When reviewer was triggered via the normal message dispatch path (not
the review_ready check path), output was sent through the owner channel.
Now checks paired task status to determine the correct output channel.
- Remove UNIFIED_MODE legacy: single service manages all 3 Discord bots
- Add OWNER_AGENT_TYPE / REVIEWER_AGENT_TYPE env vars for configurable agent selection
- Fix Discord channel routing: reviewer output goes through correct bot (discord/discord-review)
- Fix channel name assignment: explicit names prevent agentTypeFilter collision
- Remove silent output suppression system: harness-level protections replace prompt workarounds
- Add reviewer approval detection: DONE marker on first line stops ping-pong
- Include user's original message in reviewer prompt for context
- Fix round_trip_count auto-reset on new user message
- Fix session ID conflict: reviewer doesn't reuse owner's session
- Fix pending progress text flush in runner on close sentinel
- Promote buffered intermediate text to final result when result event has no text
- Remove legacy files: .env.codex.example, .env.codex-review.example, migrate-unify.cjs
- Update CLAUDE.md: server-side build deployment, unified architecture docs
- Add UNIFIED_MODE flag (default on, disable with UNIFIED_MODE=0)
- Register all 3 Discord bots in one process (claude, codex, review)
- Load all registered groups regardless of agent_type (codex/owner priority)
- Start credential proxy and container cleanup at unified startup
- shouldServiceProcessChat returns true in unified mode
- Add findChannelByName for role-based response routing
- Backward compatible: UNIFIED_MODE=0 restores per-service behavior
Two leak paths caused Discord typing indicators to persist indefinitely:
1. If runAgent() threw before turnController.finish(), setTyping(false)
was never called. Wrap the agent run in try/finally to guarantee cleanup.
2. Follow-up message piping called setTyping(true) fire-and-forget. If
the Promise resolved after finish()'s setTyping(false), the typing
interval was recreated with nobody to clear it. Await the call to
serialize the on/off sequence.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two v1/v2 regressions fixed:
1. Progress messages became too brittle: editMessage failure killed all
subsequent progress updates for the turn. Now resets progressMessageId
and recreates on next update instead of permanently stopping.
2. Follow-up messages stuck in active agent without output: after 10s of
no output, closeStdin and requeue the follow-up as a fresh run with
cursor rollback, instead of silently dropping it.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove duplicate processGroupMessages, runAgent, startMessageLoop, and
recoverPendingMessages from index.ts. All message processing now flows
through createMessageRuntime() in message-runtime.ts, eliminating the
dual-path issue that caused the v1 follow-up turn reset bug.
index.ts reduced from ~2300 to ~1210 lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
