yuneng-jiang b395bfefdd fix: repair seven regressions caught by CircleCI on main (#42640) ... * fix: repair seven regressions caught by CircleCI on main - vertex_ai: stop treating fine-tuned endpoint ids (numeric or vertex_ai/gemini/<id>) and gemma models as Gemini 3+, which injected temperature=1.0 and Gemini 3 thinking config into their requests (#42465) - cost: price Azure DALL-E 3 from its azure/<quality>/<size>/dall-e-3 rows; it only worked through the OpenAI rows that #42435 removed - bedrock: stream bedrock/invoke/moonshot through an OpenAI-shaped chunk decoder; the generic decoder dropped every chunk, which the supports_response_schema flag from #42338 un-skipped in CI - proxy: keep the public model_group on pre-routing rejections so the Usage page groups them under the model name, not the deployment (#41077) - cost map: mirror the base rows' capability flags onto Bedrock regional and cross-region copies (#42254 and later syncs) - whitelist the new regional Bedrock rows from #42543 and #42588 for the converse routing check, following the existing regional-row convention * fix(model-prices): mirror capability flags onto ap-southeast-3 bedrock rows * refactor(bedrock): tighten types on the moonshot stream decoder and its tests		2026-09-23 02:26:36 +00:00
..
helpers	fix(agents): evict the cached agent access groups on every agent write and cap the model listing	2026-09-17 20:31:03 +00:00
prisma_and_spend	Merge remote-tracking branch 'origin/main' into litellm_redis_durable_spend_log_buffer	2026-09-20 08:52:32 +00:00
proxy_logging	fix: repair seven regressions caught by CircleCI on main (#42640)	2026-09-23 02:26:36 +00:00
__init__.py	test(proxy/utils): pin bottom-of-file helper behavior (#29509)	2026-06-02 17:45:19 -07:00