chore(chore): capitalize step 0-1 learnings, eval and journal

This commit is contained in:
bchanot committed 2026-10-08 21:41:40 +02:00
1 parent e84cbaf884
commit e9047a99d2
3 files changed
+28

No files matched your search

+7
View File
@@ -35,3 +35,10 @@ Method: /tour full pipeline on faunosteo — semgrep floor ×3 + cso posture (it
Result: re-verify PASS (0 findings on 20 modified files); checks green throughout (typecheck, lint 0, 174/174, build, docker run non-root). Convergence honest: it2 surfaced 1 new tuning note (min-release-age 1440 < 10080 rec) → triaged open → it3 semgrep identical → converged at 3-iteration bound.
Anomaly: both Phase A agents died mid-run on "monthly spend limit" — SendMessage to same agentId resumed from transcript, zero rework. PostToolUse hook false-positived 3× on 'dangerouslySetInnerHTML' as prose inside audit REPORTS (not code).
Action: none blocking. Consider excluding .claude/audits/*.md from sink-pattern hook scan.
## EVAL-005 | 2026-10-08 | Step 1 characterisation suite (91 cases)
Method: 7 files on real assets (SVG, catalog, fixtures), oracle = audit tables (06 §4, 05 §2.4). Run typecheck/test/lint/build.
Result: 271/271 green, 0 src change. Audit figures all confirmed (26 mappings score 0, 792/612/41, 48 attrs…).
Anomalies: 4 assertions wrong on first run, all test-side (census regex, stale closure, ZONES drawn as bullet rows not ' · ' line, attachment names in object streams). None app-side.
Action: LRN-033. Known quirks pinned as "KNOWN:" tests (orphan findings, no_attachment cause lost, sphenoid id, fuzzy FR pairs).