Commit Graph

12 Commits

Author SHA1 Message Date
ejclaw
fdc27836a3 Unify codex rotation retry guards 2026-04-06 20:53:48 +09:00
ejclaw
7612b2c4cc Format retry rule refactor files 2026-04-06 20:38:38 +09:00
ejclaw
83c45c3ce3 Extract executor retry decision rules 2026-04-06 20:38:10 +09:00
ejclaw
d75d26c23d Stabilize paired reviewer recovery and owner follow-up 2026-04-06 07:49:26 +09:00
Eyejoker
dddf18428e fix: /stop leaves stale paired task, sawOutput guard, progress text overwrite
- /stop now resets the active paired task to completed so the next
  user message routes to the owner instead of the stuck reviewer
- Owner completion with sawOutput=false (e.g. interrupted by /stop)
  no longer auto-triggers the reviewer — treated as interrupted
- Clear pendingProgressText when intermediate updates arrive on an
  existing progress message, preventing flushPendingProgress from
  overwriting latestProgressText with stale buffered content
2026-03-31 02:54:04 +09:00
Eyejoker
68901e5da9 feat: global failover + dashboard model config section
- Failover is now global (account-level, not per-channel)
- Dashboard shows role model config (Owner/Reviewer/Arbiter + MoA refs)
- Dashboard shows failover status when active
- Auto-clear failover on successful Claude rotation
- Remove per-channel lease writes from failover path
2026-03-31 00:38:29 +09:00
Eyejoker
38d96578a4 refactor: move retry and recovery paths to structured output helpers 2026-03-28 06:17:52 +09:00
Eyejoker
ba9f6871b6 feat: add codex review failover and suppress output hardening 2026-03-28 05:40:38 +09:00
Eyejoker
94eeaa5e3e refactor: introduce AgentTriggerReason type union as SSOT for error reason strings
Replace scattered reason string literals with a centralized type hierarchy:
- AgentTriggerReason: all possible trigger reasons
- ClaudeRotationReason, CodexRotationReason, NoFallbackCooldownReason:
  derived subtypes for specific contexts
- AgentErrorClassification, FallbackTriggerResult, CodexRotationTriggerResult:
  discriminated unions for compile-time narrowing

Remove dead export isUsageExhausted() (superseded by
isPrimaryNoFallbackCooldownActive). Replace NO_FALLBACK_COOLDOWN_REASONS
Set with isNoFallbackCooldownReason() type guard.

Add tests for agent-error-detection and provider-retry (423 total passing).

Known limitation: 6 `as CodexRotationReason` casts in Codex rotation paths
where streamed trigger reason is AgentTriggerReason but runtime value is
always CodexRotationReason-compatible.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 17:46:43 +09:00
Eyejoker
60a9fe86ec fix: detect org-access-denied errors, suppress chat output, and rotate Claude tokens
When a Claude account is suspended, the API returns "Your organization does
not have access to Claude" on the success path or "Failed to authenticate.
API Error: 403 terminated" on the error path. Both are now classified as
'org-access-denied', suppressed from Discord output, and trigger automatic
token rotation. If all tokens are exhausted, enters cooldown without Kimi
fallback (same as usage-exhausted and auth-expired).

Changes:
- agent-error-detection: add isClaudeOrgAccessDeniedMessage(), expand
  classifyClaudeAuthError() and shouldRotateClaudeToken()
- streamed-output-evaluator: detect org-access-denied in success-path chain
- provider-fallback: add NO_FALLBACK_COOLDOWN_REASONS set and
  isPrimaryNoFallbackCooldownActive() helper
- provider-retry: handle org-access-denied in rotation loop
- message-agent-executor / task-scheduler: use generalized no-fallback
  cooldown check
- Tests: +8 test cases across 5 test files (415 total passing)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 17:24:10 +09:00
Eyejoker
b6d3f879ef refactor: add recovery mode + shared JSON/error/fetch utilities
- GroupQueue recovery mode: limit to 3 concurrent agents for 60s after restart
  to prevent API rate-limit storms (configurable via env vars)
- getErrorMessage: replace 14 occurrences of instanceof Error pattern
- readJsonFile/writeJsonFile: replace 19 occurrences of JSON+fs pattern
- fetchWithTimeout: replace 3 occurrences of AbortController pattern

354/354 tests passing
2026-03-25 07:08:49 +09:00
Eyejoker
5ea3439c5f refactor: extract shared utilities, protocol constants, and retry loop
Phase 3: provider-retry.ts — shared Claude rotation loop (SSOT)
  - retryClaudeWithRotation extracted from message-agent-executor + task-scheduler
  - ~200 lines of duplicated retry logic removed

Phase 4: types.ts — AgentOutputPhase + VisiblePhase unified
Phase 5: types.ts — AgentConfig extended with claudeThinking/claudeThinkingBudget

Utilities (utils.ts):
  - getErrorMessage: 14 occurrences of instanceof Error pattern → 1 function
  - readJsonFile/writeJsonFile: 19 occurrences of JSON+fs pattern → 2 functions
  - fetchWithTimeout: 3 occurrences of AbortController pattern → 1 function
  - formatElapsedKorean: deduplicated from task-watch-status + message-turn-controller

Protocol (agent-protocol.ts):
  - OUTPUT_START/END_MARKER centralized (runners keep local copies with SSOT reference)
  - IMAGE_TAG_RE, IPC constants documented

Runner: show "대화 요약 중..." progress message during auto-compact

Net: -137 lines, 354/354 tests passing
2026-03-25 04:59:49 +09:00