mateo-berri 98b1e2e7b4 fix(gigachat): correct cached-token accounting, stream usage on all finish reasons, stop mutating cached request body ... precached_prompt_tokens is a subset of prompt_tokens (OpenAI cached_tokens semantics), so map it to prompt_tokens_details.cached_tokens instead of adding it on top of prompt/total. Emit stream usage from any final chunk carrying it rather than only finish_reason stop, which dropped tokens for function_call and length streams. Merge auth metadata into a new dict in the gigachat router handler instead of mutating the shared parsed-body cache in place.		2026-08-31 14:28:30 -07:00
..
llm_provider_handlers	fix(anthropic): scale cache costs by fast mode and trust served speed	2026-08-26 11:24:12 -07:00
test_carry_guardrail_logging_info.py	fix(passthrough): emit otel guardrail span when a guardrail blocks (#29470)	2026-06-02 11:46:25 -07:00
test_llm_pass_through_endpoints.py	fix(gigachat): correct cached-token accounting, stream usage on all finish reasons, stop mutating cached request body	2026-08-31 14:28:30 -07:00
test_managed_id_rewriter.py	fix(passthrough): recognize CR-only SSE frame delimiters when minting streamed managed ids	2026-08-26 01:36:18 -07:00
test_method_specific_routing.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_pass_through_endpoints.py	fix(passthrough): record ownership of streamed responses under managed ids	2026-08-26 01:05:15 -07:00
test_passthrough_auth_default.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_passthrough_endpoint_router.py	fix: harden vertex live passthrough against client model forms and dict credentials	2026-08-20 03:05:48 -07:00
test_passthrough_endpoints_common_utils.py	test(aws): type the new partition test parameters	2026-08-29 02:27:18 -07:00
test_passthrough_guardrail_block_otel_span.py	fix: missing span for guardrail passthrough (#29552)	2026-06-03 01:25:15 +00:00
test_passthrough_guardrails.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_passthrough_guardrails_field_targeting.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_passthrough_post_call_guardrails.py	fix(proxy): strip only the authenticating secret on credential-less Vertex passthrough	2026-08-25 21:04:27 -07:00
test_streaming_handler.py	test(pass_through): pin stream pricing tests to injected divergent rate cards	2026-08-26 16:54:05 -07:00
test_streaming_handler_interrupt.py	fix(guardrails): match deferred stream dispatch shape per stream owner and defer passthrough logging until guardrail eos	2026-08-29 02:23:12 -07:00
test_upstream_usage_headers.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_vertex_ai_batch_passthrough.py	feat(batches): aggregate reasoning tokens and per-line pass/fail counts	2026-08-17 11:25:55 -04:00
test_vertex_passthrough_load_balancing.py	fix(proxy): strip only the authenticating secret on credential-less Vertex passthrough	2026-08-25 21:04:27 -07:00
test_watsonx_proxy_route.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00