llama-stack-mirror/llama_stack/providers
Ashwin Bharambe 30ba8c8655
fix(responses): sync conversation before yielding terminal events in streaming (#3888)
Move conversation sync logic before yield to ensure it executes even
when
streaming consumers break early after receiving response.completed
event.

## Test Plan

```
OLLAMA_URL=http://localhost:11434 \
  pytest -sv tests/integration/responses/ \
  --stack-config server:ci-tests \
  --text-model ollama/llama3.2:3b-instruct-fp16 \
  --inference-mode live \
  -k conversation_multi
```

This test now passes.
2025-10-22 14:31:12 -07:00
..
inline fix(responses): sync conversation before yielding terminal events in streaming (#3888) 2025-10-22 14:31:12 -07:00
registry revert: "chore(cleanup)!: remove tool_runtime.rag_tool" (#3877) 2025-10-21 11:22:06 -07:00
remote chore(cleanup)!: kill vector_db references as far as possible (#3864) 2025-10-20 20:06:16 -07:00
utils feat: Add rerank models and rerank API change (#3831) 2025-10-22 12:02:28 -07:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
datatypes.py chore(cleanup)!: kill vector_db references as far as possible (#3864) 2025-10-20 20:06:16 -07:00