e346b54e0f
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>
24 lines
1.5 KiB
Markdown
24 lines
1.5 KiB
Markdown
# Claim Coverage Table
|
|
|
|
Each row is a finding paired with whether existing tests cover the affected area.
|
|
Phase B emits this shape; LLM-side claim generation lands in Phase C.
|
|
|
|
| Claim | Code Location | Existing Test | Missing Test | Risk |
|
|
|---|---|---|---|---|
|
|
| Environment file in source tree | `.env:?` | _unknown_ | _likely_ | high |
|
|
| Hardcoded absolute path | `src/handler.go:10` | _unknown_ | _likely_ | medium |
|
|
| Shell command execution | `src/handler.go:19` | _unknown_ | _likely_ | high |
|
|
| Raw SQL interpolation | `src/handler.go:14` | _unknown_ | _likely_ | high |
|
|
| Possible secret committed to source | `src/handler.go:23` | _unknown_ | _likely_ | critical |
|
|
| Possible secret committed to source | `src/handler.go:23` | _unknown_ | _likely_ | critical |
|
|
| TODO/FIXME comment | `src/handler.go:9` | _unknown_ | _likely_ | low |
|
|
| TODO/FIXME comment | `src/handler.go:22` | _unknown_ | _likely_ | low |
|
|
| Hardcoded private-network IP | `src/handler.go:11` | _unknown_ | _likely_ | medium |
|
|
| Large file | `src/huge.go:1-901` | _unknown_ | _likely_ | medium |
|
|
| Wildcard CORS | `src/server.js:2` | _unknown_ | _likely_ | high |
|
|
| Possible secret committed to source | `src/server.js:5` | _unknown_ | _likely_ | critical |
|
|
| TODO/FIXME comment | `src/server.js:1` | _unknown_ | _likely_ | low |
|
|
| Mutation route in file with no visible auth | `src/server.js:7` | _unknown_ | _likely_ | medium |
|
|
| Mutation route in file with no visible auth | `src/server.js:8` | _unknown_ | _likely_ | medium |
|
|
| No tests found | `.:?` | _unknown_ | _likely_ | medium |
|