Commit Graph

5 Commits

Author SHA1 Message Date
cthomas
c162de5127 fix: use shared event + .athrow() to properly set stream_was_cancelle… (#9019)
fix: use shared event + .athrow() to properly set stream_was_cancelled flag

**Problem:**
When a run is cancelled via /cancel endpoint, `stream_was_cancelled` remained
False because `RunCancelledException` was raised in the consumer code (wrapper),
which closes the generator from outside. This causes Python to skip the
generator's except blocks and jump directly to finally with the wrong flag value.

**Solution:**
1. Shared `asyncio.Event` registry for cross-layer cancellation signaling
2. `cancellation_aware_stream_wrapper` sets the event when cancellation detected
3. Wrapper uses `.athrow()` to inject exception INTO generator (not consumer-side raise)
4. All streaming interfaces check event in `finally` block to set flag correctly
5. `streaming_service.py` handles `RunCancelledException` gracefully, yields [DONE]

**Changes:**
- streaming_response.py: Event registry + .athrow() injection + graceful handling
- openai_streaming_interface.py: 3 classes check event in finally
- gemini_streaming_interface.py: Check event in finally
- anthropic_*.py: Catch RunCancelledException
- simple_llm_stream_adapter.py: Create & pass event to interfaces
- streaming_service.py: Handle RunCancelledException, yield [DONE], skip double-update
- routers/v1/{conversations,runs}.py: Pass event to wrapper
- integration_test_human_in_the_loop.py: New test for approval + cancellation

**Tests:**
- test_tool_call with cancellation (OpenAI models) 
- test_approve_with_cancellation (approval flow + concurrent cancel) 

**Known cosmetic warnings (pre-existing):**
- "Run already in terminal state" - agent loop tries to update after /cancel
- "Stream ended without terminal event" - background streaming timing race

👾 Generated with [Letta Code](https://letta.com)

Co-authored-by: Letta <noreply@letta.com>
2026-01-29 12:44:04 -08:00
Kian Jones
e60e8ed670 chore: bump wait_for_server from 30 to 60 seconds (#8435)
bump 30 to 60 seconds
2026-01-12 10:57:49 -08:00
Sarah Wooders
f417e53638 fix: fix cancellation issues without making too many changes to message_ids persistence (#6442) 2025-12-15 12:02:19 -08:00
cthomas
e5bddab11c test: migrate cancellation test to 1.0 sdk [LET-6327] (#6375)
* test: migrate cancellation test to 1.0 sdk

* revert async change

* debug redis

* cleanup
2025-11-26 14:39:39 -08:00
Charles Packer
a6077f3927 fix(core): Fix agent loop continuing after cancellation in letta_agent_v3 [LET-6006] (#5905)
* Fix agent loop continuing after cancellation in letta_agent_v3

Bug: When a run is cancelled, _check_run_cancellation() sets
self.should_continue=False and returns early from _step(), but the outer
for loop (line 245) continues to the next iteration, executing subsequent
steps even though cancellation was requested.

Symptom: User hits cancel during step 1, backend marks run as cancelled,
but agent continues executing steps 2, 3, etc.

Root cause: After the 'async for chunk in response' loop completes (line 255),
there was no check of self.should_continue before continuing to the next
iteration of the outer step loop.

Fix: Added 'if not self.should_continue: break' check after the inner loop
to exit the outer step loop when cancellation is detected. This makes v3
consistent with v2 which already had this check (line 306-307).

🐾 Generated with [Letta Code](https://letta.com)

Co-authored-by: Letta <noreply@letta.com>

* add integration tests

* fix: misc fixes required to get cancellations to work on letta code localhost

---------

Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2025-11-13 15:36:39 -08:00