Commit Graph

49 Commits

Author SHA1 Message Date
Codex
0984d6798c feat: shift usage windows to 07/12/17/22 KST with a 03-07 gap
Primer slots move from 08/13/18/23 to 07/12/17/22 and the daily alignment
hold from 04-08 to 03-07, so the Claude 5h windows run 07-12, 12-17, 17-22
and 22-03 as requested.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 08:26:13 +09:00
Codex
fdd98e9eb8 feat: keep typing during scheduled tasks and tell waiting users
A group-context scheduled task occupies the room queue, so a human message
sent meanwhile waited silently (up to the whole task run) with no typing
indicator; the room looked unresponsive.

- Scheduled tasks (not CI watchers) hold the room's typing indicator for
  their whole run (DiscordChannel.setTypingHold: typing stays on while any
  hold is active, independent of message-turn setTyping(false)).
- A human message that has to wait behind a running scheduled task gets a
  one-time notice per wait: "지금 예약 작업을 진행하고 있습니다. 이 작업을
  마친 뒤 바로 답변드리겠습니다." (GroupQueue.claimScheduledTaskWaitNotice,
  reset when the waiting messages run).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-27 23:12:00 +09:00
Codex
0d7e345d3d fix: check every scheduled Claude attempt for the usage limit
The alignment-hold check in runTask only looked at the first attempt's
streamed trigger. A limit that came back only as the final error (no
streamed output) or on the retry after an auth refresh extended nothing.
holdAlignmentAfterClaudeTaskLimit now runs inside runTaskAttempt for
every Claude attempt and reads the streamed trigger, the final error and
the attempt error (classifyClaudeTrigger), then calls the shared
holdUntilSlotAfterLimitReset.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 13:09:03 +09:00
Codex
0a5436e4ad fix: alignment hold also covers scheduled-task limits and the primer
- A scheduled Claude task that hits the usage limit now extends the
  alignment hold to the next slot when the reset is off the grid, like a
  room turn (it called runAgentProcess directly and skipped that path).
- The Claude primer is skipped while a hold outlasts its slot (e.g. the
  08:00 primer during a realignment hold until 13:00). A hold ending at
  the slot itself does not count: the slot timer fired at 07:59:59.999
  for 08:00 on 2026-10-16.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 13:04:44 +09:00
Codex
a2b9898c0b fix: keep usage resets on the slot grid when Claude hits 100%
Evidence (journal): 10/04 and 10/05 08:00 and 10/12 23:00 the primer
failed (exit 1) because the account was at 100% in an off-slot window
(resets 9am / 3am); the first request after that reset then opened the
next window off the slot too, and the drift carried on.

- Usage limit that resets off the slot grid (not ~04/08/13/18/23:00 KST):
  extend the alignment hold to the next window start (08/13/18/23), so
  nothing opens a window between the reset and the primer. The pause
  notice names both times. Rooms paused by the limit stay paused
  (silently, now alignment-only, @-mention bypass works) until the hold
  ends; an expired real limit no longer counts as a limit.
- A real limit takes precedence over the hold in the pre-run gate.
- Primer: when the current 5h window (cached usage) ends within 10 min
  after the slot, wait until 5 s after that reset before firing, so the
  primer is not counted in, or rejected by, the old window.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 06:03:38 +09:00
Codex
f944f97e54 feat: usage-alignment hold (04-08 KST daily + one-off hold until a set time)
Bring back the dawn gap that keeps Claude's 5h windows on the primer
slots (08-13, 13-18, 18-23, 23-04): it was dropped by the 2026-06-08
upstream merge (1dd948a).

- usage-alignment-hold.ts: hold during 04:00-08:00 KST, or until the ISO
  time in router_state `usage_alignment_hold_until` (ignored once past,
  so only the daily gap remains). A one-off end inside the gap runs on to
  08:00.
- Claude turns during a hold pause through the existing usage-pause path
  (messages kept, room resumed at the hold end) with an alignment notice.
  The stored pause is marked alignmentOnly so it does not act as an
  account-wide usage limit.
- Due Claude scheduled tasks stay due until the hold ends (Codex and
  GitHub CI watchers are not held).
- Urgent bypass like the old gate: a human @-mention lets that room run
  until the hold ends.
- Tests stub the wall-clock hold in test/vitest-env.ts so the suite does
  not pause when run between 04 and 08 KST.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-16 05:54:39 +09:00
Codex
aed7371cfa feat: pause room work on the Claude usage limit and resume after reset
Before, a Claude run that hit the account usage limit closed the open
paired task as claude_usage_limit, posted the reset time and consumed the
user's messages, so the work was lost and had to be re-requested.

Now the room is paused instead:
- The failed turn is released without touching the paired task (no
  failure count, no status change, no follow-up) and the queue keeps the
  human messages unconsumed, so the same turn can run again.
- The room is recorded in router_state `claude_usage_pause` with the reset
  time (error text, else cached usage API reset, else a 10 min retry). A
  banner time that just passed is read as "now", not tomorrow.
- While the limit lasts, paused rooms run nothing and any other room's
  Claude turn pauses that room without spawning a run (the limit is
  account-wide). A stop request still goes through and drops the room
  from the resume list.
- The scheduler tick clears the pause 1 min after the reset, posts a
  resume notice and re-queues the rooms; the pending turn or the kept
  messages then run again. The state survives restarts.

Safety refusals keep closing the task as before.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 13:14:56 +09:00
Codex
a9eab5cb94 refactor: run Claude and Codex on one fixed account each
The deployment has a single Claude OAuth credential and a single Codex
ChatGPT account, so the N-account rotation machinery only added state
files, cooldown bookkeeping and code paths that never ran.

Removed:
- Claude token rotation (token-rotation.ts, token-rotation-base.ts):
  rotate-on-limit, per-token cooldowns, token-rotation-state.json.
  CLAUDE_CODE_OAUTH_TOKENS is still read, but only its first entry.
- Codex account rotation (codex-token-rotation.ts): account pool,
  rotate-on-429/auth, dead-auth/cooldown tracking, round-robin advance,
  d7 auto-rotate, codex-rotation-state.json, manual account switch.
- Account index plumbing in token-refresh, claude-credentials-path
  (CLAUDE_ACCOUNTS_DIR / ~/.claude-accounts/<n>), Claude/Codex usage
  collectors, the dashboard rows and the Codex warm-up.
- provider-retry.ts rotation loops and the Codex retry path.

Kept:
- Codex exclusive auth lease (one Codex run at a time), the 15-minute
  waitForCodexAuthLease, and a usage-poll lease that skips while a run
  holds the account (codex-auth.ts).
- Session auth copy and write-back of refreshed tokens
  (syncCodexSessionAuthBack, syncClaudeSessionAuthBack).
- Codex auth path: ~/.codex-accounts/0/auth.json, else ~/.codex/auth.json
  (now resolved per run, so a re-login needs no restart).
- Claude token refresh loop, CLAUDE_CREDENTIALS_PATH and the
  CLAUDE_TOKEN_REFRESH_* / CLAUDE_USAGE_USE_HOME_CREDENTIALS flags; an
  auth-expired run still force-refreshes the token and retries once.
- Error classification (classifyClaudeTrigger, classifyCodexTrigger).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-01 20:14:38 +09:00
Codex
f127ac7a2b refactor: remove the main room concept
No room has room_settings.is_main = 1, so every main-only path was dead,
and admin work is done from the host shell. Each room's agent may now
only act on its own room:

- IPC: messages/inbound injection only to the source room; schedule,
  update, pause, resume and cancel only for the source room's tasks;
  drop the assign_room and refresh_groups IPC tasks and the deps they
  needed (assignRoom/syncGroups/getAvailableGroups/writeGroupsSnapshot)
- DB/host evidence is always scoped to the source group folder
- runner MCP server: drop the assign_room tool, the target_group_jid
  parameters and the isMain flag; list_tasks shows only the room's tasks
- drop EJCLAW_IS_MAIN, RunnerInput.isMain and AgentInput.isMain; the
  global CLAUDE.md memory is now included for every room
- drop the available_groups.json snapshot (available-groups.ts), the
  inferred restart announcement that only went to the main room, and
  the unused Channel.syncGroups hook
- setup register: drop --is-main; deregister-room: drop the main-room
  refusal and --force, and fix its unknown[] binding type error
- remove the groups/main/ template

The room_settings.is_main column and migrations are untouched; new rows
get the column default (0) and nothing reads it anymore.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-01 19:37:29 +09:00
Codex
80ddb1aa0d fix(scheduler): forward only final agent output to chat
Scheduled tasks only suppressed phase 'progress', so intermediate
preambles (e.g. "I'll run the watchdog checks.") leaked to the chat
each run while the actual <internal>-wrapped result was correctly
stripped. The interactive path treats intermediate/tool-activity as
silent (toVisiblePhase); align the scheduler to forward only the final
message, with error outputs still falling through to rotation/error
handling.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-13 14:37:42 +09:00
ejclaw
5648b61075 fix: stop Codex pool retry loops 2026-06-02 05:30:04 +09:00
Eyejoker
96b800e812 fix: keep CI watcher completion actionable 2026-05-29 04:00:28 +09:00
ejclaw
b78421e92e fix: send terminal watcher status as new message 2026-05-26 06:25:51 +09:00
ejclaw
a6e1b8172c fix: route scheduled watcher output by room role 2026-05-26 04:17:59 +09:00
ejclaw
4e05f60400 refactor: land approved runtime cleanup and room binding cutover 2026-04-10 21:04:23 +09:00
ejclaw
8b9bebd29e refactor: complete config unification and split db helpers 2026-04-08 19:05:19 +09:00
ejclaw
d75d26c23d Stabilize paired reviewer recovery and owner follow-up 2026-04-06 07:49:26 +09:00
Eyejoker
54abb5bb4e Apply formatter after local memory refactor 2026-04-04 03:52:28 +09:00
Eyejoker
3dd772c229 Refactor local memory and role-fixed runtime routing 2026-04-04 03:50:28 +09:00
Eyejoker
141898f764 refactor: scope runtime log context 2026-03-31 17:23:43 +09:00
Eyejoker
aad1e93df5 refactor: separate scheduler tick execution path 2026-03-31 07:26:21 +09:00
Eyejoker
54fc67e283 test: align prompt and scheduler expectations 2026-03-30 03:55:58 +09:00
Eyejoker
e1fdc47552 style: sync pre-commit formatting fallout 2026-03-28 05:41:16 +09:00
Eyejoker
ba9f6871b6 feat: add codex review failover and suppress output hardening 2026-03-28 05:40:38 +09:00
Eyejoker
7b63ba859d fix: deduplicate CI watchers and remove task ID from watcher prompts
Prevent duplicate CI completion notifications in paired rooms by checking
for existing active watchers with the same channel+provider+metadata before
creating a new one. Remove Task ID from watcher prompt construction to
avoid router secret redaction (task- IDs contain sk- pattern), passing
EJCLAW_RUNTIME_TASK_ID via env var instead and making cancel_task
auto-resolve when task_id is omitted.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-26 20:57:59 +09:00
Eyejoker
a330ebdf2a fix: suppress Claude 502 provider errors from chat output 2026-03-26 10:11:24 +09:00
Eyejoker
20ca6c10fc style: fix prettier formatting in GitHub watcher scheduler tests 2026-03-25 22:44:02 +09:00
Eyejoker
09b4309d96 feat: add GitHub watcher backoff and auto-pause safeguards 2026-03-25 22:43:35 +09:00
Eyejoker
57f2045ca6 style: fix prettier formatting in github-ci and scheduler tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 22:31:52 +09:00
Eyejoker
33fcf9c788 feat: add host-driven GitHub Actions CI watcher (Level 3)
Replace LLM-per-tick polling with direct `gh api` calls for GitHub
Actions watchers. New `ci_provider` discriminator column routes tasks
to either the host-driven path (zero LLM tokens) or the existing
generic LLM path. GitHub watchers poll at 15s intervals (min 10s)
via `checkGitHubActionsRun()` in the scheduler, with completion
messages sent directly to chat on terminal state.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 22:31:42 +09:00
Eyejoker
c3c75882e4 fix: add watcher TTL and cleanup task-scoped artifacts 2026-03-25 21:54:15 +09:00
Eyejoker
113c540f10 style: fix prettier formatting in task-scheduler test 2026-03-25 21:41:08 +09:00
Eyejoker
24d93d5c78 fix: fail fast on missing host IPC dir for task runtimes 2026-03-25 21:40:34 +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
eebee00e60 refactor: share streamed output evaluation 2026-03-25 11:46:16 +09:00
Eyejoker
8b2c46b89e fix: harden agent shutdown and auth rotation 2026-03-24 17:08:48 +09:00
Eyejoker
f6ba879e8a fix: usage API rate-limit guard and cleanup debug logging 2026-03-24 03:47:46 +09:00
Eyejoker
120f16e9e1 fix: Claude token rotation, usage-exhausted fallback, and usage API caching
- Fix token rotation not taking effect: getCurrentToken() was shadowed
  by static .env CLAUDE_CODE_OAUTH_TOKEN value in agent environment
- Don't fall back to Kimi on usage-exhausted (only on transient 429/network)
- Add disk cache for Claude usage API data (survives restarts, 429s)
- Rate-limit usage API calls to 1 per token per 5 minutes
- Add ignoreRateLimits option to rotateToken() for exhausted recovery
- Rotate to next token in getActiveProvider() when current is exhausted
- Add isUsageExhausted() helper to provider-fallback
2026-03-24 03:40:51 +09:00
Eyejoker
42d721a9ec fix claude turn teardown and start CI watchers immediately 2026-03-23 08:55:48 +09:00
Eyejoker
f5eae07657 fix: use resolved ipc dirs for recovery flow 2026-03-23 07:18:47 +09:00
Eyejoker
9def49f7fb fix: isolate watcher task runtimes 2026-03-23 07:16:07 +09:00
Eyejoker
a2db8f6c0e refactor: extract dashboard and task helpers 2026-03-23 06:59:59 +09:00
Eyejoker
4df30a9b9b fix: keep ci watchers off the chat queue 2026-03-23 05:40:31 +09:00
Eyejoker
2eebe3c7f4 fix: prevent isolated watchers from blocking chat 2026-03-23 05:30:58 +09:00
Eyejoker
127eacb564 fix: restore watcher elapsed status updates 2026-03-23 05:22:52 +09:00
Eyejoker
b647502a10 feat: add seq cursor, work_items, provider fallback, and delivery reliability
Major reliability improvements to the message processing pipeline:

- Add messages.seq monotonic cursor replacing timestamp-based cursors,
  preventing message loss from timestamp collisions with LIMIT queries
- Add work_items table separating agent production from delivery,
  enabling delivery retry without re-running the agent
- Propagate Discord send failures instead of silently swallowing them
- Add Claude 429 → Kimi K2.5 automatic provider fallback with cooldown
- Fix follow-up turn state reset in live index.ts path (not just
  message-runtime.ts) to prevent final output from being lost
- Add restart context tracking for graceful restart announcements
- Lazy migration from timestamp cursors to seq cursors for existing data

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-23 00:11:32 +09:00
Eyejoker
41afcb91cf feat: integrate Memento MCP for shared memory across agents
- Add MEMENTO_MCP_SSE_URL/ACCESS_KEY/REMOTE_PATH to readEnvFile
- Merge .env vars into cleanEnv for runner process inheritance
- Claude Code runner: add memento-mcp via mcp-remote in mcpServers
- Codex runner: inject memento-mcp section into config.toml
- Various improvements: CI watch, task scheduler, DB, IPC auth
2026-03-20 00:12:43 +09:00
Gabi Simons
f794185c21 fix: atomic claim prevents scheduled tasks from executing twice (#657)
* fix: atomic claim prevents scheduled tasks from executing twice (#138)

Replace the two-phase getDueTasks() + deferred updateTaskAfterRun() with
an atomic SQLite transaction (claimDueTasks) that advances next_run
BEFORE dispatching tasks to the queue. This eliminates the race window
where subsequent scheduler polls re-discover in-progress tasks.

Key changes:
- claimDueTasks(): SELECT + UPDATE in a single db.transaction(), so no
  poll can read stale next_run values. Once-tasks get next_run=NULL;
  recurring tasks get next_run advanced to the future.
- computeNextRun(): anchors interval tasks to the scheduled time (not
  Date.now()) to prevent cumulative drift. Includes a while-loop to
  skip missed intervals and a guard against invalid interval values.
- updateTaskAfterRun(): simplified to only record last_run/last_result
  since next_run is already handled by the claim.

Closes #138, #211, #300, #578

Co-authored-by: @taslim (PR #601)
Co-authored-by: @baijunjie (Issue #138)
Co-authored-by: @Michaelliv (Issue #300)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

* style: apply prettier formatting

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: track running task ID in GroupQueue to prevent duplicate execution (#138)

Previous commits implemented an "atomic claim" approach (claimDueTasks)
that advanced next_run before execution. Per Gavriel's review, this
solved the symptom at the wrong layer and introduced crash-recovery
risks for once-tasks.

This commit reverts claimDueTasks and instead fixes the actual bug:
GroupQueue.enqueueTask() only checked pendingTasks for duplicates, but
running tasks had already been shifted out. Adding runningTaskId to
GroupState closes that gap with a 3-line fix at the correct layer.

The computeNextRun() drift fix is retained, applied post-execution
where it belongs.

Closes #138, #211, #300, #578

Co-authored-by: @taslim (PR #601)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: add changelog entry for scheduler duplicate fix

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: add contributors for scheduler race condition fix

Co-Authored-By: Taslim <9999802+taslim@users.noreply.github.com>
Co-Authored-By: BaiJunjie <7956480+baijunjie@users.noreply.github.com>
Co-Authored-By: Michael <13676242+Michaelliv@users.noreply.github.com>
Co-Authored-By: Kyle Zhike Chen <3477852+kk17@users.noreply.github.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: gavrielc <gabicohen22@yahoo.com>
Co-authored-by: Taslim <9999802+taslim@users.noreply.github.com>
Co-authored-by: BaiJunjie <7956480+baijunjie@users.noreply.github.com>
Co-authored-by: Michael <13676242+Michaelliv@users.noreply.github.com>
Co-authored-by: Kyle Zhike Chen <3477852+kk17@users.noreply.github.com>
2026-03-04 16:23:29 +02:00
Lawyered
02d8528684 fix: pause malformed scheduled tasks 2026-02-22 21:01:53 +02:00