scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-14 04:09:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 139
litellm/tests/integration/providers
History
Mateo Wang 9d3bf29d6d
fix(responses): keep cache breakpoints on blocks the bridge stringifies (#40032) 
* fix(responses): keep cache breakpoints on requests that reach the Responses API

The chat-completions bridge rebuilt every content block without the
prompt_cache_breakpoint marker the cache-control hook had just placed on it, so
the request went out with prompt_cache_options set to explicit mode and nothing
actually marked. Explicit mode caches only what is marked, so those deployments
lost the implicit caching they were getting before the injection point was added

The native surface had a second miss. The bridging check looked the provider
config up with the still-prefixed model while the config keys on the bare one,
so every bedrock_mantle model read as having no native Responses support, and
role-targeted injection points were deferred to a chat-completions pass that
never runs for them

* fix(responses): keep prompt cache breakpoint on stringified content blocks

* test: cover the responses/ routing prefix in the native cache point case

* fix(responses): keep only the fallback-branch marker carry, main already routes the hook

#42281 landed the text, image_url and file branch carry and the implicit default
on main, and the Responses routing lookup this branch changed has no observable
effect there, so the PR shrinks to the unknown-block fallback branch and its
regression test

* fix(responses): drop a malformed prompt_cache_breakpoint under drop_params in the chat-to-Responses bridge

* fix(responses): accept the 30m prompt_cache_breakpoint ttl under drop_params

OpenAI's Responses API takes a ttl of 30m on an explicit breakpoint marker, so the drop_params validation keeps it instead of stripping it as an unknown key. Trims the bridge test docstrings to the dated vendor citation.

* test(integration): audit cells for prompt_cache_breakpoint through the chat-to-Responses bridge

Adds the /audit cells for the bridge's prompt_cache_breakpoint carry: valid and malformed markers on every
carrying block kind and on tool and assistant content, the drop_params on and off contract, the hook-injected
system marker, the Anthropic SDK path through the Responses adapter, upstream errors, idempotent spend rows,
and the chaos cells (mixed burst, upstream outage, slow streams, worker SIGKILL and a proxy restart mid burst),
all against a scripted Responses endpoint with the request it received read back by response id

* test(integration): give every scripted responses reply its own id

The prompt-cache-breakpoint audit's scripted upstream minted the response id
from the request's marker, so three identical marked requests shared one id.
The spend-log writer skips rows whose request_id already landed, and the
idempotent-logging cell saw one row for three calls on every leg. The upstream
now mints a unique id per reply like a real provider, and the cells match a
response to its request by the marker inside that id.
2026-10-07 18:28:39 -07:00
..
_cache_control_marks_support.py fix(caching): count tool_call cache_control marks in the injection census (#43556) 2026-10-03 17:33:48 -07:00
_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
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 fix(anthropic): stop repeating streamed thinking text in the signature chunk (#44127) 2026-10-02 19:38:41 -07:00
test_anthropic_thinking_signature_stream_wire.py fix(anthropic): stop repeating streamed thinking text in the signature chunk (#44127) 2026-10-02 19:38:41 -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_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_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(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
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 test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
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 feat(bedrock): drop lookaround regex patterns from tool schemas for Converse models that reject them (#44138) 2026-10-02 19:47:25 -07:00
test_bedrock_converse_lookaround_regex_wire.py feat(bedrock): drop lookaround regex patterns from tool schemas for Converse models that reject them (#44138) 2026-10-02 19:47:25 -07:00
test_bedrock_converse_missing_content_wire.py fix(bedrock): accept Converse messages with no content key (#43936) 2026-10-01 15:14:34 -07:00
test_bedrock_converse_stream_event_frames_wire.py fix(bedrock): surface unrecognized converse-stream event frames instead of an empty turn (#44112) 2026-10-02 16:06:26 -07:00
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 feat(bedrock): serve gpt-5.6+ chat completions natively by default, with chat_completions/ opt-in for gpt-oss and grok (#44307) 2026-10-02 19:55:54 -07:00
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_kimi_k3_cache_point_wire.py fix(bedrock): stop emitting Converse cachePoint blocks for Kimi K3 (#44292) 2026-10-03 18:11:46 +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(bedrock_mantle): route Claude chat completions to the native Messages endpoint (#43646) 2026-10-03 15:24:41 -07:00
test_bedrock_mantle_claude_chat_wire.py test(integration): assert the Messages API health probe on Mantle Claude (#44612) 2026-10-05 15:28:02 -07:00
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_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_passthrough_stream_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
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 test(ci): fix six CircleCI test regressions on main (#44429) 2026-10-03 20:55:01 -07:00
test_bedrock_runtime_chat_completions_sad_wire.py feat(bedrock): serve gpt-5.6+ chat completions natively by default, with chat_completions/ opt-in for gpt-oss and grok (#44307) 2026-10-02 19:55:54 -07:00
test_bedrock_runtime_chat_completions_wire.py feat(bedrock): serve gpt-5.6+ chat completions natively by default, with chat_completions/ opt-in for gpt-oss and grok (#44307) 2026-10-02 19:55:54 -07:00
test_bedrock_stream_timeout_chaos.py fix(bedrock): honor the per-request timeout on Converse and Invoke streaming (internal copy of #38210) (#44134) 2026-10-03 19:29:15 +00:00
test_bedrock_stream_timeout_wire.py fix(responses): stop SDK retries nesting under router retries, and unbreak CircleCI integration tests (#44791) 2026-10-06 15:57:33 +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 fix(caching): count tool_call cache_control marks in the injection census (#43556) 2026-10-03 17:33:48 -07:00
test_cache_control_tool_call_marks_wire.py fix(caching): count tool_call cache_control marks in the injection census (#43556) 2026-10-03 17:33:48 -07:00
test_chatgpt_responses_caller_stream_chaos.py fix(responses): honor caller stream flag when provider forces SSE (internal copy of #34095) (#41235) 2026-10-06 03:30:47 +00:00
test_chatgpt_responses_caller_stream_wire.py fix(responses): honor caller stream flag when provider forces SSE (internal copy of #34095) (#41235) 2026-10-06 03:30:47 +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_dashscope_chat_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_databricks_chat_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -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_decisions_chaos.py feat(decisions): add unified /v1/decisions endpoint for Jev-compatible providers (#44236) 2026-10-03 17:38:38 +00:00
test_decisions_wire.py feat(decisions): add unified /v1/decisions endpoint for Jev-compatible providers (#44236) 2026-10-03 17:38:38 +00:00
test_deepseek_vision_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_device_code_login_guard_boot.py fix(chatgpt,github_copilot): refuse device-code login inside an event loop or worker thread (#39585) 2026-10-06 03:20:07 +00:00
test_device_code_login_guard_wire.py fix(chatgpt,github_copilot): refuse device-code login inside an event loop or worker thread (#39585) 2026-10-06 03:20:07 +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 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_passthrough_wire.py fix(fal_ai): align /fal_ai queue gate with the pricer and normalise resolution type (#42505) 2026-09-22 13:12:07 -07:00
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_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_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_thinking_replay_chaos.py fix(gemini): stop replaying thinking block signatures to Gemini (#44661) 2026-10-06 02:31:53 +00:00
test_gemini_thinking_replay_wire.py fix(responses): stop SDK retries nesting under router retries, and unbreak CircleCI integration tests (#44791) 2026-10-06 15:57:33 +00:00
test_hosted_vllm_reasoning_content_chaos.py fix(hosted_vllm): keep reasoning_content on replayed assistant messages (#43599) 2026-09-30 13:12:28 -07:00
test_hosted_vllm_reasoning_content_wire.py test(ci): repair stale tests and flaky CI infrastructure (#43983) 2026-10-01 17:46:43 +00:00
test_image_gen_drop_params_wire.py refactor(types): replace Any with proven types in 7 files (#43704) 2026-09-29 06:12:58 -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_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_ollama_prompt_tools_chaos.py test(e2e): cover ollama and ollama_chat on chat completions, responses and messages (#45079) 2026-10-07 20:17:35 +00:00
test_ollama_prompt_tools_wire.py test(e2e): cover ollama and ollama_chat on chat completions, responses and messages (#45079) 2026-10-07 20:17:35 +00:00
test_openai_chat_wire.py fix(responses): honor request cache controls on chat completions bridged to the Responses API (#44676) 2026-10-05 17:52:44 -07:00
test_openai_image_edit_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_openai_realtime_transcription_url.py fix(openai/realtime): drop model from upstream URL for intent=transcription (#43854) 2026-10-05 19:14:56 +00:00
test_openai_responses_websocket_wire.py test(integration): move legacy proxy, router and Redis tests into tests/integration (#44128) 2026-10-01 23:00:54 -07:00
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_provider_lookup_status.py fix(proxy): return 4xx instead of 500 for missing required params, invalid pagination and unknown ids (#43787) 2026-10-02 22:48:53 -07:00
test_realtime_transcription_guardrail_session_update.py fix(realtime): run transcript guardrails on raw-path transcription sessions with a transcription-safe block (#44844) 2026-10-07 11:59:34 -07:00
test_request_boundary.py fix(tests): resolve the integration support package without run.py's PYTHONPATH 2026-09-15 21:10:08 -07:00
test_rerank_latency_headers_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_bridge_incomplete.py fix(responses): merge bridged tool calls into the same choice as the text (#44346) 2026-10-03 07:00:52 +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 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_wire.py fix(responses): keep cache breakpoints on blocks the bridge stringifies (#40032) 2026-10-07 18:28:39 -07:00
test_responses_bridge_prompt_cache_breakpoint_wire_chaos.py fix(responses): keep cache breakpoints on blocks the bridge stringifies (#40032) 2026-10-07 18:28:39 -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_minted_reasoning_replay_chaos.py fix(responses): drop bridge-minted reasoning items from OpenAI replays (#44132) 2026-10-02 19:39:48 -07:00
test_responses_minted_reasoning_replay_wire.py fix(responses): drop bridge-minted reasoning items from OpenAI replays (#44132) 2026-10-02 19:39:48 -07:00
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_s3_wire.py test: cover provider wire contracts, streaming and recovery 2026-09-16 12:48:30 -07:00
test_sagemaker_chat_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_tencent_chat_wire.py test(integration): regression tests for August provider translation and streaming bugs (#42621) 2026-09-22 20:52:00 -07:00
test_validated_reply_boundaries_under_faults.py refactor(types): replace Any with proven types in 157 files (#44798) 2026-10-06 15:31:54 +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_gemini_fragmented_stream_wire.py test(integration): regression tests for July provider translation, routing and streaming bugs (#42693) 2026-09-23 09:51:06 -07:00
test_vertex_gemini_function_call_wire.py refactor(types): replace Any with proven types in 7 files (#43704) 2026-09-29 06:12:58 -07:00
test_vertex_partner_count_tokens_wire.py fix(vertex_ai): forward system and tools to partner model count_tokens (#43900) 2026-10-03 16:36:14 -07:00
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_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 test(integration): move Xiaomi MiMo coverage from live e2e to the providers wire shard (#42395) 2026-09-21 19:51:26 -07:00