ryan-crabbe-berri 634852a183 fix(anthropic): key the /v1/messages prompt cache on Claude Code's session_id only ... The bridges derived prompt_cache_key as the first 64 chars of metadata.user_id. Claude Code packs a JSON object into that field whose prefix is the per-install device_id, so every session and subagent on one machine shared a single key, and a plain end-user id pinned all of that user's conversations to one slot. Parse the JSON and use session_id; send no key otherwise so the provider falls back to its own prompt-prefix hashing. An explicit prompt_cache_key still wins. Fixes #39145		2026-09-08 18:06:39 -07:00
..
batches	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
chat	perf: move Anthropic, Vertex Anthropic, Ollama and HF template fetches off the event loop (#40311)	2026-09-08 15:53:43 -07:00
experimental_pass_through	fix(anthropic): key the /v1/messages prompt cache on Claude Code's session_id only	2026-09-08 18:06:39 -07:00
files	fix(batches): price anthropic passthrough message batches correctly in batch cost job (#32307)	2026-07-06 20:33:57 -07:00
messages	fix(advisor): exclude in-sequence system rows from the advisor sub-call context	2026-08-18 13:51:01 -07:00
__init__.py	test(batches): add 1:1 test file scaffold for batches component paths (#30529)	2026-06-29 09:22:58 +05:30
test_anthropic_common_utils.py	fix: skip one-shot Claude Code cache injection (#40175)	2026-09-07 18:03:43 -07:00
test_anthropic_count_tokens_transformation.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_anthropic_files_and_batches.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_anthropic_output_format_filter.py	fix(anthropic): strip all remaining output_format schema keywords rejected by Anthropic	2026-07-22 16:16:04 -07:00
test_anthropic_reasoning_effort.py	fix(anthropic/bedrock): request summarized adaptive thinking for reasoning_effort and use provider thinking token counts	2026-08-22 23:10:42 +00:00
test_anthropic_schema_filter.py	fix(anthropic): reconcile enum with declared type in output_format schema (#37882)	2026-08-24 11:43:47 -07:00
test_anthropic_structured_output.py	fix(model_map): flag native structured outputs on Anthropic-direct claude-sonnet-5 and claude-haiku-4-5 (#35930)	2026-08-15 11:51:35 -07:00
test_azure_ai_cache_pricing.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_cost_calculation_dict_safety.py	refactor: dedupe server_tool_use web search reads and type fresh test locals	2026-08-27 08:01:52 +00:00
test_count_tokens_oauth.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_message_sanitization.py	fix(anthropic, mcp): sanitize tool names to match Anthropic's [a-zA-Z0-9_-]{1,128} pattern (#26788)	2026-05-06 00:00:36 +00:00