Commit Graph
5 Commits
Author SHA1 Message Date
Jesse_ChenandClaude Opus 5.5 a00c40d4b8 refactor(rectification): split runV9AgentTurn into prepare / attempt / retry / finish
Move-only (TASK-rectification-code-split-20260926 T3/T4). No behavior,
receipt, billing, Skill or scoring change.

- agent-run.ts: 1400 -> 135 lines; runV9AgentTurn 1046 -> 25 lines, no
  nested functions. It keeps the public types, the budget constants and the
  phase order: agent-run-prepare.ts (reliability, session, year re-ask, Skill
  identity, delivered guard, reserve, turn row / replay),
  agent-run-retry.ts (attempt loop), agent-run-attempt.ts (the old nested
  streamAttempt), agent-run-finish.ts (billing settle, receipts, interview,
  finalize), agent-run-support.ts (outcome types, retry classification, turn
  receipt writers), agent-run-messages.ts (buildAgentMessages /
  buildOpeningBrief, re-exported).
- One token changed with the move: the attempt passes its own
  `previousErrorCode` argument to buildAgentMessages instead of reading the
  enclosing `lastAttemptError`; the loop passes that same value (clears the
  old unused-parameter warning).
- Tests: whole-source contracts read tests/rectification-agent-run-surface.ts;
  behavioral runV9AgentTurn tests unchanged. agent-run growth caps added.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
2026-09-26 19:52:51 +08:00
Jesse_ChenandCursor 5d54d0597d test(rectification): lock failReceipt engine_message for compare failures
Independent Staging Quality Gate / validate (push) Successful in 12m27s
Independent Staging Quality Gate / publish (push) Successful in 7m46s
BUG-659 moved compare tool_failed fingerprints into failReceipt; keep the
source lock on the shared helper so the staging gate still requires a
redacted engine_message.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-13 11:03:20 +08:00
Jesse_ChenandCursor 6c9a089620 fix(rectification): refresh remaining probes and targeted collect before delivering range (BUG-653/654)
Independent Staging Quality Gate / validate (push) Successful in 13m54s
Independent Staging Quality Gate / publish (push) Successful in 10m50s
Dated-choice exhaustion is not convergence. Refresh probes from remaining
active candidates, then ask a targeted collect, then deliver. Skill 10.0.24.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-11 18:28:39 +08:00
Jesse_ChenandCursor ab57d03f06 fix(rectification): persist stop scores and deliver a range card (BUG-581–582)
Independent Staging Quality Gate / validate (push) Successful in 14m1s
Independent Staging Quality Gate / publish (push) Failing after 19m46s
Stop/idle reuse the scored evidence path so existing answers stay on the range. Delivery uses one range card (Skill 10.0.15) instead of four minute cards.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-07 19:22:01 +08:00
Jesse_ChenandCursor 4e0db55f03 fix(rectification): keep compare requests valid after style cards (BUG-577–580)
Engine asked_probe_keys no longer include varga split hashes that 400 the scorer, failed compares become visible and retry, user stop can still deliver a range on a stale snapshot, and holdout no longer reasks domains already in the ledger.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-07 15:46:33 +08:00