mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-09-20 00:11:37 +00:00
* feat(skills): add ce-plan — GitNexus+PDG implementation-planning skill Adds .claude/skills/ce-plan: a planning-only skill that builds implementation-ready plans from GitNexus graph navigation (query/context/ impact/trace), bounded statement-level PDG slices (pdg_query, impact mode:pdg, explain), and targeted source verification, with a context ledger to prevent repeated reads and a machine-readable implementation context pack (stable contract for a future ce-implement). Whitelisted in .gitignore and registered in AGENTS.md and CLAUDE.md outside the auto-managed gitnexus block. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills): apply ce-plan validation findings (tool contract, consistency, conventions) Tool contract: impact mode:'pdg' shape now includes the schema-required direction param; CDG branch sense documented as the result 'label' field (reason is cypher/raw-edge only); explain caveats corrected to its real false-negative classes (cross-function TAINT_PATH is modeled). Consistency: PDG slice homed in working memory (ledger keeps one-liners); depth knob defined and category-overrides-baseline ordering stated; call_depth (consumed by nothing) and content-hash bookkeeping dropped; Never section folded into Hard rules; Phase 3 deduplicated to a pointer; allowed-repeat escalations defined; budget/discard accounting clarified; verification-commands gathering added to Phase 4; open_questions added to the context pack. From scenario runs: plans now pin the verified-at HEAD commit and index freshness in a header, tag claims [verified]/[graph]/[inferred]/[assumed], quote load-bearing tool output, prefer pre-hook-carrying npm scripts, and support an out:<path> destination override; output path defined as the Phase 1 target repo root. Conventions: AGENTS.md 1.9.0 / CLAUDE.md 1.4.0 changelog rows + metadata bumps; future ce-implement qualified as future. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): rename ce-plan → gitnexus-plan; add cross-CLI (Codex) entrypoints Renames the skill dir, frontmatter, output filename convention, plan H1 (GitNexus Engineering Plan), the future executor handle (gitnexus-implement), the .gitignore whitelist entry, and all AGENTS.md/CLAUDE.md references. Follows the pr-swarm-review cross-CLI pattern: SKILL.md is the canonical CLI-neutral spec, AGENTS.md § Engineering planning is the Codex/any-agent entrypoint, and the README documents the optional user-level ~/.codex/prompts/gitnexus-plan.md slash command plus an invocation matrix. Skill prose de-branded from Claude Code (agent-neutral verification layer). Also fixes two post-review README contradictions: the anti-reread claim now names the ledger's allowed escalations, and 'read-only by contract' is now 'planning-only' (the skill writes exactly one repo file — the plan); the scope-creep rule and template §12 now agree on where deferred follow-ups land. Drops the stale plugin-collision limitation. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(skills): document Codex user-level install path for gitnexus-plan Codex discovers SKILL.md skills from ~/.agents/skills (same path the other gitnexus-* skills install to); README now documents the cp install plus the optional ~/.codex/prompts slash-command file, with the prompt body preferring the repo copy and falling back to the user-level install. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): gitnexus-plan freshness gate + active PDG-layer refresh Freshness is now a Phase 1 gate, not advisory: under the default freshness:strict, a stale index is refreshed once per planning session via node .gitnexus/run.cjs analyze --index-only (appending --pdg when the task will reach the PDG phase), then the context resource is re-read. A missing PDG layer likewise triggers the one permitted --index-only --pdg refresh and re-probe instead of a passive recommendation. freshness:accept (or a failed/impractical refresh) preserves the old behavior: plan on the stale graph, source-weighted, labelled in the plan header. --index-only is the load-bearing flag choice — it suppresses all file generation, so the planning-only contract holds (only the .gitnexus store changes). Ledger gains an index_refresh record; plan header states fresh / refreshed / refresh-skipped-with-reason. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): gitnexus-plan runner build check before freshness refresh When the target repo builds the analyzer from its own source (bin → dist/ mapping, as gitnexus/ does), the Phase 1 freshness gate now verifies dist/ is current before running the analyze refresh — rebuilding via the package's build script when any analyzer source file is newer than the built entrypoint — and prefers that freshly built CLI. Otherwise a stale dist re-indexes with outdated extraction logic and the 'fresh' index lies. Rebuilds are recorded in the ledger's index_refresh; the PDG-phase refresh inherits the same check. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): add gitnexus-work executor and gitnexus-lfg pipeline gitnexus-work executes a gitnexus-plan as verified atomic commits: consumes the §11 implementation_context pack, drift-checks the plan's evidence pin against HEAD, re-verifies assumptions before relying on them, runs impact before every symbol edit and detect_changes before every commit (repo mandates), builds tests from the plan's scenarios, and routes structural drift back to gitnexus-plan Deepen mode instead of coding around it. gitnexus-lfg is a thin orchestrator: gitnexus-plan → blocking user gate (deepen / proceed / stop, deepen loops allowed) → gitnexus-work → review via the existing gitnexus-pr-review skill (open PR, else branch diff vs default). One bounded fix cycle for review findings; never pushes or opens a PR on its own. gitnexus-plan gains a Deepen mode (re-run freshness gate, escalate to depth:deep, re-verify graph/inferred/assumed claims toward verified, rewrite the same file); its 'future gitnexus-implement' placeholder is retired in favor of gitnexus-work. Registered via .gitignore whitelists, AGENTS.md 1.10.0 (section renamed to Engineering planning & execution), CLAUDE.md 1.5.0. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills): apply cross-skill review findings to the gitnexus skill family Two P1s: gitnexus-plan Deepen mode now re-anchors before re-pinning (diffs the old evidence pin over every [verified]-claim file and re-reads or downgrades before the header moves — moving the pin without this laundered stale claims as verified); the index-refresh budget is stated once in Phase 1 (one --index-only refresh plus at most one Phase 3 --pdg upgrade per session, Deepen = its own session) with ledger and pdg-slice deferring to it. Contract fixes: gitnexus-work's drift check now covers every file the pack cites (not just files_to_modify) and parses the full pack incl. primary/related symbols and acceptance_criteria (walked in Phase 4 alongside §13); a pre-completed check skips §7 steps already landed and Deepen gains a reconcile-execution-state step, closing the mid-execution route-back loop; pack assumptions must name what to check and how. lfg: Lane 4 passes the merge-base to detect_changes compare (two-dot diff misattributes upstream commits when default advanced), branch-diff is the stated normal case, oversized review findings route to the plan gate instead of overflowing direct mode, the one-fix-cycle cap is explicit on re-run, and headless runs end at the plan gate with the plan as deliverable. work: blank mode narrowed to *gitnexus-plan*.md with a re-execution guard, direct-mode discipline spelled out, branch meaningfulness defined against the plan slug, and the plan document is committed as the branch's docs commit (review diff includes it). Planning-only contract now names the dist/ rebuild as the second permitted state change; Phase 5.1 names the four claim tags; stale AGENTS.md anchors fixed. Known latent issue left untouched: gitnexus/gitnexus-pr-review pairs a three-dot example with a two-dot detect_changes compare — that skill is also shipped by the plugin, so fixing it here would drift the copies; lfg compensates by passing the merge-base. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): ship the engineering skill family with the gitnexus package npm i -g gitnexus users now get gitnexus-plan / gitnexus-work / gitnexus-lfg: the three skills are added to gitnexus/skills/ in directory form (SKILL.md + references/), which installSkillsTo already enumerates dynamically and copies recursively to every editor target (~/.agents/skills for Codex, Cursor, OpenCode, Qoder, ...) on gitnexus setup — uninstall enumerates the same root, so removal stays clean. The Claude Code plugin channel (gitnexus-claude-plugin/skills/) carries the same copies plus the standard per-skill mcp.json. Global-install support in the skill text: gitnexus-plan Phase 1 now resolves the analyzer runner explicitly — node .gitnexus/run.cjs analyze when the project has a runner, else gitnexus analyze (installed CLI), else npx gitnexus analyze — and all analyze mentions route through it, satisfying the skills-steering policy (#1939/#1945) which sweeps the plugin copies. New drift guard test/unit/shipped-skills-sync.test.ts asserts the npm and plugin copies stay byte-identical to the canonical .claude/skills/ family (plugin = canonical + mcp.json), same discipline as run.cjs ↔ resolve-invocation.ts. skills-steering + shipped-skills-sync: 11/11 green. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(eval): workflow_bench — measure the skill workflow's token savings Benchmarks gitnexus-plan → gitnexus-work against a baseline agent (--disallowedTools Skill) on identical tasks, in fresh detached worktrees, using real headless Claude Code sessions; every number comes from the CLI's --output-format json usage report (field names validated against a live 2.1.207 session). Reports per-arm medians (input/cache/output tokens, cost, wall time, turns), a savings row, and resolve status from a per-task verify command — savings on failed tasks are flagged, not celebrated. Per-task setup hook prepares fresh worktrees (deps); --permission-mode bypassPermissions (default) lets sessions run unattended in the throwaway trees. Free-model support: --base-url/--auth-token/--model route headless sessions through any Anthropic-compatible endpoint; free-model.litellm.yaml is a ready litellm-proxy template for OpenRouter :free variants or local Ollama, so benchmarking burns no paid tokens (README documents rate limits and the small-model skill-following caveat). Harness validated end-to-end with a stub CLI (worktree lifecycle, both arms, plan→work chaining, verify, aggregation, report) and 4 pytest units for the pure aggregation/savings/report helpers. AGENTS.md 1.11.0. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(eval): record first workflow_bench calibration run Trivial-task calibration (add -V alias): both arms resolved; workflow arm ~4.3x baseline cost — the documented overhead-dominated regime, recorded so the regime boundary is empirical rather than asserted. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(eval): workflow_bench scenario matrix — arm variants, task classes, churn Ground-base measurement across scenarios: tasks.scenarios.yaml spans four labeled classes (trivial → investigation-bug → investigation-feature → cross-module) with deterministic verifies (prescribed test files). New arms: workflow_direct (gitnexus-work direct mode — the middle option that locates the routing boundary lfg's gate and work's triage encode) and baseline_nomcp (no skills AND no graph tools — separates workflow-discipline value from GitNexus-tool value; off by default). Records now carry task class and diff churn (files/+ins/−del vs the starting commit) as an over-engineering proxy; the report renders a class column and per-arm savings rows vs baseline. 5 pytest units + stub-CLI e2e of the full three-arm matrix. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(eval): record workflow_bench ground base; fix churn measurement bias Ground base (3 classes x 3 arms, n=1/cell): every arm resolved every task — pass/fail quality saturates at this difficulty, making the comparison pure cost. Full plan→work never amortized its ~$9-11 fixed cost on tasks a baseline finishes in ≤35 turns (−211% to −333% cost); workflow_direct sits near baseline (−15% to −55%, once faster wall) with more test coverage. Routing implication recorded: direct mode/plain agent below this scale, full workflow for cross-module / multi-session / plan-as-deliverable work. The cross-module cell and multi-run variance are the next measurements. Churn fix: git add --intent-to-add -A before diffing (arms that never commit no longer undercount new files) and :(exclude)docs/plans (the committed plan doc no longer inflates workflow churn); this run's churn numbers predate the fix and are omitted from the recorded table. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * perf(skills): cost-optimize the workflow from measured ground base Every optimization targets a measured fixed-cost component (eval/workflow_bench ground base: workflow arm −211% to −333% vs baseline, all tasks resolved): - Plan form is category-priced: compact form (core sections w/ § anchors preserved, ≤80 lines excl. pack, mini-pack subset of the context pack) for narrow/default categories; the full 13 sections only for deep work (refactor/security/performance/concurrency/architecture). A compact plan outgrowing its cap reclassifies to full rather than overflowing. - Freshness gate is category-priced: compact categories default to accept (source-weighted, refresh only when a graph claim becomes load-bearing); strict stays the default for full-plan categories — the rebuild+re-index was the largest single fixed cost. - Turn economy: per-category tool-call budgets (~10 to ~45; architecture uncapped); budget exhaustion routes open questions to §12 instead of more digging. - gitnexus-work fast path: HEAD == evidence pin → skip all citation re-reading (the pin's entire point); mini-pack fields tolerated. - lfg Lane 1 boundary triage: tasks below the measured ~35-turn boundary get offered gitnexus-work direct mode before the plan lane is spent. Copies re-synced (npm skills/, plugin, ~/.agents); steering + sync guards green. Re-measurement of the workflow arm follows to verify the numbers actually improve. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(eval): record optimization re-measurement — inv-bug workflow cell −20% cost Same task, same conditions, post-830a0459 skills: $14.56→$11.70 (−20%), 83→72 turns, cache_read −24%; verified in-transcript that the compact form, turn budget, and skipped rebuild/re-index all fired. Wall +15% from a work- session test-debugging tail (n=1 variance). Regime unchanged (~3.5x baseline on this class) — routing rule stands. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(eval): per-arm clone isolation — worktree ref-namespace leak contaminated an arm The cross-module workflow_direct cell reported an impossible 28-turn solve with churn byte-identical to the workflow arm: git worktree add shares the repo's ref namespace, so the workflow arm's slug branch (created by gitnexus-work Phase 2) survived worktree removal and the direct arm found and adopted the completed work. Arms now get isolated git clone --shared copies (object store via alternates, refs clone-local — agent branches and stashes die with the clone; origin/<ref> fallback for non-default refs). Leaked branch deleted; baseline arm verified clean (0 branch references in its transcript); cell marked invalidated pending re-run. Records the valid cross-module cells: workflow $18.32 vs baseline $18.03 (premium −1.6%, vs −211%..−333% on smaller classes) — fixed costs amortize at this scale, with a less destructive diff and a plan artifact as bonus; resolve rate still tied. Churn fingerprinting is what caught the contamination — noted in the README as an integrity check. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(eval): complete cross-module cell — direct mode wins 47% cost / 56% wall Clean clone-isolated re-run: workflow_direct resolved the hardest class at $9.53/52 turns/15m vs $18.03/98/34m baseline and $18.32/107/37m full workflow. The measured story across all four classes: the execution discipline (gitnexus-work) is the consistent sweet spot and delivers real token savings on hard tasks; the planning pass buys its artifact, not same-session savings. Resolve rate tied everywhere (n=1/cell caveat). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(eval): add trajectory-gated skill evolution (#2431) - Pair prompt candidates with incumbent workflow arms - Gate promotions on pinned-model quality and efficiency - Expire router evidence and document its lifecycle * fix(eval): allow pr-review skill candidates * feat(skills): rename and generalize GitNexus review * feat(eval): external-comparator and review arms for workflow_bench - ce_workflow / ce_workflow_direct: compound-engineering ce-plan/ce-work arms prompted with the same structure as the gitnexus arms - review / ce_review: gitnexus-review vs ce-code-review on an identical diff applied by the task's setup - plan handoff is snapshot-based: committed example plans in docs/plans/ tie on clone mtimes and broke the name-glob pick (executed a stale plan) - verify output tail is recorded per run and the final working-tree patch is kept, so failed rows are diagnosable after the clone is destroyed Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(skills,eval): address #2431 review — data-safe rename migration, fail-closed bench evidence - setup: never delete a legacy renamed skill dir — the installer cannot prove ownership (users customize or hand-write skills under these names); warn with the path instead, and the test now asserts survival - workflow_bench: fail closed when a session's --output-format json report is empty, malformed, or missing usage fields — an exit-0 shell with no parseable usage no longer counts as measured evidence (5 parametrized regression tests) - workflow_bench: document the trust model prominently (task setup/verify are shell-executed, sessions run bypassPermissions with the parent env, candidate overlays are prompt injection surface) in README + docstring - free-model.litellm.yaml: master_key from LITELLM_MASTER_KEY env instead of a static token; loopback-binding warning - ci: run the eval workflow_bench pytest suite on ubuntu (pytest+pyyaml only — no full eval stack) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(eval): demand observed foreground verification in headless work-arm prompts In a headless -p session there is no later turn: a work arm backgrounded its slow test run, scheduled wakeups that can never fire, and reported done while two of its tests failed. All four work-arm prompts (both skill families, symmetric) now require verification output to be observed inside the session. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): ask plan depth up front instead of offering deepen afterwards gitnexus-plan Phase 0 now asks one blocking question in interactive sessions — quick / standard / deep, mapped onto the existing depth/form/ freshness knobs — when the invocation carries no explicit depth signal. Explicit knobs and headless runs skip the question (category posture unchanged, so benchmarks and automation behave as before). gitnexus-lfg's plan gate slims to proceed/stop: depth was already the user's up-front choice, so deepening is no longer offered by default — an explicit deepen request at the gate and executor route-backs still run Deepen mode, which remains the mechanism for strengthening an existing plan document. All shipped copies resynced (npm skills/, Claude plugin); AGENTS.md 1.13.0 and CLAUDE.md 1.7.0 pointers updated, including the analyzer's regenerated index-stats block at this branch's head. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): taint pass, expert lenses, and post-work index refresh gitnexus-review gains a PDG-backed taint-and-dependence pass (explain + pdg_query, --pdg folded into the stale refresh on trust-boundary diffs) and an Expert lenses section: domain reviewers derived from the graph's clusters plus four cross-cutting lenses (architectural fit, language conformance per the repo's own contract, Definition of Done, simplicity), dispatched once after the evidence-gathering steps and scaled to the diff. gitnexus-work Phase 4 now refreshes the knowledge graph after the DoD walk via the resolved-runner ladder with analyze --index-only, so the lfg review lane and later sessions query the finished work without dirtying the tree. lfg's threshold-governance paragraph moves to its README; eval citations are tagged as measured in the GitNexus repo. All shipped copies re-synced. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(cli): remove legacy gitnexus-pr-review on uninstall; cover the rename migration uninstall's removal set now includes LEGACY_SKILL_DIR_NAMES derived from RENAMED_SKILL_DIRS, so a pre-rename install is cleaned up instead of orphaned. The rename warning gains behavioral coverage (fires with a legacy dir present, silent without), and shipped-skills-sync asserts legacy names stay absent from every shipped tree. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(eval): metric provenance, error-kind rows, skill-invocation verification, gate noise floor The promotion gate defaults to cost_usd (the only metric that includes subagent spend); token metrics carry an explicit main-loop-only warning in the report and promotion.json. Rows are classified by error_kind (session-error / verify-failed / infra-error), excluded from efficiency medians, and the gate requires equal valid-run counts. Each session's transcript is scanned for the expected Skill invocation and fails closed on a verified miss; a one-run resolution edge no longer promotes (noise floor). Per-run timeouts and setup failures record an infra-error row instead of aborting the sweep. Overlays touching skills no candidate arm exercises are rejected up front. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: fix skill routing paths, version headers, and skill rosters Routing tables point at the tracked direct skill paths (matching the post-#2434 generator output), AGENTS.md/CLAUDE.md headers match their latest changelog rows, the 1.12.0 row describes what the migration actually does, package/cursor READMEs list the full shipped skill roster, and the swarm READMEs describe /gitnexus-review's expert lenses instead of calling it single-agent. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * ci: drift-guard workflow for skill copies; pin eval pip deps; track docs/plans ci.yml ignores '**.md', so an md-only skill edit would merge without the shipped-skills-sync test running — skill-sync.yml triggers exactly on the guarded trees. The eval job's pip install is version-pinned, and docs/plans/ is unignored so gitnexus-plan output can be committed. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(ci): keep the runner-invocation literal in gitnexus-review; add concurrency block to skill-sync skills-steering requires skills with a stale-index hint to carry the exact 'node .gitnexus/run.cjs analyze' form — restore it with the fallback ladder as a parenthetical instead of replacing it. skill-sync.yml gains the top-level concurrency block the workflow-convention check enforces. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(skills): token-economy guidance for expert lenses Merge lenses that ground in the same material into one reviewer, and use cheaper model/effort tiers for mechanical lenses where the harness offers them, reserving the strongest engine for adversarial judgment. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test(eval): isolate transcript home on Windows Ensure workflow_bench transcript tests set USERPROFILE alongside HOME so Path.home() resolves to the temporary test home on Windows. * docs(skills): fold PR #2522 execution learnings into review/work/plan Eight incident-backed hardenings from running the full skill cycle (review -> plan -> work, 28-finding fix series) on PR #2522: gitnexus-review: - Expert lenses execute the code under review on candidate failing shapes (empirical probe outranks source reading — every HIGH the language lenses found came from a probe, not a read). - Step 7 re-runs the exact CI check for refreshed baselines/fingerprints (a stale committed artifact is invisible in the diff; caught a red benchmarks arm). - Step 8 treats version/invalidation constants as review surface (INCREMENTAL_SCHEMA_VERSION class recurred verbatim from #2494). gitnexus-work: - Step 4 proves regression tests discriminate against the pre-fix tree. - Step 5 rebuilds executed build output before every verification run (parse workers load dist/; a correct fix 'failed' until rebuilt). - Step 6 makes stage -> detect_changes -> commit one unbroken sequence. gitnexus-plan: - Phase 0 seeded-evidence mode: plan FROM a completed review's verified findings instead of re-running the graph ladder. - Template §7: fingerprint/golden-guarded output rebaselines once, at the series tip. All distribution copies resynced; shipped-skills-sync + skills-steering 24/24 locally. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(eval): close the skill-evolution loop with an automated proposer driver workflow_bench.evolve adds the three arrows the README described as manual: a proposer session that turns loser trajectories (results.jsonl rows, transcripts, patches, the learning queue) into ONE bounded candidate overlay, a driver that iterates propose -> paired benchmark -> deterministic gate up to --generations, and an --apply step that copies a promoted overlay onto the canonical skills and shipped mirrors as a working-tree diff. The trust boundary is unchanged: overlays re-validate through candidate_overlay_files before any benchmark or apply consumes them, and committing, CI, and the PR merge stay human. learnings.jsonl is gitignored: it is machine-local evidence, like the session transcripts it complements. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(skills): route live-task friction into the evolution learning queue Each family skill gains a short 'Skill feedback' section: on friction with the skill's own instructions, append one JSON line to eval/workflow_bench/learnings.jsonl (GitNexus repo only) — never self-edit the skill from a live task. The proposer in workflow_bench.evolve consumes the queue as hints; a learning reaches a shipped skill only by beating the incumbent on the paired benchmark. All shipped mirrors re-copied byte- identical. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * ci(tests): run the evolve helper tests in the eval pytest job test_evolve.py needs only pytest+pyyaml, same as the harness tests the job already runs — without this line the new module had no CI coverage. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(ci): comment-triggered GitNexus review agent for PRs '@gitnexus review' from a maintainer (OWNER/MEMBER/COLLABORATOR; the action re-validates write access) runs the repo's gitnexus-review skill headlessly against the PR and posts the review as a sticky comment — remote triggering with no local setup. Read-only by construction: contents: read token, Write/Edit and web tools disallowed, Bash allowlisted to git reads and the gitnexus CLI; analyze parses PR code with tree-sitter, never executes it. Requires the ANTHROPIC_API_KEY repository secret; activates once the file is on the default branch. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat(ci): dispatch lane + existing OAuth secret for the review agent Align with claude.yml: same action pin and the CLAUDE_CODE_OAUTH_TOKEN secret the repo already carries — no new secret to configure. Add a workflow_dispatch lane (PR number input) so the agent can be triggered from the Actions UI and tested before the issue_comment trigger reaches the default branch. Allowlist gh pr view/diff and gh api, which the review skill uses to pin PR SHAs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(ci): close a fork-PR RCE vector in the review agent's tool allowlist A live headless run of the exact workflow session against PR #2431 (66 turns, full gitnexus-review pass) surfaced a real HIGH-severity confused deputy: .gitnexus/ is gitignored, not blocked — a fork PR can commit its own .gitnexus/run.cjs, issue_comment checks out PR-head content, and the skill's runner ladder tries 'node .gitnexus/run.cjs analyze' first. That would execute fork-controlled JS inside a job holding CLAUDE_CODE_OAUTH_TOKEN and a write-scoped GITHUB_TOKEN — the opposite of the 'PR code is read, never executed' claim in the workflow's own header. Fix: drop the run.cjs allowlist entry so analyze always resolves through npx gitnexus (npm registry, not the checked-out tree); the skill's documented fallback mode covers the resulting graceful degradation. Also drop 'gh api' (not read-only — accepts -X POST/PATCH/DELETE) and downgrade pull-requests: write to read (comment posting only needs issues: write; the prompt already forbids formal review submission). Same session flagged a latent evolve.py bug: select_evidence's cost sort used dict.get's missing-key default, which doesn't cover an explicit JSON null in a foreign --seed-results row and crashes proposer setup with TypeError. Guarded with 'or 0.0' and added a regression test. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: harden PR review and evolution trust boundaries * ci: follow workflow concurrency convention * fix(eval): make terminating error paths explicit * fix: unblock hardened review runtime checks * test: make containment canaries deterministic * test: expose Claude canary tool failures * fix: adapt clean shell environment for Claude * fix(eval): accept the runner's transcript source key in evidence preflight The proposer evidence preflight required transcript-artifact metadata to be exactly {path, sha256, bytes}, but the runner stamps a fourth provenance key (source=parent-captured-stream-json). Any --seed-results or generation>=2 run therefore aborted with SandboxError before proposing or promoting. Pin the producer literal as PARENT_EVENT_STREAM_SOURCE and validate it in the metadata check, and round-trip real producer output through sum_sessions into the preflight so the schema can't drift again. * fix(eval): treat an unmeasured session cost as unavailable, not $0 well_formed validated only the nested usage block, so an otherwise-successful session missing total_cost_usd was recorded as cost_usd=0.0 — and cost_usd is the default promotion metric (lower wins), so a cost-less session scored as free and could win promotion it never earned. Extract cost via measured_cost() (None on absent/garbage, a measured 0.0 preserved), propagate None through sum_sessions/aggregate/savings/report, and have the gate refuse to rank on a metric that was not measured on every run in both arms. * fix(eval): warn when ranking on the main-loop-only num_turns metric num_turns comes from the CLI's top-level usage (main-loop session only), like output_tokens, but selecting it emitted no metric_warning — so a subagent-heavy candidate could look artificially efficient. Add num_turns to MAIN_LOOP_ONLY_METRICS and broaden the warning to cover turns. * fix(eval): fail closed when an overlay adds a file with no committed base An overlay adding a new .md under gitnexus-{plan,work} passes the structural overlay checks but has no committed base for committed_destination_base_digests to bind against, so it raised an uncaught ValueError that crashed the evolve driver (and runner --candidate-overlay) mid-run. Catch it at both call sites: evolve reports NOT PROMOTED and exits, runner routes it through parser.error. * feat(eval): circuit-break the runner sweep on a systemic outage A sustained upstream outage used to pay out every remaining --timeout window one session at a time. Track consecutive session/infra/cleanup failures via a pure systemic_outage_streak helper; after --outage-streak (default 5) in a row, stop the sweep, still write report.md/promotion.json from partial evidence, and exit non-zero so evolve.py halts instead of proposing from truncated evidence. A task's own resolved=False never trips the breaker. * fix(cli): report a dirty working tree as stale in gitnexus status status --json (and the human output) computed up-to-date from commit + runner identity + completeness only, so a repo with uncommitted source changes at a matching HEAD was reported up-to-date while analyze would still re-index it. A graph-backed agent gating on that JSON could skip re-analysis on a stale graph. Extract analyze's dirty-tree check into a shared isWorkingTreeDirty() in storage/git and fold it into the status freshness decision. * fix(ci): use single-slash deny globs in the review agent's disallowedTools github.workspace already expands to an absolute path, so Read(/${{ github.workspace }}/**) and Read(//proc/**),(//sys/**),(//dev/**) produced double-slash patterns that a normalizing matcher may not match — silently no-opping the deny layer. Not exploitable (the allowlist is the primary control and never grants those paths), but the globs should be well-formed. Update the pinned test strings. * ci: install gitnexus-shared with npm ci from the committed lockfile The gitnexus-shared build floated its deps via npm install in three workflows (skill-sync, ci-tests, and — most importantly — the release publish.yml) while every other install step uses npm ci. The lockfile is committed and in sync, so switch all three to npm ci for reproducible, locked installs. * test(cli): make the shipped-skills drift guard reject symlinks listFilesRecursive walked with readdirSync and snapshotDir read with readFileSync, both of which follow symlinks — so a mirror file symlinked to the canonical tree passed the byte-compare (and a symlinked mirror dir would be followed too). Reject a symlinked root via lstat and any symlinked entry via Dirent.isSymbolicLink, with negative tests (skipped on Windows). * test(eval): guard the candidate-skill vs mirror-root coverage invariant MIRROR_SKILL_ROOTS omits the Cursor tree, safe only because no candidate skill is cursor-shipped. Pin that invariant: every CANDIDATE_SKILLS entry must exist under canonical + every mirror root and must not ship to Cursor, so adding a cursor-shipped skill to the candidate set (the PR #2488 asymmetric-sync class) fails loudly instead of syncing three of four trees. * docs(ci): describe the review agent's staged post-merge rollout The DoD asked for a dry-run or triggered run before merge, but an issue_comment (or newly added workflow_dispatch) workflow only ever executes the default-branch copy, so it cannot be exercised from the PR that introduces it. Reword the DoD and the activation checklist to a staged rollout: merge registered-but-disabled, validate same-repo and fork execution post-merge, then enable the variable. * fix: pin plugin skill mcp.json to the release version via #2445 tooling The ten plugin skill mcp.json launched `npx -y gitnexus@latest mcp` on every skill connect — non-reproducible and a supply-chain surface, and (unlike the persisted setup config) never pinned. Extend sync-plugin-manifests.mjs with an mcp surface kind that stamps the gitnexus@<version> launch arg, pin all ten to 1.6.9 now, and keep them byte-identical so the drift guard stays green. The release lifecycle + publish.yml --check now re-stamp them like the four manifest surfaces; only READMEs stay on @latest as docs. * test(eval): prove the proposer's built-in file tools are confined The real-Claude canary only exercised Bash + MCP, so it proved process/MCP containment but not that the proposer's built-in file tools stay inside their mounts. Add a canary over the exact PROPOSER_ALLOWED_TOOLS surface and the same read-only /evidence mount as run_proposer (allowlist extracted to a shared constant so it can't drift): Read reaches /evidence, a Write into the read-only evidence mount is denied, and a Write lands in the output tree. * fix(eval): apply the candidate overlay after task setup for fair arms The candidate overlay was applied before the task's untrusted setup ran, so setup could observe candidate prose and the incumbent/candidate arms started from different pre-overlay state. Reorder within the sandbox: capture the base (pre-overlay) skill digest, run setup against the base skills, verify setup did not tamper them, then apply the overlay and capture the post-overlay digest the model must preserve. apply_candidate_overlay stages path-specific overlay files, so setup's uncommitted changes stay out of the baseline and churn is unchanged. Graph freshness for the review arm is handled by the status dirty-tree fix plus the review skill's stale-triggered re-index, not by reordering the cached per-task-sha graph materialization (which is mechanically blocked). * test(eval): end-to-end containment proof of the autonomous proposer Drives the real run_proposer through bubblewrap with a deterministic scripted model (no paid API): it reads the read-only evidence bundle and writes a candidate gitnexus-plan skill edit plus a rationale into the sandbox output tree; run_proposer enforces the trust boundary and copies only the validated overlay + proposal out. This exercises the autonomous-proposal stage of the self-evolution loop end-to-end in the eval/containment CI job (the gate and apply stages are covered by test_workflow_bench_evolution and test_promotion_apply). Env-gated on GITNEXUS_REQUIRE_CLAUDE_CANARY, so it runs only where the pinned Claude binary and user namespaces are available. * fix(eval): let the proposer author its overlay via Bash Running the end-to-end proposer canary in the containment CI job surfaced a real bug: run_proposer starts the session with --bare, which hard-disables the Write/Edit tools ("Write exists but is not enabled in this context"), yet allowlisted Edit/Write and omitted Bash. The proposer therefore had no working way to write its candidate overlay — the self-evolution loop could never produce a candidate. The sandbox settings already pre-authorize Bash (autoAllowBashIfSandboxed) and confine writes to workspace/tmp/home, so switch PROPOSER_ALLOWED_TOOLS to Read/Grep/Glob/Bash and tell the proposer to author files with Bash. The end-to-end test now drives the real run_proposer through bubblewrap and asserts a validated overlay + proposal are produced (this also replaces the earlier file-tool canary, whose Write/Edit premise was moot). * test(eval): author the proposer overlay with newline-free Bash content The nested shell-sandbox prefix mangles embedded newlines, so the multi-line overlay content never landed. Use single-line content for the deterministic proposer canary. * test(eval): drop the unverifiable end-to-end proposer canary The scripted proposer overlay never materialized in the containment job across runs, and the model tool-result content is not visible in CI logs, so the test cannot be finalized without an environment where the sandbox can actually run. Keep the verified production fix (Bash-authoring in run_proposer); the proposer sandbox/containment stays covered by the existing Bash+MCP and process-tree canaries. * test(cli): drop run-analyze.ts from the windowsHide spawn-family list U7 moved run-analyze.ts's only child_process call (the git status --porcelain dirty check) into storage/git.ts (already covered by this test, with windowsHide). run-analyze.ts no longer imports a spawn-family function, so the windowsHide-regression test's 'must have >=1 spawn call' invariant failed for it. Remove it from SRC_FILES. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: Zander Raycraft <zanderjraycraft@gmail.com> Co-authored-by: Azizur Rahman <azizur100389@gmail.com>
492 lines
18 KiB
Python
492 lines
18 KiB
Python
"""Workspace, patch, and verifier evidence for workflow benchmark runs."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import os
|
|
import re
|
|
import shutil
|
|
import stat
|
|
import tempfile
|
|
from dataclasses import dataclass
|
|
from pathlib import Path, PurePosixPath
|
|
from typing import Any, Iterator, Sequence
|
|
|
|
from .evolution import skill_fingerprint
|
|
from .process_control import ManagedProcessError, ManagedProcessResult, run_checked, run_managed
|
|
from .proposer_sandbox import SANDBOX_WORKSPACE, SandboxSession, build_sandbox_environment
|
|
|
|
MAX_PATCH_BYTES = 300_000
|
|
MAX_WORKSPACE_SNAPSHOT_ENTRIES = 100_000
|
|
MAX_WORKSPACE_SNAPSHOT_PATH_BYTES = 16 * 1024 * 1024
|
|
MAX_WORKSPACE_SNAPSHOT_FILE_BYTES = 1024 * 1024 * 1024
|
|
|
|
IMPLEMENTATION_ARMS = frozenset(
|
|
{
|
|
"workflow",
|
|
"workflow_direct",
|
|
"ce_workflow",
|
|
"ce_workflow_direct",
|
|
"baseline",
|
|
"baseline_nomcp",
|
|
}
|
|
)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class VerificationResult:
|
|
"""Verifier output that preserves infrastructure terminal state."""
|
|
|
|
command: Sequence[str] | str
|
|
process: ManagedProcessResult
|
|
output: str
|
|
|
|
@property
|
|
def passed(self) -> bool:
|
|
return self.process.ok
|
|
|
|
def __iter__(self) -> Iterator[bool | str]:
|
|
# Preserve the historical two-value unpacking API for standalone
|
|
# callers while runner.py inspects ``process.state`` explicitly.
|
|
yield self.passed
|
|
yield self.output
|
|
|
|
|
|
def workspace_snapshot(worktree: Path) -> dict[str, str]:
|
|
"""Hash the workspace without following links, excluding Git internals."""
|
|
|
|
root = worktree.expanduser().absolute()
|
|
mode = root.lstat().st_mode
|
|
if stat.S_ISLNK(mode) or not stat.S_ISDIR(mode) or root.resolve(strict=True) != root:
|
|
raise ValueError(f"workspace snapshot root must be a real directory: {root}")
|
|
|
|
snapshot: dict[str, str] = {}
|
|
pending: list[tuple[Path, PurePosixPath]] = [(root, PurePosixPath())]
|
|
entry_count = 0
|
|
path_bytes = 0
|
|
file_bytes = 0
|
|
nofollow = getattr(os, "O_NOFOLLOW", 0)
|
|
while pending:
|
|
directory, relative_dir = pending.pop()
|
|
try:
|
|
children = sorted(os.scandir(directory), key=lambda entry: entry.name, reverse=True)
|
|
except OSError as exc:
|
|
raise ValueError(f"workspace snapshot directory is unreadable: {directory}: {exc}") from exc
|
|
for entry in children:
|
|
relative = relative_dir / entry.name
|
|
if relative.parts[0] == ".git":
|
|
continue
|
|
entry_count += 1
|
|
path_bytes += len(relative.as_posix().encode())
|
|
if entry_count > MAX_WORKSPACE_SNAPSHOT_ENTRIES or path_bytes > MAX_WORKSPACE_SNAPSHOT_PATH_BYTES:
|
|
raise ValueError("workspace snapshot exceeds its bounded entry or path limit")
|
|
metadata = entry.stat(follow_symlinks=False)
|
|
permissions = stat.S_IMODE(metadata.st_mode)
|
|
if stat.S_ISDIR(metadata.st_mode):
|
|
snapshot[relative.as_posix()] = f"d:{permissions:o}"
|
|
pending.append((Path(entry.path), relative))
|
|
continue
|
|
if stat.S_ISLNK(metadata.st_mode):
|
|
snapshot[relative.as_posix()] = f"l:{permissions:o}:{os.readlink(entry.path)}"
|
|
continue
|
|
if not stat.S_ISREG(metadata.st_mode):
|
|
snapshot[relative.as_posix()] = f"s:{metadata.st_mode}"
|
|
continue
|
|
file_bytes += metadata.st_size
|
|
if file_bytes > MAX_WORKSPACE_SNAPSHOT_FILE_BYTES:
|
|
raise ValueError("workspace snapshot exceeds its bounded file-byte limit")
|
|
descriptor = os.open(entry.path, os.O_RDONLY | nofollow)
|
|
try:
|
|
opened = os.fstat(descriptor)
|
|
if (
|
|
not stat.S_ISREG(opened.st_mode)
|
|
or opened.st_dev != metadata.st_dev
|
|
or opened.st_ino != metadata.st_ino
|
|
):
|
|
raise ValueError(f"workspace file changed while opening: {entry.path}")
|
|
digest = hashlib.sha256()
|
|
while chunk := os.read(descriptor, 64 * 1024):
|
|
digest.update(chunk)
|
|
after = os.fstat(descriptor)
|
|
if (opened.st_size, opened.st_mtime_ns) != (after.st_size, after.st_mtime_ns):
|
|
raise ValueError(f"workspace file changed while hashing: {entry.path}")
|
|
finally:
|
|
os.close(descriptor)
|
|
snapshot[relative.as_posix()] = f"f:{permissions:o}:{metadata.st_size}:{digest.hexdigest()}"
|
|
return snapshot
|
|
|
|
|
|
def enforce_phase_workspace(
|
|
worktree: Path,
|
|
before: dict[str, str],
|
|
*,
|
|
allowed_artifact: Path,
|
|
) -> None:
|
|
"""Require a phase to change only its one explicit workspace artifact."""
|
|
|
|
root = worktree.expanduser().absolute()
|
|
artifact = allowed_artifact.expanduser().absolute()
|
|
try:
|
|
relative = PurePosixPath(artifact.relative_to(root).as_posix())
|
|
except ValueError as exc:
|
|
raise ValueError(f"phase artifact escapes the workspace: {allowed_artifact}") from exc
|
|
after = workspace_snapshot(root)
|
|
changed = {path for path in before.keys() | after.keys() if before.get(path) != after.get(path)}
|
|
artifact_key = relative.as_posix()
|
|
artifact_state = after.get(artifact_key)
|
|
if before.get(artifact_key) == artifact_state:
|
|
raise ValueError(f"phase did not create or change its required artifact: {relative}")
|
|
if artifact_state is None or not artifact_state.startswith("f:"):
|
|
raise ValueError(f"phase artifact must be a regular non-symlink file: {relative}")
|
|
|
|
try:
|
|
metadata = artifact.lstat()
|
|
descriptor = os.open(artifact, os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0))
|
|
except OSError as exc:
|
|
raise ValueError(f"phase artifact must be a readable regular non-symlink file: {relative}") from exc
|
|
try:
|
|
opened = os.fstat(descriptor)
|
|
if (
|
|
stat.S_ISLNK(metadata.st_mode)
|
|
or not stat.S_ISREG(metadata.st_mode)
|
|
or not stat.S_ISREG(opened.st_mode)
|
|
or metadata.st_dev != opened.st_dev
|
|
or metadata.st_ino != opened.st_ino
|
|
):
|
|
raise ValueError(f"phase artifact must be a regular non-symlink file: {relative}")
|
|
finally:
|
|
os.close(descriptor)
|
|
|
|
allowed = {artifact_key}
|
|
parent = relative.parent
|
|
while parent.parts:
|
|
parent_key = parent.as_posix()
|
|
if parent_key not in before and after.get(parent_key, "").startswith("d:"):
|
|
allowed.add(parent_key)
|
|
parent = parent.parent
|
|
unauthorized = sorted(changed - allowed)
|
|
if unauthorized:
|
|
preview = ", ".join(unauthorized[:8])
|
|
suffix = " …" if len(unauthorized) > 8 else ""
|
|
raise ValueError(f"phase changed unauthorized workspace path(s): {preview}{suffix}")
|
|
|
|
|
|
def require_skill_fingerprint(worktree: Path, arm: str, expected: str | None, *, phase: str) -> None:
|
|
"""Fail closed when a bounded phase changes the evaluated prompt roots."""
|
|
|
|
try:
|
|
observed = skill_fingerprint(worktree, arm)
|
|
except (OSError, ValueError) as exc:
|
|
raise ValueError(f"{phase} changed the evaluated skill fingerprint") from exc
|
|
if observed != expected:
|
|
raise ValueError(f"{phase} changed the evaluated skill fingerprint")
|
|
|
|
|
|
def snapshot_plan_docs(worktree: Path) -> dict[Path, str]:
|
|
"""Hash direct, regular plan artifacts without following links."""
|
|
|
|
plans = worktree / "docs" / "plans"
|
|
if not plans.exists():
|
|
return {}
|
|
if plans.is_symlink() or not plans.is_dir():
|
|
raise ValueError(f"plan directory must be a real directory: {plans}")
|
|
|
|
snapshot: dict[Path, str] = {}
|
|
for path in sorted(plans.iterdir()):
|
|
if path.suffix.lower() not in {".md", ".html"}:
|
|
continue
|
|
metadata = path.lstat()
|
|
if stat.S_ISLNK(metadata.st_mode):
|
|
raise ValueError(f"plan artifact cannot be a symlink: {path}")
|
|
if not stat.S_ISREG(metadata.st_mode):
|
|
raise ValueError(f"plan artifact must be a regular file: {path}")
|
|
descriptor = os.open(path, os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0))
|
|
try:
|
|
opened = os.fstat(descriptor)
|
|
if not stat.S_ISREG(opened.st_mode) or opened.st_dev != metadata.st_dev or opened.st_ino != metadata.st_ino:
|
|
raise ValueError(f"plan artifact changed while opening: {path}")
|
|
with os.fdopen(descriptor, "rb", closefd=False) as handle:
|
|
snapshot[path] = hashlib.file_digest(handle, "sha256").hexdigest()
|
|
after = os.fstat(descriptor)
|
|
if (opened.st_size, opened.st_mtime_ns) != (after.st_size, after.st_mtime_ns):
|
|
raise ValueError(f"plan artifact changed while hashing: {path}")
|
|
finally:
|
|
os.close(descriptor)
|
|
return snapshot
|
|
|
|
|
|
def new_plan_doc(worktree: Path, before: dict[Path, str]) -> Path:
|
|
"""Return the sole new or modified plan, rejecting ambiguous evidence."""
|
|
|
|
after = snapshot_plan_docs(worktree)
|
|
deleted = sorted(path for path in before if path not in after)
|
|
if deleted:
|
|
raise ValueError("planning deleted existing plan artifact(s): " + ", ".join(str(path) for path in deleted))
|
|
changed = sorted(path for path, digest in after.items() if before.get(path) != digest)
|
|
if len(changed) != 1:
|
|
raise ValueError(f"planning must create or modify exactly one plan artifact; observed {len(changed)}")
|
|
return changed[0]
|
|
|
|
|
|
def make_worktree(repo: Path, ref: str, parent: Path) -> Path:
|
|
"""Create a self-contained clone per benchmark arm."""
|
|
|
|
target = Path(tempfile.mkdtemp(prefix="wfbench-", dir=parent))
|
|
target.rmdir()
|
|
try:
|
|
run_checked(
|
|
[
|
|
"git",
|
|
"clone",
|
|
"--no-local",
|
|
"--no-hardlinks",
|
|
"--quiet",
|
|
str(repo),
|
|
str(target),
|
|
],
|
|
timeout=600,
|
|
)
|
|
alternates = target / ".git" / "objects" / "info" / "alternates"
|
|
if alternates.exists():
|
|
raise RuntimeError(f"clone unexpectedly has an external object alternate: {alternates}")
|
|
for obj in (target / ".git" / "objects").rglob("*"):
|
|
if obj.is_file() and obj.stat().st_nlink > 1:
|
|
raise RuntimeError(f"clone object is hardlinked to host storage: {obj}")
|
|
for candidate in (ref, f"origin/{ref}"):
|
|
proc = run_managed(
|
|
["git", "-C", str(target), "checkout", "--detach", "--quiet", candidate],
|
|
timeout=60,
|
|
)
|
|
if proc.ok:
|
|
return target
|
|
raise RuntimeError(f"ref {ref!r} not found in clone of {repo}")
|
|
except BaseException as primary:
|
|
if target.exists():
|
|
try:
|
|
shutil.rmtree(target)
|
|
except OSError as cleanup:
|
|
primary.add_note(f"clone cleanup also failed: {type(cleanup).__name__}: {cleanup}")
|
|
raise
|
|
|
|
|
|
def remove_clone(clone: Path) -> None:
|
|
"""Delete one throwaway arm clone (created by make_worktree)."""
|
|
|
|
shutil.rmtree(clone)
|
|
|
|
|
|
def parse_shortstat(text: str) -> dict[str, int]:
|
|
"""Parse `git diff --shortstat` output into churn counters."""
|
|
|
|
keys = {
|
|
"file": "diff_files",
|
|
"insertion": "diff_insertions",
|
|
"deletion": "diff_deletions",
|
|
}
|
|
out = dict.fromkeys(keys.values(), 0)
|
|
for count, word in re.findall(r"(\d+) (file|insertion|deletion)", text):
|
|
out[keys[word]] = int(count)
|
|
return out
|
|
|
|
|
|
def _sandbox_git(sandbox: SandboxSession, args: list[str], *, timeout: int = 60) -> str:
|
|
command = ["/usr/bin/git", "-c", "core.fsmonitor=false", *args]
|
|
result = sandbox.run(command, timeout=timeout, env=build_sandbox_environment())
|
|
if not result.ok:
|
|
raise ManagedProcessError(command, result)
|
|
return result.stdout_tail
|
|
|
|
|
|
def _prepare_untracked_for_diff(sandbox: SandboxSession) -> None:
|
|
_sandbox_git(sandbox, ["add", "--intent-to-add", "-A"])
|
|
|
|
|
|
def implementation_diff_digest(
|
|
sandbox: SandboxSession,
|
|
orig_sha: str,
|
|
*,
|
|
prepare_untracked: bool = True,
|
|
) -> str:
|
|
"""Digest non-plan final work entirely inside the containment boundary."""
|
|
|
|
if not re.fullmatch(r"[0-9a-fA-F]{40,64}", orig_sha):
|
|
raise ValueError(f"unsafe git object id: {orig_sha!r}")
|
|
if prepare_untracked:
|
|
_prepare_untracked_for_diff(sandbox)
|
|
command = (
|
|
"/usr/bin/git -c core.fsmonitor=false diff --no-ext-diff --no-textconv --binary "
|
|
f"{orig_sha} -- . ':(exclude)docs/plans' ':(exclude).claude/skills' "
|
|
"| /usr/bin/sha256sum"
|
|
)
|
|
result = sandbox.run(
|
|
["/bin/sh", "-c", command],
|
|
timeout=60,
|
|
env=build_sandbox_environment(),
|
|
)
|
|
if not result.ok:
|
|
raise ManagedProcessError(command, result)
|
|
digest = result.stdout_tail.strip().split()[0] if result.stdout_tail.strip() else ""
|
|
if not re.fullmatch(r"[0-9a-f]{64}", digest):
|
|
raise RuntimeError("sandboxed git diff did not produce a SHA-256 digest")
|
|
return digest
|
|
|
|
|
|
def diff_churn(
|
|
sandbox: SandboxSession,
|
|
orig_sha: str,
|
|
*,
|
|
prepare_untracked: bool = True,
|
|
) -> dict[str, int]:
|
|
"""Return code churn versus the arm's starting SHA."""
|
|
|
|
if prepare_untracked:
|
|
_prepare_untracked_for_diff(sandbox)
|
|
output = _sandbox_git(
|
|
sandbox,
|
|
[
|
|
"diff",
|
|
"--no-ext-diff",
|
|
"--no-textconv",
|
|
"--shortstat",
|
|
orig_sha,
|
|
"--",
|
|
".",
|
|
":(exclude)docs/plans",
|
|
":(exclude).claude/skills",
|
|
],
|
|
)
|
|
return parse_shortstat(output)
|
|
|
|
|
|
def _bounded_regular_bytes(path: Path, *, limit: int) -> bytes:
|
|
"""Read at most ``limit`` bytes without following a generated link."""
|
|
|
|
metadata = path.lstat()
|
|
if stat.S_ISLNK(metadata.st_mode) or not stat.S_ISREG(metadata.st_mode):
|
|
raise RuntimeError(f"generated artifact is not a regular non-symlink file: {path}")
|
|
nofollow = getattr(os, "O_NOFOLLOW", 0)
|
|
descriptor = os.open(path, os.O_RDONLY | nofollow)
|
|
try:
|
|
opened = os.fstat(descriptor)
|
|
if not stat.S_ISREG(opened.st_mode):
|
|
raise RuntimeError(f"generated artifact changed type while opening: {path}")
|
|
chunks: list[bytes] = []
|
|
remaining = limit
|
|
while remaining > 0:
|
|
chunk = os.read(descriptor, min(64 * 1024, remaining))
|
|
if not chunk:
|
|
break
|
|
chunks.append(chunk)
|
|
remaining -= len(chunk)
|
|
return b"".join(chunks)
|
|
finally:
|
|
os.close(descriptor)
|
|
|
|
|
|
def capture_patch(sandbox: SandboxSession, worktree: Path, orig_sha: str) -> bytes:
|
|
"""Stream a final patch inside the sandbox while retaining a bounded prefix."""
|
|
|
|
artifact_dir = Path(tempfile.mkdtemp(prefix=".wfbench-artifact-", dir=worktree))
|
|
artifact_dir.chmod(0o700)
|
|
patch = artifact_dir / "final.patch"
|
|
sandbox_path = f"{SANDBOX_WORKSPACE}/{artifact_dir.relative_to(worktree).as_posix()}/final.patch"
|
|
sink = """\
|
|
import subprocess
|
|
import sys
|
|
|
|
limit = int(sys.argv[1])
|
|
output = sys.argv[2]
|
|
command = sys.argv[3:]
|
|
with open(output, "xb") as handle:
|
|
process = subprocess.Popen(command, stdout=subprocess.PIPE)
|
|
assert process.stdout is not None
|
|
remaining = limit
|
|
for chunk in iter(lambda: process.stdout.read(65536), b""):
|
|
if remaining:
|
|
retained = chunk[:remaining]
|
|
handle.write(retained)
|
|
remaining -= len(retained)
|
|
process.stdout.close()
|
|
returncode = process.wait()
|
|
if returncode:
|
|
raise SystemExit(returncode)
|
|
"""
|
|
command = [
|
|
"/usr/bin/python3",
|
|
"-I",
|
|
"-c",
|
|
sink,
|
|
str(MAX_PATCH_BYTES),
|
|
sandbox_path,
|
|
"/usr/bin/git",
|
|
"-c",
|
|
"core.fsmonitor=false",
|
|
"diff",
|
|
"--no-ext-diff",
|
|
"--no-textconv",
|
|
"--binary",
|
|
orig_sha,
|
|
"--",
|
|
".",
|
|
":(exclude).wfbench-artifact-*",
|
|
]
|
|
result = sandbox.run(command, timeout=60, env=build_sandbox_environment())
|
|
if not result.ok:
|
|
raise ManagedProcessError(command, result)
|
|
return _bounded_regular_bytes(patch, limit=MAX_PATCH_BYTES)
|
|
|
|
|
|
def enforce_work_evidence(
|
|
record: dict[str, Any],
|
|
*,
|
|
arm: str,
|
|
before_digest: str,
|
|
after_digest: str,
|
|
) -> None:
|
|
if arm not in IMPLEMENTATION_ARMS or not record.get("resolved"):
|
|
return
|
|
if before_digest != after_digest:
|
|
return
|
|
record["resolved"] = False
|
|
record["error_kind"] = "no-work-produced"
|
|
record["error_detail"] = "verifier passed but the implementation arm produced no non-plan repository change"
|
|
|
|
|
|
def run_verify(
|
|
command: str,
|
|
cwd: Path,
|
|
timeout: int,
|
|
*,
|
|
command_prefix: list[str] | None = None,
|
|
env: dict[str, str] | None = None,
|
|
require_pid_namespace: bool = False,
|
|
) -> VerificationResult:
|
|
"""Run the task's verify command; keep its output tail for diagnosis."""
|
|
|
|
if command_prefix:
|
|
# HOME is writable during model execution. A non-login shell prevents
|
|
# candidate-created profile files from running inside trusted evidence
|
|
# collection or either verifier.
|
|
managed_command: list[str] | str = [*command_prefix, "/bin/sh", "-c", command]
|
|
shell = False
|
|
managed_cwd: Path | None = None
|
|
else:
|
|
managed_command = command
|
|
shell = True
|
|
managed_cwd = cwd
|
|
proc = run_managed(
|
|
managed_command,
|
|
shell=shell,
|
|
cwd=managed_cwd,
|
|
env=env,
|
|
timeout=timeout,
|
|
require_pid_namespace=require_pid_namespace,
|
|
)
|
|
output = proc.stdout_tail + "\n" + proc.stderr_tail
|
|
if proc.detail:
|
|
output += f"\n[{proc.state}] {proc.detail}"
|
|
return VerificationResult(
|
|
command=managed_command,
|
|
process=proc,
|
|
output=output[-4000:],
|
|
)
|