scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-13 08:52:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 174
litellm/tests/integration/providers
History
Exact
HootRock 8f19607259
fix(proxy)!: preserve Responses SSE event framing (#47980) 
* fix(proxy): preserve Responses SSE event framing

* style(proxy): format Responses stream terminator condition

* fix(proxy): validate Responses guardrail event names

* fix(proxy): keep Responses first-event errors and keepalive failures in Responses framing

* test(proxy): use controlled clocks for Responses keepalive failures

* fix(proxy): end late Responses failures with an error event the SDK raises on

Errors that arrive after keepalive pings, and guardrail error strings yielded
mid-stream, now end /v1/responses with a named `error` event carrying the
same error object chat sends, so the OpenAI SDK still raises APIError with a
clean message and provider_specific_fields. Background polling passes the
same framing and records an `error` event as a failed response. The first
data line of a frame is found by splitting on newlines only, so a U+2028 in
an error message no longer hides a first-event error.

* fix(proxy): match OpenAI's Responses error event and stream late passthrough blocks as block responses

* fix(proxy): keep the reason when a background Responses request fails

A background poll of a request a post-call guardrail blocked saved a
null code and message, because the guardrail's error event nests them.
A request whose first chunk was an error polled as completed with no
error. Both now poll failed with the same code and message a late
failure gets.

* test(proxy): type the first-chunk poll test parameters

* fix(proxy): keep first-chunk error detection to lone error frames and handle string poll errors

* fix(proxy): keep the HTTP status on late Responses errors and end Responses streams on error events

A late error body without a code now takes the response's status, an upstream error event counts as the stream's terminal event, and a Responses stream that fails before its first chunk ends with an error event instead of data: [DONE].

* test(proxy): type the first-chunk failure test's parameters

* fix(proxy): keep cursor chat framing and JSON-encode Responses hook errors

* fix(proxy): encode non-dict Mapping Responses chunks as JSON objects

* fix(proxy): encode mappings and models nested in Responses stream chunks as JSON objects

* test(proxy): freeze the hook-output fixture

* fix(proxy): keep masked mappings and odd keys safe in Responses stream frames

Only read-only dict views and pydantic models nested in a hook chunk or error event expand into JSON objects. Other mappings, such as httpx.Headers, keep their own string form so masked values stay masked. Keys JSON cannot take become strings, and a chunk JSON still cannot encode goes out as the plain data frame it was before.

* fix(proxy): never fail a Responses stream frame on a value JSON cannot encode

Only dicts and read-only dict views expand into JSON, at the top level too, so a header mapping yielded as a whole chunk keeps its masked string form. Any failure while encoding a chunk falls back to the plain data frame the base sent, and an error event that cannot encode still goes out with its code and message, so a late block never drops the connection.

* fix(proxy): keep what a nested value's repr hides out of Responses stream frames

* fix(proxy): print values in Responses stream frames the way each base path did

* fix(proxy): send string and number subclasses whose repr shows their value as that value in Responses stream frames

* fix(proxy): print container subclasses and SDK models in Responses stream frames the way base did

* fix(proxy): read hook container storage the way repr does and send error-event models as str()

* fix(proxy): frame streamed Responses reads and send unreadable hook values as base did

Track pre-framed and raw SSE frames so a late failure never follows a terminal event, accept CRLF and CR line breaks in a first named error, frame GET /v1/responses/{id}?stream=true as Responses events, print a whole hook proxy chunk once and fall back to its text, ignore a non-integer status_code in a hook error frame, read a late-block dict subclass through items() when that view differs from its storage, and keep the order and inline form base's repr printed for nested mappings

* fix(proxy): match base on Responses stream edge cases

Read a decimal-string or integral-float status_code as its integer again, so
"429" and 429.0 still map to rate_limit_exceeded. Print each hook value's repr
once and reuse it, so a repr that changes between calls cannot reach the
client. Track only pre-framed sequence numbers from 0 to 2**63-1, so a huge
one cannot break the failure event. Build nested JSON with one frame per level
again, which restores the nesting depth sent as JSON. Count a pre-framed frame
as terminal from its data type, and a named error frame only when its data
carries an error, the way the OpenAI SDKs read them.

* fix(proxy): print hook proxies once and keep base's chunk tracking

Read-only mappings in hook chunks now emit the text from their first print, hook
chunks are read without their error field, only a non-empty error object makes a
framed error event terminal, and framed sequence numbers stay below 2**63-1 while
hook chunks keep base's unbounded tracking

* fix(proxy): print each read-only mapping item once and poll framed error events as failed

A MappingProxyType in a hook chunk or error detail now expands from the
mapping it wraps, so each item is printed once, the way base printed it.
A value whose repr changes between calls stays masked, a value whose repr
works once is kept, and deep nesting keeps one stack frame per level

The background reader takes each frame's type from the same terminal rule
the stream uses, so an event: error frame with an error object polls
failed even when its data names another type or none

* fix(proxy): print self-holding hook values once and poll how the stream ended

A container that holds itself now goes out as the marker its repr prints, like {...}, [...] or mappingproxy({...}), and the dict behind a read-only mapping joins the cycle check, so no item is printed a second time. A dict whose item repr adds a key keeps going after the items already shown, the way dict's repr does, instead of printing the whole dict again

A whole read-only mapping chunk that cannot go out as JSON is printed once by the formatter, so a print that fails fails the stream as it did on the base

The background poll reads the event type from the block it parses, as on the base, and keeps the first error frame the stream treats as terminal anywhere in a chunk. That frame fails the poll only when no response.completed, response.failed or response.incomplete follows it

* fix(proxy): name hook chunk events from the sent JSON and keep polls on frames they cannot read

A mapping chunk now takes its event: line from the JSON it sends, so a masked type value never reaches that line, and a chunk the event model cannot read goes out as a plain data frame instead of failing the stream

A dict whose item repr deletes or swaps keys keeps printing every key not yet shown, and an error code past the integer digit limit reads as no status

The background poll skips a frame whose shape it cannot read, as base skipped frames it could not parse, stops reading a chunk at [DONE], and lets only the last terminal frame in a chunk decide its status

A Responses stream's first chunk answers as a JSON error only for codes 400 and up

* fix(proxy): read every frame of a polled chunk and name model chunks from the sent JSON

A background poll parsed only the first data frame of each chunk, so a terminal event behind an error or delta frame in the same chunk was lost, and the poll stored a status its own stream never ended with. It now reads every frame up to [DONE]

A terminal event whose response is a string or null kept no status and polled completed. Its status now comes from the event type, and final output items that are not objects are skipped, so the rest of the final output is still stored

Model chunks now take their event line from the JSON they send, as mapping chunks already do, so a serializer that drops type no longer sends event: response.completed over {}

* fix(proxy): read polled chunks as SSE events and keep draining past a mid-chunk [DONE]

A background poll split a chunk into data lines, so one event with two data lines parsed as two payloads, and a frame with an integer past the digit limit raised a ValueError the parse guard did not catch, which failed the poll and dropped its spend row. The poll now joins each event's data lines the way an SSE reader does and skips any frame it cannot parse

A [DONE] behind another frame in one chunk ended the poll and left the stream unbilled. Only a chunk that opens with [DONE] ends the poll now, as on main, and the poll stops reading a chunk at its first terminal event, so two terminal events in one chunk poll the first one as main did

* fix(proxy): JSON-encode only plain hook chunks on Responses streams

A hook chunk whose whole tree is builtin JSON types streams as its named
event. Any other chunk keeps the base data frame, so nothing a custom
repr hides reaches the wire. Error event details encode the way the chat
error frame does.

* fix(proxy): skip containers already visited when checking hook chunks for JSON

* fix(responses): keep streaming past an event with no type

The Responses stream iterator read event.type directly when it noted a
yielded event, so an event whose JSON had no type, like a custom hook's
dict that the proxy now sends as JSON, raised AttributeError and ended
the stream. Read it with getattr, as the iterator's other checks do.

* fix(proxy): keep hook dicts with no type on the base Responses frame

A hook dict with no type is not a Responses event, so it gets no event
name either way. Sending it as JSON only made litellm SDKs that read
type on every event stop the stream. Keep such dicts on the frame the
base sends, so every SDK version reads them as before.

* fix(responses): keep a background poll's first terminal status and take a first-chunk error code from its HTTP status

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-11-06 20:17:57 -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 test(bedrock): expect native output on Opus 4.8 profiles after #50222 (#50343) 2026-11-06 11:04:32 -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(bedrock): forward Codex agent messages that carry encrypted content intact (#50457) 2026-11-06 17:47:43 -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 fix(proxy)!: preserve Responses SSE event framing (#47980) 2026-11-06 20:17:57 -08:00
test_bedrock_mantle_claude_chat_wire.py fix(proxy)!: preserve Responses SSE event framing (#47980) 2026-11-06 20:17:57 -08:00
test_bedrock_mantle_codex_input_wire.py fix(bedrock): forward Codex agent messages that carry encrypted content intact (#50457) 2026-11-06 17:47:43 -08:00
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 fix(bedrock): forward Codex agent messages that carry encrypted content intact (#50457) 2026-11-06 17:47:43 -08:00
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 test(bedrock): expect native output on Opus 4.8 profiles after #50222 (#50343) 2026-11-06 11:04:32 -08:00
test_bedrock_nova_sonic_realtime_guardrails.py fix(bedrock): run realtime guardrails on Nova Sonic sessions (#49833) 2026-11-06 13:18:48 -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(bedrock): run realtime guardrails on Nova Sonic sessions (#49833) 2026-11-06 13:18:48 -08:00
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 test(bedrock): expect native output on Opus 4.8 profiles after #50222 (#50343) 2026-11-06 11:04:32 -08:00
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