Merge remote main (token rotation, usage API, dashboard fixes)
with local memory pipeline changes. Smart quote encoding fixed.
Test alignment pending.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add automatic memory integration so EJClaw host directly calls Memento
MCP for recall at session start and reflect on compact, removing
reliance on agent voluntary tool use.
Stage 1: New sessions get room memory briefing injected into system
prompt (CLAUDE.md / AGENTS.md) via host-side MCP client.
Stage 2: PreCompact hook automatically calls reflect + remember to
persist session summaries as room-memory fragments.
Also restores missing source files (token-rotation, codex-token-rotation,
claude-usage exports) to fix full build from source.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 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
- Call /api/oauth/profile for each token, cache in memory
- Display plan type (max/pro/free) next to Claude account names
- Profiles fetched once on startup, no periodic refresh needed
- Iterate all rate limits per account instead of just display[0]
- Track and persist 7-day reset time separately (resetD7At)
- Show both 5h and 7d cached usage for inactive Codex accounts
- Scan all Codex accounts by spawning app-server with each auth dir
- Cache primary (5h) and secondary (7d) usage per account
- Show cached usage + reset remaining time on dashboard
- Persist d7 usage in rotation state file
- formatResetRemaining: "Xh Ym 후" / "N일 후" format
- Remove isRateLimited guard for cached display
- Parse "try again at" time from rate-limit errors instead of
fixed 1-hour cooldown, with 3-min buffer after reset
- Pass error message to rotateToken/rotateCodexToken for parsing
- Cache usage % and reset time per Codex account for dashboard
- Persist cached usage in rotation state file across restarts
- Show rate-limited Codex accounts with cached 100% + reset time
- Fix dashboard text indicators (*!/space) for monospace alignment
- Save currentIndex + rateLimits to JSON file in DATA_DIR
- Restore on startup so rotation survives service restarts
- Replace emoji indicators with text (*/!) for monospace alignment
- Dynamic column width based on longest name
- Show Codex accounts with plan type on dashboard
- New codex-token-rotation module: rotates between multiple
~/.codex-accounts/{n}/auth.json on rate-limit
- Copies active account auth to session dir before each spawn
- Fix detectFallbackTrigger to match "usage limit" / "hit your limit"
- Fix streamed error detection: remove claude-only guard so codex
rate-limit errors are caught even when output.status is "success"
- Add rotation in both task-scheduler and message-agent-executor
- Replace expect/CLI hack with direct HTTP API call
(GET api.anthropic.com/api/oauth/usage with OAuth token)
- Add fetchAllClaudeUsage() for per-token usage fetching
- Export getAllTokens() from token-rotation for usage queries
- Dashboard shows each account separately (Claude1⚡, Claude2)
with ⚡ for active token, 🚫 for rate-limited
- New token-rotation module: stores multiple tokens from
CLAUDE_CODE_OAUTH_TOKENS env var (comma-separated)
- On rate-limit, rotates to next healthy token before falling
back to Kimi provider
- Also fixes: intermediate text routes to progress message
when no subagents active (prevents message flooding)
- 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
Track each subagent separately via agentId from SDK task events.
Single subagent shows detailed view with activity sub-lines,
multiple subagents show compact one-line-each format.
Add 'intermediate' phase for assistant text between tool calls.
These are sent as separate Discord messages without finalizing
or disrupting the active progress message.
Intermediate assistant text (e.g., "서브에이전트 4개 병렬로 띄웠어요")
is now emitted as regular messages (no phase), not progress heading
updates. Progress heading is only set by task_started (🔄) events.
Buffer intermediate assistant text in the runner. When result arrives
with matching text, discard the buffered progress instead of emitting
it. This prevents the duplicate from ever reaching Discord, eliminating
the flash-then-revert behavior.
- Show subagent description from task_started immediately (no 30s wait)
- Remove AI summary (agentProgressSummaries) — task_started is sufficient
- Revert progress heading to previous when final text matches current
- Track previousProgressText in direct-update path
- Ensure progressTicker runs during tool-activity updates for time refresh
- Last activity line uses └ instead of ├
- Summary (📋) and description shown together when both present
- Description indented as sub-item under summary
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.
Display subagent tool descriptions as sub-lines under the main
progress text, updating in-place via Discord message edit.
Shows up to 5 recent tool activities (e.g., "Reading index.ts").
Progress updates are now buffered: each new progress flushes the
previous one. The latest pending progress is discarded when final
arrives with matching text, preventing duplicate display in Discord.
When the final result text is identical to the last progress update,
edit the progress message back to the previous progress text to avoid
showing the same content twice in Discord.
- Use system/task_progress subtype (not top-level type) for subagent events
- Extract intermediate assistant text between tool calls as progress
- Only show SDK-generated summaries for subagent progress (skip noisy per-tool updates)
- Truncate progress messages to Discord 2000 char limit
- Remove verbose debug logging from production
- Set agentProgressSummaries: true in SDK query options
- Handle task_progress and task_started events from subagents
- Subagent progress summaries streamed as progress phase to Discord
- Auto-suspend tasks after 3 consecutive quota/auth errors with
retry-after date parsing and Discord notification
- Add tool_progress and tool_use_summary streaming from Claude Agent SDK
- Prefix progress messages with invisible marker so bots ignore them
- Fix misleading provider label in codex service logs
