit/repo-manager.test.ts @@ -4,10 +4,11 @@ * Tests: getStoragePath, getStoragePaths, readRegistry, registerRepo, unregisterRepo * Covers hardening fixes #29 (API key file permissions) and #30 (case-insensitive paths on Windows) */ -import { describe, it, expect, beforeEach, afterEach } from 'vitest'; +import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest'; import path from 'path'; import os from 'os'; import fs from 'fs/promises'; +import { _captureLogger } from '../../src/core/logger.js'; import { getStoragePath, getStoragePaths, @@ -73,6 +74,7 @@ describe('ensureGitNexusIgnored (#1233)', () => { }); afterEach(async () => { + vi.restoreAllMocks(); await tmpRepo.cleanup(); }); @@ -139,6 +141,74 @@ describe('ensureGitNexusIgnored (#1233)', () => { }); expect(status).toBe(''); }); + + // ─ Read-only workspace tolerance (#1549) ──────────────────────────── + // The documented Docker workflow mounts the host workspace at /workspace:ro + // and runs `gitnexus index /workspace/`. The host has already created + // the .gitnexus dir during a prior `analyze`, so the gitignore file already + // exists with the correct content — there's no real work to do. The tests + // below pin two pieces of behaviour that make that workflow work: + // (a) the function short-circuits when the file is already correct + // (no write attempt, no mtime bump); + // (b) when a write *is* needed but the FS is not writable + // (EROFS / EACCES / EPERM), the function logs and continues instead of + // throwing — so the caller's `registerRepo` work stays committed. + + it('does not re-write .gitnexus/.gitignore when it already has the desired content', async () => { + await ensureGitNexusIgnored(tmpRepo.dbPath); + const gitignorePath = path.join(tmpRepo.dbPath, '.gitnexus', '.gitignore'); + const before = await fs.stat(gitignorePath); + + await new Promise((resolve) => setTimeout(resolve, 25)); + + await ensureGitNexusIgnored(tmpRepo.dbPath); + + const after = await fs.stat(gitignorePath); + expect(after.mtimeMs).toBe(before.mtimeMs); + }); + + it.skipIf(process.platform === 'win32' || process.getuid?.() === 0)( + 'does not throw when .gitnexus/.gitignore is already correct and the storage dir is read-only', + async () => { + await ensureGitNexusIgnored(tmpRepo.dbPath); + const storagePath = path.join(tmpRepo.dbPath, '.gitnexus'); + + await fs.chmod(storagePath, 0o555); + try { + await expect(ensureGitNexusIgnored(tmpRepo.dbPath)).resolves.not.toThrow(); + } finally { + await fs.chmod(storagePath, 0o755); + } + }, + ); + + it.skipIf(process.platform === 'win32' || process.getuid?.() === 0)( + 'warns and continues when the storage dir is read-only and the file does not yet exist', + async () => { + const storagePath = path.join(tmpRepo.dbPath, '.gitnexus'); + await fs.mkdir(storagePath, { recursive: true }); + await fs.chmod(storagePath, 0o555); + + const cap = _captureLogger(); + try { + await expect(ensureGitNexusIgnored(tmpRepo.dbPath)).resolves.not.toThrow(); + expect( + cap + .records() + .some( + (r) => + r.level === 40 && + (r.code === 'EACCES' || r.code === 'EPERM') && + String(r.msg ?? '').includes('.gitnexus/.gitignore') && + String(r.path ?? '').includes('.gitnexus'), + ), + ).toBe(true); + } finally { + cap.restore(); + await fs.chmod(storagePath, 0o755); + } + }, + ); }); // ─── readRegistry ──────────────────────────────────────────────────── diff --git a/gitnexus/test/unit/safe-parse.test.ts b/gitnexus/test/unit/safe-parse.test.ts new file mode 100644 index 000000000..e536bbd40 --- /dev/null +++ b/gitnexus/test/unit/safe-parse.test.ts @@ -0,0 +1,74 @@ +import { describe, it, expect } from 'vitest'; +import Parser from 'tree-sitter'; +import Python from 'tree-sitter-python'; +import { parseSourceSafe } from '../../src/core/tree-sitter/safe-parse.js'; + +const makeParser = (): Parser => { + const p = new Parser(); + p.setLanguage(Python); + return p; +}; + +const buildSource = (chars: number, lineLen = 80): string => { + const line = 'x = 1' + ' '.repeat(Math.max(0, lineLen - 6)) + '\n'; + const lines = Math.ceil(chars / line.length); + return line.repeat(lines).slice(0, chars); +}; + +describe('parseSourceSafe', () => { + it('parses small ASCII sources via the direct path', () => { + const tree = parseSourceSafe(makeParser(), 'x = 1\n'); + expect(tree.rootNode.type).toBe('module'); + expect(tree.rootNode.hasError).toBe(false); + }); + + it('parses sources at the direct/callback boundary (16 KiB)', () => { + const src = buildSource(16 * 1024); + const tree = parseSourceSafe(makeParser(), src); + expect(tree.rootNode.hasError).toBe(false); + expect(tree.rootNode.endIndex).toBe(src.length); + }); + + it('parses sources just above the boundary via the callback path', () => { + const src = buildSource(16 * 1024 + 1); + const tree = parseSourceSafe(makeParser(), src); + expect(tree.rootNode.hasError).toBe(false); + expect(tree.rootNode.endIndex).toBe(src.length); + }); + + it('parses sources at and around the 32 767-char Windows crash boundary', () => { + for (const len of [32_766, 32_767, 32_768]) { + const src = buildSource(len); + const tree = parseSourceSafe(makeParser(), src); + expect(tree.rootNode.hasError, `len=${len}`).toBe(false); + expect(tree.rootNode.endIndex, `len=${len}`).toBe(src.length); + } + }); + + it('parses a single line longer than the chunk size (no newlines)', () => { + const src = '"' + 'a'.repeat(20_000) + '"\n'; + const tree = parseSourceSafe(makeParser(), src); + expect(tree.rootNode.hasError).toBe(false); + expect(tree.rootNode.endIndex).toBe(src.length); + }); + + it('parses sources with CRLF line endings near a chunk boundary', () => { + const line = 'x = 1' + ' '.repeat(75) + '\r\n'; + const src = line.repeat(Math.ceil(20_000 / line.length)); + const tree = parseSourceSafe(makeParser(), src); + expect(tree.rootNode.hasError).toBe(false); + expect(tree.rootNode.endIndex).toBe(src.length); + }); + + it('parses a large all-non-ASCII source identically to the direct path', () => { + const small = '# ' + '漢'.repeat(50) + '\n'; + const direct = makeParser().parse(small); + const safe = parseSourceSafe(makeParser(), small); + expect(safe.rootNode.toString()).toBe(direct.rootNode.toString()); + + const large = ('# ' + '漢'.repeat(8_000) + '\n').repeat(3); + const tree = parseSourceSafe(makeParser(), large); + expect(tree.rootNode.hasError).toBe(false); + expect(tree.rootNode.endIndex).toBe(large.length); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/c/c-arity.test.ts b/gitnexus/test/unit/scope-resolution/c/c-arity.test.ts new file mode 100644 index 000000000..fddf1b932 --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/c/c-arity.test.ts @@ -0,0 +1,212 @@ +/** + * Unit tests for C arity computation and compatibility. + */ + +import { describe, it, expect } from 'vitest'; +import { getCParser } from '../../../../src/core/ingestion/languages/c/query.js'; +import { + computeCDeclarationArity, + computeCCallArity, +} from '../../../../src/core/ingestion/languages/c/arity-metadata.js'; +import { cArityCompatibility } from '../../../../src/core/ingestion/languages/c/arity.js'; +import type { SyntaxNode } from '../../../../src/core/ingestion/utils/ast-helpers.js'; +import type { Callsite, SymbolDefinition } from 'gitnexus-shared'; + +function parseFunctionNode(src: string): SyntaxNode | null { + const tree = getCParser().parse(src); + for (let i = 0; i < tree.rootNode.namedChildCount; i++) { + const child = tree.rootNode.namedChild(i); + if (child?.type === 'function_definition' || child?.type === 'declaration') { + return child as SyntaxNode; + } + } + return null; +} + +function parseCallNode(src: string): SyntaxNode | null { + const tree = getCParser().parse(src); + // Walk deeper to find call_expression + function findCall(node: SyntaxNode): SyntaxNode | null { + if (node.type === 'call_expression') return node; + for (let i = 0; i < node.namedChildCount; i++) { + const found = findCall(node.namedChild(i) as SyntaxNode); + if (found !== null) return found; + } + return null; + } + return findCall(tree.rootNode as SyntaxNode); +} + +describe('computeCDeclarationArity', () => { + it('returns count for simple parameters', () => { + const node = parseFunctionNode('int add(int a, int b) { return a + b; }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBe(2); + expect(arity.requiredParameterCount).toBe(2); + }); + + it('returns zero for (void) parameter list', () => { + const node = parseFunctionNode('void f(void) { }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBe(0); + expect(arity.requiredParameterCount).toBe(0); + expect(arity.parameterTypes).toEqual([]); + }); + + it('handles variadic functions — parameterCount is undefined', () => { + const node = parseFunctionNode('int printf(const char *fmt, ...) { return 0; }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBeUndefined(); + expect(arity.requiredParameterCount).toBe(1); + expect(arity.parameterTypes).toContain('...'); + }); + + it('extracts parameter types', () => { + const node = parseFunctionNode('void f(int a, float b, char *c) { }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterTypes).toEqual(['int', 'float', 'char']); + }); + + it('handles pointer-return function', () => { + const node = parseFunctionNode('int *create(int size) { return 0; }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBe(1); + }); + + it('handles function prototype (no body)', () => { + const node = parseFunctionNode('int add(int a, int b);'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBe(2); + }); + + it('returns empty for non-function node', () => { + const node = parseFunctionNode('int x = 5;'); + // This might be a declaration node, but without function_declarator + if (node !== null) { + const arity = computeCDeclarationArity(node); + expect(arity.parameterCount).toBeUndefined(); + } + }); + + it('handles single parameter', () => { + const node = parseFunctionNode('void f(int x) { }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBe(1); + expect(arity.requiredParameterCount).toBe(1); + }); + + it('returns unknown arity for K&R empty parameter list int foo()', () => { + const node = parseFunctionNode('int foo() { return 0; }'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + // K&R old-style: unspecified parameters, NOT zero parameters + expect(arity.parameterCount).toBeUndefined(); + expect(arity.requiredParameterCount).toBeUndefined(); + expect(arity.parameterTypes).toBeUndefined(); + }); + + it('distinguishes K&R int foo() from explicit int foo(void)', () => { + const knrNode = parseFunctionNode('int foo() { return 0; }'); + const voidNode = parseFunctionNode('int foo(void) { return 0; }'); + expect(knrNode).not.toBeNull(); + expect(voidNode).not.toBeNull(); + + const knrArity = computeCDeclarationArity(knrNode!); + const voidArity = computeCDeclarationArity(voidNode!); + + // K&R: unknown arity + expect(knrArity.parameterCount).toBeUndefined(); + // Explicit void: zero params + expect(voidArity.parameterCount).toBe(0); + expect(voidArity.requiredParameterCount).toBe(0); + }); + + it('returns unknown arity for K&R prototype int foo();', () => { + const node = parseFunctionNode('int foo();'); + expect(node).not.toBeNull(); + const arity = computeCDeclarationArity(node!); + expect(arity.parameterCount).toBeUndefined(); + expect(arity.requiredParameterCount).toBeUndefined(); + }); +}); + +describe('computeCCallArity', () => { + it('counts zero arguments', () => { + const node = parseCallNode('void f(void) { init(); }'); + expect(node).not.toBeNull(); + expect(computeCCallArity(node!)).toBe(0); + }); + + it('counts two arguments', () => { + const node = parseCallNode('void f(void) { add(1, 2); }'); + expect(node).not.toBeNull(); + expect(computeCCallArity(node!)).toBe(2); + }); + + it('counts three arguments', () => { + const node = parseCallNode('void f(void) { func(a, b, c); }'); + expect(node).not.toBeNull(); + expect(computeCCallArity(node!)).toBe(3); + }); + + it('counts string literal arguments', () => { + const node = parseCallNode('void f(void) { printf("hello %s", name); }'); + expect(node).not.toBeNull(); + expect(computeCCallArity(node!)).toBe(2); + }); +}); + +describe('cArityCompatibility', () => { + function makeDef(params: Partial): SymbolDefinition { + return { + nodeId: 'test', + filePath: 'test.c', + type: 'Function', + ...params, + }; + } + + function makeCallsite(arity: number): Callsite { + return { arity } as Callsite; + } + + it('returns compatible for exact match', () => { + const def = makeDef({ parameterCount: 2, requiredParameterCount: 2 }); + expect(cArityCompatibility(def, makeCallsite(2))).toBe('compatible'); + }); + + it('returns incompatible for too few args', () => { + const def = makeDef({ parameterCount: 3, requiredParameterCount: 3 }); + expect(cArityCompatibility(def, makeCallsite(1))).toBe('incompatible'); + }); + + it('returns incompatible for too many args (non-variadic)', () => { + const def = makeDef({ parameterCount: 2, requiredParameterCount: 2 }); + expect(cArityCompatibility(def, makeCallsite(5))).toBe('incompatible'); + }); + + it('returns compatible for variadic with enough args', () => { + const def = makeDef({ + requiredParameterCount: 1, + parameterTypes: ['const char *', '...'], + }); + expect(cArityCompatibility(def, makeCallsite(3))).toBe('compatible'); + }); + + it('returns unknown when no arity info on def', () => { + const def = makeDef({}); + expect(cArityCompatibility(def, makeCallsite(2))).toBe('unknown'); + }); + + it('returns unknown for negative callsite arity', () => { + const def = makeDef({ parameterCount: 2, requiredParameterCount: 2 }); + expect(cArityCompatibility(def, makeCallsite(-1))).toBe('unknown'); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/c/c-captures.test.ts b/gitnexus/test/unit/scope-resolution/c/c-captures.test.ts new file mode 100644 index 000000000..68c9ef22b --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/c/c-captures.test.ts @@ -0,0 +1,355 @@ +/** + * Unit tests for C scope query + captures orchestrator. + * + * Pins the capture-tag vocabulary + range shape for every construct + * the scope-resolution pipeline reads. Runs against tree-sitter-c + * so it catches grammar drift before the integration parity gate does. + */ + +import { describe, it, expect, beforeEach } from 'vitest'; +import { emitCScopeCaptures } from '../../../../src/core/ingestion/languages/c/captures.js'; +import { + clearStaticNames, + isStaticName, +} from '../../../../src/core/ingestion/languages/c/static-linkage.js'; + +function tagsFor(src: string, filePath = 'test.c'): string[][] { + const matches = emitCScopeCaptures(src, filePath); + return matches.map((m) => Object.keys(m).sort()); +} + +function findMatch(src: string, predicate: (tags: string[]) => boolean, filePath = 'test.c') { + const matches = emitCScopeCaptures(src, filePath); + return matches.find((m) => predicate(Object.keys(m))); +} + +function allMatches(src: string, predicate: (tags: string[]) => boolean, filePath = 'test.c') { + const matches = emitCScopeCaptures(src, filePath); + return matches.filter((m) => predicate(Object.keys(m))); +} + +describe('emitCScopeCaptures — scopes', () => { + it('captures translation_unit as @scope.module', () => { + const all = tagsFor('int x = 1;'); + expect(all.some((t) => t.includes('@scope.module'))).toBe(true); + }); + + it('captures struct_specifier as @scope.class', () => { + const all = tagsFor('struct Point { int x; int y; };'); + expect(all.some((t) => t.includes('@scope.class'))).toBe(true); + }); + + it('captures union_specifier as @scope.class', () => { + const all = tagsFor('union Data { int i; float f; };'); + expect(all.some((t) => t.includes('@scope.class'))).toBe(true); + }); + + it('captures function_definition as @scope.function', () => { + const all = tagsFor('void foo(void) { }'); + expect(all.some((t) => t.includes('@scope.function'))).toBe(true); + }); + + it('captures block-level scopes (if, for, while, do, switch, case)', () => { + const src = ` + void f(void) { + if (1) { } + for (;;) { } + while (1) { } + do { } while (0); + switch (0) { case 0: break; } + } + `; + const all = tagsFor(src); + const blocks = all.filter((t) => t.includes('@scope.block')); + // compound_statement + if + for + while + do + switch + case = at least 6 blocks + expect(blocks.length).toBeGreaterThanOrEqual(6); + }); +}); + +describe('emitCScopeCaptures — struct declarations', () => { + it('captures named struct with @declaration.struct', () => { + const m = findMatch('struct User { int age; };', (t) => t.includes('@declaration.struct')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('User'); + }); + + it('captures typedef struct with @declaration.struct (not typedef)', () => { + const m = findMatch('typedef struct { int age; } User;', (t) => + t.includes('@declaration.struct'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('User'); + }); + + it('suppresses @declaration.typedef when struct already captured same range', () => { + const matches = emitCScopeCaptures('typedef struct { int age; } User;', 'test.c'); + const typedefs = matches.filter((m) => '@declaration.typedef' in m); + expect(typedefs).toHaveLength(0); + }); +}); + +describe('emitCScopeCaptures — union declarations', () => { + it('captures named union with @declaration.union', () => { + const m = findMatch('union Data { int i; float f; };', (t) => t.includes('@declaration.union')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Data'); + }); + + it('captures typedef union with @declaration.union', () => { + const m = findMatch('typedef union { int i; float f; } Value;', (t) => + t.includes('@declaration.union'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Value'); + }); +}); + +describe('emitCScopeCaptures — enum declarations', () => { + it('captures enum with @declaration.enum', () => { + const m = findMatch('enum Color { RED, GREEN, BLUE };', (t) => t.includes('@declaration.enum')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Color'); + }); + + it('captures enum constants as @declaration.const', () => { + const matches = allMatches('enum Color { RED, GREEN, BLUE };', (t) => + t.includes('@declaration.const'), + ); + const names = matches.map((m) => m['@declaration.name'].text); + expect(names).toContain('RED'); + expect(names).toContain('GREEN'); + expect(names).toContain('BLUE'); + }); +}); + +describe('emitCScopeCaptures — function declarations', () => { + it('captures function definition with @declaration.function', () => { + const m = findMatch('int add(int a, int b) { return a + b; }', (t) => + t.includes('@declaration.function'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('add'); + }); + + it('captures function prototype (declaration) with @declaration.function', () => { + const m = findMatch('int add(int a, int b);', (t) => t.includes('@declaration.function')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('add'); + }); + + it('captures pointer-return function definition', () => { + const m = findMatch('int *create(void) { return 0; }', (t) => + t.includes('@declaration.function'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('create'); + }); + + it('captures pointer-return function prototype', () => { + const m = findMatch('char *get_name(void);', (t) => t.includes('@declaration.function')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('get_name'); + }); +}); + +describe('emitCScopeCaptures — other declarations', () => { + it('captures typedef as @declaration.typedef', () => { + const m = findMatch('typedef int MyInt;', (t) => t.includes('@declaration.typedef')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('MyInt'); + }); + + it('captures function pointer typedef as @declaration.typedef', () => { + const m = findMatch('typedef void (*callback)(int, int);', (t) => + t.includes('@declaration.typedef'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('callback'); + }); + + it('captures struct field as @declaration.field', () => { + const m = findMatch('struct P { int x; };', (t) => t.includes('@declaration.field')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('x'); + }); + + it('captures pointer struct field as @declaration.field', () => { + const m = findMatch('struct N { struct N *next; };', (t) => t.includes('@declaration.field')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('next'); + }); + + it('captures variable with initializer as @declaration.variable', () => { + const m = findMatch('int x = 42;', (t) => t.includes('@declaration.variable')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('x'); + }); + + it('captures macro as @declaration.macro', () => { + const m = findMatch('#define MAX 100', (t) => t.includes('@declaration.macro')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('MAX'); + }); + + it('captures function-like macro as @declaration.macro', () => { + const m = findMatch('#define SQUARE(x) ((x) * (x))', (t) => t.includes('@declaration.macro')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('SQUARE'); + }); +}); + +describe('emitCScopeCaptures — imports', () => { + it('captures local #include as @import.statement with source', () => { + const m = findMatch('#include "header.h"', (t) => t.includes('@import.statement')); + expect(m).toBeDefined(); + expect(m!['@import.source'].text).toBe('header.h'); + expect(m!['@import.kind'].text).toBe('wildcard'); + }); + + it('captures system #include with @import.system tag', () => { + const m = findMatch('#include ', (t) => t.includes('@import.statement')); + expect(m).toBeDefined(); + expect(m!['@import.system']).toBeDefined(); + }); + + it('captures nested path includes', () => { + const m = findMatch('#include "utils/helpers.h"', (t) => t.includes('@import.statement')); + expect(m).toBeDefined(); + expect(m!['@import.source'].text).toBe('utils/helpers.h'); + }); +}); + +describe('emitCScopeCaptures — references', () => { + it('captures free call invocations', () => { + const m = findMatch('void f(void) { foo(); }', (t) => t.includes('@reference.call.free')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('foo'); + }); + + it('captures member call via pointer (ptr->func())', () => { + const m = findMatch('void f(struct S *s) { s->method(); }', (t) => + t.includes('@reference.call.member'), + ); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('method'); + }); + + it('captures field reads', () => { + const m = findMatch('void f(struct S *s) { int x = s->field; }', (t) => + t.includes('@reference.read'), + ); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('field'); + }); + + it('captures field writes (assignment)', () => { + const m = findMatch('void f(struct S *s) { s->field = 1; }', (t) => + t.includes('@reference.write'), + ); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('field'); + }); +}); + +describe('emitCScopeCaptures — type bindings', () => { + it('captures parameter type annotations', () => { + const m = findMatch('void f(int x) { }', (t) => t.includes('@type-binding.parameter')); + expect(m).toBeDefined(); + expect(m!['@type-binding.name'].text).toBe('x'); + }); + + it('captures variable type bindings', () => { + const m = findMatch('void f(void) { int x = 1; }', (t) => + t.includes('@type-binding.assignment'), + ); + expect(m).toBeDefined(); + expect(m!['@type-binding.name'].text).toBe('x'); + }); +}); + +describe('emitCScopeCaptures — arity metadata', () => { + it('synthesizes parameter-count on function definitions', () => { + const m = findMatch('int add(int a, int b) { return a + b; }', (t) => + t.includes('@declaration.parameter-count'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.parameter-count'].text).toBe('2'); + }); + + it('synthesizes parameter-types on function definitions', () => { + const m = findMatch('int add(int a, float b) { return 0; }', (t) => + t.includes('@declaration.parameter-types'), + ); + expect(m).toBeDefined(); + const types = JSON.parse(m!['@declaration.parameter-types'].text); + expect(types).toEqual(['int', 'float']); + }); + + it('(void) parameter list yields zero parameters', () => { + const m = findMatch('void f(void) { }', (t) => t.includes('@declaration.function')); + expect(m).toBeDefined(); + expect(m!['@declaration.parameter-count'].text).toBe('0'); + expect(m!['@declaration.required-parameter-count'].text).toBe('0'); + }); + + it('variadic function has undefined parameter-count but defined required-parameter-count', () => { + const m = findMatch('int printf(const char *fmt, ...) { return 0; }', (t) => + t.includes('@declaration.function'), + ); + expect(m).toBeDefined(); + // variadic → parameterCount is undefined (not emitted) + expect(m!['@declaration.parameter-count']).toBeUndefined(); + expect(m!['@declaration.required-parameter-count'].text).toBe('1'); + }); + + it('synthesizes arity on call references', () => { + const m = findMatch( + 'void f(void) { add(1, 2); }', + (t) => t.includes('@reference.call.free') && t.includes('@reference.arity'), + ); + expect(m).toBeDefined(); + expect(m!['@reference.arity'].text).toBe('2'); + }); + + it('zero-argument call has arity 0', () => { + const m = findMatch( + 'void f(void) { init(); }', + (t) => t.includes('@reference.call.free') && t.includes('@reference.arity'), + ); + expect(m).toBeDefined(); + expect(m!['@reference.arity'].text).toBe('0'); + }); +}); + +describe('emitCScopeCaptures — static storage class', () => { + beforeEach(() => { + clearStaticNames(); + }); + + it('marks static function definitions as file-local', () => { + emitCScopeCaptures('static int helper(void) { return 0; }', 'a.c'); + expect(isStaticName('a.c', 'helper')).toBe(true); + }); + + it('does not mark non-static function definitions as file-local', () => { + emitCScopeCaptures('int helper(void) { return 0; }', 'a.c'); + expect(isStaticName('a.c', 'helper')).toBe(false); + }); + + it('marks static function prototypes as file-local', () => { + emitCScopeCaptures('static int helper(int x);', 'a.c'); + expect(isStaticName('a.c', 'helper')).toBe(true); + }); + + it('static functions are scoped to their file', () => { + emitCScopeCaptures('static int helper(void) { return 0; }', 'a.c'); + emitCScopeCaptures('int helper(void) { return 1; }', 'b.c'); + expect(isStaticName('a.c', 'helper')).toBe(true); + expect(isStaticName('b.c', 'helper')).toBe(false); + }); + + it('static pointer-return functions are detected', () => { + emitCScopeCaptures('static char *get_buffer(void) { return 0; }', 'a.c'); + expect(isStaticName('a.c', 'get_buffer')).toBe(true); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/c/c-header-scan.test.ts b/gitnexus/test/unit/scope-resolution/c/c-header-scan.test.ts new file mode 100644 index 000000000..1543db006 --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/c/c-header-scan.test.ts @@ -0,0 +1,103 @@ +/** + * Unit tests for C header scanning — specifically the skip-list + * for build output directories. + */ + +import { describe, it, expect, beforeEach, afterEach } from 'vitest'; +import { mkdirSync, writeFileSync, rmSync } from 'fs'; +import { join } from 'path'; +import { scanHeaderFiles } from '../../../../src/core/ingestion/languages/c/header-scan.js'; + +const TMP = join(__dirname, '__header_scan_tmp__'); + +function touch(rel: string): void { + const full = join(TMP, rel); + mkdirSync(join(full, '..'), { recursive: true }); + writeFileSync(full, ''); +} + +beforeEach(() => { + mkdirSync(TMP, { recursive: true }); +}); + +afterEach(() => { + rmSync(TMP, { recursive: true, force: true }); +}); + +describe('scanHeaderFiles — build-directory skip list', () => { + it('finds .h files in source directories', () => { + touch('src/foo.h'); + touch('include/bar.h'); + const headers = scanHeaderFiles(TMP); + expect(headers).toContain('src/foo.h'); + expect(headers).toContain('include/bar.h'); + }); + + it('skips node_modules', () => { + touch('node_modules/dep/header.h'); + touch('src/real.h'); + const headers = scanHeaderFiles(TMP); + expect(headers).not.toContain('node_modules/dep/header.h'); + expect(headers).toContain('src/real.h'); + }); + + it('skips .git directory', () => { + touch('.git/refs/header.h'); + const headers = scanHeaderFiles(TMP); + expect(headers.size).toBe(0); + }); + + it('skips vendor directory', () => { + touch('vendor/lib/header.h'); + const headers = scanHeaderFiles(TMP); + expect(headers.size).toBe(0); + }); + + it('skips dist directory', () => { + touch('dist/generated.h'); + touch('src/real.h'); + const headers = scanHeaderFiles(TMP); + expect(headers).not.toContain('dist/generated.h'); + expect(headers).toContain('src/real.h'); + }); + + it('skips build directory', () => { + touch('build/config.h'); + const headers = scanHeaderFiles(TMP); + expect(headers).not.toContain('build/config.h'); + }); + + it('skips out directory', () => { + touch('out/gen/auto.h'); + const headers = scanHeaderFiles(TMP); + expect(headers.size).toBe(0); + }); + + it('skips target directory', () => { + touch('target/release/bindings.h'); + const headers = scanHeaderFiles(TMP); + expect(headers.size).toBe(0); + }); + + it('skips _build directory', () => { + touch('_build/default/lib.h'); + const headers = scanHeaderFiles(TMP); + expect(headers.size).toBe(0); + }); + + it('skips .next directory', () => { + touch('.next/cache/header.h'); + const headers = scanHeaderFiles(TMP); + expect(headers.size).toBe(0); + }); + + it('skips cmake-build-* directories', () => { + touch('cmake-build-debug/generated.h'); + touch('cmake-build-release/generated.h'); + touch('src/real.h'); + const headers = scanHeaderFiles(TMP); + expect(headers).not.toContain('cmake-build-debug/generated.h'); + expect(headers).not.toContain('cmake-build-release/generated.h'); + expect(headers).toContain('src/real.h'); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/c/c-imports.test.ts b/gitnexus/test/unit/scope-resolution/c/c-imports.test.ts new file mode 100644 index 000000000..549e651bb --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/c/c-imports.test.ts @@ -0,0 +1,166 @@ +/** + * Unit tests for C import decomposition, interpretation, and target resolution. + */ + +import { describe, it, expect } from 'vitest'; +import { getCParser } from '../../../../src/core/ingestion/languages/c/query.js'; +import { splitCInclude } from '../../../../src/core/ingestion/languages/c/import-decomposer.js'; +import { interpretCImport } from '../../../../src/core/ingestion/languages/c/interpret.js'; +import { resolveCImportTarget } from '../../../../src/core/ingestion/languages/c/import-target.js'; +import type { SyntaxNode } from '../../../../src/core/ingestion/utils/ast-helpers.js'; + +function parseIncludeNode(src: string): SyntaxNode | null { + const tree = getCParser().parse(src); + for (let i = 0; i < tree.rootNode.namedChildCount; i++) { + const child = tree.rootNode.namedChild(i); + if (child?.type === 'preproc_include') return child as SyntaxNode; + } + return null; +} + +function capt(name: string, text: string) { + return { name, text, range: { startLine: 1, startCol: 1, endLine: 1, endCol: 1 } }; +} + +describe('C import decomposition (splitCInclude)', () => { + it('decomposes local include "#include \\"foo.h\\""', () => { + const node = parseIncludeNode('#include "foo.h"'); + expect(node).not.toBeNull(); + const match = splitCInclude(node!); + expect(match).not.toBeNull(); + expect(match!['@import.source'].text).toBe('foo.h'); + expect(match!['@import.kind'].text).toBe('wildcard'); + expect(match!['@import.system']).toBeUndefined(); + }); + + it('decomposes system include "#include "', () => { + const node = parseIncludeNode('#include '); + expect(node).not.toBeNull(); + const match = splitCInclude(node!); + expect(match).not.toBeNull(); + expect(match!['@import.source'].text).toBe('stdio.h'); + expect(match!['@import.system']).toBeDefined(); + }); + + it('decomposes nested path include', () => { + const node = parseIncludeNode('#include "utils/helpers.h"'); + expect(node).not.toBeNull(); + const match = splitCInclude(node!); + expect(match).not.toBeNull(); + expect(match!['@import.source'].text).toBe('utils/helpers.h'); + }); +}); + +describe('C import interpretation (interpretCImport)', () => { + it('interprets local include as wildcard import', () => { + const result = interpretCImport({ + '@import.kind': capt('@import.kind', 'wildcard'), + '@import.source': capt('@import.source', 'header.h'), + }); + expect(result).toEqual({ kind: 'wildcard', targetRaw: 'header.h' }); + }); + + it('returns null for system headers', () => { + const result = interpretCImport({ + '@import.kind': capt('@import.kind', 'wildcard'), + '@import.source': capt('@import.source', 'stdio.h'), + '@import.system': capt('@import.system', 'true'), + }); + expect(result).toBeNull(); + }); + + it('returns null when @import.source is missing', () => { + const result = interpretCImport({ + '@import.kind': capt('@import.kind', 'wildcard'), + }); + expect(result).toBeNull(); + }); +}); + +describe('C import target resolution (resolveCImportTarget)', () => { + it('resolves exact match', () => { + const result = resolveCImportTarget('foo.h', 'main.c', new Set(['foo.h', 'bar.h'])); + expect(result).toBe('foo.h'); + }); + + it('resolves suffix match to shortest path', () => { + const result = resolveCImportTarget( + 'foo.h', + 'main.c', + new Set(['src/include/foo.h', 'include/foo.h', 'other/bar.h']), + ); + expect(result).toBe('include/foo.h'); + }); + + it('resolves nested include path with directory components', () => { + const result = resolveCImportTarget( + 'utils/helpers.h', + 'main.c', + new Set(['src/utils/helpers.h', 'lib/utils/helpers.h']), + ); + // Both have same depth (3 components), so lexicographic tiebreak picks lib/ + expect(result).toBe('lib/utils/helpers.h'); + }); + + it('returns null for empty target', () => { + expect(resolveCImportTarget('', 'main.c', new Set(['foo.h']))).toBeNull(); + }); + + it('returns null when no match found', () => { + expect(resolveCImportTarget('missing.h', 'main.c', new Set(['foo.h']))).toBeNull(); + }); + + it('is deterministic on depth ties — lexicographic tiebreak', () => { + const files = new Set(['test/util/foo.h', 'src/util/foo.h']); + const result1 = resolveCImportTarget('foo.h', 'main.c', files); + const result2 = resolveCImportTarget('foo.h', 'main.c', files); + expect(result1).toBe(result2); + // Lexicographic: src/util/foo.h < test/util/foo.h + expect(result1).toBe('src/util/foo.h'); + }); + + it('prefers shallower path over lexicographic order', () => { + const result = resolveCImportTarget('foo.h', 'main.c', new Set(['a/b/c/foo.h', 'z/foo.h'])); + expect(result).toBe('z/foo.h'); + }); + + it('handles backslash paths (Windows)', () => { + const result = resolveCImportTarget('foo.h', 'main.c', new Set(['include\\foo.h'])); + expect(result).toBe('include\\foo.h'); + }); + + it('prefers same-directory sibling over deeper suffix match', () => { + // src/foo.c includes "bar.h" — src/bar.h should win over include/bar.h + const result = resolveCImportTarget( + 'bar.h', + 'src/foo.c', + new Set(['include/bar.h', 'src/bar.h']), + ); + expect(result).toBe('src/bar.h'); + }); + + it('prefers same-directory sibling over shallower suffix match', () => { + // deep/nested/main.c includes "foo.h" — deep/nested/foo.h wins over foo.h + const result = resolveCImportTarget( + 'foo.h', + 'deep/nested/main.c', + new Set(['foo.h', 'deep/nested/foo.h']), + ); + expect(result).toBe('deep/nested/foo.h'); + }); + + it('falls back to suffix match when no same-directory sibling exists', () => { + const result = resolveCImportTarget('missing.h', 'src/foo.c', new Set(['lib/missing.h'])); + expect(result).toBe('lib/missing.h'); + }); + + it('same-directory sibling with nested target path', () => { + // src/foo.c includes "sub/bar.h" — src/sub/bar.h should win + const result = resolveCImportTarget( + 'sub/bar.h', + 'src/foo.c', + new Set(['other/sub/bar.h', 'src/sub/bar.h']), + ); + expect(result).toBe('src/sub/bar.h'); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/cpp/cpp-arity.test.ts b/gitnexus/test/unit/scope-resolution/cpp/cpp-arity.test.ts new file mode 100644 index 000000000..a89a3167d --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/cpp/cpp-arity.test.ts @@ -0,0 +1,168 @@ +/** + * Unit tests for C++ arity compatibility and metadata. + */ + +import { describe, it, expect } from 'vitest'; +import { cppArityCompatibility } from '../../../../src/core/ingestion/languages/cpp/arity.js'; +import { + computeCppDeclarationArity, + computeCppCallArity, +} from '../../../../src/core/ingestion/languages/cpp/arity-metadata.js'; +import { getCppParser } from '../../../../src/core/ingestion/languages/cpp/query.js'; +import type { SyntaxNode } from '../../../../src/core/ingestion/utils/ast-helpers.js'; +import type { SymbolDefinition, Callsite } from 'gitnexus-shared'; + +function parseFuncDef(src: string): SyntaxNode | null { + const tree = getCppParser().parse(src); + for (let i = 0; i < tree.rootNode.namedChildCount; i++) { + const child = tree.rootNode.namedChild(i); + if (child?.type === 'function_definition') return child as SyntaxNode; + } + return null; +} + +function parseCallExpr(src: string): SyntaxNode | null { + const tree = getCppParser().parse(src); + const walk = (node: SyntaxNode): SyntaxNode | null => { + if (node.type === 'call_expression') return node; + for (let i = 0; i < node.namedChildCount; i++) { + const found = walk(node.namedChild(i) as SyntaxNode); + if (found) return found; + } + return null; + }; + return walk(tree.rootNode as SyntaxNode); +} + +function mkDef(overrides: Partial = {}): SymbolDefinition { + return { + nodeId: 'test-def', + qualifiedName: 'test', + filePath: 'test.cpp', + type: 'Function', + ...overrides, + } as SymbolDefinition; +} + +function mkCallsite(arity: number): Callsite { + return { arity } as Callsite; +} + +// ── Declaration arity ─────────────────────────────────────────────────────── + +describe('computeCppDeclarationArity', () => { + it('computes arity for zero-parameter function', () => { + const node = parseFuncDef('void foo() {}'); + expect(node).not.toBeNull(); + const arity = computeCppDeclarationArity(node!); + expect(arity.parameterCount).toBe(0); + expect(arity.requiredParameterCount).toBe(0); + }); + + it('computes arity for (void) parameter', () => { + const node = parseFuncDef('void foo(void) {}'); + expect(node).not.toBeNull(); + const arity = computeCppDeclarationArity(node!); + expect(arity.parameterCount).toBe(0); + expect(arity.requiredParameterCount).toBe(0); + }); + + it('computes arity for multiple parameters', () => { + const node = parseFuncDef('void foo(int x, int y, int z) {}'); + expect(node).not.toBeNull(); + const arity = computeCppDeclarationArity(node!); + expect(arity.parameterCount).toBe(3); + expect(arity.requiredParameterCount).toBe(3); + }); + + it('computes arity with default parameters', () => { + const node = parseFuncDef('void foo(int x, int y = 5, int z = 10) {}'); + expect(node).not.toBeNull(); + const arity = computeCppDeclarationArity(node!); + expect(arity.parameterCount).toBe(3); + expect(arity.requiredParameterCount).toBe(1); + }); + + it('detects variadic function', () => { + const node = parseFuncDef('void foo(int x, ...) {}'); + expect(node).not.toBeNull(); + const arity = computeCppDeclarationArity(node!); + expect(arity.parameterCount).toBeUndefined(); // variadic → undefined max + expect(arity.requiredParameterCount).toBe(1); + expect(arity.parameterTypes).toContain('...'); + }); + + it('handles pointer return type', () => { + const node = parseFuncDef('int* create(int size) {}'); + expect(node).not.toBeNull(); + const arity = computeCppDeclarationArity(node!); + expect(arity.parameterCount).toBe(1); + }); +}); + +// ── Call-site arity ───────────────────────────────────────────────────────── + +describe('computeCppCallArity', () => { + it('computes arity for no-argument call', () => { + const node = parseCallExpr('void f() { foo(); }'); + expect(node).not.toBeNull(); + expect(computeCppCallArity(node!)).toBe(0); + }); + + it('computes arity for multi-argument call', () => { + const node = parseCallExpr('void f() { foo(1, 2, 3); }'); + expect(node).not.toBeNull(); + expect(computeCppCallArity(node!)).toBe(3); + }); + + it('computes arity for single-argument call', () => { + const node = parseCallExpr('void f() { foo(42); }'); + expect(node).not.toBeNull(); + expect(computeCppCallArity(node!)).toBe(1); + }); +}); + +// ── Arity compatibility ───────────────────────────────────────────────────── + +describe('cppArityCompatibility', () => { + it('returns compatible for exact match', () => { + const def = mkDef({ parameterCount: 2, requiredParameterCount: 2 }); + expect(cppArityCompatibility(def, mkCallsite(2))).toBe('compatible'); + }); + + it('returns compatible when call uses default params', () => { + const def = mkDef({ parameterCount: 3, requiredParameterCount: 1 }); + expect(cppArityCompatibility(def, mkCallsite(1))).toBe('compatible'); + expect(cppArityCompatibility(def, mkCallsite(2))).toBe('compatible'); + expect(cppArityCompatibility(def, mkCallsite(3))).toBe('compatible'); + }); + + it('returns incompatible for too few args', () => { + const def = mkDef({ parameterCount: 3, requiredParameterCount: 2 }); + expect(cppArityCompatibility(def, mkCallsite(1))).toBe('incompatible'); + }); + + it('returns incompatible for too many args (non-variadic)', () => { + const def = mkDef({ parameterCount: 2, requiredParameterCount: 2 }); + expect(cppArityCompatibility(def, mkCallsite(5))).toBe('incompatible'); + }); + + it('returns compatible for variadic with extra args', () => { + const def = mkDef({ + parameterCount: undefined, + requiredParameterCount: 1, + parameterTypes: ['int', '...'], + }); + expect(cppArityCompatibility(def, mkCallsite(5))).toBe('compatible'); + }); + + it('returns unknown when no metadata', () => { + const def = mkDef({}); + expect(cppArityCompatibility(def, mkCallsite(2))).toBe('unknown'); + }); + + it('returns unknown for negative arity', () => { + const def = mkDef({ parameterCount: 2, requiredParameterCount: 2 }); + expect(cppArityCompatibility(def, mkCallsite(-1))).toBe('unknown'); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/cpp/cpp-captures.test.ts b/gitnexus/test/unit/scope-resolution/cpp/cpp-captures.test.ts new file mode 100644 index 000000000..8e000261c --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/cpp/cpp-captures.test.ts @@ -0,0 +1,426 @@ +/** + * Unit tests for C++ scope query + captures orchestrator. + * + * Pins the capture-tag vocabulary + range shape for every construct + * the scope-resolution pipeline reads. Runs against tree-sitter-cpp. + */ + +import { describe, it, expect, beforeEach } from 'vitest'; +import { emitCppScopeCaptures } from '../../../../src/core/ingestion/languages/cpp/captures.js'; +import { + clearFileLocalNames, + isFileLocal, +} from '../../../../src/core/ingestion/languages/cpp/file-local-linkage.js'; + +function tagsFor(src: string, filePath = 'test.cpp'): string[][] { + const matches = emitCppScopeCaptures(src, filePath); + return matches.map((m) => Object.keys(m).sort()); +} + +function findMatch(src: string, predicate: (tags: string[]) => boolean, filePath = 'test.cpp') { + const matches = emitCppScopeCaptures(src, filePath); + return matches.find((m) => predicate(Object.keys(m))); +} + +function allMatches(src: string, predicate: (tags: string[]) => boolean, filePath = 'test.cpp') { + const matches = emitCppScopeCaptures(src, filePath); + return matches.filter((m) => predicate(Object.keys(m))); +} + +// ── Scopes ────────────────────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — scopes', () => { + it('captures translation_unit as @scope.module', () => { + const all = tagsFor('int x = 1;'); + expect(all.some((t) => t.includes('@scope.module'))).toBe(true); + }); + + it('captures class_specifier as @scope.class', () => { + const all = tagsFor('class Foo { int x; };'); + expect(all.some((t) => t.includes('@scope.class'))).toBe(true); + }); + + it('captures struct_specifier as @scope.class', () => { + const all = tagsFor('struct Point { int x; int y; };'); + expect(all.some((t) => t.includes('@scope.class'))).toBe(true); + }); + + it('captures namespace_definition as @scope.namespace', () => { + const all = tagsFor('namespace foo { int x; }'); + expect(all.some((t) => t.includes('@scope.namespace'))).toBe(true); + }); + + it('captures function_definition as @scope.function', () => { + const all = tagsFor('void foo() { }'); + expect(all.some((t) => t.includes('@scope.function'))).toBe(true); + }); + + it('captures lambda_expression as @scope.function', () => { + const all = tagsFor('auto f = [](int x) { return x; };'); + expect(all.some((t) => t.includes('@scope.function'))).toBe(true); + }); + + it('captures block-level scopes (if, for, while, do, switch, case, try, catch)', () => { + const src = ` + void f() { + if (true) { } + for (int i = 0; i < 10; i++) { } + while (true) { } + do { } while (false); + switch (0) { case 0: break; } + try { } catch (...) { } + } + `; + const all = tagsFor(src); + const blocks = all.filter((t) => t.includes('@scope.block')); + expect(blocks.length).toBeGreaterThanOrEqual(6); + }); + + it('captures for_range_loop as @scope.block', () => { + const src = ` + #include + void f() { + std::vector v; + for (auto& x : v) { } + } + `; + const all = tagsFor(src); + const blocks = all.filter((t) => t.includes('@scope.block')); + expect(blocks.length).toBeGreaterThanOrEqual(1); + }); +}); + +// ── Declarations — classes / structs ──────────────────────────────────────── + +describe('emitCppScopeCaptures — class declarations', () => { + it('captures named class with @declaration.class', () => { + const m = findMatch('class Foo { int x; };', (t) => t.includes('@declaration.class')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Foo'); + }); + + it('captures named struct with @declaration.struct', () => { + const m = findMatch('struct Point { int x; int y; };', (t) => + t.includes('@declaration.struct'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Point'); + }); + + it('captures template class with @declaration.class', () => { + const m = findMatch('template class Container { T val; };', (t) => + t.includes('@declaration.class'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Container'); + }); +}); + +// ── Declarations — namespaces ─────────────────────────────────────────────── + +describe('emitCppScopeCaptures — namespace declarations', () => { + it('captures named namespace with @declaration.namespace', () => { + const m = findMatch('namespace foo { int x; }', (t) => t.includes('@declaration.namespace')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('foo'); + }); + + it('anonymous namespace has no @declaration.namespace (only @scope.namespace)', () => { + const matches = allMatches('namespace { int x; }', (t) => t.includes('@declaration.namespace')); + // Anonymous namespace should NOT produce a @declaration.namespace + expect(matches.length).toBe(0); + }); +}); + +// ── Declarations — functions / methods ────────────────────────────────────── + +describe('emitCppScopeCaptures — function declarations', () => { + it('captures function definition with @declaration.function', () => { + const m = findMatch('void foo() {}', (t) => t.includes('@declaration.function')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('foo'); + }); + + it('captures function with pointer return as @declaration.function', () => { + const m = findMatch('int* create() {}', (t) => t.includes('@declaration.function')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('create'); + }); + + it('captures out-of-class method (qualified_identifier) as @declaration.method', () => { + const m = findMatch('void Foo::bar() {}', (t) => t.includes('@declaration.method')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('bar'); + }); + + it('captures destructor as @declaration.method', () => { + const m = findMatch('void Foo::~Foo() {}', (t) => t.includes('@declaration.method')); + expect(m).toBeDefined(); + // destructor_name includes the ~ + expect(m!['@declaration.name'].text).toContain('~'); + }); + + it('captures inline method (field_identifier) as @declaration.method', () => { + const src = 'class Foo { void bar() {} };'; + const m = findMatch(src, (t) => t.includes('@declaration.method')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('bar'); + }); + + it('captures function prototype as @declaration.function', () => { + const m = findMatch('void foo();', (t) => t.includes('@declaration.function')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('foo'); + }); + + it('captures template function as @declaration.function', () => { + const m = findMatch('template void foo(T x) {}', (t) => + t.includes('@declaration.function'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('foo'); + }); +}); + +// ── Declarations — fields ─────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — field declarations', () => { + it('captures plain field', () => { + const m = findMatch('class Foo { int val; };', (t) => t.includes('@declaration.field')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('val'); + }); + + it('captures pointer field', () => { + const m = findMatch('class Foo { int* ptr; };', (t) => t.includes('@declaration.field')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('ptr'); + }); + + it('captures reference field', () => { + const m = findMatch('class Foo { int& ref; };', (t) => t.includes('@declaration.field')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('ref'); + }); +}); + +// ── Declarations — variables ──────────────────────────────────────────────── + +describe('emitCppScopeCaptures — variable declarations', () => { + it('captures variable with initializer', () => { + const m = findMatch('int x = 42;', (t) => t.includes('@declaration.variable')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('x'); + }); +}); + +// ── Declarations — enums ──────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — enum declarations', () => { + it('captures enum with @declaration.enum', () => { + const m = findMatch('enum Color { Red, Green, Blue };', (t) => t.includes('@declaration.enum')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('Color'); + }); + + it('captures enum constants with @declaration.const', () => { + const matches = allMatches('enum Color { Red, Green, Blue };', (t) => + t.includes('@declaration.const'), + ); + expect(matches.length).toBe(3); + const names = matches.map((m) => m['@declaration.name'].text).sort(); + expect(names).toEqual(['Blue', 'Green', 'Red']); + }); +}); + +// ── Declarations — typedef / alias ────────────────────────────────────────── + +describe('emitCppScopeCaptures — typedef/alias declarations', () => { + it('captures typedef as @declaration.typedef', () => { + const m = findMatch('typedef int MyInt;', (t) => t.includes('@declaration.typedef')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('MyInt'); + }); + + it('captures using alias as @declaration.typedef', () => { + const m = findMatch('using MyInt = int;', (t) => t.includes('@declaration.typedef')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('MyInt'); + }); +}); + +// ── Declarations — macros ─────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — macro declarations', () => { + it('captures #define as @declaration.macro', () => { + const m = findMatch('#define MAX 100', (t) => t.includes('@declaration.macro')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('MAX'); + }); + + it('captures #define function as @declaration.macro', () => { + const m = findMatch('#define ADD(a,b) ((a)+(b))', (t) => t.includes('@declaration.macro')); + expect(m).toBeDefined(); + expect(m!['@declaration.name'].text).toBe('ADD'); + }); +}); + +// ── Imports ───────────────────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — imports', () => { + it('captures #include local as wildcard import', () => { + const m = findMatch('#include "foo.h"', (t) => t.includes('@import.source')); + expect(m).toBeDefined(); + expect(m!['@import.source'].text).toBe('foo.h'); + expect(m!['@import.kind'].text).toBe('wildcard'); + expect(m!['@import.system']).toBeUndefined(); + }); + + it('captures #include system with system marker', () => { + const m = findMatch('#include ', (t) => t.includes('@import.source')); + expect(m).toBeDefined(); + expect(m!['@import.source'].text).toBe('iostream'); + expect(m!['@import.system']).toBeDefined(); + }); + + it('captures using namespace as wildcard import', () => { + const m = findMatch('using namespace std;', (t) => t.includes('@import.using-namespace')); + expect(m).toBeDefined(); + expect(m!['@import.source'].text).toBe('std'); + expect(m!['@import.kind'].text).toBe('wildcard'); + }); + + it('captures using declaration as named import', () => { + const m = findMatch('using std::vector;', (t) => t.includes('@import.name')); + expect(m).toBeDefined(); + expect(m!['@import.source'].text).toBe('std'); + expect(m!['@import.name'].text).toBe('vector'); + expect(m!['@import.kind'].text).toBe('named'); + }); +}); + +// ── References ────────────────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — references', () => { + it('captures free call', () => { + const src = 'void f() { foo(); }'; + const m = findMatch(src, (t) => t.includes('@reference.call.free')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('foo'); + }); + + it('captures member call (obj.method())', () => { + const src = 'void f() { obj.method(); }'; + const m = findMatch(src, (t) => t.includes('@reference.call.member')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('method'); + }); + + it('captures member call (ptr->method())', () => { + const src = 'void f() { ptr->method(); }'; + const m = findMatch(src, (t) => t.includes('@reference.call.member')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('method'); + }); + + it('captures qualified call (Namespace::func())', () => { + const src = 'void f() { Foo::bar(); }'; + const m = findMatch(src, (t) => t.includes('@reference.call.qualified')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('bar'); + }); + + it('captures field read', () => { + const src = 'void f() { int x = obj.val; }'; + const m = findMatch(src, (t) => t.includes('@reference.read')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('val'); + }); + + it('captures field write', () => { + const src = 'void f() { obj.val = 42; }'; + const m = findMatch(src, (t) => t.includes('@reference.write')); + expect(m).toBeDefined(); + expect(m!['@reference.name'].text).toBe('val'); + }); +}); + +// ── Type bindings ─────────────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — type bindings', () => { + it('captures parameter type binding', () => { + const src = 'void foo(int x) {}'; + const m = findMatch(src, (t) => t.includes('@type-binding.parameter')); + expect(m).toBeDefined(); + expect(m!['@type-binding.name'].text).toBe('x'); + }); + + it('captures variable type binding', () => { + const src = 'int x = 42;'; + const m = findMatch(src, (t) => t.includes('@type-binding.assignment')); + expect(m).toBeDefined(); + expect(m!['@type-binding.name'].text).toBe('x'); + }); +}); + +// ── Arity enrichment ──────────────────────────────────────────────────────── + +describe('emitCppScopeCaptures — arity enrichment', () => { + it('enriches function declaration with parameter count', () => { + const m = findMatch('void foo(int x, int y) {}', (t) => + t.includes('@declaration.parameter-count'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.parameter-count'].text).toBe('2'); + }); + + it('enriches zero-parameter function', () => { + const m = findMatch('void foo() {}', (t) => t.includes('@declaration.parameter-count')); + expect(m).toBeDefined(); + expect(m!['@declaration.parameter-count'].text).toBe('0'); + }); + + it('detects default parameters (required < total)', () => { + const m = findMatch('void foo(int x, int y = 5) {}', (t) => + t.includes('@declaration.required-parameter-count'), + ); + expect(m).toBeDefined(); + expect(m!['@declaration.required-parameter-count'].text).toBe('1'); + expect(m!['@declaration.parameter-count'].text).toBe('2'); + }); + + it('enriches call reference with arity', () => { + const src = 'void f() { foo(1, 2, 3); }'; + const m = findMatch(src, (t) => t.includes('@reference.arity')); + expect(m).toBeDefined(); + expect(m!['@reference.arity'].text).toBe('3'); + }); +}); + +// ── Static / anonymous namespace detection ────────────────────────────────── + +describe('emitCppScopeCaptures — file-local linkage', () => { + beforeEach(() => { + clearFileLocalNames(); + }); + + it('detects static function as file-local', () => { + emitCppScopeCaptures('static void helper() {}', 'test.cpp'); + expect(isFileLocal('test.cpp', 'helper')).toBe(true); + }); + + it('does not mark non-static function as file-local', () => { + emitCppScopeCaptures('void helper() {}', 'test.cpp'); + expect(isFileLocal('test.cpp', 'helper')).toBe(false); + }); + + it('detects function in anonymous namespace as file-local', () => { + emitCppScopeCaptures('namespace { void helper() {} }', 'test.cpp'); + expect(isFileLocal('test.cpp', 'helper')).toBe(true); + }); + + it('does not mark function in named namespace as file-local', () => { + emitCppScopeCaptures('namespace foo { void helper() {} }', 'test.cpp'); + expect(isFileLocal('test.cpp', 'helper')).toBe(false); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/cpp/cpp-imports.test.ts b/gitnexus/test/unit/scope-resolution/cpp/cpp-imports.test.ts new file mode 100644 index 000000000..6bc6e1b86 --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/cpp/cpp-imports.test.ts @@ -0,0 +1,161 @@ +/** + * Unit tests for C++ import decomposition, interpretation, and target resolution. + */ + +import { describe, it, expect } from 'vitest'; +import { getCppParser } from '../../../../src/core/ingestion/languages/cpp/query.js'; +import { + splitCppInclude, + splitCppUsingDecl, +} from '../../../../src/core/ingestion/languages/cpp/import-decomposer.js'; +import { interpretCppImport } from '../../../../src/core/ingestion/languages/cpp/interpret.js'; +import { resolveCppImportTarget } from '../../../../src/core/ingestion/languages/cpp/import-target.js'; +import type { SyntaxNode } from '../../../../src/core/ingestion/utils/ast-helpers.js'; + +function parseNode(src: string, type: string): SyntaxNode | null { + const tree = getCppParser().parse(src); + for (let i = 0; i < tree.rootNode.namedChildCount; i++) { + const child = tree.rootNode.namedChild(i); + if (child?.type === type) return child as SyntaxNode; + } + return null; +} + +function capt(name: string, text: string) { + return { name, text, range: { startLine: 1, startCol: 1, endLine: 1, endCol: 1 } }; +} + +// ── #include decomposition ────────────────────────────────────────────────── + +describe('C++ include decomposition (splitCppInclude)', () => { + it('decomposes local include "#include \\"foo.h\\""', () => { + const node = parseNode('#include "foo.h"', 'preproc_include'); + expect(node).not.toBeNull(); + const match = splitCppInclude(node!); + expect(match).not.toBeNull(); + expect(match!['@import.source'].text).toBe('foo.h'); + expect(match!['@import.kind'].text).toBe('wildcard'); + expect(match!['@import.system']).toBeUndefined(); + }); + + it('decomposes system include "#include "', () => { + const node = parseNode('#include ', 'preproc_include'); + expect(node).not.toBeNull(); + const match = splitCppInclude(node!); + expect(match).not.toBeNull(); + expect(match!['@import.source'].text).toBe('iostream'); + expect(match!['@import.system']).toBeDefined(); + }); + + it('decomposes C++ header include "#include \\"utils/helpers.hpp\\""', () => { + const node = parseNode('#include "utils/helpers.hpp"', 'preproc_include'); + expect(node).not.toBeNull(); + const match = splitCppInclude(node!); + expect(match).not.toBeNull(); + expect(match!['@import.source'].text).toBe('utils/helpers.hpp'); + }); +}); + +// ── using declaration decomposition ───────────────────────────────────────── + +describe('C++ using declaration decomposition (splitCppUsingDecl)', () => { + it('decomposes "using namespace std;" as wildcard import', () => { + const node = parseNode('using namespace std;', 'using_declaration'); + expect(node).not.toBeNull(); + const match = splitCppUsingDecl(node!); + expect(match).not.toBeNull(); + expect(match!['@import.kind'].text).toBe('wildcard'); + expect(match!['@import.source'].text).toBe('std'); + expect(match!['@import.using-namespace']).toBeDefined(); + }); + + it('decomposes "using std::vector;" as named import', () => { + const node = parseNode('using std::vector;', 'using_declaration'); + expect(node).not.toBeNull(); + const match = splitCppUsingDecl(node!); + expect(match).not.toBeNull(); + expect(match!['@import.kind'].text).toBe('named'); + expect(match!['@import.source'].text).toBe('std'); + expect(match!['@import.name'].text).toBe('vector'); + }); + + it('decomposes nested namespace "using namespace foo::bar;"', () => { + const node = parseNode('using namespace foo::bar;', 'using_declaration'); + expect(node).not.toBeNull(); + const match = splitCppUsingDecl(node!); + expect(match).not.toBeNull(); + expect(match!['@import.kind'].text).toBe('wildcard'); + expect(match!['@import.source'].text).toBe('foo::bar'); + }); +}); + +// ── Import interpretation ─────────────────────────────────────────────────── + +describe('C++ import interpretation (interpretCppImport)', () => { + it('interprets local include as wildcard import', () => { + const result = interpretCppImport({ + '@import.kind': capt('@import.kind', 'wildcard'), + '@import.source': capt('@import.source', 'header.hpp'), + }); + expect(result).toEqual({ kind: 'wildcard', targetRaw: 'header.hpp' }); + }); + + it('returns null for system headers', () => { + const result = interpretCppImport({ + '@import.kind': capt('@import.kind', 'wildcard'), + '@import.source': capt('@import.source', 'iostream'), + '@import.system': capt('@import.system', 'true'), + }); + expect(result).toBeNull(); + }); + + it('interprets named import (using std::vector)', () => { + const result = interpretCppImport({ + '@import.kind': capt('@import.kind', 'named'), + '@import.source': capt('@import.source', 'std'), + '@import.name': capt('@import.name', 'vector'), + }); + expect(result).not.toBeNull(); + expect(result!.kind).toBe('named'); + expect(result!.targetRaw).toBe('std'); + }); + + it('returns null when @import.source is missing', () => { + const result = interpretCppImport({ + '@import.kind': capt('@import.kind', 'wildcard'), + }); + expect(result).toBeNull(); + }); +}); + +// ── Import target resolution ──────────────────────────────────────────────── + +describe('C++ import target resolution (resolveCppImportTarget)', () => { + it('resolves .hpp header', () => { + const result = resolveCppImportTarget('foo.hpp', 'main.cpp', new Set(['foo.hpp', 'bar.cpp'])); + expect(result).toBe('foo.hpp'); + }); + + it('resolves .hxx header', () => { + const result = resolveCppImportTarget('foo.hxx', 'main.cpp', new Set(['foo.hxx'])); + expect(result).toBe('foo.hxx'); + }); + + it('prefers same-directory sibling', () => { + const result = resolveCppImportTarget( + 'bar.hpp', + 'src/foo.cpp', + new Set(['include/bar.hpp', 'src/bar.hpp']), + ); + expect(result).toBe('src/bar.hpp'); + }); + + it('resolves suffix match with depth tiebreak', () => { + const result = resolveCppImportTarget('foo.h', 'main.cpp', new Set(['a/b/c/foo.h', 'z/foo.h'])); + expect(result).toBe('z/foo.h'); + }); + + it('returns null for no match', () => { + expect(resolveCppImportTarget('missing.hpp', 'main.cpp', new Set(['foo.h']))).toBeNull(); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/overload-narrowing.test.ts b/gitnexus/test/unit/scope-resolution/overload-narrowing.test.ts index 810c3a79b..9a14fdddd 100644 --- a/gitnexus/test/unit/scope-resolution/overload-narrowing.test.ts +++ b/gitnexus/test/unit/scope-resolution/overload-narrowing.test.ts @@ -69,11 +69,26 @@ describe('narrowOverloadCandidates — arity filtering', () => { expect(result.map((d) => d.nodeId)).toEqual(['v:1']); }); - it('falls back to the full overload list when arity filter empties it', () => { + it('returns empty when arity filter empties the set AND every candidate had definite bounds', () => { // argCount=5 doesn't match any overload (none variadic, all have max < 5). + // Post-commit af9af4a9 (PR #1497 / U1): the empty result is now authoritative + // because every rejected candidate had defined `parameterCount` / + // `requiredParameterCount`. The old "always fall back to full list" rescue + // was deliberately removed so resolvers actually drop calls that are + // definitively arity-incompatible (e.g., PHP `f(int $req, ...$rest)` + // called with zero args). const result = narrowOverloadCandidates([add1, add2, add3], 5, undefined); - expect(result.map((d) => d.nodeId)).toEqual(['add:1', 'add:2', 'add:3']); + expect(result.map((d) => d.nodeId)).toEqual([]); }); + + // Note: the `anyUnknownBounds ? overloads : []` branch in + // narrowOverloadCandidates is structurally unreachable in this caller's + // shape — a candidate with both `parameterCount` and `requiredParameterCount` + // undefined always passes the arity filter (neither `argCount > max` nor + // `argCount < min` can fire), so `arityMatches.length` is always > 0 + // whenever `anyUnknownBounds` is true. The branch is preserved in the + // source as a defensive guard for future refactors that might add + // additional rejection criteria in the filter. }); describe('narrowOverloadCandidates — type narrowing', () => { diff --git a/gitnexus/test/unit/scope-resolution/pick-implicit-this-overload.test.ts b/gitnexus/test/unit/scope-resolution/pick-implicit-this-overload.test.ts new file mode 100644 index 000000000..26f526382 --- /dev/null +++ b/gitnexus/test/unit/scope-resolution/pick-implicit-this-overload.test.ts @@ -0,0 +1,156 @@ +/** + * Unit tests for `pickImplicitThisOverload` — the implicit-`this` free-call + * resolver in `free-call-fallback.ts`. + * + * Codex PR #1497 review, finding 2: the previous implementation returned + * `candidates[0]` after `narrowOverloadCandidates` regardless of how many + * candidates survived narrowing. When two same-name methods on the same + * class had identical arity and unknown argument types, narrowing left both + * compatible and the resolver emitted a high-confidence CALLS edge whose + * target depended on registration order. The fix tightens the picker to + * require a UNIQUE post-narrowing candidate; otherwise the call is left + * unresolved. + * + * These tests exercise the function via synthetic stubs — no fixtures, no + * pipeline — because the failure shape (two same-arity overloads with + * indistinguishable types) cannot be produced by a PHP integration fixture + * (PHP forbids method overloading) and any C# fixture would entangle this + * unit's contract with the wider C# resolver. + */ + +import { describe, it, expect } from 'vitest'; +import type { Scope, ScopeId, SymbolDefinition } from 'gitnexus-shared'; +import { pickImplicitThisOverload } from '../../../src/core/ingestion/scope-resolution/passes/free-call-fallback.js'; +import type { ScopeResolutionIndexes } from '../../../src/core/ingestion/model/scope-resolution-indexes.js'; +import type { SemanticModel } from '../../../src/core/ingestion/model/semantic-model.js'; +import type { WorkspaceResolutionIndex } from '../../../src/core/ingestion/scope-resolution/workspace-index.js'; + +const CLASS_SCOPE_ID = 'scope:test.cs#1:1-100:1:Class' as ScopeId; +const CLASS_DEF_ID = 'def:test.cs:Foo'; + +const mkMethod = (overrides: Partial & { nodeId: string }): SymbolDefinition => ({ + nodeId: overrides.nodeId, + filePath: 'x.cs', + type: 'Method', + ...overrides, +}); + +const mkClassScope = (): Scope => + ({ + id: CLASS_SCOPE_ID, + parent: null, + kind: 'Class', + range: { startLine: 1, startCol: 1, endLine: 100, endCol: 1 }, + filePath: 'test.cs', + bindings: new Map(), + typeBindings: new Map(), + ownedDefs: [], + }) as unknown as Scope; + +const mkScopes = (scope: Scope): ScopeResolutionIndexes => + ({ + scopeTree: { + getScope: (id: ScopeId) => (id === scope.id ? scope : undefined), + }, + }) as unknown as ScopeResolutionIndexes; + +const mkWorkspaceIndex = (mapping: ReadonlyMap): WorkspaceResolutionIndex => + ({ + classScopeIdToDefId: mapping, + }) as unknown as WorkspaceResolutionIndex; + +const mkModel = ( + overloadsByName: ReadonlyMap, +): SemanticModel => + ({ + methods: { + lookupAllByOwner: (_classDefId: string, name: string) => + overloadsByName.get(name) ?? ([] as readonly SymbolDefinition[]), + }, + }) as unknown as SemanticModel; + +describe('pickImplicitThisOverload — uniqueness guard (Codex #1497 finding 2)', () => { + const site = { + inScope: CLASS_SCOPE_ID, + name: 'save', + arity: 1, + argumentTypes: undefined, + }; + + it('returns the sole overload when only one method exists on the owner', () => { + const sole = mkMethod({ nodeId: 'm:1', parameterCount: 1, requiredParameterCount: 1 }); + const scopes = mkScopes(mkClassScope()); + const workspace = mkWorkspaceIndex(new Map([[CLASS_SCOPE_ID, CLASS_DEF_ID]])); + const model = mkModel(new Map([['save', [sole]]])); + + const result = pickImplicitThisOverload(site, scopes, workspace, model); + + expect(result?.nodeId).toBe('m:1'); + }); + + it('returns the single survivor when narrowing disambiguates by arity', () => { + const save1 = mkMethod({ nodeId: 'm:1', parameterCount: 1, requiredParameterCount: 1 }); + const save2 = mkMethod({ nodeId: 'm:2', parameterCount: 2, requiredParameterCount: 2 }); + const scopes = mkScopes(mkClassScope()); + const workspace = mkWorkspaceIndex(new Map([[CLASS_SCOPE_ID, CLASS_DEF_ID]])); + const model = mkModel(new Map([['save', [save1, save2]]])); + + // site.arity = 1 → only save1 survives narrowing. + const result = pickImplicitThisOverload(site, scopes, workspace, model); + + expect(result?.nodeId).toBe('m:1'); + }); + + it('returns undefined when narrowing leaves two compatible candidates (the bug)', () => { + // Two same-arity, same-required-count overloads with no disambiguating + // parameter-type info on either def. `narrowOverloadCandidates` keeps + // both; pre-fix code returned `candidates[0]` (registration order); + // post-fix code returns undefined. + const save1 = mkMethod({ nodeId: 'm:1', parameterCount: 1, requiredParameterCount: 1 }); + const save2 = mkMethod({ nodeId: 'm:2', parameterCount: 1, requiredParameterCount: 1 }); + const scopes = mkScopes(mkClassScope()); + const workspace = mkWorkspaceIndex(new Map([[CLASS_SCOPE_ID, CLASS_DEF_ID]])); + const model = mkModel(new Map([['save', [save1, save2]]])); + + const result = pickImplicitThisOverload(site, scopes, workspace, model); + + expect(result).toBeUndefined(); + }); + + it('returns undefined when no method on the owner matches the call name', () => { + const scopes = mkScopes(mkClassScope()); + const workspace = mkWorkspaceIndex(new Map([[CLASS_SCOPE_ID, CLASS_DEF_ID]])); + const model = mkModel(new Map()); + + const result = pickImplicitThisOverload(site, scopes, workspace, model); + + expect(result).toBeUndefined(); + }); + + it('returns undefined when the call site is not inside a Class scope', () => { + // Module-scope sites: no enclosing class, so the implicit-this picker + // has nothing to pick from. Different from an empty-narrowing miss. + const moduleScope = { + id: 'scope:test.cs#1:1-100:1:Module' as ScopeId, + parent: null, + kind: 'Module', + range: { startLine: 1, startCol: 1, endLine: 100, endCol: 1 }, + filePath: 'test.cs', + bindings: new Map(), + typeBindings: new Map(), + ownedDefs: [], + } as unknown as Scope; + const scopes = mkScopes(moduleScope); + const workspace = mkWorkspaceIndex(new Map()); + const model = mkModel(new Map()); + + const result = pickImplicitThisOverload( + { ...site, inScope: moduleScope.id }, + scopes, + workspace, + model, + ); + + expect(result).toBeUndefined(); + }); +}); diff --git a/gitnexus/test/unit/scope-resolution/registries.test.ts b/gitnexus/test/unit/scope-resolution/registries.test.ts index b204287b5..2681af69f 100644 --- a/gitnexus/test/unit/scope-resolution/registries.test.ts +++ b/gitnexus/test/unit/scope-resolution/registries.test.ts @@ -250,7 +250,13 @@ describe('Step 5: arity filter', () => { ); }); - it('keeps incompatible candidates when no compatible candidate exists (soft penalty)', () => { + it('drops every candidate when ALL are incompatible AND none unknown (hard rejection)', () => { + // Post-commit af9af4a9 (PR #1497 / U1): the old soft-penalty fallback + // that kept incompatible candidates with `arityMatchIncompatible` + // weight was deliberately removed at this layer too. When every + // candidate is definitively arity-incompatible, the registry returns + // no resolution — matching the PHP variadic case `f(int $req, ...$rest)` + // called with zero args. const save3 = mkDef({ nodeId: 'def:save-three', type: 'Method', @@ -268,8 +274,41 @@ describe('Step 5: arity filter', () => { const results = buildMethodRegistry(ctx).lookup('save', 'scope:m', { callsite: { arity: 1 }, }); - expect(results).toHaveLength(1); - expect(evidenceOfKind(results[0]!, 'arity-match')?.weight).toBe( + expect(results).toHaveLength(0); + }); + + it('keeps incompatible candidates when at least one verdict is unknown (soft penalty)', () => { + // The soft-rescue path is still active when at least one candidate's + // arity verdict is 'unknown' — that signals missing metadata rather + // than a definitive mismatch, so all candidates (including incompatible + // ones) are preserved with their evidence weights for downstream + // tie-breaking. + const save3 = mkDef({ + nodeId: 'def:save-three', + type: 'Method', + qualifiedName: 'User.save', + parameterCount: 3, + }); + const saveUnknown = mkDef({ + nodeId: 'def:save-unknown', + type: 'Method', + qualifiedName: 'User.save', + }); + const mod = mkScope({ + id: 'scope:m', + parent: null, + bindings: { save: [mkBinding(save3, 'local'), mkBinding(saveUnknown, 'local')] }, + }); + const ctx = makeCtx([mod], [save3, saveUnknown], { + arity: (_callsite, def) => (def.nodeId === 'def:save-unknown' ? 'unknown' : 'incompatible'), + }); + const results = buildMethodRegistry(ctx).lookup('save', 'scope:m', { + callsite: { arity: 1 }, + }); + expect(results).toHaveLength(2); + const incompat = results.find((r) => r.def.nodeId === 'def:save-three'); + expect(incompat).toBeDefined(); + expect(evidenceOfKind(incompat!, 'arity-match')?.weight).toBe( EvidenceWeights.arityMatchIncompatible, ); }); diff --git a/gitnexus/test/unit/scope-resolution/resolver-parity-expected-failures.test.ts b/gitnexus/test/unit/scope-resolution/resolver-parity-expected-failures.test.ts index eae68e09d..7a830efa8 100644 --- a/gitnexus/test/unit/scope-resolution/resolver-parity-expected-failures.test.ts +++ b/gitnexus/test/unit/scope-resolution/resolver-parity-expected-failures.test.ts @@ -7,6 +7,11 @@ import { const csharpNamespaceRootImportTest = 'emits the using-import edge App/Program.cs -> Models/User.cs through the scope-resolution path'; +const cppBaseNamespaceAdlTests = [ + 'resolves log(d) to base_lib::log via ADL when Derived inherits from base_lib::Base', + 'resolves trace(m) via full MRO walk when MultiLevel inherits via middle_lib::Mid -> base_lib::Root', + 'diamond inheritance contributes base namespace once (no duplicate/crash)', +] as const; describe('resolver parity expected legacy failures', () => { it('uses the same env var convention as the parity workflow', () => { @@ -44,4 +49,14 @@ describe('resolver parity expected legacy failures', () => { ), ).toBe(false); }); + + it('does not mark cpp base-namespace ADL coverage as expected failures in legacy parity', () => { + for (const testName of cppBaseNamespaceAdlTests) { + expect( + isLegacyResolverParityExpectedFailure('cpp', testName, { + REGISTRY_PRIMARY_CPP: '0', + }), + ).toBe(false); + } + }); }); diff --git a/gitnexus/test/unit/setup.test.ts b/gitnexus/test/unit/setup.test.ts index 95ad261f0..bdf1cd1fd 100644 --- a/gitnexus/test/unit/setup.test.ts +++ b/gitnexus/test/unit/setup.test.ts @@ -267,6 +267,21 @@ describe('setupClaudeCode', () => { }); }); + it('copies hook-db-lock-probe.cjs and win-rm-list-json.ps1 to ~/.claude/hooks/gitnexus/', async () => { + setPlatform('linux'); + + const { setupCommand } = await import('../../src/cli/setup.js'); + await setupCommand(); + + const destHooksDir = path.join(tempHome, '.claude', 'hooks', 'gitnexus'); + await expect( + fs.access(path.join(destHooksDir, 'hook-db-lock-probe.cjs')), + ).resolves.toBeUndefined(); + await expect( + fs.access(path.join(destHooksDir, 'win-rm-list-json.ps1')), + ).resolves.toBeUndefined(); + }); + it('falls back to first line on Windows when no .cmd/.bat wrapper found', async () => { setPlatform('win32'); // Edge case: where returns only the POSIX script (no .cmd wrapper) diff --git a/gitnexus/test/unit/skip-git-cli.test.ts b/gitnexus/test/unit/skip-git-cli.test.ts index e82bb7b13..80c07ed17 100644 --- a/gitnexus/test/unit/skip-git-cli.test.ts +++ b/gitnexus/test/unit/skip-git-cli.test.ts @@ -5,9 +5,11 @@ import os from 'os'; import fs from 'fs'; describe('--skip-git CLI flag', () => { + const cliPath = path.resolve(__dirname, '../../dist/cli/index.js'); + it('Commander maps --skip-git to options.skipGit (not --no-git inversion)', () => { // Verify the CLI defines --skip-git and --skip-agents-md in analyze help. - const helpOutput = execSync('node dist/cli/index.js analyze --help', { + const helpOutput = execSync(`node "${cliPath}" analyze --help`, { cwd: path.resolve(__dirname, '../..'), encoding: 'utf8', timeout: 10000, @@ -15,9 +17,41 @@ describe('--skip-git CLI flag', () => { expect(helpOutput).toContain('--skip-git'); expect(helpOutput).toContain('--skip-agents-md'); + expect(helpOutput).toContain('--skip-skills'); + expect(helpOutput).toContain('--index-only'); expect(helpOutput).not.toContain('--no-git'); }); + it('warns when --index-only overrides --skills (PR 1485)', () => { + // `--index-only` suppresses the post-index skill step that `--skills` + // would otherwise trigger. Without an explicit warning, the user sees a + // pipeline re-index complete and silently no skill files written — the + // silent-contradiction case flagged in PR 1485 review. + const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-index-only-skills-')); + const gitnexusHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-index-only-skills-home-')); + // Make tmpDir a git repo so analyze accepts it without --skip-git. + execSync('git init', { cwd: tmpDir, stdio: 'ignore' }); + fs.writeFileSync(path.join(tmpDir, 'a.ts'), 'export const a = 1;\n'); + + const env = { + ...process.env, + HOME: gitnexusHome, + GITNEXUS_HOME: gitnexusHome, + GITNEXUS_LBUG_EXTENSION_INSTALL: 'never', + }; + + try { + const output = execSync( + `node "${cliPath}" analyze "${tmpDir}" --index-only --skills --skip-agents-md`, + { encoding: 'utf8', timeout: 60000, env }, + ); + expect(output).toContain('--index-only overrides --skills'); + } finally { + fs.rmSync(tmpDir, { recursive: true, force: true }); + fs.rmSync(gitnexusHome, { recursive: true, force: true }); + } + }); + it('rejects non-git folder without --skip-git', () => { const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-no-git-')); fs.writeFileSync(path.join(tmpDir, 'test.ts'), 'export const x = 1;'); @@ -37,8 +71,59 @@ describe('--skip-git CLI flag', () => { } }); + it('still respects .gitnexusignore when run with --skip-git', () => { + const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-skip-git-ignore-')); + const gitnexusHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-skip-git-ignore-home-')); + fs.mkdirSync(path.join(tmpDir, 'src'), { recursive: true }); + fs.mkdirSync(path.join(tmpDir, 'customskip'), { recursive: true }); + fs.writeFileSync(path.join(tmpDir, '.gitnexusignore'), 'customskip/\n'); + fs.writeFileSync(path.join(tmpDir, 'src', 'keep.ts'), 'export function keep() { return 1; }\n'); + fs.writeFileSync( + path.join(tmpDir, 'customskip', 'leaked.ts'), + 'export function leaked() { return 42; }\n', + ); + + const env = { + ...process.env, + HOME: gitnexusHome, + GITNEXUS_HOME: gitnexusHome, + GITNEXUS_LBUG_EXTENSION_INSTALL: 'never', + }; + + try { + execSync(`node "${cliPath}" analyze "${tmpDir}" --skip-git --skip-agents-md`, { + encoding: 'utf8', + timeout: 60000, + env, + }); + + const keepContext = execSync( + `node "${cliPath}" context keep --repo "${path.basename(tmpDir)}"`, + { + encoding: 'utf8', + timeout: 60000, + env, + }, + ); + expect(keepContext).toContain('"status": "found"'); + expect(keepContext).toContain('"filePath": "src/keep.ts"'); + + const leakedContext = execSync( + `node "${cliPath}" context leaked --repo "${path.basename(tmpDir)}"`, + { + encoding: 'utf8', + timeout: 60000, + env, + }, + ); + expect(leakedContext).toContain(`"error": "Symbol 'leaked' not found"`); + } finally { + fs.rmSync(tmpDir, { recursive: true, force: true }); + fs.rmSync(gitnexusHome, { recursive: true, force: true }); + } + }); + describe('--skip-git does not walk up to parent git repo (#1232)', () => { - const cliPath = path.resolve(__dirname, '../../dist/cli/index.js'); let parentDir: string; let gitnexusHome: string; diff --git a/gitnexus/test/unit/u8-redos-resource-exhaustion.test.ts b/gitnexus/test/unit/u8-redos-resource-exhaustion.test.ts deleted file mode 100644 index 6dd6d9955..000000000 --- a/gitnexus/test/unit/u8-redos-resource-exhaustion.test.ts +++ /dev/null @@ -1,196 +0,0 @@ -/** - * Regression tests for U8 — closes: - * #186 js/redos rust-workspace-extractor.ts - * #187 js/redos cobol-preprocessor.ts - * #184 js/resource-exhaustion cross-impact.ts - * - * These tests import the production symbols directly. A previous shape - * dynamic-imported names that did not exist (`extractRustWorkspace` vs. - * the real `extractRustWorkspaceLinks`) and `??`-fell-back to inline - * regex copies, so the tests stayed green even when the production - * fixes regressed. Static imports + named symbols make a regression in - * any of the three sites a hard test failure. - */ -import { describe, expect, it } from 'vitest'; -import { RE_SET_TO_TRUE, RE_SET_INDEX } from '../../src/core/ingestion/cobol/cobol-preprocessor.js'; -import { parseCargoPackageName } from '../../src/core/group/extractors/rust-workspace-extractor.js'; -import { - clampTimeout, - IMPACT_TIMEOUT_MIN_MS, - IMPACT_TIMEOUT_MAX_MS, -} from '../../src/core/group/cross-impact.js'; - -/** - * Time a single regex.exec call. Used by the linearity tests below to - * compute a 10k/5k ratio in addition to the absolute <500ms bound. - * - * Ratio assertions catch sub-exponential O(n²) regressions that fit - * inside the absolute cap on warm CI; the absolute cap catches - * catastrophic backtracking on cold CI. Two complementary signals. - */ -function timeRegex(re: RegExp, input: string): number { - // Reset regex.lastIndex for global/sticky regexes — ours are not, but - // be defensive in case future shape changes add the `g` flag. - re.lastIndex = 0; - const start = performance.now(); - re.exec(input); - return performance.now() - start; -} - -function timeFn(fn: () => T): number { - const start = performance.now(); - fn(); - return performance.now() - start; -} - -// Linear scaling is ~2.0× when input doubles; 3.0× allows generous -// slack for CI-runner GC and tier-up jitter. An O(n²) regression on a -// 2× input takes ~4× as long, well outside this bound. -const LINEAR_RATIO_BOUND = 3.0; - -/** - * Minimum elapsed time (in ms) below which `performance.now()` ratios - * are dominated by scheduler jitter and become meaningless. When both - * timed runs come in below this floor, we skip the ratio assertion — - * the absolute <500ms bound still catches catastrophic backtracking, - * and the next CI run will measure higher absolute times that the - * ratio assertion can evaluate reliably. - * - * Calibrated empirically: a flake on macOS reported ratio 5.29× - * between two sub-millisecond measurements (~0.5ms vs ~2.6ms), both - * genuinely linear but indistinguishable from noise. 5ms is a - * comfortable floor where individual measurements are well-separated - * from the ~10-100µs `performance.now()` resolution band. - */ -const RATIO_MEASUREMENT_FLOOR_MS = 5; - -/** - * Assert linear scaling between two timed runs on inputs that differ - * by 2×. When measurements are too small to be reliable, the ratio - * assertion is skipped (the absolute bound still fires elsewhere). - */ -function assertSubLinearRatio(elapsedSmall: number, elapsedLarge: number, label: string): void { - if (elapsedSmall < RATIO_MEASUREMENT_FLOOR_MS && elapsedLarge < RATIO_MEASUREMENT_FLOOR_MS) { - // Both runs completed faster than the noise floor — the ratio is - // not meaningful. The absolute <500ms bound elsewhere in this - // describe block still pins linearity; we skip rather than risk a - // flake on a genuinely-linear implementation. - return; - } - const ratio = elapsedLarge / Math.max(elapsedSmall, 0.001); - if (ratio >= LINEAR_RATIO_BOUND) { - throw new Error( - `${label}: ratio ${ratio.toFixed(2)}× exceeds bound ${LINEAR_RATIO_BOUND}× ` + - `(small=${elapsedSmall.toFixed(2)}ms, large=${elapsedLarge.toFixed(2)}ms)`, - ); - } -} - -describe('cobol-preprocessor RE_SET_TO_TRUE — linear time on pathological input', () => { - it('matches in <500ms on 50k repetitions of "A OF A " AND 100k/50k ratio is sub-linear when measurable', () => { - // 50k/100k repetitions chosen so timings exceed the - // RATIO_MEASUREMENT_FLOOR_MS noise floor on typical CI hardware. - // Pre-fix nested-quantifier shape would be exponential here; the - // post-fix `.+?` shape is linear (~2× when input doubles). - const inputSmall = 'SET ' + 'A OF A '.repeat(50_000) + 'TO TRUE'; - const inputLarge = 'SET ' + 'A OF A '.repeat(100_000) + 'TO TRUE'; - const elapsedSmall = timeRegex(RE_SET_TO_TRUE, inputSmall); - const elapsedLarge = timeRegex(RE_SET_TO_TRUE, inputLarge); - expect(RE_SET_TO_TRUE.exec(inputSmall)).not.toBeNull(); - expect(elapsedSmall).toBeLessThan(500); - expect(elapsedLarge).toBeLessThan(500); - assertSubLinearRatio(elapsedSmall, elapsedLarge, 'RE_SET_TO_TRUE'); - }); - - it('still matches a normal SET ... TO TRUE statement', () => { - const m = RE_SET_TO_TRUE.exec('SET WS-FLAG TO TRUE'); - expect(m).not.toBeNull(); - expect(m?.[1]).toBe('WS-FLAG'); - }); -}); - -describe('cobol-preprocessor RE_SET_INDEX — linear time on pathological input', () => { - it('rejects in <500ms on 50k tokens with no valid suffix AND 100k/50k ratio is sub-linear when measurable', () => { - // Forces backtracking against the (TO|UP\s+BY|DOWN\s+BY) alternation - // — the richer pathological surface of the two regexes. - const inputSmall = 'SET ' + 'A '.repeat(50_000) + 'X'; - const inputLarge = 'SET ' + 'A '.repeat(100_000) + 'X'; - const elapsedSmall = timeRegex(RE_SET_INDEX, inputSmall); - const elapsedLarge = timeRegex(RE_SET_INDEX, inputLarge); - expect(RE_SET_INDEX.exec(inputSmall)).toBeNull(); - expect(elapsedSmall).toBeLessThan(500); - expect(elapsedLarge).toBeLessThan(500); - assertSubLinearRatio(elapsedSmall, elapsedLarge, 'RE_SET_INDEX'); - }); - - it('still matches a normal SET INDEX statement', () => { - const m = RE_SET_INDEX.exec('SET WS-IDX TO 5'); - expect(m).not.toBeNull(); - expect(m?.[1]).toBe('WS-IDX'); - expect(m?.[2]).toBe('TO'); - expect(m?.[3]).toBe('5'); - }); -}); - -describe('rust-workspace parseCargoPackageName — linear-time line walk', () => { - it('extracts the package name in <500ms on 100k blank lines AND 200k/100k ratio is sub-linear when measurable', () => { - // 100k/200k blank lines chosen so timings exceed the - // RATIO_MEASUREMENT_FLOOR_MS noise floor. Earlier 10k/20k pairing - // produced sub-millisecond measurements where scheduler jitter - // dominated and the ratio became meaningless (a real macOS run - // saw 5.29× between two genuinely-linear sub-ms measurements). - const cargoTomlSmall = - '[package]\n' + '\n'.repeat(100_000) + 'name = "myrepo"\nversion = "0.1.0"\n'; - const cargoTomlLarge = - '[package]\n' + '\n'.repeat(200_000) + 'name = "myrepo"\nversion = "0.1.0"\n'; - const elapsedSmall = timeFn(() => parseCargoPackageName(cargoTomlSmall)); - const elapsedLarge = timeFn(() => parseCargoPackageName(cargoTomlLarge)); - expect(parseCargoPackageName(cargoTomlSmall)).toBe('myrepo'); - expect(elapsedSmall).toBeLessThan(500); - expect(elapsedLarge).toBeLessThan(500); - assertSubLinearRatio(elapsedSmall, elapsedLarge, 'parseCargoPackageName'); - }); - - it('returns null when [package] section is absent', () => { - expect(parseCargoPackageName('[workspace]\nmembers = ["a"]\n')).toBeNull(); - }); - - it('stops at the next section header (does not pick up a name= from a later section)', () => { - const toml = '[package]\nversion = "1.0"\n[other]\nname = "wrong"\n'; - expect(parseCargoPackageName(toml)).toBeNull(); - }); - - it('extracts the name from a normal [package] section', () => { - const toml = '[package]\nname = "real-crate"\nversion = "0.1.0"\n'; - expect(parseCargoPackageName(toml)).toBe('real-crate'); - }); -}); - -describe('cross-impact clampTimeout — bounds user-supplied impact timeouts', () => { - it('rejects negative and zero timeouts, returning MIN', () => { - expect(clampTimeout(0)).toBe(IMPACT_TIMEOUT_MIN_MS); - expect(clampTimeout(-1)).toBe(IMPACT_TIMEOUT_MIN_MS); - expect(clampTimeout(-999_999)).toBe(IMPACT_TIMEOUT_MIN_MS); - }); - - it('rejects NaN/Infinity, returning MIN', () => { - expect(clampTimeout(NaN)).toBe(IMPACT_TIMEOUT_MIN_MS); - expect(clampTimeout(Infinity)).toBe(IMPACT_TIMEOUT_MIN_MS); - expect(clampTimeout(-Infinity)).toBe(IMPACT_TIMEOUT_MIN_MS); - }); - - it('caps very large timeouts at MAX (5 minutes)', () => { - expect(clampTimeout(999_999_999)).toBe(IMPACT_TIMEOUT_MAX_MS); - expect(clampTimeout(IMPACT_TIMEOUT_MAX_MS + 1)).toBe(IMPACT_TIMEOUT_MAX_MS); - }); - - it('passes through a reasonable timeout unchanged (truncated to integer)', () => { - expect(clampTimeout(30_000)).toBe(30_000); - expect(clampTimeout(30_500.7)).toBe(30_500); - }); - - it('floors below-MIN positive values to MIN', () => { - expect(clampTimeout(50)).toBe(IMPACT_TIMEOUT_MIN_MS); - expect(clampTimeout(0.1)).toBe(IMPACT_TIMEOUT_MIN_MS); - }); -}); diff --git a/gitnexus/test/unit/wiki-llm-client.test.ts b/gitnexus/test/unit/wiki-llm-client.test.ts index c9d429904..52b633566 100644 --- a/gitnexus/test/unit/wiki-llm-client.test.ts +++ b/gitnexus/test/unit/wiki-llm-client.test.ts @@ -5,6 +5,7 @@ import { isAzureProvider, isReasoningModel, buildRequestUrl, + validateLLMBaseUrl, } from '../../src/core/wiki/llm-client.js'; describe('isAzureProvider', () => { @@ -330,3 +331,88 @@ describe('readSSEStream — content_filter handling', () => { ).rejects.toThrow('content filter'); }); }); + +describe('validateLLMBaseUrl', () => { + it('allows https:// for any public host', () => { + expect(() => validateLLMBaseUrl('https://api.openai.com/v1')).not.toThrow(); + expect(() => validateLLMBaseUrl('https://openrouter.ai/api/v1')).not.toThrow(); + expect(() => validateLLMBaseUrl('https://myres.openai.azure.com/openai/v1')).not.toThrow(); + }); + + it('allows http:// for localhost', () => { + expect(() => validateLLMBaseUrl('http://localhost:11434/v1')).not.toThrow(); + expect(() => validateLLMBaseUrl('http://127.0.0.1:11434/v1')).not.toThrow(); + // IPv6 loopback — Node's URL parser preserves brackets in hostname: "[::1]" + expect(() => validateLLMBaseUrl('http://[::1]:11434/v1')).not.toThrow(); + }); + + it('allows http:// for LOCALHOST (uppercase) — lowercased before comparison', () => { + expect(() => validateLLMBaseUrl('http://LOCALHOST:11434/v1')).not.toThrow(); + }); + + it('rejects http:// for non-loopback hosts', () => { + expect(() => validateLLMBaseUrl('http://evil.example.com/v1')).toThrow('Insecure http://'); + expect(() => validateLLMBaseUrl('http://192.168.1.1/v1')).toThrow('Insecure http://'); + // Private IP ranges + expect(() => validateLLMBaseUrl('http://10.0.0.1/v1')).toThrow('Insecure http://'); + // AWS/GCP IMDS — should be blocked + expect(() => validateLLMBaseUrl('http://169.254.169.254/latest/meta-data')).toThrow( + 'Insecure http://', + ); + }); + + it('rejects http:// hostname-spoofing attempts', () => { + // Full-hostname comparison prevents prefix/suffix attacks + expect(() => validateLLMBaseUrl('http://localhost.evil.com/v1')).toThrow('Insecure http://'); + expect(() => validateLLMBaseUrl('http://127.0.0.1.evil.com/v1')).toThrow('Insecure http://'); + // Trailing dot — hostname 'localhost.' ≠ 'localhost' + expect(() => validateLLMBaseUrl('http://localhost./v1')).toThrow('Insecure http://'); + }); + + it('rejects http:// non-loopback IPv6 addresses', () => { + // Link-local IPv6 + expect(() => validateLLMBaseUrl('http://[fe80::1]/v1')).toThrow('Insecure http://'); + // IPv4-mapped IPv6 loopback — bracket-stripped to '::ffff:127.0.0.1' ≠ '::1' + expect(() => validateLLMBaseUrl('http://[::ffff:127.0.0.1]/v1')).toThrow('Insecure http://'); + }); + + it('rejects non-http schemes', () => { + expect(() => validateLLMBaseUrl('file:///etc/passwd')).toThrow('must use http:// or https://'); + expect(() => validateLLMBaseUrl('javascript:alert(1)')).toThrow('must use http:// or https://'); + expect(() => validateLLMBaseUrl('data:text/plain,evil')).toThrow( + 'must use http:// or https://', + ); + expect(() => validateLLMBaseUrl('ftp://example.com')).toThrow('must use http:// or https://'); + }); + + it('rejects malformed URLs', () => { + expect(() => validateLLMBaseUrl('not-a-url')).toThrow('Invalid LLM base URL'); + expect(() => validateLLMBaseUrl('')).toThrow('Invalid LLM base URL'); + }); + + it('does not include the raw URL in error messages (credential hygiene)', () => { + // Simulates a URL with an embedded API key + const urlWithCreds = 'http://192.168.1.1/v1?apikey=sk-secret'; + let msg = ''; + try { + validateLLMBaseUrl(urlWithCreds); + } catch (e) { + msg = (e as Error).message; + } + expect(msg).not.toContain('sk-secret'); + expect(msg).not.toContain(urlWithCreds); + }); + + it('callLLM rejects an invalid base URL before fetching', async () => { + const { callLLM } = await import('../../src/core/wiki/llm-client.js'); + await expect( + callLLM('prompt', { + apiKey: 'key', + baseUrl: 'file:///etc/passwd', + model: 'gpt-4o', + maxTokens: 100, + temperature: 0, + }), + ).rejects.toThrow('must use http:// or https://'); + }); +}); diff --git a/gitnexus/test/unit/wiki-mermaid-sanitizer.test.ts b/gitnexus/test/unit/wiki-mermaid-sanitizer.test.ts new file mode 100644 index 000000000..e8c74c8cb --- /dev/null +++ b/gitnexus/test/unit/wiki-mermaid-sanitizer.test.ts @@ -0,0 +1,97 @@ +import { describe, expect, it } from 'vitest'; + +import { + sanitizeMermaidDiagram, + sanitizeMermaidMarkdown, +} from '../../src/core/wiki/mermaid-sanitizer.js'; + +describe('sanitizeMermaidMarkdown', () => { + it('replaces literal newline escapes inside rectangle and diamond labels', () => { + const markdown = [ + '```mermaid', + 'flowchart TD', + ' A[HTTP request\\nwith ID param] --> B{Preceding tei:zone\\nwith @start=#pid?}', + '```', + ].join('\n'); + + const sanitized = sanitizeMermaidMarkdown(markdown); + + expect(sanitized).toContain('A[HTTP request
with ID param]'); + expect(sanitized).toContain('B{Preceding tei:zone
with @start=#pid?}'); + expect(sanitized).not.toContain('\\n'); + }); + + it('quotes unsafe edge labels without changing safe labels', () => { + const diagram = [ + 'graph LR', + ' Script -->|doc()| eXist[(eXist-db XML)]', + ' Client -->|HTTP params| Script', + ].join('\n'); + + const sanitized = sanitizeMermaidDiagram(diagram); + + expect(sanitized).toContain('Script -->|"doc()"| eXist[(eXist-db XML)]'); + expect(sanitized).toContain('Client -->|HTTP params| Script'); + }); + + it('escapes backslashes and quotes in quoted edge labels', () => { + const diagram = ['graph LR', ' Script -->|doc("C:\\\\tmp")| Target'].join('\n'); + + const sanitized = sanitizeMermaidDiagram(diagram); + + expect(sanitized).toContain('Script -->|"doc(\\"C:\\\\\\\\tmp\\")"| Target'); + }); + + it('aliases bare node IDs that contain dots and keeps display labels', () => { + const diagram = [ + 'graph LR', + ' Client -->|xmlurl + xslurl| xslt-conversion.xq', + ' xslt-conversion.xq -->|stream-transform| lbpwebjs-main.xsl', + ' lbpwebjs-main.xsl -->|fetches| TEI-XML[(TEI XML in eXist)]', + ].join('\n'); + + const sanitized = sanitizeMermaidDiagram(diagram); + + expect(sanitized).toContain( + 'Client -->|xmlurl + xslurl| xslt-conversion_xq["xslt-conversion.xq"]', + ); + expect(sanitized).toContain( + 'xslt-conversion_xq["xslt-conversion.xq"] -->|stream-transform| lbpwebjs-main_xsl["lbpwebjs-main.xsl"]', + ); + expect(sanitized).toContain( + 'lbpwebjs-main_xsl["lbpwebjs-main.xsl"] -->|fetches| TEI-XML[(TEI XML in eXist)]', + ); + }); + + it('aliases unsafe node IDs while preserving existing inline labels', () => { + const diagram = [ + 'graph LR', + ' file.name.ts[(eXist-db XML)] --> target.node["Target node"]', + ].join('\n'); + + const sanitized = sanitizeMermaidDiagram(diagram); + + expect(sanitized).toContain('file_name_ts[(eXist-db XML)] --> target_node["Target node"]'); + }); + + it('only rewrites fenced Mermaid blocks in markdown', () => { + const markdown = [ + 'Regular text with doc() and file.name.ts.', + '', + '```ts', + 'const label = "A\\nB";', + '```', + '', + '```mermaid', + 'flowchart LR', + ' A -->|doc()| file.name.ts', + '```', + ].join('\n'); + + const sanitized = sanitizeMermaidMarkdown(markdown); + + expect(sanitized).toContain('Regular text with doc() and file.name.ts.'); + expect(sanitized).toContain('const label = "A\\nB";'); + expect(sanitized).toContain('A -->|"doc()"| file_name_ts["file.name.ts"]'); + }); +}); diff --git a/gitnexus/test/utils/hook-test-helpers.ts b/gitnexus/test/utils/hook-test-helpers.ts index 6f5c5fbfd..3f519bc81 100644 --- a/gitnexus/test/utils/hook-test-helpers.ts +++ b/gitnexus/test/utils/hook-test-helpers.ts @@ -7,12 +7,14 @@ export function runHook( hookPath: string, input: Record, cwd?: string, + options: { env?: NodeJS.ProcessEnv } = {}, ): { stdout: string; stderr: string; status: number | null } { const result = spawnSync(process.execPath, [hookPath], { input: JSON.stringify(input), encoding: 'utf-8', timeout: 10000, cwd, + env: options.env, stdio: ['pipe', 'pipe', 'pipe'], }); return {