Luis Tomas Bolivar f7c2973aa5 fix: Avoid BadRequestError due to invalid max_tokens (#3667) ... This patch ensures if max tokens is not defined, then is set to None instead of 0 when calling openai_chat_completion. This way some providers (like gemini) that cannot handle the `max_tokens = 0` will not fail Issue: #3666		2025-10-30 14:23:22 -07:00
..
apis	fix: Avoid BadRequestError due to invalid max_tokens (#3667)	2025-10-30 14:23:22 -07:00
cli	fix(logging): move module-level initialization to explicit setup calls (#3874)	2025-10-21 11:08:25 -07:00
core	fix(inference): enable routing of models with provider_data alone (#3928)	2025-10-30 14:23:22 -07:00
distributions	revert: "chore(cleanup)!: remove tool_runtime.rag_tool" (#3877)	2025-10-21 11:22:06 -07:00
models	chore: remove dead code (#3729)	2025-10-07 20:26:02 -07:00
providers	fix(inference): enable routing of models with provider_data alone (#3928)	2025-10-30 14:23:22 -07:00
strong_typing	chore: refactor (chat)completions endpoints to use shared params struct (#3761)	2025-10-10 15:46:34 -07:00
testing	feat(ci): add support for docker:distro in tests (#3832)	2025-10-16 19:33:13 -07:00
ui	build: Bump version to 0.3.0	2025-10-21 23:58:10 +00:00
__init__.py	chore(rename): move llama_stack.distribution to llama_stack.core (#2975)	2025-07-30 23:30:53 -07:00
env.py	refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401)	2025-03-04 14:53:47 -08:00
log.py	fix(logs): restore uvicorn and llama_stack logger settings	2025-10-21 15:47:55 -07:00
schema_utils.py	fix(auth): allow unauthenticated access to health and version endpoints (#3736)	2025-10-10 13:41:43 -07:00