phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix!: Enhance response API support to not fail with tool calling (#3385)
Some checks failed
Python Package Build Test / build (3.12) (push) Failing after 8s
Details
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Details
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 3s
Details
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 5s
Details
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 6s
Details
Python Package Build Test / build (3.13) (push) Failing after 6s
Details
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 10s
Details
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Details
Unit Tests / unit-tests (3.12) (push) Failing after 19s
Details
Test External API and Providers / test-external (venv) (push) Failing after 1m3s
Details
Vector IO Integration Tests / test-matrix (push) Failing after 1m6s
Details
API Conformance Tests / check-schema-compatibility (push) Successful in 1m17s
Details
UI Tests / ui-tests (22) (push) Successful in 1m18s
Details
Pre-commit / pre-commit (push) Successful in 3m5s
Details

Browse source 
# What does this PR do?
Introduces two main fixes to enhance the stability of Responses API when
dealing with tool calling responses and structured outputs.

### Changes Made

1. It added OpenAIResponseOutputMessageMCPCall and ListTools to
OpenAIResponseInput but
https://github.com/llamastack/llama-stack/pull/3810 got merge that did
the same in a different way. Still this PR does it in a way that keep
the sync between OpenAIResponsesOutput and the allowed objects in
OpenAIResponseInput.

2. Add protection in case self.ctx.response_format does not have type
attribute

BREAKING CHANGE: OpenAIResponseInput now uses OpenAIResponseOutput union
type.
This is semantically equivalent - all previously accepted types are
still supported
via the OpenAIResponseOutput union. This improves type consistency and
maintainability.
This commit is contained in:
Luis Tomas Bolivar 2025-10-27 17:33:02 +01:00 • committed by GitHub
parent f18b5eb537
commit 63422e5b36
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 84 additions and 79 deletions
Download patch file Download diff file Expand all files Collapse all files

7
docs/static/llama-stack-spec.yaml vendored
View file

@ -5522,14 +5522,9 @@ components:
Error details for failed OpenAI response requests.
OpenAIResponseInput:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutput'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
- $ref: '#/components/schemas/OpenAIResponseMessage'
OpenAIResponseInputToolFileSearch:
type: object