Document the full subagent lifecycle: spawn, concurrency queue,
execution, completion handling, two-tier announcement delivery,
and record archival. Include provider inheritance chain and
error propagation diagrams.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add error reporting rule to subagent system prompt: subagents must
explicitly report tool failures and missing credentials in their
final message. Add timeout guidelines to parent system prompt with
recommended values by task complexity (10-30 min).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When subagents are still running, sessions_list now returns an
explicit instruction telling the LLM not to poll again and wait
for automatic result delivery. Normalizes status display to
uppercase ([RUNNING], [OK], [ERROR]).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pass parent's resolvedProvider through the tool chain (tools.ts →
sessions-spawn.ts → hub.createSubagent) so subagents use the same
LLM provider as the parent. Previously subagents fell back to the
hardcoded default provider, causing API key errors.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace immediate record deletion with archiveAtMs-based deferred
cleanup (60min retention). This keeps records queryable via
sessions_list after completion. Add sweeper to clean expired records.
Check childAgent.lastRunError after waitForIdle to detect failed runs
that resolve the promise without throwing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add isRunning flag to Agent (runner.ts) for detecting active runs.
Add lastRunError to AsyncAgent for propagating child run errors to
the registry. Fix duplicate message emission in writeInternal by
resetting forwardInternalAssistant before persistAssistantSummary.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add announce-queue.ts for batching nearby subagent completions with
debounce (1s) and collect mode. Implement two-tier delivery in
announce.ts: queue when parent is busy, writeInternal when idle.
All delivery uses writeInternal() to mark messages as internal,
preventing announcement bubbles from appearing in the UI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
setProvider() updated the resolved provider and model but did not
rebuild the system prompt, so the runtime info line still showed the
old provider/model (e.g. claude-code/claude-opus-4-6) after switching.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Registry model IDs used hyphens (claude-sonnet-4-5) but pi-ai expects
dots (claude-sonnet-4.5). Also adds a fallback model config for OpenRouter
models not in pi-ai's registry, since OpenRouter supports thousands of models.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Queued through the serialization queue to safely switch provider,
send a minimal test prompt, and restore the previous provider.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wire registry and sessions_spawn through the lane-based queue so
sub-agents respect max concurrency. Add resolveSubagentTimeoutMs()
with defaults (10 min), 0 = no timeout, and safe clamping.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduces a command queue system adapted from OpenClaw to prevent
unbounded sub-agent spawning. Default max concurrency: 10.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
