The reviewer's Codex app-server logged "failed to refresh available models:
failed to decode models response: unknown variant `max`" on every run: the
server now advertises a `max` reasoning effort the old CLI cannot parse. Each
failure also dumped the whole models payload (instruction templates included)
into the service journal.
The pin was misleading: codex-runner actually resolved an untracked stale
runners/codex-runner/node_modules/@openai/codex 0.124.0 from 2026-04-26 that
shadowed the root workspace copy, so earlier version bumps never reached the
runner. That nested copy (not in bun.lock, gitignored) was removed on the host
so the runner resolves the lockfile-managed root install.
End-to-end check through the real CodexAppServerClient with the reviewer's
account: thread start, turn, goal set/get, close and thread resume with context
retained all succeed, with 0 app-server errors (was 2 per run) and a simple
turn taking 5s instead of 49s.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Upgrade EJClaw bundled Codex CLI to 0.124.0 for gpt-5.5 access
- Resolve Claude Agent SDK native binary packages via package.json
- Prefer glibc Claude binary before musl on Linux and align platform binary names
- Add regression coverage for optional package resolution
When the Codex SDK returns 'interrupted' (API-side timeout/disconnect),
retry the turn once before reporting failure. Prevents unnecessary
"요청을 완료하지 못했습니다" messages for transient issues.
- Replace better-sqlite3 with bun:sqlite (native, no native addon build)
- Change all spawn('node') to spawn('bun') for agent processes
- Update package.json scripts: node→bun, tsx→bun, npm→bun
- Add bun-types for tsc compatibility
- Add bun:sqlite→better-sqlite3 shim for vitest (tests run on Node.js)
- Update Dockerfile: install bun alongside Node.js (CLIs need Node)
- Update setup/platform.ts: getNodePath() resolves bun binary
- Remove better-sqlite3 from production dependencies (devDep only for tests)
- Replace commit hash comparison with git tree hash (HEAD^{tree}) to
avoid false re-review triggers on commit-only operations
- Use git diff --quiet for actual file change detection
- Update source_ref on failed reviewer execution with done verdict
- Add tests for empty-commit finalize and code-change re-review
- Document Codex reviewer bash mutation gap in reviewer-runtime
prependRoomRoleHeader was called BEFORE /compact detection, turning
"/compact" into "[PAIRED ROOM: owner]\n/compact" which failed the
exact match check. Now session commands are detected first.
- Track lastIntermediateText to prevent duplicate Discord delivery
when same text arrives as both intermediate and final
- Filter task_progress descriptions >80 chars (AI summaries)
- Mark completed subagents with ✅ instead of removing
- Update claude-agent-sdk 0.2.76→0.2.81, codex 0.115→0.116
- 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
No longer using Docker containers — agents run as direct host
processes. The directory name now reflects the actual purpose.
Updated all references across source code, docs, and skills.