llama-stack-mirror/llama_stack/providers/inline/agents/meta_reference/responses
grs 96886afaca
fix(responses): fix regression in support for mcp tool require_approval argument (#3731)
# What does this PR do?

It prevents a tool call message being added to the chat completions
message without a corresponding tool call result, which is needed in the
case that an approval is required first or if the approval request is
denied. In both these cases the tool call messages is popped of the next
turn messages.

Closes #3728

## Test Plan
Ran the integration tests
Manual check of both approval and denial against gpt-4o

Signed-off-by: Gordon Sim <gsim@redhat.com>
2025-10-08 10:47:17 -04:00
..
__init__.py chore(responses): Refactor Responses Impl to be civilized (#3138) 2025-08-15 00:05:35 +00:00
openai_responses.py fix(responses): fix regression in support for mcp tool require_approval argument (#3731) 2025-10-08 10:47:17 -04:00
streaming.py fix(responses): fix regression in support for mcp tool require_approval argument (#3731) 2025-10-08 10:47:17 -04:00
tool_executor.py feat: Enabling Annotations in Responses (#3698) 2025-10-07 14:00:56 -04:00
types.py feat: Enabling Annotations in Responses (#3698) 2025-10-07 14:00:56 -04:00
utils.py feat: Enabling Annotations in Responses (#3698) 2025-10-07 14:00:56 -04:00