When an agent turn fails, users only saw "요청을 완료하지 못했습니다. 다시
시도해 주세요." with no clue why. Capture the failure reason (explicit
error field, or provider-error text like "API Error: 529 Overloaded"
classified by detectClaudeProviderFailureMessage) in the turn controller
and append it to the failure message ("...\n\n오류 내용: <reason>",
secret-redacted + length-capped). Update the paired-room loop filter to
startsWith so a failure-with-reason is still recognized and not
re-injected into prompt history. Unit-tested.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- resolveSessionFolder now always returns unique folder for arbiter
(prevents sharing session with owner when both use same agent type)
- Arbiter sessionId forced to undefined to prevent resume attempts
resolveCursorKey and resolveChannel both duplicated the same
taskStatus→role switch. Now resolveActiveRole() is the single
mapping, and both functions derive from it.
Replace all manual cursor key construction (hardcoded chatJid:reviewer,
chatJid:arbiter, pairedCursorKey, 3-way ternary) with a single
resolveCursorKey(chatJid, taskStatus) function.
- Removed pairedCursorKey import (no longer needed)
- Removed loopIsReviewerTurn, loopIsArbiterTurn intermediate variables
- All cursor key logic now flows through one function that maps
task status to the correct role-specific key
Root cause: owner and reviewer shared the same message cursor. When
the owner's turn completed, the cursor advanced past the owner's
message. The reviewer's turn then only saw messages after that cursor,
missing the owner's response entirely.
Now paired rooms use role-aware cursor keys (chatJid for owner,
chatJid:reviewer for reviewer). Each role advances only its own
cursor, so the reviewer always sees the owner's latest messages
and vice versa.
- 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
Exclude is_bot_message from implicit continuation trigger check.
Previously, bot A's response would trigger bot B's continuation
window, causing infinite back-and-forth responses.
Also: tool activity sub-lines use description over summary,
and max activities reduced to 2.