llama-stack-mirror/llama_stack/apis
ehhuang cf422da825 fix: responses <> chat completion input conversion (#3645)
# What does this PR do?

closes #3268
closes #3498

When resuming from previous response ID, currently we attempt to convert
from the stored responses input to chat completion messages, which is
not always possible, e.g. for tool calls where some data is lost once
converted from chat completion message to repsonses input format.

This PR stores the chat completion messages that correspond to the
_last_ call to chat completion, which is sufficient to be resumed from
in the next responses API call, where we load these saved messages and
skip conversion entirely.

Separate issue to optimize storage:
https://github.com/llamastack/llama-stack/issues/3646

## Test Plan
existing CI tests
2025-10-02 21:50:13 -07:00
..
agents fix: responses <> chat completion input conversion (#3645) 2025-10-02 21:50:13 -07:00
batches chore!: add double routes for v1/openai/v1 (#3636) 2025-10-02 21:50:12 -07:00
benchmarks feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
common feat: Add Kubernetes auth provider to use SelfSubjectReview and kubernetes api server (#2559) 2025-09-08 11:25:10 +02:00
datasetio feat(api): implement v1beta leveling, and additional alpha (#3594) 2025-10-01 09:18:11 -07:00
datasets feat(api): implement v1beta leveling, and additional alpha (#3594) 2025-10-01 09:18:11 -07:00
eval feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
files chore!: add double routes for v1/openai/v1 (#3636) 2025-10-02 21:50:12 -07:00
inference feat(tools)!: substantial clean up of "Tool" related datatypes (#3627) 2025-10-02 21:50:13 -07:00
inspect feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
models chore!: add double routes for v1/openai/v1 (#3636) 2025-10-02 21:50:12 -07:00
post_training feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
prompts feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
providers feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
safety chore!: add double routes for v1/openai/v1 (#3636) 2025-10-02 21:50:12 -07:00
scoring feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
scoring_functions feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
shields feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
synthetic_data_generation feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
telemetry feat(api): implement v1beta leveling, and additional alpha (#3594) 2025-10-01 09:18:11 -07:00
tools feat(tools)!: substantial clean up of "Tool" related datatypes (#3627) 2025-10-02 21:50:13 -07:00
vector_dbs feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00
vector_io chore!: add double routes for v1/openai/v1 (#3636) 2025-10-02 21:50:12 -07:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
datatypes.py feat: Adding OpenAI Prompts API (#3319) 2025-09-08 11:05:13 -04:00
resource.py feat: Adding OpenAI Prompts API (#3319) 2025-09-08 11:05:13 -04:00
version.py feat: introduce API leveling, post_training, eval to v1alpha (#3449) 2025-09-26 16:18:07 +02:00