Commit Graph
3 Commits
Author SHA1 Message Date
thanhnvandClaude Opus 4.8 1b61d7f381 feat(log): unified CASAN_LOG_LEVEL across Boss, agent step, harness wrapper
Add a shared log taxonomy (error<warn<info<debug<trace, default info) wired
through all three layers, plus a machine-readable per-step run log.

- scripts/casan-log.mjs + .specify/scripts/bash/casan-log.sh: shared logger
  ([LEVEL] ts [component] msg), stderr-only so stdout contracts and exit codes
  are byte-identical. Node side includes trace-level redaction (secret/PII).
- run-casan-pipeline.mjs: per-STEP info line, loop-activation warnings
  (BACK-TO-PLAN, FAIL->STEP6), debug harness rc + trace_id, trace payload
  excerpt, end-of-run 13-STEP summary table, and one JSONL line/step in
  .specify/logs/pipeline-run.jsonl. New --dry-run stubs all agents but keeps
  the real wrapper in the loop (deterministic, offline, full 13 STEP + loops).
- casan-step.mjs: debug logs for judge verdict, checkpoint, rollback; logger
  import degrades to noop when the file is copied standalone (T1 test).
- casan-harness.sh: debug-log each phase H4-in -> H5 -> [H2-gate] -> H6-exec
  -> H4-out with its rc; optional CASAN_PHASE_REPORT JSON for the Boss.

Default level (info) keeps output close to before; behavior opt-in via env.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-03 10:04:55 +09:00
thanhnvandClaude Sonnet 4.6 2f06662f5d scorecard: chấm live 2 mục hardcode; pipeline: fallback real + honest scoring doc
Hướng A — scorecard.sh (video demo):
- h5_1 approval workflow: hardcode 0 → governance-check deploy live (approval_required)
- h6_2 hallucination rate: hardcode 0 → hallucination-scan phân biệt dirty>clean live
- "N/5 mục" chuyển từ text cứng sang đếm động
- H4/H5/H6 → 100/100 (5/5 gate live), Average 57.9 → 90.0

Hướng B — run-casan-pipeline.mjs:
- fallback: stub 'exit 9' → 'cat /nonexistent' (real failure, nhất quán adversarial T3)
- drift: giữ so fallback-output vs golden (clean run=1.0); năng lực phát hiện
  drift thật chứng minh ở adversarial suite
- Full 12-step run verify: H1 CONTEXT_VALID=24, H2 tool-audit records=25 signed,
  H5 audit-chain records=22 signed, H6 provider_telemetry per-step thật, H7 rollback real

phase3-real-run-scoring.md: giải thích vì sao scorecard cũ cho H5=60/H6=80
(hardcode), phân biệt scorecard-90 vs re-score-84 (2 mục đích khác nhau).

Verify: adversarial 44/0, security-gate 11/0/0, pipeline 12 steps OK.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-07-03 00:18:43 +09:00
thanhnv 07ac1bdcdd update first - 84 2026-06-30 02:21:39 +09:00