llama-stack-mirror/docs/docs/providers
Matthew Farrellee e892a3f7f4
feat: add refresh_models support to inference adapters (default: false) (#3719)
# What does this PR do?

inference adapters can now configure `refresh_models: bool` to control
periodic model listing from their providers

BREAKING CHANGE: together inference adapter default changed. previously
always refreshed, now follows config.

addresses "models: refresh" on #3517

## Test Plan

ci w/ new tests
2025-10-07 15:19:56 +02:00
..
agents chore: fix precommit (#3663) 2025-10-02 14:51:41 -07:00
batches chore: fix precommit (#3663) 2025-10-02 14:51:41 -07:00
datasetio docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
eval docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
external docs!: adjust external provider docs (#3484) 2025-10-03 15:48:41 +02:00
files docs: API docstrings cleanup for better documentation rendering (#3661) 2025-10-06 10:46:33 -07:00
inference feat: add refresh_models support to inference adapters (default: false) (#3719) 2025-10-07 15:19:56 +02:00
post_training docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
safety feat: add refresh_models support to inference adapters (default: false) (#3719) 2025-10-07 15:19:56 +02:00
scoring docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
telemetry fix(logging): disable console telemetry sink by default (#3623) 2025-09-30 14:58:05 -07:00
tool_runtime docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
vector_io docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
index.mdx docs: fix broken links (#3540) 2025-09-24 14:16:31 -07:00
openai.mdx feat(openai_movement)!: Change URL structures to kill /openai/v1 (part 2) (#3605) 2025-09-29 22:57:37 -07:00