* fix(agents): bypass pendingDescendantRuns guard for cron announce delivery
Standalone cron job completions were blocked from direct channel delivery
when the cron run had spawned subagents that were still registered as
pending. The pendingDescendantRuns guard exists for live orchestration
coordination and should not apply to fire-and-forget cron announce sends.
Thread the announceType through the delivery chain and skip both the
child-descendant and requester-descendant pending-run guards when the
announce originates from a cron job.
Closes#34966
* fix: ensure outbound session entry for cron announce with named agents (#32432)
Named agents may not have a session entry for their delivery target,
causing the announce flow to silently fail (delivered=false, no error).
Two fixes:
1. Call ensureOutboundSessionEntry when resolving the cron announce
session key so downstream delivery can find channel metadata.
2. Fall back to direct outbound delivery when announce delivery fails
to ensure cron output reaches the target channel.
Closes#32432
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: guard announce direct-delivery fallback against suppression leaks (#32432)
The `!delivered` fallback condition was too broad — it caught intentional
suppressions (active subagents, interim messages, SILENT_REPLY_TOKEN) in
addition to actual announce delivery failures. Add an
`announceDeliveryWasAttempted` flag so the direct-delivery fallback only
fires when `runSubagentAnnounceFlow` was actually called and failed.
Also remove the redundant `if (route)` guard in
`resolveCronAnnounceSessionKey` since `resolved` being truthy guarantees
`route` is non-null.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(cron): harden announce synthesis follow-ups
---------
Co-authored-by: scoootscooob <zhentongfan@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
createOllamaStreamFn() only accepted baseUrl, ignoring custom headers
configured in models.providers.<provider>.headers. This caused 403
errors when Ollama endpoints are behind reverse proxies that require
auth headers (e.g. X-OLLAMA-KEY via HAProxy).
Add optional defaultHeaders parameter to createOllamaStreamFn() and
merge them into every fetch request. Provider headers from config are
now passed through at the call site in the embedded runner.
Fixes#24285
Synthesize runtime state transition fixes for compaction tool-use integrity and long-running handler backpressure.
Sources: #33630, #33583
Co-authored-by: Kevin Shenghui <shenghuikevin@gmail.com>
Co-authored-by: Theo Tarr <theodore@tarr.com>
fix: improve compaction summary instructions to preserve active work
Expand staged-summary merge instructions to preserve active task status, batch progress, latest user request, and follow-up commitments so compaction handoffs retain in-flight work context.
Co-authored-by: joetomasone <56984887+joetomasone@users.noreply.github.com>
Co-authored-by: Josh Lehman <josh@martian.engineering>
* fix(gateway): flush throttled delta before emitChatFinal
The 150ms throttle in emitChatDelta can suppress the last text chunk
before emitChatFinal fires, causing streaming clients (e.g. ACP) to
receive truncated responses. The final event carries the complete text,
but clients that build responses incrementally from deltas miss the
tail end.
Flush one last unthrottled delta with the complete buffered text
immediately before sending the final event. This ensures all streaming
consumers have the full response without needing to reconcile deltas
against the final payload.
* fix(gateway): avoid duplicate delta flush when buffer unchanged
Track the text length at the time of the last broadcast. The flush in
emitChatFinal now only sends a delta if the buffer has grown since the
last broadcast, preventing duplicate sends when the final delta passed
the 150ms throttle and was already broadcast.
* fix(gateway): honor heartbeat suppression in final delta flush
* test(gateway): add final delta flush and dedupe coverage
* fix(gateway): skip final flush for silent lead fragments
* docs(changelog): note gateway final-delta flush fix credits
---------
Co-authored-by: Jonathan Taylor <visionik@pobox.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* fix(agents): recognize connection errors as retryable timeout failures
## Problem
When a model endpoint becomes unreachable (e.g., local proxy down,
relay server offline), the failover system fails to switch to the
next candidate model. Errors like "Connection error." are not
classified as retryable, causing the session to hang on a broken
endpoint instead of falling back to healthy alternatives.
## Root Cause
Connection/network errors are not recognized by the current failover
classifier:
- Text patterns like "Connection error.", "fetch failed", "network error"
- Error codes like ECONNREFUSED, ENOTFOUND, EAI_AGAIN (in message text)
While `failover-error.ts` handles these as error codes (err.code),
it misses them when they appear as plain text in error messages.
## Solution
Extend timeout error patterns to include connection/network failures:
**In `errors.ts` (ERROR_PATTERNS.timeout):**
- Text: "connection error", "network error", "fetch failed", etc.
- Regex: /\beconn(?:refused|reset|aborted)\b/i, /\benotfound\b/i, /\beai_again\b/i
**In `failover-error.ts` (TIMEOUT_HINT_RE):**
- Same patterns for non-assistant error paths
## Testing
Added test cases covering:
- "Connection error."
- "fetch failed"
- "network error: ECONNREFUSED"
- "ENOTFOUND" / "EAI_AGAIN" in message text
## Impact
- **Compatibility:** High - only expands retryable error detection
- **Behavior:** Connection failures now trigger automatic fallback
- **Risk:** Low - changes are additive and well-tested
* style: fix code formatting for test file
