Merge branch 'main' into fix/rust-axum-route-extraction-1504

This commit is contained in:
Gergő Magyar 2026-05-14 06:46:42 +01:00 • committed by GitHub
commit 26cd416afa
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
242 changed files with 15321 additions and 975 deletions

View file

@ -3,6 +3,9 @@ name: E2E Tests
on:
workflow_call:
permissions:
contents: read
jobs:
check-changes:
name: Check web module changes

View file

@ -3,6 +3,9 @@ name: Quality Checks
on:
workflow_call:
permissions:
contents: read
jobs:
format:
runs-on: ubuntu-latest

View file

@ -28,6 +28,9 @@ name: Scope Resolution Parity
on:
workflow_call:
permissions:
contents: read
jobs:
discover:
name: Discover migrated languages

View file

@ -3,6 +3,9 @@ name: Tests
on:
workflow_call:
permissions:
contents: read
jobs:
tests:
name: ubuntu / coverage

View file

@ -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

View file

@ -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'

View file

@ -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' }}

View file

@ -10,6 +10,9 @@ on:
pull_request:
branches: [main]
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

View file

@ -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 }}

View file

@ -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' }}

View file

@ -336,7 +336,7 @@ jobs:
# Push auth is provided inline at push time via the URL.
- name: Checkout PR head
if: steps.locate.outputs.found == 'true'
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.4
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v5.0.4
with:
repository: ${{ steps.locate.outputs.head_repo }}
ref: ${{ steps.locate.outputs.head_sha }}

View file

@ -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

View file

@ -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

View file

@ -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/<HEAD_SHA> marker pointing at HEAD?
MARKER="rc/${HEAD_SHA}"
if git rev-parse "refs/tags/$MARKER" >/dev/null 2>&1; then

View file

@ -20,6 +20,9 @@ on:
- cron: '0 8 * * 1'
workflow_dispatch:
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: false

View file

@ -15,6 +15,9 @@ on:
paths:
- '.github/**'
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

View file

@ -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.

View file

@ -40,8 +40,8 @@ RUN npm prune --omit=dev --prefix gitnexus
# 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
@ -55,8 +55,18 @@ 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/<repo>`)
# 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.

View file

@ -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.

View file

@ -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 <seconds> # Per-attempt LLM request timeout in seconds (default: 60)
gitnexus wiki --retries <n> # 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.

View file

@ -0,0 +1,95 @@
/**
* Custom ESLint rule: require `parseSourceSafe(parser, content, ...)` instead
* of direct `<parser>.parse(<content>, ...)` 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 `<parser>.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?$/.test(filename)) return {};
const sourceCode = context.sourceCode ?? context.getSourceCode();
return {
CallExpression(node) {
const callee = node.callee;
if (callee.type !== 'MemberExpression') return;
if (callee.computed) return;
if (callee.property.type !== 'Identifier') return;
if (callee.property.name !== 'parse') return;
// Skip known non-tree-sitter receivers.
if (callee.object.type === 'Identifier' && SKIPPED_RECEIVERS.has(callee.object.name)) {
return;
}
// Smoke tests pass a string literal directly; those are trivially safe.
const firstArg = node.arguments[0];
if (!firstArg) return;
if (firstArg.type === 'Literal' && typeof firstArg.value === 'string') return;
if (firstArg.type === 'TemplateLiteral' && firstArg.expressions.length === 0) return;
const receiverText = sourceCode.getText(callee.object);
// Receiver-text-shape skip: anything matching well-known JS APIs that
// happen to have a `.parse(<expr>)` shape but aren't tree-sitter.
if (
/^(JSON|URL|marked|Number|Math|Date|globalThis\.JSON)\b/.test(receiverText) ||
/\bjson\.parse\b/i.test(receiverText)
) {
return;
}
context.report({
node,
messageId: 'useSafeParse',
data: { receiver: receiverText },
fix(fixer) {
const argsText = node.arguments.map((arg) => sourceCode.getText(arg)).join(', ');
return fixer.replaceText(node, `parseSourceSafe(${receiverText}, ${argsText})`);
},
});
},
};
},
};

View file

@ -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 `<parser>.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}'],

6
eval/uv.lock generated
View file

@ -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]]

View file

@ -14,6 +14,7 @@
const fs = require('fs');
const path = require('path');
const { spawnSync } = require('child_process');
const { acquireHookSlot } = require('./hook-lock.js');
/**
* Read JSON input from stdin synchronously.
@ -217,7 +218,8 @@ 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 || {};
@ -227,6 +229,9 @@ function handlePreToolUse(input) {
const pattern = extractPattern(toolName, toolInput);
if (!pattern || pattern.length < 3) return;
const release = acquireHookSlot(gitNexusDir);
if (!release) return;
let result = '';
try {
const child = runGitNexusCli(['augment', '--', pattern], cwd, 7000);
@ -235,6 +240,8 @@ function handlePreToolUse(input) {
}
} catch {
/* graceful failure */
} finally {
release();
}
if (result && result.trim()) {

View file

@ -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,
};

View file

@ -62,6 +62,8 @@ Generates repository documentation from the knowledge graph using an LLM. Requir
| `--api-key <key>` | LLM API key |
| `--concurrency <n>` | Parallel LLM calls (default: 3) |
| `--gist` | Publish wiki as a public GitHub Gist |
| `--timeout <seconds>` | Per-attempt LLM request timeout in seconds (default: 60) |
| `--retries <n>` | Max LLM retry attempts per request (default: 3) |
### list — Show all indexed repos

View file

@ -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
<your-project>/
├── .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/*` | ✅ |
| `<project>/.cursor/hooks.json` + `<project>/hooks/gitnexus-hook.cjs` + `<project>/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.

View file

@ -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

View file

@ -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 <pattern>`, 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();

View file

@ -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,
};

View file

@ -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
}
]
}

View file

@ -40,11 +40,27 @@ export interface MethodDispatchIndex {
readonly mroByOwnerDefId: ReadonlyMap<DefId, readonly DefId[]>;
/** Interfaces / traits → classes that implement them. */
readonly implsByInterfaceDefId: ReadonlyMap<DefId, readonly DefId[]>;
/**
* 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<DefId, readonly DefId[]>;
/** `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<DefId, readonly DefId[]>();
const extendsOnlyByOwnerDefId = input.computeExtendsOnlyMro
? new Map<DefId, readonly DefId[]>()
: undefined;
const implsBuilding = new Map<DefId, DefId[]>();
const implsSeen = new Map<DefId, Set<DefId>>();
@ -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<DefId, readonly DefId[]>,
implsByInterfaceDefId: Map<DefId, readonly DefId[]>,
extendsOnlyMroByOwnerDefId: Map<DefId, readonly DefId[]> | 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;
}

View file

@ -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) {

View file

@ -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"
},
@ -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": {
@ -1679,12 +1648,12 @@
}
},
"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 +1713,9 @@
}
},
"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 +1738,9 @@
}
},
"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 +1754,9 @@
}
},
"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 +1770,9 @@
}
},
"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 +1786,9 @@
}
},
"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 +1802,9 @@
}
},
"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 +1818,9 @@
}
},
"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 +1834,9 @@
}
},
"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 +1850,9 @@
}
},
"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 +1866,9 @@
}
},
"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 +1882,9 @@
}
},
"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 +1898,9 @@
}
},
"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 +1914,9 @@
}
},
"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 +1930,9 @@
}
},
"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 +1948,9 @@
}
},
"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 +1964,9 @@
}
},
"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 +2769,14 @@
"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 +2879,8 @@
"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 +3612,6 @@
"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 +4569,16 @@
"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 +5595,21 @@
"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 +5961,9 @@
}
},
"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 +6355,14 @@
}
},
"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 +6373,14 @@
"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 +7136,9 @@
}
},
"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 +7515,9 @@
}
},
"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 +7867,13 @@
"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 +7882,27 @@
"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 +8622,15 @@
}
},
"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 +8647,7 @@
},
"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 +8795,6 @@
"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",

View file

@ -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"
}

View file

@ -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 <limit>` 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

View file

@ -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 |

View file

@ -14,6 +14,7 @@
const fs = require('fs');
const path = require('path');
const { spawnSync } = require('child_process');
const { acquireHookSlot } = require('./hook-lock.cjs');
/**
* Read JSON input from stdin synchronously.
@ -207,7 +208,8 @@ 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 || {};
@ -217,6 +219,9 @@ function handlePreToolUse(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 {
@ -226,6 +231,8 @@ function handlePreToolUse(input) {
}
} catch {
/* graceful failure */
} finally {
release();
}
if (result && result.trim()) {

View file

@ -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,
};

View file

@ -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",
@ -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": {
@ -1646,9 +1646,9 @@
"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": {
@ -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"
},

View file

@ -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",

View file

@ -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…');

View file

@ -28,6 +28,7 @@ interface RepoStats {
export interface AIContextOptions {
skipAgentsMd?: boolean;
noStats?: boolean;
skipSkills?: boolean;
}
const GITNEXUS_START_MARKER = '<!-- gitnexus:start -->';
@ -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}`;
}
/**
@ -319,6 +337,7 @@ export async function generateAIContextFiles(
generatedSkills,
groupNames,
options?.noStats,
options?.skipSkills,
);
const createdFiles: string[] = [];
@ -337,10 +356,14 @@ export async function generateAIContextFiles(
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 };

View file

@ -119,6 +119,10 @@ 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;
/** 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 +154,24 @@ 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<AnalyzeOptions, 'skills' | 'indexOnly'> | undefined,
pipelineResult: unknown,
): boolean => Boolean(options?.skills && pipelineResult && !options?.indexOnly);
export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOptions) => {
if (ensureHeap()) return;
@ -245,6 +267,18 @@ 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 +433,9 @@ 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,
{
@ -410,7 +447,8 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption
embeddingsNodeLimit,
dropEmbeddings: options?.dropEmbeddings,
skipGit: options?.skipGit,
skipAgentsMd: options?.skipAgentsMd,
skipAgentsMd,
skipSkills,
noStats: options?.noStats,
registryName: options?.name,
// Registry-collision bypass — its own CLI flag, intentionally NOT
@ -456,8 +494,10 @@ 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 +537,7 @@ export const analyzeCommand = async (inputPath?: string, options?: AnalyzeOption
processes: s.processes,
},
skillResult.skills,
{ skipAgentsMd: options?.skipAgentsMd, noStats: options?.noStats },
{ skipAgentsMd, skipSkills, noStats: options?.noStats },
);
}
} catch {

View file

@ -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 <pattern>
* Returns enriched text to stdout.

View file

@ -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 <n>', 'Parallel LLM calls (default: 3)', '3')
.option('--timeout <seconds>', 'Per-attempt LLM request timeout in seconds (default: 60)')
.option('--retries <n>', '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')

View file

@ -364,6 +364,15 @@ async function installClaudeCodeHooks(result: SetupResult): Promise<void> {
// 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
}
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`

View file

@ -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(
{

View file

@ -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<string> {
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<string> {
}
// 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<string> {
repoId,
`
MATCH (n) WHERE n.filePath = '${escaped}'
AND n.name CONTAINS '${pattern.replace(/'/g, "''").split(/\s+/)[0]}'
AND n.name CONTAINS '${patternFirstWord}'
RETURN n.id AS id, n.name AS name, labels(n)[0] AS type, n.filePath AS filePath
LIMIT 3
`,
@ -143,6 +144,29 @@ export async function augment(pattern: string, cwd?: string): Promise<string> {
}
}
// When FTS indexes are unavailable (read-only DB, first run before indexes are built),
// fall back to a direct name CONTAINS query so enrichment still works.
if (symbolMatches.length === 0 && !ftsAvailable) {
const fallbackRows = await executeQuery(
repoId,
`
MATCH (n)
WHERE n.name CONTAINS '${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

View file

@ -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<string, any>();
@ -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([

View file

@ -40,8 +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;
@ -91,7 +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,
@ -99,7 +108,16 @@ const httpEmbedBatch = async (
model: string,
apiKey: string,
batchIndex = 0,
dimensions?: number,
): Promise<EmbeddingItem[]> => {
const requestBody: { input: string[]; model: string; dimensions?: number } = {
input: batch,
model,
};
if (dimensions !== undefined) {
requestBody.dimensions = dimensions;
}
let resp: Response;
try {
resp = await resilientFetch(
@ -111,7 +129,7 @@ const httpEmbedBatch = async (
'Content-Type': 'application/json',
Authorization: `Bearer ${apiKey}`,
},
body: JSON.stringify({ input: batch, model }),
body: JSON.stringify(requestBody),
},
{
breakerKey: HTTP_BREAKER_KEY,
@ -169,7 +187,14 @@ export const httpEmbed = async (texts: string[]): Promise<Float32Array[]> => {
for (let i = 0; i < texts.length; i += HTTP_BATCH_SIZE) {
const batch = texts.slice(i, i + HTTP_BATCH_SIZE);
const batchIndex = Math.floor(i / HTTP_BATCH_SIZE);
const items = await httpEmbedBatch(url, batch, config.model, config.apiKey, batchIndex);
const items = await httpEmbedBatch(
url,
batch,
config.model,
config.apiKey,
batchIndex,
config.dimensions,
);
if (items.length !== batch.length) {
throw new Error(
@ -212,7 +237,14 @@ export const httpEmbedQuery = async (text: string): Promise<number[]> => {
if (!config) throw new Error('HTTP embedding not configured');
const url = `${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)})`);
}

View file

@ -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;

View file

@ -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<string, string> = {
@ -77,11 +79,161 @@ const REQUESTS_GENERIC_PATTERNS = compilePatterns({
],
} satisfies LanguagePatterns<Record<string, never>>);
// ─── 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<Record<string, never>>);
// ─── 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<Record<string, never>>);
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<string>();
const preferClass = clientNode.text.includes('.');
const nearestScope = getScopeKey(clientNode.parent, preferClass);
keys.add(nearestScope);
return [...keys];
}
function collectHttpxAsyncClients(tree: Parser.Tree): Map<string, Set<string>> {
const clients = new Map<string, Set<string>>();
const addClient = (clientNode: Parser.SyntaxNode | undefined) => {
if (!clientNode) return;
const scopeKey = trackedClientScopeKey(clientNode);
const clientText = clientNode.text;
const scopes = clients.get(clientText) ?? new Set<string>();
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<string, Set<string>>,
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<Record<string, never>>);
// ─── 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<Record<string, never>>);
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.<verb>("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;
},
};

View file

@ -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;

View file

@ -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);

View file

@ -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;

View file

@ -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<TMeta>(
let tree: Parser.Tree;
try {
parser.setLanguage(plugin.language);
tree = parser.parse(content);
tree = parseSourceSafe(parser, content);
} catch {
return [];
}

View file

@ -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<string>();
// (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];
};

View file

@ -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<nodeId, filePath> for every File-bound node in the graph.
* Graph-wide nodes (Community/Process) have no filePath and are filtered.
*/
const indexNodeFilePaths = (fullGraph: KnowledgeGraph): Map<string, string> => {
const idx = new Map<string, string>();
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<string>,
): KnowledgeGraph => {
const sub = createKnowledgeGraph();
const writableNodeIds = new Set<string>();
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<string>,
): Set<string> => {
const nodeFilePaths = indexNodeFilePaths(fullGraph);
const expanded = new Set<string>(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;
};

View file

@ -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<string, Map<string, FieldInfo>>,
): Map<string, FieldInfo> | 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<string, FieldInfo>();
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<string, Map<string, string>>;
@ -771,7 +830,7 @@ 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 +918,120 @@ 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<string, Map<string, FieldInfo>>();
for (const { file, language, provider, matches, typeEnv } of prepared) {
const callRouter = provider.callRouter;
if (!callRouter) continue;
matches.forEach((match) => {
const captureMap: Record<string, any> = {};
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<string, FieldInfo> | 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
@ -929,9 +1102,10 @@ export const processCalls = async (
provider,
);
const srcId = enclosing || generateId('File', file.path);
// 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.
// Defer resolution so write-access tracking sees the FINAL graph
// state — properties from the pre-pass are present, but receiver-type
// resolution can still depend on inference that completes during the
// main loop. Resolve after all files have been processed.
pendingWrites.push({ receiverTypeName, propertyName, filePath: file.path, srcId });
}
// Assignment-only capture (no @call sibling): skip the rest of this
@ -1052,47 +1226,8 @@ 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;
}
@ -3283,7 +3418,7 @@ 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 {

View file

@ -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<never>((_, reject) =>

View file

@ -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 {

View file

@ -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) {

View file

@ -128,7 +128,21 @@ 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.
// NOTE: This fallback only applies to relative imports. Path alias imports
// (e.g. @/utils.js via tsconfig paths) do not yet strip .js extensions —
// that is a known limitation tracked for follow-up.
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 +196,19 @@ 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;
}

View file

@ -9,8 +9,12 @@ export const EXTENSIONS = [
// TypeScript/JavaScript
'.tsx',
'.ts',
'.mts',
'.cts',
'.jsx',
'.js',
'.mjs',
'.cjs',
'.vue',
'/index.tsx',
'/index.ts',

View file

@ -46,6 +46,15 @@ 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';
const C_BUILT_INS: ReadonlySet<string> = new Set([
'printf',
@ -367,6 +376,16 @@ 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({

View file

@ -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;
}

View file

@ -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';
}

View file

@ -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<ReturnType<typeof getCParser>['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<string>();
for (const m of rawMatches) {
const grouped: Record<string, Capture> = {};
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;
}

View file

@ -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<string> {
const headers = new Set<string>();
walk(repoPath, repoPath, headers);
return headers;
}
function walk(dir: string, root: string, out: Set<string>): 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, '/'));
}
}
}
}

View file

@ -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: <stdio.h> → 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<string, Capture> = {
'@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;
}

View file

@ -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>,
): 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;
}

View file

@ -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';

View file

@ -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. <stdio.h>) 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;
}

View file

@ -0,0 +1,32 @@
import type { BindingRef } from 'gitnexus-shared';
const TIER: Record<BindingRef['origin'], number> = {
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<string>();
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;
});
}

View file

@ -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<Parser['setLanguage']>[0]);
}
return _parser;
}
export function getCScopeQuery(): Parser.Query {
if (_query === null) {
_query = new Parser.Query(C as Parameters<Parser['setLanguage']>[0], C_SCOPE_QUERY);
}
return _query;
}

View file

@ -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<string> | 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);
},
};

View file

@ -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;
}

View file

@ -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<string, Set<string>>();
/** 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<string>();
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<string>();
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 ?? '';
}

View file

@ -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<ReturnType<typeof getCsharpParser>['parse']> | undefined;
if (tree === undefined) {
tree = getCsharpParser().parse(sourceText, undefined, {
tree = parseSourceSafe(getCsharpParser(), sourceText, undefined, {
bufferSize: getTreeSitterBufferSize(sourceText),
});
recordCacheMiss();

View file

@ -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<ReturnType<typeof getCsharpParser>['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);
}

View file

@ -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<ReturnType<typeof getGoParser>['parse']> | undefined;
if (tree === undefined) {
tree = getGoParser().parse(sourceText, undefined, {
tree = parseSourceSafe(getGoParser(), sourceText, undefined, {
bufferSize: getTreeSitterBufferSize(sourceText),
});
recordGoCacheMiss();

View file

@ -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<typeof parser.parse> | undefined) ??
parser.parse(sourceText, undefined, {
parseSourceSafe(parser, sourceText, undefined, {
bufferSize: getTreeSitterBufferSize(sourceText),
});
const moduleScope = parsed.scopes.find((s) => s.kind === 'Module');

View file

@ -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,
});

View file

@ -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,
};
}

View file

@ -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';
}

View file

@ -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;
}

View file

@ -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<ReturnType<typeof getJavaParser>['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<string, Capture> = {};
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<ReturnType<typeof getJavaParser>['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;
}

View file

@ -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<string, Capture> = {
'@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;
}

View file

@ -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<string>;
}
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;
}

View file

@ -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';

View file

@ -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<T>` becomes
// `BaseModel<T>` 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>` → `User`, `Optional<User>` → `User`).
* 2. Known two-arg map/container types → extract the value type
* (`Map<String, User>` → `User`).
* 3. **Fallback (JVM type erasure):** any other generic type →
* strip the generic parameters and keep the raw class name
* (`BaseModel<T>` → `BaseModel`, `CustomList<Foo>` → `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<T>` → `BaseModel`, `Builder<Self>` → `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<List<String>>` → `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);
}

View file

@ -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<string, BindingRef>();
for (const b of survivors) seen.set(b.def.nodeId, b);
return [...seen.values()];
}

View file

@ -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<Parser['setLanguage']>[0]);
}
return _parser;
}
export function getJavaScopeQuery(): Parser.Query {
if (_query === null) {
_query = new Parser.Query(Java as Parameters<Parser['setLanguage']>[0], JAVA_SCOPE_QUERY);
}
return _query;
}

View file

@ -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<string, Capture> = {
'@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;
}

View file

@ -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<T>` 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<T>`) — 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 };

View file

@ -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;
}

View file

@ -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,
});

View file

@ -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,
};
}

View file

@ -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';
}

Some files were not shown because too many files have changed in this diff Show more