Instead of keeping announced runs in the registry for 60 minutes
(archive sweeper), delete them right after findings are delivered
to the parent. This prevents stale completed tasks from appearing
in sessions_list on subsequent parent turns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After child subagents complete, the coalesced announcement runs as an
internal turn which rolls back all messages from the parent's in-memory
context. This causes the parent LLM to lose findings in subsequent turns.
Add persistResponse option to writeInternal that re-injects the LLM's
summary as a non-internal assistant message after the internal run
completes. The internal prompt stays hidden while the summary persists
in both memory and session JSONL for future turns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Announcement messages from subagent completion flows were persisted as
regular user messages, polluting conversation history and leaking
orchestration instructions to frontend/CLI.
- Add `internal?: boolean` to SessionEntry message variant
- SessionManager.saveMessage accepts { internal: true } option
- SessionManager.loadMessages filters internal by default
- Agent.runInternal() tags messages as internal, rolls back from memory
- Agent.withRunMutex() prevents concurrent run/runInternal mis-tagging
- AsyncAgent.writeInternal() suppresses event forwarding during internal runs
- Announce flows use writeInternal() instead of write()
- Desktop IPC getHistory reads from session storage (filtered)
- CLI session show parses SessionEntry, supports --show-internal flag
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Change default security from "allowlist" to "full" (allow all commands)
- Change default ask from "on-miss" to "off" (never prompt)
- Change DEFAULT_APPROVAL_TIMEOUT_MS from 60s to -1 (no timeout)
- Support timeoutMs=-1 to wait indefinitely for user decision
- Update CLI and Hub approval flows to skip setTimeout when timeout<0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a new `sessions_list` tool to the Subagent tool group, allowing
agents to query the status of their spawned sub-tasks. Supports both
list mode (all runs) and detail mode (specific runId).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Cover formatCoalescedAnnouncementMessage (single/multi record,
mixed outcomes, missing findings), registry coalescing state
transitions, shutdown capture, and new field serialization.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When multiple children complete, buffer findings per-child and only
send one combined announcement to the parent after all unannounced
runs for the same requester have finished. This avoids N separate
LLM calls and gives the parent a complete picture of all results.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The model was confused about payload capabilities. Explicitly state
that agent-turn spawns an isolated agent with ALL tools (exec, write,
web_fetch, etc.) and add usage guidance for choosing between
system-event and agent-turn.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The bundled ESM environment does not support require(). Use the
already-imported fs functions instead.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace Type.Union(Type.Literal(...)) with flat stringEnum helper
to avoid anyOf in JSON schema (better LLM provider compatibility)
- Rewrite description to structured ACTIONS/SCHEDULE/PAYLOAD/CONSTRAINTS
format without markdown headers or code blocks
- Add CRITICAL CONSTRAINTS section for sessionTarget+payload rules
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add explicit list of valid actions in parameter description
- Add IMPORTANT note at start of tool description
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 'group:cron' to TOOL_GROUPS in IPC handler and agent tools
- Add cron tool description and group name to use-tools hook
- Add Time04Icon for cron group in tool-list component
- Add subagent group icon (UserMultipleIcon) for completeness
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add createCronTool to the agent's default tools list so agents
can use the cron tool to manage scheduled tasks.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Initialize CronService on Hub startup
- Set executeCronJob as the job executor
- Shutdown CronService on Hub cleanup
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds CLI support for managing scheduled tasks:
- multica cron status: Show service status
- multica cron list: List all scheduled jobs
- multica cron add: Create new jobs with --at/--every/--cron
- multica cron run: Execute jobs immediately
- multica cron enable/disable: Toggle job status
- multica cron remove: Delete jobs
- multica cron logs: View run history
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a cron tool that allows agents to create, manage,
and execute scheduled tasks. Supports:
- status: Get service status
- list: List all jobs with optional filters
- add: Create one-shot, interval, or cron jobs
- update: Modify existing jobs
- remove: Delete jobs
- run: Execute jobs immediately
- logs: View run history
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements a timer-based cron job system:
- types.ts: Job types (at, every, cron schedules)
- schedule.ts: Next run computation using croner
- store.ts: Persistent JSON storage with JSONL run logs
- service.ts: CronService with timer management
- execute.ts: Job execution (system-event, agent-turn)
Based on OpenClaw's implementation (MIT License).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The closing fence regex was not checking for an empty info string,
allowing e.g. ```python to incorrectly close an open fence. Also
adds missing test for tool_execution_update passthrough.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Message aggregation should not be managed by the Hub. The aggregator
is a standalone utility for client adapters to use internally — the
Hub stays clean and only does event forwarding. Third-party messaging
integrations (Discord, Telegram) will use MessageAggregator in their
own adapter layer.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Return latest messages by default instead of oldest. Support paginated
loading of older messages when scrolling up via IntersectionObserver,
with scrollHeight compensation to preserve scroll position.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add enableAggregation/disableAggregation methods to Hub for per-agent
aggregation control. When enabled, streaming text deltas are buffered
and emitted as block-reply events instead of raw stream events. The
existing streaming mode remains the default for own clients.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
BlockChunker splits streaming text at natural boundaries (paragraph,
newline, sentence, word) with configurable min/max chars and markdown
fence-safe splitting. MessageAggregator consumes AgentEvents, buffers
text deltas, and emits complete BlockReply objects via callbacks.
Enables future third-party messaging integrations (Discord, Telegram)
that cannot consume raw streaming deltas.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign each search request with HMAC-SHA256 using Hub ID, a per-request
nonce (UUIDv7), and unix timestamp. The signed reqId is sent in the
request body to prevent unauthorized API usage.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add localApprovalHandlers map so exec approval requests can be routed
to the Electron renderer via IPC instead of requiring a Gateway
connection. Expose setLocalApprovalHandler/removeLocalApprovalHandler
and resolveExecApproval on Hub for the IPC layer to use.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Rename CopilotHub references to Devv Search (constants, types, function
names, error message). Remove unused resolveTimeoutSeconds/resolveCacheTtlMs
imports and use constants directly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove "requires API key" wording and rebrand to Devv Search across
tool definition, desktop UI, system prompt, and README.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove Brave and Perplexity providers in favor of a single CopilotHub
search endpoint (api-dev.copilothub.ai/web-search). Simplifies schema
to query-only, removes credential dependencies, retains caching.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Keep needsCompaction() method from compaction-feedback PR
- Keep tool result pruning from this branch
- Add "pruning" to CompactionEndEvent.reason type in events.ts
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adding explicit return type to help TypeScript resolve the type
correctly across different build configurations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The CompactionResult type includes "pruning" as a reason but SessionEntry
did not, causing type errors when writing compaction entries.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Two-phase pruning approach based on OpenClaw's microcompact-style:
- Soft Trim (30% utilization): Keep head 1500 + tail 1500 chars of large tool results
- Hard Clear (50% utilization): Replace old tool results with placeholder
Protections:
- Never prunes before first real user message (bootstrap protection)
- Protects last 3 assistant messages and their corresponding tool results
- Skips image-containing tool results
- Respects tool allow/deny lists
Enabled by default in tokens/summary compaction modes.
