Claude (review-harness setup) 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>

2026-04-30 01:13:39 -05:00

1.6 KiB

Raw Blame History

Risk Register

Findings ranked by severity. Suspected rows haven't been validated yet (Phase D).

ID	Severity	Status	File	Line	Title
`9bc97c579efc`	critical	suspected	`src/handler.go`	23	Possible secret committed to source
`9bc97c579efc`	critical	suspected	`src/handler.go`	23	Possible secret committed to source
`d3c2c5606e1d`	critical	suspected	`src/server.js`	5	Possible secret committed to source
`750676119e4a`	high	confirmed	`.env`	—	Environment file in source tree
`3a198539c923`	high	suspected	`src/handler.go`	14	Raw SQL interpolation
`5bf85ae888a0`	high	suspected	`src/handler.go`	19	Shell command execution
`ef8bb39704d3`	high	suspected	`src/server.js`	2	Wildcard CORS
`4d59806aeb57`	medium	confirmed	`.`	—	No tests found
`eb3c41b3a186`	medium	suspected	`src/handler.go`	10	Hardcoded absolute path
`bb70e8e262d6`	medium	suspected	`src/handler.go`	11	Hardcoded private-network IP
`512b795dc551`	medium	suspected	`src/huge.go`	1-901	Large file
`7ed1cab08825`	medium	suspected	`src/server.js`	7	Mutation route in file with no visible auth
`2b765c240c96`	medium	suspected	`src/server.js`	8	Mutation route in file with no visible auth
`f99cd5bb5f2c`	low	suspected	`src/handler.go`	22	TODO/FIXME comment
`f3e510b70ec9`	low	suspected	`src/handler.go`	9	TODO/FIXME comment
`4a631055edd1`	low	suspected	`src/server.js`	1	TODO/FIXME comment

1.6 KiB Raw Blame History

Risk Register

1.6 KiB

Raw Blame History