mateo-berri bf3de2f5cb fix(anthropic): run tool search on azure_ai, gate it on Databricks Claude, and strip deferral without recursion ... Anthropic's Foundry docs list no tool search exclusion for either hosting option, so the claude-tool-search rule now fills azure_ai. Databricks Claude models route their tools through the same unsupported-tool-search gate, so a tool_search tool answers 400 or drops under drop_params instead of a 500. _without_deferral strips two fixed levels instead of walking recursively.		2026-10-13 23:43:12 -07:00
..
chat	fix(anthropic): run tool search on azure_ai, gate it on Databricks Claude, and strip deferral without recursion	2026-10-13 23:43:12 -07:00
decisions	fix(databricks): call the ai_decide AI Function route for decisions and the auto-router (#45722)	2026-10-10 23:58:16 -07:00
responses	test(unit): make every tests/unit directory a package so pytest collection is unique	2026-09-20 11:50:59 +00:00
__init__.py	test(unit): make every tests/unit directory a package so pytest collection is unique	2026-09-20 11:50:59 +00:00
test_databricks_common_utils.py	test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759)	2026-10-11 07:58:53 +00:00
test_databricks_cost_calculator.py	fix(streaming): keep the served service_tier on streamed chunks and spend rows (#42870)	2026-09-29 12:54:17 -07:00
test_databricks_partner_integration.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00
test_databricks_streaming_utils.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191)	2026-09-25 12:43:23 -07:00