ab550a7c5a917f261a18121bcbe9ab4c7fe4b01e
6
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Claude (review-harness setup)andClaude Opus 4.7
|
ab550a7c5a |
Apply B5 from 2026-04-30 scrum — scanner skip-list scoped to harness self
Opus-only BLOCK from the cross-lineage scrum: pre-fix SkipDirs basename-matched bin/build/dist/target/reports for ANY repo, silently excluding legitimate source dirs on real targets. The lakehouse Rust repo has reports/ holding markdown; some Java/ Python/Go projects use bin/ as a source dir; target/ is project- specific. Skipping them globally produced silent false-negative scans the operator would never know about. Fix: trim SkipDirs to dirs that are universally not source code — .git, .hg, .svn (VCS metadata); node_modules, vendor (dep caches); __pycache__, .venv, venv (Python envs); .idea, .vscode (editor state). Removed: bin, build, dist, target, reports. For the harness's own self-skip (it shouldn't scan its own bin/ or reports/), added path-scoped skip via selfSkipsFor — detects "this is the harness repo" by the presence of BOTH cmd/review-harness/ AND internal/analyzers/ subdirs (combination unique to this codebase), then skips the absolute paths bin/ and reports/ for that scan only. Two regression tests: - TestWalk_DoesNotSkipBinReportsInTargetRepo plants files under bin/, reports/, build/, dist/, target/ in a synthetic target repo; asserts all 5 appear in scan, while .git/ + node_modules/ + vendor/ are still skipped. - TestWalk_SelfSkipsBinReportsInHarnessRepo plants the harness's marker dirs (cmd/review-harness/, internal/analyzers/) plus bin/ + reports/ + ordinary src/; asserts self-skip fires on bin/+reports/ but real src/ scans normally. Compiled artifacts inside bin/ are filtered by the analyzers' isTextLike extension check (.exe / .dll / .so), so target repos with bin/ holding compiled output don't waste cycles decoding it. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Claude (review-harness setup)andClaude Opus 4.7
|
305f5b9ac0 |
Apply B1+B2+B3+B4 from 2026-04-30 cross-lineage scrum
Cross-lineage scrum (Opus 4.7 / Kimi K2.6 / Qwen3-coder via chatd's
/v1/chat) on the harness's first 4 commits surfaced 5 real bugs;
this commit lands the 4 inside the LLM/validator stack. B5 (scanner
skip-list semantics) ships separately as it changes scan behavior
on every target repo.
B1 (Kimi BLOCK + Opus WARN convergent) — internal/validators:
evidencePresent had two flaws: (1) cursor advanced on match in the
trim-line fallback, breaking same-line repeated matches AND skipping
not-yet-considered lines so out-of-order evidence spuriously failed;
(2) strings.Contains on a single `}` trim-matched any closing brace
in the file, defeating the "evidence quotes real text" contract.
Fix: trivial-evidence guard FIRST (reject anything <4 non-whitespace
chars) + per-line search no longer advances a cursor. New regression
test TestEvidencePresent_RejectsTrivialMatches covers `}`, `{`, `)`,
empty, and out-of-order multi-line evidence (which now passes —
order isn't part of the contract).
B2 (Kimi WARN + Opus WARN convergent) — internal/pipeline:
WriteJSON error for rejected-findings.json was swallowed with
`if err == nil`, so a write failure left the validation phase
reporting status="ok" while the audit trail vanished. Mirror the
validated-findings branch: surface the error in
validatePhase.Errors + bump status to degraded + ExitCode=66.
B3 (Kimi BLOCK + Opus BLOCK convergent) — internal/llm/ollama.go:
HealthCheck.basic_prompt_ok was set to true on ANY non-empty
response, so a model emitting `<think>...` traces or apologies
passed silently. Now requires the response to contain "OK"
(uppercase, substring). Substring rather than equality lets minor
whitespace/punctuation variations through (some models add a
trailing period). Errors now record what the model actually said
when it fails the check.
B4 (Opus BLOCK only — same class as today's chatd Anthropic-temp
fix) — internal/llm/ollama.go: chatBody had `if opts.Temperature != 0`
which silently dropped Temperature=0 from the request, so HealthCheck
+ Reviewer (both pass Temperature=0 expecting determinism) actually
ran at Ollama's ~0.8 default. Always forward Temperature now. The
two callers always set explicit values, so "0 means 0" is correct;
if a future caller wants Ollama's default they'll switch
CompleteOptions.Temperature to *float64 like chatd did this morning.
Verified end-to-end: insecure-repo + --enable-llm still produces 25
confirmed findings (16 static + 9 LLM), 0 rejected. Validator unit
tests: 11 pass (added TestEvidencePresent_RejectsTrivialMatches).
Same-day-as-shipping scrum, same-day-as-shipping fixes. The
convergent-≥2 gate caught 3 of these; the 4th was Opus-only but
verified by reading the code (same idiom as today's chatd bug).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Claude (review-harness setup)andClaude Opus 4.7
|
4dc53c5798 |
Phase D — validator cross-checks LLM findings + 2 close-out fixes
Implements PROMPT.md / docs/REVIEW_PIPELINE.md Phase 3:
"AI may suggest. Code validates."
internal/validators/validate.go — 3 hard checks per the
"Reject A Finding If" list:
- file does not exist (with path-traversal guard against the LLM
hallucinating ../../../etc/passwd)
- cited evidence does not appear in the file (verbatim or
trim-line-by-line — models often re-indent quotes when quoting code)
- line hint exceeds file line count
3 soft checks documented as open (claim semantics, suggested-fix
relevance, invented tests/commands — all need another LLM pass).
internal/validators/validate_test.go — 9 tests including:
- TestValidate_RejectsNonexistentFile (gate D1)
- TestValidate_RejectsEvidenceNotInFile
- TestValidate_RejectsLineHintBeyondFile
- TestValidate_AcceptsRealFinding
- TestValidate_AcceptsEvidenceWithDifferentLeadingWhitespace
- TestValidate_RejectsEmptyEvidence
- TestValidate_PassesThroughStaticFindings
- TestValidate_RejectsPathEscapingRepo (path-traversal protection)
- TestValidate_AcceptsRelativeRepoPath (the regression — see below)
Pipeline phase 3 wired between LLM review (Phase C) and report gen
(Phase 4). validated-findings.json contains the confirmed set;
rejected-findings.json contains rejects with per-finding reason +
detail. Receipt phase entry honest about output files + status.
=== Bug J caught ===
First Phase D run rejected EVERY real LLM finding as file_not_found
because the path-traversal check compared a relative joined path
(`tests/fixtures/insecure-repo/src/handler.go`) against an absolute
repoAbs (`/home/profit/share/.../insecure-repo`), so HasPrefix
always returned false. Both sides now resolved via filepath.Abs
before comparison. Regression test
TestValidate_AcceptsRelativeRepoPath locks this in — runs the
validator against a relative repo path AND a relative chdir, the
exact shape that hit the bug.
J's framing was honest: "I don't know what the problem is, but you
know what we're trying to accomplish." The fix-it-yourself signal
let me trace through the rejection details + see the smoking gun
in the detail string ("escapes repo root"). Without that prompt the
9 false rejections might have looked like real LLM bugs.
=== 2 close-out fixes ===
1. .gitignore: changed `/reports/latest/` → `**/reports/latest/`
(and same for `run-*`). Phase C committed 22 generated files
from `tests/fixtures/*/reports/latest/` because the original
pattern was anchored at the harness root only. Existing tracked
files removed via git rm --cached; new pattern keeps fixture
reports out of version control going forward.
2. pipeline.cleanOutputDir: pipeline now deletes the bounded list
of known per-run files at the start of each run. Before this,
a prior run's rejected-findings.json could linger when the
current run had no rejections — confused J during the bug hunt
above. cleanOutputDir is bounded (deletes only files we emit)
so operator-owned adjacent files stay.
Verified end-to-end: insecure-repo + --enable-llm → 25 confirmed
findings (16 static + 9 LLM), 0 rejected.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Claude (review-harness setup)andClaude Opus 4.7
|
e346b54e0f |
Phase C — local-Ollama LLM review wired end-to-end
Implements PROMPT.md / docs/REVIEW_PIPELINE.md Phase 2:
- internal/llm/ollama.go — real Ollama provider:
- HealthCheck probes /api/tags + a 1-token completion + a JSON-mode
probe ({"ok": true} round-trip), populating the model-doctor.json
schema documented in docs/LOCAL_MODEL_SETUP.md
- Complete + CompleteJSON via /api/chat with stream=false
- think=false set for ALL completions (qwen3.5:latest is reasoning-
capable but the inner-loop hot path wants direct answers, not
reasoning traces consuming the token budget — same finding as
the Lakehouse-Go chatd 2026-04-30 wave)
- internal/llm/review.go — Reviewer wrapper:
- 2-attempt flow: prompt → parse → repair-prompt → parse
- Strict JSON shape enforced; markdown fences stripped before parse
- Severity normalized to enum; out-of-range confidence clamped
- Per-file chunking (file-level for v0; function-level Phase D+)
- Bounded by review-profile max_file_bytes + max_llm_chunk_chars
- pipeline.go — Phase 2 wired between static scan + report gen:
- --enable-llm flag opts in (off by default — static-only is
cheaper and faster)
- Raw output ALWAYS saved to llm-findings.raw.json (forensics)
- Normalized findings → llm-findings.normalized.json
- LLM findings merged into the report findings list (sourced
"llm" so consumers can filter)
- Receipts honestly mark phase status: "ok" | "degraded" | "skipped"
- cli model doctor — real probes replace the Phase A stub.
Verified:
- model doctor: status="ok" with qwen3.5:latest + qwen3:latest both
loaded, basic_prompt_ok=true, json_mode_ok=true
- insecure-repo with --enable-llm: 9 LLM findings; qwen3.5 correctly
flagged SQLi, RCE, hardcoded credentials as critical with verbatim
evidence; 27s wall for 3 chunks
- clean-repo with --enable-llm: 0 LLM findings, 4 parsed chunks, 2.8s
- self-review with --enable-llm: 77 LLM findings + 83 static; 3 of
~30 chunks needed retry (PROMPT.md, REPORT_SCHEMA.md,
SCRUM_TEST_TEMPLATE.md — all eventually parsed); 5min wall
go vet + go test -short clean. Fixture stray.go now `package fixture`
so go-tooling doesn't choke on the orphan.
Phase D (validator cross-check) + Phase E (memory + diff/rules
subcommands) remain.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Claude (review-harness setup)andClaude Opus 4.7
|
70d68757f7 |
docs: SELF_REVIEW snapshot from f3ee472 (Phase A+B MVP)
Per PROMPT.md "Final Deliverable" — capture the harness's review of its own repo as a tracked artifact. reports/latest/ stays gitignored for routine runs; this snapshot is the deliverable proof. Captured: 28 findings, 3 critical (all from tests/fixtures/insecure-repo planted secrets, intentionally), 16 high (mostly shell-exec patterns mentioned by name in PROMPT.md and chatd-style scripts), 6 medium, 3 low. Verdict "blocked" because of fixture criticals. Banner header notes that fixture findings are dismissable; real codebase secrets land in identical shape — operators dismiss the fixture path explicitly. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Claude (review-harness setup)andClaude Opus 4.7
|
f3ee4722a8 |
Phase A + B (MVP) — local review harness
Implements the MVP cutline from the planning artifact: - Phase A: skeleton + CLI dispatch + provider interface + stub model doctor - Phase B: scanner + git probe + 12 static analyzers + reporters + pipeline - Phase B fixtures: clean-repo, insecure-repo, degraded-repo 12 static analyzers per PROMPT.md "Suggested Static Checks For MVP": hardcoded_paths, shell_execution, raw_sql_interpolation, broad_cors, secret_patterns, large_files, todo_comments, missing_tests, env_file_committed, unsafe_file_io, exposed_mutation_endpoint, hardcoded_local_ip. Acceptance gates passing: - B1 (intake produces accurate counts) ✓ - B2 (insecure fixture fires ≥8 distinct check_ids — actually 11/12) ✓ - B3 (clean fixture produces 0 confirmed findings — no false positives) ✓ - B4 (scrum mode produces all 6 required markdown + JSON reports) ✓ - B5 (receipts.json marks degraded phases honestly) ✓ - F (self-review on this repo runs without crashing) ✓ — exit 66 (degraded because Phase C LLM review is hardcoded skipped) Phases C (LLM review), D (validation cross-check), E (memory + diff + rules subcommands) deferred per the cutline. The MVP delivers the evidence-first path; LLM is purely additive. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |