* fix(agents): wait for agent idle before flushing pending tool results
When pi-agent-core's auto-retry mechanism handles overloaded/rate-limit
errors, it resolves waitForRetry() on assistant message receipt — before
tool execution completes in the retried agent loop. This causes the
attempt's finally block to call flushPendingToolResults() while tools
are still executing, inserting synthetic 'missing tool result' errors
and causing silent agent failures.
The fix adds a waitForIdle() call before the flush to ensure the agent's
retry loop (including tool execution) has fully completed.
Evidence from real session: tool call and synthetic error were only 53ms
apart — the tool never had a chance to execute before being flushed.
Root cause is in pi-agent-core's _resolveRetry() firing on message_end
instead of agent_end, but this workaround in OpenClaw prevents the
symptom without requiring an upstream fix.
Fixes#8643Fixes#13351
Refs #6682, #12595
* test: add tests for tool result flush race condition
Validates that:
- Real tool results are not replaced by synthetic errors when they arrive in time
- Flush correctly inserts synthetic errors for genuinely orphaned tool calls
- Flush is a no-op after real tool results have already been received
Refs #8643, #13748
* fix(agents): add waitForIdle to all flushPendingToolResults call sites
The original fix only covered the main run finally block, but there are
two additional call sites that can trigger flushPendingToolResults while
tools are still executing:
1. The catch block in attempt.ts (session setup error handler)
2. The finally block in compact.ts (compaction teardown)
Both now await agent.waitForIdle() with a 30s timeout before flushing,
matching the pattern already applied to the main finally block.
Production testing on VPS with debug logging confirmed these additional
paths can fire during sub-agent runs, producing spurious synthetic
'missing tool result' errors.
* fix(agents): centralize idle-wait flush and clear timeout handle
---------
Co-authored-by: Renue Development <dev@renuebyscience.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
- Update @mariozechner/pi-agent-core, pi-ai, pi-coding-agent, pi-tui to 0.51.0
- Delete src/types/pi-coding-agent.d.ts (declared additionalExtensionPaths which SDK never supported)
- Fix ToolDefinition.execute signature (parameter order changed in 0.51.0)
- Remove dead additionalExtensionPaths from createAgentSession calls
* fix: detect Anthropic 'Request size exceeds model context window' as context overflow
Anthropic now returns 'Request size exceeds model context window' instead of
the previously detected 'prompt is too long' format. This new error message
was not recognized by isContextOverflowError(), causing auto-compaction to
NOT trigger. Users would see the raw error twice without any recovery attempt.
Changes:
- Add 'exceeds model context window' and 'request size exceeds' to
isContextOverflowError() detection patterns
- Add tests that fail without the fix, verifying both the raw error
string and the JSON-wrapped format from Anthropic's API
- Add test for formatAssistantErrorText to ensure the friendly
'Context overflow' message is shown instead of the raw error
Note: The upstream pi-ai package (@mariozechner/pi-ai) also needs a fix
in its OVERFLOW_PATTERNS regex: /exceeds the context window/i should be
changed to /exceeds.*context window/i to match both 'the' and 'model'
variants for triggering auto-compaction retry.
* fix(tests): remove unused imports and helper from test files
Remove WorkspaceBootstrapFile references and _makeFile helper that were
incorrectly copied from another test file. These caused type errors and
were unrelated to the context overflow detection tests.
* fix: trigger auto-compaction on context overflow promptError
When the LLM rejects a request with a context overflow error that surfaces
as a promptError (thrown exception rather than streamed error), the existing
auto-compaction in pi-coding-agent never triggers. This happens because the
error bypasses the agent's message_end → agent_end → _checkCompaction path.
This fix adds a fallback compaction attempt directly in the run loop:
- Detects context overflow in promptError (excluding compaction_failure)
- Calls compactEmbeddedPiSessionDirect (bypassing lane queues since already in-lane)
- Retries the prompt after successful compaction
- Limits to one compaction attempt per run to prevent infinite loops
Fixes: context overflow errors shown to user without auto-compaction attempt
* style: format compact.ts and run.ts with oxfmt
* fix: tighten context overflow match (#1627) (thanks @rodrigouroz)
---------
Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* feat(whatsapp): add debounceMs for batching rapid messages
Add a `debounceMs` configuration option to WhatsApp channel settings
that batches rapid consecutive messages from the same sender into a
single response. This prevents triggering separate agent runs for
each message when a user sends multiple short messages in quick
succession (e.g., "Hey!", "how are you?", "I was wondering...").
Changes:
- Add `debounceMs` config to WhatsAppConfig and WhatsAppAccountConfig
- Implement message buffering in `monitorWebInbox` with:
- Map-based buffer keyed by sender (DM) or chat ID (groups)
- Debounce timer that resets on each new message
- Message combination with newline separator
- Single message optimization (no modification if only one message)
- Wire `debounceMs` through account resolution and monitor tuning
- Add UI hints and schema documentation
Usage example:
{
"channels": {
"whatsapp": {
"debounceMs": 5000 // 5 second window
}
}
}
Default behavior: `debounceMs: 0` (disabled by default)
Verified: All existing tests pass (3204 tests), TypeScript compilation
succeeds with no errors.
Implemented with assistance from AI coding tools.
Closes#967
* chore: wip inbound debounce
* fix: debounce inbound messages across channels (#971) (thanks @juanpablodlc)
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
