- Interactive setup wizard: deps check, env config, WhatsApp auth, daemon install, health check
- CLI entry point via yargs with bin registration (regolith onboard)
- Flags: --install-daemon, --non-interactive, --pairing-code, --json, --skip-*
- launchd (macOS) and systemd (Linux) service installation
- Refactored whatsapp-auth.ts to export authenticate() for programmatic use
- 72 tests across 6 test files
- Updated README.md and CLAUDE.md with onboard CLI docs
- Add AGENT_BACKEND config ('container' default, 'opencode' to use OpenCode runtime)
- Wire OpenCodeRuntime into runAgent() with fallback to container runner
- Skip container system check when using OpenCode backend
- Update README and CLAUDE.md with AGENT_BACKEND docs
- Add AGENT_BACKEND config ('container' default, 'opencode' to use OpenCode runtime)
- Wire OpenCodeRuntime into runAgent() with fallback to container runner
- Skip container system check when using OpenCode backend
- Update README and CLAUDE.md with AGENT_BACKEND docs
* refactor: multi-channel infrastructure with explicit channel/is_group tracking
- Add channels[] array and findChannel() routing in index.ts, replacing
hardcoded whatsapp.* calls with channel-agnostic callbacks
- Add channel TEXT and is_group INTEGER columns to chats table with
COALESCE upsert to protect existing values from null overwrites
- is_group defaults to 0 (safe: unknown chats excluded from groups)
- WhatsApp passes explicit channel='whatsapp' and isGroup to onChatMetadata
- getAvailableGroups filters on is_group instead of JID pattern matching
- findChannel logs warnings instead of silently dropping unroutable JIDs
- Migration backfills channel/is_group from JID patterns for existing DBs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: skills engine v0.1 — deterministic skill packages with rerere resolution
Three-way merge engine for applying skill packages on top of a core
codebase. Skills declare which files they add/modify, and the engine
uses git merge-file for conflict detection with git rerere for
automatic resolution of previously-seen conflicts.
Key components:
- apply: three-way merge with backup/rollback safety net
- replay: clean-slate replay for uninstall and rebase
- update: core version updates with deletion detection
- rebase: bake applied skills into base (one-way)
- manifest: validation with path traversal protection
- resolution-cache: pre-computed rerere resolutions
- structured: npm deps, env vars, docker-compose merging
- CI: per-skill test matrix with conflict detection
151 unit tests covering merge, rerere, backup, replay, uninstall,
update, rebase, structured ops, and edge cases.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Discord and Telegram skill packages
Skill packages for adding Discord and Telegram channels to NanoClaw.
Each package includes:
- Channel implementation (add/src/channels/)
- Three-way merge targets for index.ts, config.ts, routing.test.ts
- Intent docs explaining merge invariants
- Standalone integration tests
- manifest.yaml with dependency/conflict declarations
Applied via: npx tsx scripts/apply-skill.ts .claude/skills/add-discord
These are inert until applied — no runtime impact.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* remove unused docs (skills-system-status, implementation-guide)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Use pipe delimiter in sed and quote the value to prevent breakage
from names containing /, &, \, or spaces.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: WA 515 stream error reconnect exiting early before key sync
Pass isReconnect flag on 515 reconnect so the registered-creds check
doesn't bail out before the handshake completes (caused "logging in..."
hang after successful pairing).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: container permission errors on Docker with non-default uid
Make /home/node world-writable in the Dockerfile so the SDK can write
.claude.json. Add --user flag matching host uid/gid in container-runner
so bind-mounted files are accessible. Skip when running as root (uid 0),
as the container's node user (uid 1000), or on native Windows.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: write ASSISTANT_NAME to .env during setup
When a custom assistant name is chosen, persist it to .env so config.ts
picks it up at runtime. Uses temp file for cross-platform sed
compatibility (macOS/Linux/WSL).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The setup skill would skip the /convert-to-docker step because:
1. The conversion instructions were buried inline in runtime choice bullets
2. The convert-to-docker skill had disable-model-invocation: true
Restructured step 3 into explicit sub-steps with a hard gate (3b) that
checks source files for Apple Container references before allowing the
build to proceed. Enabled model invocation on the convert-to-docker skill.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace inline SKILL.md instructions with executable shell scripts
for each setup phase (environment check, deps, container, auth,
groups, channels, mounts, service, verify). Scripts emit structured
status blocks for reliable parsing.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Switches from default GITHUB_TOKEN to a scoped GitHub App token
so the workflow can push to the protected main branch.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add is_bot_message column and support dedicated phone numbers
Replace fragile content-prefix bot detection with an explicit
is_bot_message database column. The old prefix check (content NOT LIKE
'Andy:%') is kept as a backstop for pre-migration messages.
- Add is_bot_message column with automatic backfill migration
- Add ASSISTANT_HAS_OWN_NUMBER env var to skip name prefix when the
assistant has its own WhatsApp number
- Move prefix logic into WhatsApp channel (no longer a router concern)
- Remove prefixAssistantName from Channel interface
- Load .env via dotenv so launchd-managed processes pick up config
- WhatsApp bot detection: fromMe for own number, prefix match for shared
Based on #160 and #173.
Co-Authored-By: Stefan Gasser <stefan@stefangasser.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: extract shared .env parser and remove dotenv dependency
Extract .env parsing into src/env.ts, used by both config.ts and
container-runner.ts. Reads only requested keys without loading secrets
into process.env, avoiding leaking API keys to child processes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Stefan Gasser <stefan@stefangasser.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Reusable composite action that counts codebase tokens using tiktoken
and generates a shields.io-style SVG badge. Color reflects context
window usage: green (<30%), yellow-green (30-50%), yellow (50-70%),
red (70%+). Badge includes hardcoded link back to repo-tokens.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two issues fixed:
- Use 'paused' instead of 'available' to stop typing. Baileys'
sendPresenceUpdate('available') sends a global <presence> stanza and
ignores the JID, so chatstate never left 'composing' and WhatsApp
suppressed duplicate composing notifications per XEP-0085.
- Add setTyping call when piping messages to an already-running
container. Previously only the first message (which spawns a new
container) triggered the typing indicator.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Added missing Browsers mock to the Baileys vi.mock and made
triggerMessages async to flush microtasks before assertions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sending 'paused' after the first response caused WhatsApp to stop
relaying subsequent 'composing' presence updates. Using 'available'
keeps the bot in a state where typing indicators work consistently.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Without announcing 'available' after connecting, WhatsApp stops relaying
composing/paused presence updates after the first message.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pass secrets to the SDK via the `env` query option instead of setting
process.env, so Bash subprocesses never inherit API keys. Delete
/tmp/input.json immediately after reading to remove secrets from disk.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Use a PreToolUse SDK hook to prepend `unset ANTHROPIC_API_KEY
CLAUDE_CODE_OAUTH_TOKEN` to every Bash command Kit runs, preventing
secret leakage via env/printenv/echo/$PROC. Secrets are now passed
via stdin JSON instead of mounted env files, closing all known
exfiltration vectors.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Move the language switcher from above the logo into the badge row
alongside Discord. Update README_zh.md to match current English
README: add Agent Swarms announcement and feature, update
architecture section with all key files, add Community section,
and fix file descriptions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- IPC register_group handler now passes requiresTrigger field to registerGroup(),
fixing groups silently defaulting to trigger-required mode
- Agent runner scans /workspace/extra/* and passes them as additionalDirectories
to the SDK query, so CLAUDE.md files in mounted dirs are loaded automatically
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add pairing code auth with 515 reconnect handling (Baileys stream
error after pairing is now retried instead of failing)
- Use Browsers.macOS('Chrome') identifier for WhatsApp compatibility
- Fix LID-to-phone translation for DMs using signalRepository.getPNForLID
- Strip device suffix (:0) from resolved phone JIDs
- Update setup skill with three auth options (browser QR, pairing code,
terminal QR), DM channel type, and LID troubleshooting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Container timeout and idle timeout both fire at 30min, racing the
graceful shutdown. The hard kill returns error status, rolling back
the message cursor even though output was already sent — causing
duplicate messages indefinitely.
- Grace period: hard timeout is now IDLE_TIMEOUT + 30s minimum
- Timeout after output resolves as success (idle cleanup, not failure)
- Don't roll back cursor if output was already sent to user
- Remove src/telegram.ts and config vars (added to PR #156 by mistake)
- Add typecheck step to CI workflow
- Add container-runner timeout behavior tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Telegram channel with agent swarm support
Add Telegram as a messaging channel that can run alongside WhatsApp
or standalone (TELEGRAM_ONLY mode). Includes bot pool support for
agent swarms where each subagent appears as a different bot identity
in the group.
- Add grammy dependency for Telegram Bot API
- Route messages through tg: JID prefix convention
- Add storeMessageDirect for non-Baileys channels
- Add sender field to IPC send_message for swarm identity
- Support TELEGRAM_BOT_TOKEN, TELEGRAM_ONLY, TELEGRAM_BOT_POOL config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add index.ts refactor plan
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: extract channel abstraction, IPC, and router from index.ts
Break the 1088-line monolith into focused modules:
- src/channels/whatsapp.ts: WhatsAppChannel class implementing Channel interface
- src/ipc.ts: IPC watcher and task processing with dependency injection
- src/router.ts: message formatting, outbound routing, channel lookup
- src/types.ts: Channel interface, OnInboundMessage, OnChatMetadata types
Also adds regression test suite (98 tests), updates all documentation
and skill files to reflect the new architecture.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* ci: add test workflow for PRs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: remove accidentally committed pool-bot assets
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(ci): remove grammy from base dependencies
Grammy is installed by the /add-telegram skill, not a base dependency.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Agent Teams work without swarm support — they just operate behind
the scenes. Swarm support makes subagents visible as separate bots.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Enable CLAUDE_CODE_DISABLE_AUTO_MEMORY=0 and
CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1 in container env so
agents use Claude Code's built-in persistent memory instead of
manually editing CLAUDE.md. Remove instructions that told agents to
write context into CLAUDE.md files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: streaming container mode, IPC messaging, agent teams support
Major architectural shift from single-shot container runs to long-lived
streaming containers with IPC-based message injection.
- Agent runner: query loop with AsyncIterable prompt to keep stdin open
for agent teams (fixes isSingleUserTurn premature shutdown)
- New standalone stdio MCP server (ipc-mcp-stdio.ts) inheritable by
subagents, with send_message and schedule_task tools
- Streaming output: parse OUTPUT_START/END markers in real-time, send
results to WhatsApp as they arrive
- IPC file-based messaging: host writes to ipc/{group}/input/, agent
polls for follow-up messages without respawning containers
- Per-group settings.json with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
- SDK bumped to 0.2.34 for TeamCreate tool support
- Container idle timeout (30min) with _close sentinel for shutdown
- Orphaned container cleanup on startup
- alwaysRespond flag for groups that skip trigger pattern check
- Uncaught exception/rejection handlers with timestamps in logger
- Combined SDK documentation into single deep dive reference
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: remove unused ipc-mcp.ts (replaced by ipc-mcp-stdio.ts)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: clarify agent communication model in docs and tool descriptions
- CLAUDE.md (main + global): split communication instructions into
"responding to messages" vs "scheduled tasks" sections
- send_message tool: note that scheduled task output is not sent to user
- Remove structured output (outputFormat) — not needed with current flow
- Regular output is sent to WhatsApp; scheduled task output is only logged
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: ignore dynamic group data while preserving base structure
Only track groups/main/CLAUDE.md and groups/global/CLAUDE.md. All other
group directories and files are ignored to prevent tracking user-specific
session data.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve critical bugs in streaming container mode
Bug 1 (scheduled task hang): Task scheduler now passes onOutput callback
with idle timer that writes _close sentinel after IDLE_TIMEOUT, so
containers exit cleanly instead of blocking queue slots for 30 minutes.
Scheduled tasks stay alive for interactive follow-up via IPC.
Bug 2 (timeout disabled): Remove resetTimeout() from stderr handler.
SDK writes debug logs continuously, resetting the timer on every line.
Timeout now only resets on actual output markers in stdout.
Bug 3 (trigger bypass): Piped messages in startMessageLoop now check
trigger pattern for non-main groups. Non-trigger messages accumulate in
DB and are pulled as context via getMessagesSince when a trigger arrives.
Bug 7 (non-atomic IPC writes): GroupQueue.sendMessage uses temp file +
rename for atomic writes, matching ipc-mcp-stdio.ts pattern.
Also: flip isVerbose back to false (debug leftover), add isScheduledTask
to host-side ContainerInput interface.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: idle timer not starting + scheduled task groupFolder missing
Two bugs that prevented the scheduled task idle timeout fix from working:
1. onOutput was only called when parsed.result !== null, but session
update markers have result: null. The idle timer never started for
"silent" query completions, leaving containers parked at
waitForIpcMessage until hard timeout.
2. Scheduler's onProcess callback didn't pass groupFolder to
queue.registerProcess, so closeStdin no-oped (groupFolder was null).
The _close sentinel was never written even when the idle timer fired.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: duplicate messages and timestamp rollback in piping path
Two bugs introduced by the trigger context accumulation change:
1. processGroupMessages didn't advance lastAgentTimestamp until after
the container finished. The piping path's getMessagesSince(lastAgent
Timestamp) re-fetched messages already sent as the initial prompt,
causing duplicates.
2. processGroupMessages overwrote lastAgentTimestamp with the original
batch timestamp on completion, rolling back any advancement made by
the piping path while the container was running.
Fix: advance lastAgentTimestamp immediately after building the prompt,
before starting the container. This matches the piping path behavior
and eliminates both the overlap and the rollback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: container idles 30 extra minutes after _close during query
When _close was detected during pollIpcDuringQuery, it was consumed
(deleted) and stream.end() was called. But after runQuery returned,
main() still emitted a session-update marker (resetting the host's idle
timer) and called waitForIpcMessage (which polled forever since _close
was already gone). The container had to wait for a second _close.
Fix: runQuery now returns closedDuringQuery. When true, main() skips
the session-update marker and waitForIpcMessage, exiting immediately.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resume branching, internal tags, and output forwarding
- Fix resume branching: pass resumeSessionAt with last assistant UUID
to anchor each query loop resume to the correct conversation tree
position. Prevents agent responses landing on invisible branches
when agent teams subagents create parallel JSONL entries.
- Add <internal> tag stripping: agent can wrap internal reasoning in
<internal> tags which are logged but not sent to WhatsApp. Prevents
duplicate messages and internal monologue reaching users.
- Forward scheduled task output: scheduled tasks now send result text
to WhatsApp (with <internal> stripping), matching regular message
behavior. No more special-case instructions.
- Update Communication guidance in CLAUDE.md: simplified to "your
output is sent to the user or group" with soft guidance on
<internal> tags and send_message usage.
- Add messaging behavior docs to schedule_task tool: prompts the
scheduling agent to include guidance on whether the task should
always/conditionally/never message the user.
- Mount security: containerPath now optional, defaults to basename
of hostPath.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: cursor rollback on error, flush guard, verbose logging
- Roll back lastAgentTimestamp on container error so retries can
re-process the messages instead of silently losing them.
- Add guard flag to flushOutgoingQueue to prevent duplicate sends
from concurrent flushes during rapid WA reconnects.
- Revert isVerbose from hardcoded false back to env-based check
(LOG_LEVEL=debug|trace).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: orphan container cleanup was silently failing
The startup cleanup used `container ls --format {{.Names}}` which is
Docker Go-template syntax. Apple Container only supports `--format json`
or `--format table`. The command errored with exit code 64, but the
catch block silently swallowed it — orphan containers were never cleaned
up on restart.
Fixed to use `--format json` and parse `configuration.id` from the
JSON output. Also filters by `status: running` and logs a warning on
failure instead of silently catching.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add Discord badge and community section
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: idle timer reset on null results and flush queue message loss
- Only reset idle timer on actual results (non-null), not session-update
markers. Prevents containers staying alive 30 extra minutes after the
agent finishes work.
- flushOutgoingQueue now uses shift() instead of splice(0) so unattempted
messages stay in the queue if an unexpected error bails the loop.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add Agent Swarms to README
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: update Telegram skill for current architecture
Rewrite integration instructions to match the per-group queue/SQLite
architecture: remove onMessage callback pattern (store to DB, let
message loop pick up), fix startSchedulerLoop signature, add
TELEGRAM_ONLY service startup, SQLite registration, data/env/env sync,
@mention-to-trigger translation, and BotFather group privacy docs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: Telegram skill message chunking, media placeholders, chat discovery
- Split long messages at Telegram's 4096 char limit to prevent silent
send failures
- Store placeholder text for non-text messages (photos, voice, stickers,
etc.) so the agent knows media was sent
- Update getAvailableGroups filter to include tg: chats so the agent can
discover and register Telegram chats via IPC
- Fix removal step numbering
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: update REQUIREMENTS.md and SPEC.md for SQLite architecture
- Replace all registered_groups.json / sessions.json / router_state.json
references with SQLite equivalents
- Fix CONTAINER_TIMEOUT default (300000 → 1800000)
- Add missing config exports (IDLE_TIMEOUT, MAX_CONCURRENT_CONTAINERS)
- Update folder structure: add missing src files (logger, group-queue,
mount-security), remove non-existent utils.ts, list all skills
- Fix agent-runner entry (ipc-mcp.ts → ipc-mcp-stdio.ts)
- Update startup sequence to reflect per-group queue architecture
- Fix env mounting description (data/env/env, not extracted vars)
- Update troubleshooting to use sqlite3 commands
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: fix README architecture description, revert SPEC.md env error
- README: update architecture blurb to mention per-group queue, add
group-queue.ts to key files, update file descriptions
- SPEC.md: restore correct credential filtering description (only auth
vars are extracted from .env, not the full file)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add skill to guide users through adding Telegram as a messaging channel.
- Replace WhatsApp or run alongside it
- Support for private chats and groups
- Built-in /chatid command for easy registration
- Flexible triggering: main chat, respondToAll, @mentions, or trigger pattern
- Grammy library for modern TypeScript-first Telegram integration
No source code changes - skill provides step-by-step implementation guide.
Setup skill fixes:
- Run QR auth in foreground with long timeout, not background
- Replace fragile message-based registration with DB group sync lookup
- Personal chats: ask for phone number instead of querying empty DB
- Consolidate trigger word + security model + channel selection into one step
- Remove `timeout` shell command (unavailable on macOS), use Bash tool timeout
- Query 40 groups, display 10 at a time, support name lookup
requiresTrigger support:
- Add requiresTrigger field to RegisteredGroup type and DB schema
- Skip trigger check when requiresTrigger is false (for solo/personal chats)
- Main group still always processes all messages (unchanged)
Agent-browser visibility:
- Append global CLAUDE.md to non-main agent system prompts via SDK
- Add browser tool docs to global and main CLAUDE.md
- Update skill description to be broader (not just "web testing")
- Reference agent-browser.md in root CLAUDE.md key files
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Always log detailed input/output/stderr on error (not just in verbose
mode), and stop truncating stderr/stdout in structured log fields.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fall back to text result when success subtype has no structured_output
- Treat outputType 'message' without userMessage as 'log' with warning
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Rename status→outputType, responded/silent→message/log for clarity
- Remove scheduled task special-casing: userMessage now sent for all contexts
- Update schema, tool, and CLAUDE.md descriptions to be clear and
non-contradictory about communication mechanisms
- Use full tool name mcp__nanoclaw__send_message in docs
- Change schedule_task target_group to accept JID instead of folder name
- Only show target_group_jid parameter to main group agents
- Add defense-in-depth sanitization and error callback to exec() in shutdown
- Use "user or group" consistently (supports both 1:1 and group chats)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: wire up queue processMessagesFn before recovery to prevent silent message loss
recoverPendingMessages() was called after startMessageLoop(), which meant:
1. Recovery could race with the message loop's first iteration
2. processMessagesFn was set inside startMessageLoop, so recovery
enqueues would fire runForGroup with processMessagesFn still null,
silently skipping message processing
Move setProcessMessagesFn and recoverPendingMessages before startMessageLoop
so the queue is fully wired before any messages are enqueued.
https://claude.ai/code/session_01PCY8zNjDa2N29jvBAV5vfL
* feat: structured agent output to fix infinite retry on silent responses (#113)
Use Agent SDK's outputFormat with json_schema to get typed responses
from the agent. The agent now returns { status: 'responded' | 'silent',
userMessage?, internalLog? } instead of a plain string. This fixes a
critical bug where a null/empty agent response caused infinite 5-second
retry loops by conflating "nothing to say" with "error".
- Agent runner: add AGENT_RESPONSE_SCHEMA and parse structured_output
- Host: advance lastAgentTimestamp on both responded AND silent status
- GroupQueue: add exponential backoff (5s-80s) with max 5 retries for
actual errors, replacing unbounded fixed-interval retries
https://claude.ai/code/session_014SLc8MxP9BYhEhDCLox9U8
Co-authored-by: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Fix startup recovery running before WhatsApp connects, which could
permanently lose agent responses by advancing lastAgentTimestamp
before sock is initialized
- Add 5s retry on container failure so messages aren't silently dropped
until a new message arrives for the group
- Use `container stop` in shutdown instead of raw SIGTERM to CLI wrapper,
ensuring proper container cleanup
- Replace unnecessary dynamic imports with static imports in processTaskIpc
- Guard JSON.parse of DB-stored last_agent_timestamp against corruption
- Validate MAX_CONCURRENT_CONTAINERS (default 5, min 1, NaN-safe)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add per-group container locking with global concurrency limit to prevent
concurrent containers for the same group (#89) and cap total containers.
Fix message batching bug where lastAgentTimestamp advanced to trigger
message instead of latest in batch, causing redundant re-processing.
Move router state, sessions, and registered groups from JSON files to
SQLite with automatic one-time migration. Add SIGTERM/SIGINT handlers
with graceful shutdown (SIGTERM -> grace period -> SIGKILL). Add startup
recovery for messages missed during crash. Remove dead code: utils.ts,
Session type, isScheduledTask flag, ContainerConfig.env, getTaskRunLogs,
GroupQueue.isActive.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
