scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-08 08:08:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 80
litellm/tests/integration/providers
History
Mateo Wang 36c64ce85d
feat(bedrock): default to native structured output on Opus 5.5, Fable 5.1, Sonnet 5 and Haiku 5.5 (#50221) 
* feat(bedrock): enable native structured output by default for selected Claude models

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): keep govcloud and bare model rows off native output

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): retry rejected native schemas with the JSON tool on default-native models

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): keep the rejection retry on the unforceable-tool native path

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): retry rejected schemas on the Messages path for default-native models

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style(bedrock): format Messages native output retry

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(bedrock): allow profile-only native output metadata

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): only disable default-native output on schema-rejection retries

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(bedrock): type fixture parameters in native output retry tests

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): retry with the JSON tool when Bedrock rejects a schema's grammar size

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): drop strict tools after a native-output retry hits the grammar limit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* style(bedrock): format native output fallback

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(bedrock): honor the deployment native output opt-out and keep wide batch schemas on the JSON tool

A deployment's supports_bedrock_native_structured_output: false now keeps the JSON tool on rows that default to native output. Bedrock batch has no retry, so a record whose schema has more than 64 properties keeps the JSON tool there too.

* fix(bedrock): retry a native structured output stream as a buffered stream when Bedrock denies the stream action

A role allowed only bedrock:InvokeModel got a 403 on schema streams once these
models went native, since native streams call converse-stream while the JSON
tool path buffered through converse. The retry now sends that request again
as a buffered JSON tool stream, the shape the base sent.

The wire test moves its neither-key and opt-in cells to Opus 4.7, its
Bedrock-key-only cells to Sonnet 5.5, and its unforceable-tool cells to the
bare Opus 5.5 id, since this PR makes Opus 5.5 and Haiku 5.5 always native.

The batch wire test now checks a thinking schema record on both sides of the
contract the batch unit test already pins, the JSON tool on opt-in Sonnet 5.5
and native output on always-native Haiku 5.5, since its Haiku 5.5 and Opus 4.8
cells assumed those models were opt-in.

* fix(bedrock): move the Claude 5 native output default to a key released proxies do not read

Released proxies load the cost map from main and have none of the native
output retries, so setting supports_native_structured_output on the Opus
5.5, Fable 5.1, Sonnet 5 and Haiku 5.5 profile rows turned working wide
or min/max schemas into 400s on v1.108.1.

Those rows keep supports_native_structured_output false and gain
bedrock_native_structured_output_by_default true, which get_model_info
reports as supports_native_structured_output, so this version behaves as
before while released versions keep the JSON tool.

* fix(bedrock): rename the Claude 5 native output default key to supports_bedrock_native_structured_output_by_default

The cost map guard runs main's model catalog on the PR's cost map, and that catalog rejects any undeclared key that does not start with supports_. Declaring the old name on main first needs its own PR, so the key takes the supports_ prefix. Released proxies still never read it

* fix(bedrock): honor registered and batch opt-outs, move Opus 5 and 4.8 to the default key

A registered supports_bedrock_native_structured_output false now beats the
native output default, and batch uploads read the deployment's model_info, so
an opted-out deployment keeps the JSON tool on every record. The Opus 5 and
Opus 4.8 profile rows move to supports_bedrock_native_structured_output_by_default,
so released proxies on main's cost map keep the JSON tool on them. The 64
property batch cutoff now applies only to rows with that key, so models that
were already native keep their batch output shape.

* fix(proxy): report a deployment's Bedrock native output opt-out on /model/info

/model/info merged the deployment's model_info over the backend row, so a
deployment that set only supports_bedrock_native_structured_output: false
still showed the backend's derived supports_native_structured_output: true.
The generic flag is now derived from the merged info unless the deployment
set it itself, through the same helper get_model_info uses.

* fix(bedrock): keep native output when a denied schema stream is resent buffered

A role without bedrock:InvokeModelWithResponseStream had its native output schema stream resent as a buffered JSON tool call. The resend now keeps the native params with fake_stream set, and falls back to the JSON tool only if Bedrock then rejects native output.

* fix(bedrock): drop rejected strict tools on the JSON tool retry after a buffered native resend

* fix(bedrock): send a buffered schema stream to /invoke and keep the by-default key on its deployment

The shared HTTP handler now builds the non-streaming URL for a fake-streamed request, so the invoke route's buffered resend after a denied stream calls /invoke instead of invoke-with-response-stream. supports_bedrock_native_structured_output_by_default is deployment scoped, so setting it on one deployment no longer reaches sibling deployments of the same model

* fix(bedrock): answer a buffered invoke stream from the non-streaming reply

* fix(bedrock): keep the JSON tool retry buffered after a denied stream's schema is rejected

* fix(bedrock): count only a true fake_stream and keep the deployment by-default key out of /model/info

A fake_stream sent as "true" or 1 picked the non-streaming URL but kept the streaming reader, so Bedrock invoke streams answered 500 after three billed calls. Only a real True counts now, as on main.

/model/info read supports_bedrock_native_structured_output_by_default from the deployment, while routing reads it only from the cost map, so it reported native output for deployments that use the JSON tool.

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-11-06 09:38:00 -08:00
..
_anthropic_safeguards_beta_support.py fix(rust): add the dangerous-tool-use beta when an anthropic /v1/messages request carries safeguards (#46102) 2026-10-17 16:48:05 +00:00
_api_base_trailing_slash_support.py fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
_api_base_url_join_support.py test(llms): audit #47535 (#48786) 2026-10-28 03:38:21 -07:00
_assistants_route_errors_support.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
_cache_control_marks_support.py fix(responses): propagate cache_control through responses->chat completion bridge (#32511) 2026-10-14 15:44:34 -07:00
_coralbricks.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
_count_tokens_system_lift.py fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
_dashscope_video_support.py feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos (#43706) 2026-10-14 10:10:07 -07:00
_gemini_long_decode_support.py feat(gemini)!: auto-continue gemini-4-argon long decodes with continuationToken (#46240) 2026-10-15 22:54:23 +00:00
_gemini_tts_voice_support.py perf(ci): isolate and shard integration suites (#44146) 2026-10-10 11:15:19 -07:00
_idle_upstream_support.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
_mantle_gpt_prompt_cache_support.py fix(logging): keep the caller's call_type when chat completions are bridged to the Responses API (#49710) 2026-11-03 10:02:54 +00:00
_responses_bridge_prompt_cache_breakpoint.py fix(responses): keep prompt_cache_breakpoint markers in the chat to responses bridge (#44119) 2026-10-07 16:25:36 -07:00
_sagemaker_chat_container.py fix(sagemaker)!: parse every streamed record however SageMaker cuts the payload parts (#47495) 2026-10-20 09:36:49 +00:00
_tool_search_support.py fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
_vertex_batch_rows.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
fine_tuning_proxy_config.yaml test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
openai_fine_tuning.jsonl test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_a2a_sdk_upstream_wire.py test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
test_anthropic_context_window_stop_wire.py fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192) 2026-10-31 02:53:59 -07:00
test_anthropic_count_tokens_system_lift_wire.py fix(responses)!: answer 400 before counting a lone Responses built-in tool on Claude (#48798) 2026-10-28 12:12:45 -07:00
test_anthropic_empty_user_turn_wire.py fix(anthropic): keep trailing user messages with None or empty list content (#41397) 2026-10-16 07:41:05 +00:00
test_anthropic_passthrough_wire.py fix(proxy): forward a valid metadata.user_id to Anthropic Messages on pass-through routes (#49333) 2026-10-31 00:16:42 -07:00
test_anthropic_refusal_stop_details_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_anthropic_refusal_stop_details_wire.py fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703) 2026-11-03 01:56:52 +00:00
test_anthropic_skills_create_wire.py test(integration): cover anthropic_messages endpoint contracts (#44704) 2026-10-14 06:57:54 +00:00
test_anthropic_system_cache_control_wire.py test(integration): assert /v1/responses usage reports Anthropic system cache write then read (#42855) 2026-09-23 18:52:06 -07:00
test_anthropic_thinking_signature_logging_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_anthropic_thinking_signature_stream_wire.py test: expect the list-position index on streamed thinking blocks in the integration suite (#46618) 2026-10-15 05:52:56 +00:00
test_anthropic_tool_search_result_chaos.py fix(anthropic): keep tool_search_tool_result so the search call replays with its result (#46440) 2026-10-14 18:52:32 -07:00
test_anthropic_tool_search_result_matrix_wire.py fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
test_anthropic_tool_search_result_modify_params_wire.py fix(anthropic): count a replayed server tool call's cache mark the way modify_params sends it (#46591) 2026-10-15 14:46:43 -07:00
test_anthropic_tool_search_result_passthrough_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_anthropic_tool_search_result_wire.py fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
test_api_base_trailing_slash_chaos.py fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
test_api_base_trailing_slash_owned_proxy.py fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
test_api_base_trailing_slash_wire.py fix(ollama): forward embedding credentials, headers and timeout (#48707) 2026-10-28 09:32:47 -07:00
test_api_base_url_join_chaos.py fix(llms): join api_base and route with one shared helper (#47535) 2026-10-21 06:59:32 +00:00
test_api_base_url_join_host_owned_proxy.py test(llms): audit #47535 (#48786) 2026-10-28 03:38:21 -07:00
test_api_base_url_join_wire.py test(llms): audit #47535 (#48786) 2026-10-28 03:38:21 -07:00
test_assemblyai_passthrough.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_assistants_evals_wire.py test(integration): pin assistants and evals endpoint contracts (#44734) 2026-10-14 07:08:35 +00:00
test_assistants_route_errors_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_assistants_route_errors_wire.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_audit_any_sweep_harness_endpoint.py refactor(types): replace Any with proven types in 9 files (#44389) 2026-10-03 21:03:16 +00:00
test_audit_any_sweep_vector_store.py refactor(types): replace Any with proven types in 9 files (#44389) 2026-10-03 21:03:16 +00:00
test_azure_ai_chat_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_azure_ai_claude_messages_wire.py fix(anthropic)!: sync the beta header allowlist with what anthropic, vertex_ai, and azure_ai accept (#49409) 2026-11-02 05:57:51 -08:00
test_azure_ai_flux2_image_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_azure_ai_rerank_auth_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_azure_embedding_wire.py test(integration): cover embeddings endpoint contracts (#44660) 2026-10-14 03:38:12 +00:00
test_azure_entra_token_reuse_wire.py fix(azure): share one Entra token request per worker and audit #47348 (#48769) 2026-10-28 12:24:20 -07:00
test_azure_reasoning_effort_none_wire.py test(integration): repair seven stale integration tests on main (#47600) 2026-10-20 11:21:04 -07:00
test_azure_responses_api_version_wire.py fix(providers): route Azure Responses past dated api versions, count Grok reasoning tokens on azure_ai, refresh provider sets after register_model, fix gpt-6.1-sol Azure rows (#46377) 2026-10-16 15:23:46 -07:00
test_bedrock_anthropic_beta_header_wire.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
test_bedrock_auth_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_bedrock_batch_blank_s3_env_wire.py test(e2e): assert only litellm-owned batch behavior and move the blank S3 env pin to an integration test (#43321) 2026-09-26 11:17:03 -07:00
test_bedrock_batch_files_wire.py feat(bedrock): default to native structured output on Opus 5.5, Fable 5.1, Sonnet 5 and Haiku 5.5 (#50221) 2026-11-06 09:38:00 -08:00
test_bedrock_batch_retrieve_status_wire.py fix(bedrock): map Scheduled batch jobs to in_progress on retrieve (#45157) 2026-10-07 18:08:51 -07:00
test_bedrock_claude_thinking_wire.py fix(anthropic): drop unknown legacy thinking keys under drop_params when rebuilding adaptive thinking (#46741) 2026-10-15 23:09:30 +00:00
test_bedrock_converse_client_metadata_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_converse_config_blocks_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_bedrock_converse_lookaround_regex_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_bedrock_converse_lookaround_regex_wire.py test: update stale integration and guardrail e2e tests to intended behavior (#48665) 2026-10-28 01:11:25 +00:00
test_bedrock_converse_missing_content_wire.py test(integration): look up streamed Responses spend rows by the client-facing id (#49752) 2026-11-02 17:13:41 -08:00
test_bedrock_converse_redacted_thinking_wire.py fix(bedrock): drop another model's signed thinking when replaying to a non-Claude Converse target (#50073) 2026-11-06 03:15:49 -08:00
test_bedrock_converse_stream_event_frames_wire.py test(integration): look up streamed Responses spend rows by the client-facing id (#49752) 2026-11-02 17:13:41 -08:00
test_bedrock_deepseek_reasoning_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_embedding_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_bedrock_gpt5_reasoning_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_bedrock_gpt_responses_native_wire.py fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493) 2026-11-02 14:13:17 -08:00
test_bedrock_invoke_cache_usage_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_invoke_dangerous_tool_use_beta_wire.py fix(bedrock): drop dangerous-tool-use beta without safeguards (#44471) 2026-10-16 21:00:37 +00:00
test_bedrock_kimi_k3_cache_point_wire.py fix(cache_control)!: keep one deployment's prompt-cache opt-in from reaching siblings on the same model (#49685) 2026-11-03 07:55:51 +00:00
test_bedrock_knowledge_base_user_context_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_mantle_claude_chat_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_bedrock_mantle_claude_chat_wire.py test(bedrock_mantle): expect the generic unsupported-param 400 for temperature on fixed-sampling Claude (#50344) 2026-11-05 21:53:06 -08:00
test_bedrock_mantle_codex_input_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_mantle_context_overflow_fallbacks_wire.py fix(router): recover streamed context window errors before output (#49293) 2026-10-30 13:19:58 -07:00
test_bedrock_mantle_context_overflow_wire.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_bedrock_mantle_count_tokens_wire.py fix(responses)!: answer 400 before counting a lone Responses built-in tool on Claude (#48798) 2026-10-28 12:12:45 -07:00
test_bedrock_mantle_gpt_prompt_cache_breakpoint_wire.py test(integration): run the bedrock mantle prompt cache and output limit wire tests on their own proxy (#47152) 2026-10-17 13:51:31 -07:00
test_bedrock_mantle_output_limit_wire.py fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493) 2026-11-02 14:13:17 -08:00
test_bedrock_mantle_responses_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_mantle_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_marengo_embed_3_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_model_discovery_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_bedrock_model_discovery_wire.py fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493) 2026-11-02 14:13:17 -08:00
test_bedrock_native_guardrail_trace_spend.py feat(bedrock): price native guardrailConfig trace usage into spend and x-litellm-response-cost (#48278) 2026-10-27 12:10:45 -07:00
test_bedrock_native_structured_output_wire.py feat(bedrock): default to native structured output on Opus 5.5, Fable 5.1, Sonnet 5 and Haiku 5.5 (#50221) 2026-11-06 09:38:00 -08:00
test_bedrock_nova_sonic_realtime_tool_calls.py fix(cost): price exact cost-map names before price-free capability rules, and fix SCIM and MCP integration tests on CircleCI (#47037) 2026-10-17 06:46:52 +00:00
test_bedrock_passthrough_aws_errors.py fix(bedrock-passthrough)!: return AWS-shaped errors so AWS SDKs read the code and message (#46522) 2026-10-15 22:05:46 -07:00
test_bedrock_passthrough_guardrail_config_wire.py fix(bedrock)!: apply the deployment guardrailConfig on /bedrock pass-through routes (#47429) 2026-10-20 14:48:19 -07:00
test_bedrock_passthrough_request_metadata_wire.py feat(bedrock): apply bedrock_request_metadata_fields on the /bedrock pass-through routes (#47040) 2026-10-17 14:01:50 +00:00
test_bedrock_passthrough_stream_wire.py test(integration): cover pass_through endpoint contracts (#44690) 2026-10-14 07:38:17 +00:00
test_bedrock_rerank_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_bedrock_role_configuration.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_bedrock_runtime_chat_completions_chaos.py fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493) 2026-11-02 14:13:17 -08:00
test_bedrock_runtime_chat_completions_sad_wire.py test(integration): fix seven CircleCI integration tests that race or assume a worker spread (#47001) 2026-10-16 22:45:29 +00:00
test_bedrock_runtime_chat_completions_wire.py fix(bedrock): drop stop sequences for GPT 5.6 and newer instead of forwarding them to a 400 (#45664) 2026-10-09 15:00:24 -07:00
test_bedrock_stream_timeout_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_bedrock_stream_timeout_wire.py fix(router)!: bound fake-streamed calls by the request timeout, not stream_timeout (#47162) 2026-10-17 22:08:02 +00:00
test_bedrock_thinking_tokens_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_cache_control_tool_call_marks_owned_proxy.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_cache_control_tool_call_marks_wire.py fix(caching): stop counting an unrun server tool call mark, and follow #49192 and #35602 in their integration tests (#49468) 2026-10-31 12:27:17 -07:00
test_chat_completions_tool_search_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_chat_completions_tool_search_history_wire.py fix(anthropic)!: translate the OpenAI tool_search tool on /v1/chat/completions for Claude models (#46389) 2026-10-15 04:47:05 +00:00
test_chat_completions_tool_search_wire.py fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
test_chat_provider_annotations_wire.py fix(anthropic)!: send /v1/messages PDF documents to OpenAI-shaped providers as file parts (#47166) 2026-10-29 08:06:12 -07:00
test_chat_template_tool_count_wire.py fix(count_tokens): count grok-4-1, grok-4.3 and DeepSeek V4.1 tool requests the way their hosts bill them (#49074) 2026-11-02 12:37:35 -08:00
test_chatgpt_responses_caller_stream_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_chatgpt_responses_caller_stream_wire.py test: update stale integration and guardrail e2e tests to intended behavior (#48665) 2026-10-28 01:11:25 +00:00
test_chatgpt_responses_top_level_error_wire.py fix(responses): keep the provider code and message on top-level stream error events (#46438) 2026-10-14 16:16:46 -07:00
test_claude_thinking_content_replay_wire.py test(anthropic, bedrock): audit #47489 (#48782) 2026-10-28 04:24:50 -07:00
test_cloudflare_clairic_extraction_wire.py test(extraction): audit #47473 (#48898) 2026-10-28 17:12:07 -07:00
test_cloudflare_clef_images_chaos.py feat(decisions)!: send images to Cloudflare Clef through its images field (#45734) 2026-10-14 12:14:48 +00:00
test_cloudflare_clef_images_wire.py feat(decisions)!: send images to Cloudflare Clef through its images field (#45734) 2026-10-14 12:14:48 +00:00
test_cloudflare_clef_omni_media_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_cloudflare_clef_omni_media_wire.py feat(decisions): support Clef-omni audio and video (#45811) 2026-10-12 20:29:49 +00:00
test_container_file_routes_wire.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
test_coralbricks_provider_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_coralbricks_provider_env_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_coralbricks_provider_wire.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_count_tokens_error_shapes_wire.py test(proxy): audit #46815 (#48768) 2026-10-28 03:55:25 -07:00
test_count_tokens_model_wire.py fix(count_tokens)!: audit #47441 and keep the framed estimate for Bedrock count models from the cost map (#48805) 2026-10-28 19:11:35 +00:00
test_cursor_responses_wire.py fix(proxy)!: log and bill Responses-style bodies sent to /cursor/chat/completions (#30277) 2026-10-30 00:18:15 -07:00
test_custom_prompt_template_chaos.py fix(prompt-templates): treat initial_prompt_value and final_prompt_value as optional (#39762) 2026-10-16 10:30:59 +00:00
test_custom_prompt_template_wire.py fix(prompt-templates): treat initial_prompt_value and final_prompt_value as optional (#39762) 2026-10-16 10:30:59 +00:00
test_custom_video_provider_wire.py feat(videos): serve custom_provider_map BaseVideoConfig providers on /v1/videos (#49785) 2026-11-02 21:28:46 -08:00
test_dashscope_chat_wire.py fix(proxy): keep provider refusal, logprobs and system_fingerprint in chat completions (#44788) 2026-10-13 13:17:40 -07:00
test_dashscope_image_edit_and_speech_wire.py feat(dashscope): add image edits and text-to-speech (#48998) 2026-10-29 17:48:38 -07:00
test_dashscope_video_chaos.py feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos (#43706) 2026-10-14 10:10:07 -07:00
test_dashscope_video_wire.py feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos (#43706) 2026-10-14 10:10:07 -07:00
test_databricks_agent_wire.py feat(agents): support Databricks Agent Platform agents in the agent gateway (#45681) 2026-10-15 12:42:06 -07:00
test_databricks_chat_wire.py fix(databricks): join plain text blocks for non-Claude json_object requests (#49385) 2026-11-02 11:17:40 -08:00
test_databricks_decisions_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_databricks_oauth_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_decision_model_guardrail.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_decisions_box_deployment_flag_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_decisions_box_deployment_flag_wire.py fix(decisions): read a deployment's own supports_box_questions flag before the cost map (#46696) 2026-10-15 12:34:36 -07:00
test_decisions_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_decisions_media_deployment_flag_wire.py fix(decisions)!: honor a deployment's own supports_audio_input and supports_video_input flags (#49207) 2026-10-31 01:09:46 -07:00
test_decisions_openai_format_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_decisions_wire.py feat(decisions): add EmpirioLabs AI as a decisions provider (#49977) 2026-11-04 10:41:16 -08:00
test_deepseek_vision_wire.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_device_code_login_guard_boot.py test(copilot): align login guards with direct access tokens (#50285) 2026-11-05 15:38:33 -08:00
test_device_code_login_guard_wire.py test(copilot): align login guards with direct access tokens (#50285) 2026-11-05 15:38:33 -08:00
test_embedding_cache_partial_hit_wire.py test(integration): cover embeddings endpoint contracts (#44660) 2026-10-14 03:38:12 +00:00
test_embedding_token_array_wire.py test(integration): cover embeddings endpoint contracts (#44660) 2026-10-14 03:38:12 +00:00
test_fake_openai_upstream_routes.py test: migrate local_testing SDK and provider tests out of build_and_test (#45760) 2026-10-10 23:14:25 +00:00
test_fal_ai_chat_wire.py fix(fal_ai): honour global api_base for image generation and reject non-string reasoning_effort with 400 (#42512) 2026-09-22 13:13:54 -07:00
test_fal_ai_image_wire.py test(integration): cover images endpoint contracts (#44653) 2026-10-14 03:40:29 +00:00
test_fal_ai_passthrough_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_fal_ai_video_wire.py fix(fal_ai): reuse the status client and headers on the video result probe (#42511) 2026-09-22 13:12:51 -07:00
test_files_batches_wire.py test(integration): cover files_batches endpoint contracts (#44703) 2026-10-14 06:57:41 +00:00
test_fireworks_ai_router_slug_wire.py feat(fireworks_ai): route and list the auto, auto-instant and firerouter routers (#43641) 2026-09-28 19:08:16 -07:00
test_fireworks_ai_session_affinity_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_friendliai_replay_wire.py fix(friendliai): drop litellm-internal message fields before sending (#45092) 2026-10-20 01:22:07 +00:00
test_gemini_agents_wire.py fix(gemini)!: accept Google's current Managed Agents fields on create and interactions (#48750) 2026-10-28 12:37:59 -07:00
test_gemini_anyof_null_branches_wire.py fix(vertex_ai)!: send integer enums to Gemini instead of dropping them (#44908) 2026-10-20 17:39:51 +00:00
test_gemini_chat_video_metadata_wire.py feat(gemini): accept file content blocks with video_metadata on multimodal embeddings (#45305) 2026-10-08 13:20:03 -07:00
test_gemini_context_caching_custom_api_base_wire.py fix(vertex_ai): build the cachedContents collection URL under a custom api_base (#44783) 2026-10-29 03:46:35 -07:00
test_gemini_default_output_budget_wire.py test(gemini): audit #47542 (#48758) 2026-10-28 02:42:45 -07:00
test_gemini_embedding_file_block_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_gemini_embedding_file_block_wire.py feat(gemini): accept file content blocks with video_metadata on multimodal embeddings (#45305) 2026-10-08 13:20:03 -07:00
test_gemini_grounding_annotations_wire.py test(gemini): cover every web source for a grounded passage (#48861) 2026-10-28 16:26:28 -07:00
test_gemini_image_config_and_usage_wire.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
test_gemini_interactions_wire.py feat(interactions): forward continuation_token and type requires_continuation so callers can resume a long decode (#50151) 2026-11-05 15:38:44 -08:00
test_gemini_long_decode_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_gemini_long_decode_wire.py test(gemini): assert vertex lists on content chunks (#49734) 2026-11-02 15:40:32 -08:00
test_gemini_omitted_temperature.py test(translation): share rich fixtures across Claude, GPT and Gemini providers (#46585) 2026-10-14 19:53:09 -07:00
test_gemini_thinking_replay_chaos.py test(integration): look up streamed Responses spend rows by the client-facing id (#49752) 2026-11-02 17:13:41 -08:00
test_gemini_thinking_replay_wire.py fix(gemini): resend once with the placeholder signature when the other backend rejects a replayed thought signature (#49697) 2026-11-03 01:24:55 +00:00
test_gemini_tool_result_part_reference_chaos.py test(integration): look up streamed Responses spend rows by the client-facing id (#49752) 2026-11-02 17:13:41 -08:00
test_gemini_tool_result_part_reference_wire.py test: update stale integration and guardrail e2e tests to intended behavior (#48665) 2026-10-28 01:11:25 +00:00
test_gemini_tts_voice_mapping_owned_proxy.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_gemini_tts_voice_mapping_wire.py test: fix integration tests that fail on test order, races and intended changes (#49310) 2026-10-30 13:25:47 -07:00
test_google_genai_adapter_wire.py fix(vertex_ai): route Model Garden models through the generateContent adapter (#41836) 2026-10-15 08:06:49 -07:00
test_google_genai_native_wire.py test(integration): cover google_genai endpoint contracts (#44680) 2026-10-14 04:01:35 +00:00
test_google_genai_proxy_sdk_wire.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_google_genai_vertex_routes_wire.py fix(vertex): match standalone 403 status tokens instead of any substring (#47134) 2026-10-17 19:17:18 +00:00
test_hosted_vllm_reasoning_content_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_hosted_vllm_reasoning_content_wire.py test: cover response contracts across translation endpoints (#46632) 2026-10-15 00:05:09 -07:00
test_hosted_vllm_stream_stall_wire.py test(router): expect a primary stream's stall to cool its deployment (#50261) 2026-11-06 00:06:59 +00:00
test_huggingface_rerank_truncate_wire.py fix(huggingface): stop forcing truncate=false on TEI rerank and pass truncate params through (#48706) 2026-10-28 09:27:26 -07:00
test_huggingface_tokenizer_downloads_wire.py test(token_counter): audit #47586 (#48800) 2026-10-28 04:30:19 -07:00
test_idle_upstream_guardrail_cut_wire.py feat(guardrails): add num_retries to generic_guardrail_api for checks lost after connect (#46965) 2026-10-17 12:22:41 -07:00
test_idle_upstream_keepalive_edges_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_idle_upstream_keepalive_override_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_idle_upstream_reconnect_chaos_wire.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_idle_upstream_reconnect_routes_wire.py fix(http): restore the 15s aiohttp keep-alive default in the Python and Rust clients (#46355) 2026-10-14 10:50:11 -07:00
test_idle_upstream_reconnect_wire.py fix(http): restore the 15s aiohttp keep-alive default in the Python and Rust clients (#46355) 2026-10-14 10:50:11 -07:00
test_image_gen_drop_params_wire.py fix(images): honor max_retries and prevent Router retry amplification (#48705) 2026-10-28 10:46:47 -07:00
test_inferenceapis_context_window_fallbacks_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_inferenceapis_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_interactions_openai_bridge_wire.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
test_internal_params_wire.py fix(params): validate stream_chunk_size once, before any provider call (#43222) 2026-09-26 23:01:20 +00:00
test_lm_studio_chat_wire.py test: migrate local_testing SDK and provider tests out of build_and_test (#45760) 2026-10-10 23:14:25 +00:00
test_malformed_tools_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_malformed_tools_wire.py fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
test_moderations.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_moderations_wire.py test(integration): cover small_inference endpoint contracts (#44654) 2026-10-14 04:06:15 +00:00
test_nvidia_nim_ranking_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_nvidia_riva_wire.py fix(nvidia_riva): send the api key exactly once by calling riva over grpc directly (#50140) 2026-11-04 18:07:31 -08:00
test_ocr_multipart_wire.py test(integration): cover small_inference endpoint contracts (#44654) 2026-10-14 04:06:15 +00:00
test_ocr_router_wire.py test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
test_ollama_embedding_wire.py fix(ollama): forward embedding credentials, headers and timeout (#48707) 2026-10-28 09:32:47 -07:00
test_ollama_prompt_tools_chaos.py fix(prompt_templates): do not mutate messages in-place in function_call_prompt (#41676) 2026-10-15 14:37:11 -07:00
test_ollama_prompt_tools_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_openai_chat_prompt_cache_breakpoint_wire.py fix(providers): trim prompt_cache_breakpoint to what each API takes under drop_params (#49064) 2026-11-02 10:00:00 -08:00
test_openai_chat_wire.py fix(logging): keep the caller's call_type when chat completions are bridged to the Responses API (#49710) 2026-11-03 10:02:54 +00:00
test_openai_completion_wire.py test(integration): cover chat_completions endpoint contracts (#44688) 2026-10-14 03:45:38 +00:00
test_openai_count_tokens_tools_wire.py fix(responses)!: answer 400 before counting a lone Responses built-in tool on Claude (#48798) 2026-10-28 12:12:45 -07:00
test_openai_dialect_prompt_cache_breakpoint_owned_proxy.py fix(azure_ai)!: keep OpenAI prompt cache breakpoints on the Foundry chat completions path (#45299) 2026-10-29 23:49:55 -07:00
test_openai_embedding_timeout_wire.py test: migrate local_testing SDK and provider tests out of build_and_test (#45760) 2026-10-10 23:14:25 +00:00
test_openai_embedding_wire.py test(integration): cover embeddings endpoint contracts (#44660) 2026-10-14 03:38:12 +00:00
test_openai_error_handling.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_openai_fine_tuning.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_openai_image_edit_wire.py test(integration): cover images endpoint contracts (#44653) 2026-10-14 03:40:29 +00:00
test_openai_image_variation_wire.py test(integration): cover images endpoint contracts (#44653) 2026-10-14 03:40:29 +00:00
test_openai_like_response_headers_wire.py fix(prometheus): set the remaining rate-limit gauges from decimal headers again (#47039) 2026-10-17 05:20:00 +00:00
test_openai_passthrough_files_wire.py test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
test_openai_passthrough_multipart_wire.py test(integration): cover pass_through endpoint contracts (#44690) 2026-10-14 07:38:17 +00:00
test_openai_realtime_transcription_url.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_openai_responses_prompt_cache_breakpoint_wire.py fix(openai): carry cache_control to prompt_cache_breakpoint on /v1/responses to gpt-5.6 (#46105) 2026-10-13 15:23:07 -07:00
test_openai_responses_tool_search_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_openai_responses_websocket_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_openai_stream_text_usage_wire.py refactor(types): replace Any with proven types in 7 files (#43704) 2026-09-29 06:12:58 -07:00
test_pdf_input_support_wire.py fix(anthropic)!: send /v1/messages PDF documents to OpenAI-shaped providers as file parts (#47166) 2026-10-29 08:06:12 -07:00
test_provider_lookup_status.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_rag_ingest_wire.py test(integration): cover vector_stores endpoint contracts (#44739) 2026-10-14 03:59:08 +00:00
test_realtime_transcription_guardrail_session_update.py fix(realtime)!: send the Gemini Live setup at the first content so session.update settings apply (#39864) 2026-10-30 01:31:39 -07:00
test_realtime_unguarded_voice_turns.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_realtime_webrtc_http.py test(integration): cover realtime endpoint contracts (#44689) 2026-10-14 03:49:34 +00:00
test_request_boundary.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_rerank_latency_headers_wire.py test(integration): cover small_inference endpoint contracts (#44654) 2026-10-14 04:06:15 +00:00
test_responses_bridge_history_replay_wire.py fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912) 2026-10-29 00:56:02 -07:00
test_responses_bridge_incomplete.py fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912) 2026-10-29 00:56:02 -07:00
test_responses_bridge_input_audio_wire.py fix(responses): map input_audio blocks in the chat-to-Responses bridge (#45224) 2026-10-07 22:25:35 -07:00
test_responses_bridge_item_marks_guardrail_wire.py fix(responses): propagate cache_control through responses->chat completion bridge (#32511) 2026-10-14 15:44:34 -07:00
test_responses_bridge_message_cache_control_wire.py test(providers): expect 503 server_is_overloaded for an upstream overload on the responses bridge (#50166) 2026-11-05 04:40:22 +00:00
test_responses_bridge_message_cache_control_wire_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_responses_bridge_namespace_tools.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_responses_bridge_prompt_cache_breakpoint.py fix(responses): keep prompt_cache_breakpoint markers in the chat to responses bridge (#44119) 2026-10-07 16:25:36 -07:00
test_responses_bridge_prompt_cache_breakpoint_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_responses_bridge_prompt_cache_breakpoint_wire.py fix(providers): trim prompt_cache_breakpoint to what each API takes under drop_params (#49064) 2026-11-02 10:00:00 -08:00
test_responses_bridge_prompt_cache_breakpoint_wire_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_responses_bridge_stream_output_items_wire.py fix(ollama): one stream id, 400 on non-text tool content, separated tool results, no empty message item (#45177) 2026-10-07 19:08:26 -07:00
test_responses_bridge_tool_search_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_responses_bridge_tool_search_replay.py fix(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444) 2026-10-14 21:40:14 -07:00
test_responses_bridge_tool_search_replay_wire.py fix(responses): translate OpenAI tool_search to Anthropic tool search for Claude models (#45882) 2026-10-14 20:42:22 -07:00
test_responses_bridge_tool_search_undeferred_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_responses_bridge_tool_search_wire.py fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
test_responses_bridge_verbosity_wire.py fix(responses): preserve text verbosity when bridging to chat completions (#49049) 2026-10-30 21:41:20 -07:00
test_responses_client_header_forwarding_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_responses_codex_repeated_additional_tools_wire.py fix(responses): only merge repeated Codex tools when drop_params is on (#49112) 2026-10-29 12:55:29 -07:00
test_responses_compact_wire.py fix(responses): drop the null created_by OpenAI rejects when output items are replayed (#48783) 2026-10-28 21:11:49 -07:00
test_responses_compaction_items_wire.py fix(responses)!: round-trip Anthropic compaction blocks as compaction items (#46754) 2026-10-21 08:50:19 +00:00
test_responses_core_wire.py fix(responses)!: authorize and decode comparison response IDs (#49402) 2026-11-03 03:40:46 +00:00
test_responses_error_status_wire.py test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
test_responses_lifecycle_wire.py test(responses): isolate cancel wire checks from background polling (#50002) 2026-11-04 05:12:01 +00:00
test_responses_minted_reasoning_replay_chaos.py test(copilot): route direct-token fixtures through authenticated peers (#50307) 2026-11-05 17:42:46 -08:00
test_responses_minted_reasoning_replay_wire.py fix(bedrock): drop another model's signed thinking when replaying to a non-Claude Converse target (#50073) 2026-11-06 03:15:49 -08:00
test_responses_reasoning_item_wire.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
test_responses_websocket_session_limit.py test(integration): wait for every worker to report the websocket session cap instead of sleeping (#47412) 2026-10-19 15:35:29 -07:00
test_rust_anthropic_safeguards_beta_chaos.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_rust_anthropic_safeguards_beta_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_s3_wire.py test: fix stale and flaky tests across CircleCI, GHA and Buildkite (#45530) 2026-10-09 11:40:14 -07:00
test_sagemaker_chat_credential_sources.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_sagemaker_chat_wire.py fix(router)!: keep a deployment's own model_id over the request body's (#49045) 2026-10-30 02:40:01 -07:00
test_sagemaker_embedding_chaos.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_sagemaker_embedding_wire.py fix(router)!: keep a deployment's own model_id over the request body's (#49045) 2026-10-30 02:40:01 -07:00
test_search_wire.py fix(tavily): return raw_content, score, favicon and the response envelope from Tavily search (#48684) 2026-10-27 18:52:06 -07:00
test_strands_decider_agentcore_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_tencent_chat_wire.py fix(proxy): keep provider refusal, logprobs and system_fingerprint in chat completions (#44788) 2026-10-13 13:17:40 -07:00
test_tool_config_cache_point_wire.py fix(anthropic): apply tool_config cache-control points on chat and /v1/messages (#47394) 2026-10-19 23:26:41 +00:00
test_validated_reply_boundaries_under_faults.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_vector_store_create_wire.py test(integration): remove BUG skips for 3 tests that pass on main (#47364) 2026-10-19 21:39:35 -07:00
test_vector_store_search_wire.py test(integration): cover vector_stores endpoint contracts (#44739) 2026-10-14 03:59:08 +00:00
test_vector_store_team_model_provider_wire.py fix(proxy): route team key vector store calls to a team model of the store's provider (#46894) 2026-10-17 14:32:03 -05:00
test_vertex_anthropic_inline_tools_beta_wire.py fix(anthropic)!: sync the beta header allowlist with what anthropic, vertex_ai, and azure_ai accept (#49409) 2026-11-02 05:57:51 -08:00
test_vertex_anthropic_structured_output_wire.py fix(bedrock)!: keep Claude's thinking when response_format json_schema is set (#49696) 2026-11-05 04:07:11 +00:00
test_vertex_batch_output_info_wire.py fix(vertex_ai): keep batch output_file_id null until Vertex reports outputInfo (#43030) 2026-09-24 14:05:31 -07:00
test_vertex_batch_row_line_errors_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_vertex_batch_row_line_errors_owned_proxy.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_vertex_batch_row_line_errors_wire.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_vertex_credentials_source_wire.py test: update integration tests left stale by recent product changes (#49143) 2026-10-29 18:06:28 -07:00
test_vertex_embedding_batch_file_block_wire.py feat(gemini): accept file content blocks with video_metadata on multimodal embeddings (#45305) 2026-10-08 13:20:03 -07:00
test_vertex_embedding_file_block_wire.py feat(gemini): accept file content blocks with video_metadata on multimodal embeddings (#45305) 2026-10-08 13:20:03 -07:00
test_vertex_embedding_wire.py test(integration): cover embeddings endpoint contracts (#44660) 2026-10-14 03:38:12 +00:00
test_vertex_gemini_count_tokens_wire.py fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
test_vertex_gemini_fragmented_stream_wire.py test: update stale integration and guardrail e2e tests to intended behavior (#48665) 2026-10-28 01:11:25 +00:00
test_vertex_gemini_function_call_wire.py test: update stale integration and guardrail e2e tests to intended behavior (#48665) 2026-10-28 01:11:25 +00:00
test_vertex_partner_count_tokens_wire.py fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
test_vertex_partner_labels_wire.py fix(vertex_ai): send Vertex Claude labels as X-Vertex-AI-Labels header instead of the request body (#48753) 2026-10-28 15:41:50 +00:00
test_vertex_partner_messages_wire.py test(integration): cover anthropic_messages endpoint contracts (#44704) 2026-10-14 06:57:54 +00:00
test_vertex_passthrough_stream_wire.py fix(anthropic): answer an upstream Anthropic 529 as 529 overloaded_error on /v1/messages (#46063) 2026-11-03 17:37:09 -08:00
test_vertex_passthrough_wire.py feat(vertex_ai): let operators drop chosen anthropic-beta values on the Vertex AI pass-through routes (#47185) 2026-10-18 12:51:27 +00:00
test_vertex_realtime_multi_region_host.py fix(vertex_ai): dial the multi-region Live API host for realtime sessions (#45166) 2026-10-07 17:39:38 -07:00
test_vertex_timestamps_utc_wire.py fix(vertex_ai): parse Vertex timestamps as UTC so created_at is not shifted by the host timezone (#45550) 2026-10-10 15:18:15 -07:00
test_voyage_mongodb_host_wire.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_watsonx_passthrough_router_credentials_wire.py fix(watsonx): read pass-through credentials from use_in_pass_through deployments (#49462) 2026-10-31 11:53:25 -07:00
test_xai_batch_output_file_wire.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_xai_server_tool_usage_wire.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +00:00
test_xai_web_search_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_xiaomi_mimo_wire.py fix(proxy): keep provider refusal, logprobs and system_fingerprint in chat completions (#44788) 2026-10-13 13:17:40 -07:00