- mark Codex bearer/refresh failures as terminal auth-expired states
- sync refreshed session auth back to rotation slots and revive refreshed dead_auth slots
- stop paired arbiter retry loops when Codex accounts are unavailable
- add regression coverage for rotation leases, follow-up suppression, and arbiter closure
Deployments that shipped reviewer_failure_count as a local migration
numbered 15 record schema_migrations version 15 under that name, so the
version-number-only runner skips the canonical turn_progress_text
migration (also version 15) and never creates paired_turns.progress_text
/ progress_updated_at, which the runtime reads. Add an idempotent compat
migration (020) that re-adds the columns when missing, plus a regression
test reproducing the collided-version-15 database.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
The user only sees the final owner message, not the owner↔reviewer loop. Add a
"Finalize message format" section mandating a direct answer, a consolidated
recap (no transcript, no narrating disagreement), an explicit 사용자 액션 아이템
section (with "없음" when nothing is needed), and no reviewer-loop meta phrases.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Stop overwriting the user-registered group/room name with the live Discord
channel name during channel-meta refresh; keep the alias and log the
divergence at debug instead.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
One-off script that logs in with each configured Discord bot token and prints
the bot member's effective permission bits per guild, so capability claims can
be verified empirically instead of inferred from intents.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Replace the naive byte-slice chunk loop with a fence-aware chunkForDiscord()
splitter: prefers newline boundaries, re-closes any open ``` fence at the end
of a chunk and reopens it with the same language tag at the start of the next,
and is surrogate-pair safe. Adds 10 unit tests for the seam, multi-fence
documents, surrogate pairs, and single-line overflow.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Port the local primer subsystem onto the upstream base by intent:
- add src/usage-primer.ts (KST-slot primer firing Claude + Codex signals)
- extend codex-warmup with the ignoreZeroUsageWindow runtime option used
by the primer so a slot is never skipped just because Codex is partway
through its weekly window
- Codex primer fires unconditionally (maxUsagePct/maxD7UsagePct=100),
mirroring the Claude primer, refreshing usage before selection
- wire startUsagePrimer() into the runtime bootstrap
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Raise CODEX_PRIMER_MAX_USAGE_PCT from 1 to 100 so the Codex usage-window
primer fires at every fixed KST slot regardless of current 5h usage level,
mirroring the Claude primer (which always fires unless rate-limited). The d7
gate stays at 100 so an account whose weekly quota is exhausted is still
skipped, matching Claude's rate-limit skip.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Codex primer was skipping with no_eligible_accounts because it read a
stale usage cache and required exactly 0% usage. Re-query usage right
before the primer call and treat freshly-reset 0~1% accounts as eligible
so the 5h window can be anchored at the fixed KST slot. Also hold new
Codex-owner turns at fresh usage until the next primer slot.
Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
Follow-up to e3c8de6: prettier --check failed on the new section
(missing blank line after the "Before accepting any proposal..."
sentence ahead of the numbered list, and the "Do not include:" header
needed a blank line before the bullets). Running prettier --write
fixes those without changing semantics.
bunx prettier --check prompts/owner-common-paired-room.md → clean.
The user only sees the final owner message, not the owner↔reviewer
back-and-forth. Recent turns leaked meta-narrative like "리뷰어 지적
반영해서 정정합니다" / "PROCEED 확정" into user-visible replies and
sometimes omitted explicit action items, leaving the user to guess
whether anything was needed from them.
Add a "Finalize message format (self-contained answer)" section to
owner-common-paired-room.md that mandates:
- direct answer first
- consolidated recap (no transcript, no narrating disagreement)
- explicit "사용자 액션 아이템" section, with "없음" when there is
nothing for the user to do
- no meta phrases referencing the reviewer loop
The runner reads this prompt fresh per agent spawn
(src/agent-runner-environment.ts), so the change takes effect on the
next owner turn without a service restart.
One-off Bun script that logs each configured Discord bot in (owner /
reviewer / arbiter), walks every guild it sees, and prints the bot
member's effective permission bits for the capabilities we plan to
expose (ReadMessageHistory, ManageMessages, ManageChannels,
AddReactions, thread perms, etc.). Used to verify "current permissions
support feature X" empirically instead of guessing from intents.
Follow-up to 6505971: the pre-commit prettier hook rewrapped the new
import and an Array.from() call after the commit landed, leaving the
working tree dirty. Commit the reflow so the tree is clean.
Long bot replies that exceeded Discord's 2000-char limit were split by a
naive byte-slice loop. When the split fell inside a ```fenced code block
the first chunk lost its closing fence and the next chunk lost its
opener, so Discord rendered raw backticks and the remainder as headings
or bold instead of code.
Replace the slice loop with chunkForDiscord(), a fence-aware splitter
that prefers newline boundaries, re-closes any open fence at the end of
a chunk, and reopens it (with the same language tag) at the start of the
next. Single oversize lines still fall back to a surrogate-pair-safe
byte split. Adds 10 unit tests covering the seam, multi-fence
documents, surrogate pairs, and single-line overflow.
The reviewer (codex) sometimes emits a final result with no visible text.
The runtime marks the run failed → handleFailedReviewerExecution
preserves status as review_ready → the follow-up scheduler re-queues
another reviewer-turn → loop. The existing round_trip / arbiter caps
never fire because round_trip_count only advances on owner-side
submissions; bot-side reviewer flakes never increment it.
Mirror the owner_failure_count pattern: add reviewer_failure_count to
paired_tasks, increment on each silent failure, and escalate via
requestArbiterOrEscalate once it reaches 2. Reset to 0 on every
successful reviewer completion path (PROCEED/REVISE/arbiter/wait-for-user)
and when the owner re-submits a fresh review cycle.
Repro chat: 1507762222724546560 (stock-adiviser). Task
33968d31-0da2-480c-85d3-7a3999822ab4 logged 11 consecutive
reviewer-turn entries with no work_items and round_trip_count stuck
at 1.
