llama-stack-mirror/llama_stack/providers
Michael Dawson 80405da304 fix: ensure usage is requested if telemetry is enabled
Refs: https://github.com/llamastack/llama-stack/issues/3420

When telemetry is enabled the router uncondionally expects the
usage attribute to be availble and fails if it is not present.

Telemetry is not currently being requested by litellm_openai_mixin.py
for streaming requests which means that providers like vertexai
fail if telemetry is enabled and streaming is used.

This is part of the required fix. Other part is in litell, will
plan to submit PR for that soon.

Signed-off-by: Michael Dawson <midawson@redhat.com>
2025-09-26 15:50:11 -04:00
..
inline chore: simplify authorized sqlstore (#3496) 2025-09-19 16:13:56 -07:00
registry fix: force milvus-lite installation for inline::milvus (#3488) 2025-09-19 16:12:08 -04:00
remote chore: Refactor fireworks to use OpenAIMixin (#3480) 2025-09-22 13:19:36 -04:00
utils fix: ensure usage is requested if telemetry is enabled 2025-09-26 15:50:11 -04:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00
datatypes.py feat: combine ProviderSpec datatypes (#3378) 2025-09-18 16:10:00 +02:00