litellm/tests/unit
m.torres 150f4b706b
fix(router): count embedding batches per input in pre-call checks (#49851)
* fix(router): count embedding batches per input in pre-call checks

Embedding input lists went through the Responses input transform, which
calls .get() on each item, so every list-input /embeddings call logged
"failed to count tokens" and skipped the context window check. Lists of
texts, token IDs or token ID lists now count as their longest input,
since an embedding model's context window applies to each input on its
own

* fix(router): keep empty and boolean input lists on the Responses count path

An empty list carries no embedding evidence, and counting it as a zero
token batch skipped the instructions and tools of an empty Responses
input. Boolean lists are not token IDs

* fix(router): honor disable_token_counter for token ID embedding input

Text inputs already counted as zero through token_counter when token
counting is disabled, while token ID inputs were still measured by
length and could be rejected. The router reads the flag through its
dynamic config like its other process settings

* refactor(router): type the embedding count helper with a read-only sequence and final locals

* fix(router): count embedding batches per input on the media-free text projection

The per-input count now runs on the text projection from the embedding
media split, so data URIs a deployment embeds as media keep the media
path and only text items are checked against the context window. A
caption next to an image is checked on its own, and a text-only
deployment still counts an image data URI as text

* fix(router): keep embedding images out of the pre-call count only on image backends, and skip tokenizing inputs that fit by bytes

Media leaves the embedding count only when every deployment in the group declares image embedding input, so a text-only backend still counts a data URI as text and an image backend outside the TPM media list no longer gets a false 400. A text no longer than the smallest window in UTF-8 bytes counts as its byte length without the tokenizer, since a token is never shorter than a byte.

* fix(router): keep embedding images out of the pre-call count when any backend in the group embeds images

Mark Cohere embed-english-light-v3.0 as embedding images, as its v3 siblings are.

* fix(router): check embedding text batches only with an exact OpenAI tokenizer

litellm's default tokenizer counts non-English text several times higher than
non-OpenAI embedding providers do, so counting batches with it refused inputs
the provider accepts. Text batches on those groups now stay unchecked as at the
merge base, without the error log. Main's per-provider media split and the
cost map are restored, so strings and embedding media keep main's path.

* fix(router): count long embedding batches in slices so chat counts do not wait behind them

A text batch is now tokenized in slices of 65,536 characters, each its own offloaded call, so the FIFO count limiter can serve a chat count between slices. The no-OpenAI-tokenizer rule for text lists moved into the pre-call check, so RoutingContext.count_pre_call_check_tokens counts a text list by its longest text.

* fix(router): read embedding media off the event loop and wait on the count limiter in the fairness test

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-11-06 11:32:08 -08:00
..
a2a_protocol fix(a2a)!: bill completion-bridge agents at their own prices on /a2a send and stream (#49150) 2026-10-30 19:43:45 -07:00
accounting fix(accounting): keep spend commits working when prometheus_client is not installed (#50230) 2026-11-05 10:35:26 -08:00
anthropic_interface fix(anthropic_endpoints)!: return Anthropic error envelopes on /v1/messages auth failures (#48466) 2026-11-03 01:53:29 +00:00
batch_completion test: move routing, caching and callback tests out of local_testing (#45761) 2026-10-10 09:33:09 -07:00
batches feat(proxy)!: only let clients pick S3 buckets the admin allowed (#47496) 2026-11-06 02:50:15 +00:00
caching feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
completion_extras fix(responses): keep the system prompt in input for json_object on the chat to responses bridge (#49957) 2026-11-04 13:55:50 -08:00
compression test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
containers refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
cookbook feat(realtime)!: support latest OpenAI audio models (#35600) 2026-11-03 07:27:52 +00:00
db_scripts fix(vector-stores): keep proxy context out of provider vector store metadata (#47021) 2026-10-17 12:51:47 -07:00
decisions fix(least-busy): reserve the picked deployment so a burst of requests spreads out (#47484) 2026-11-05 00:30:12 +00:00
endpoints feat(vertex-ai)!: support gemini 3.1 flash tts (#31915) 2026-10-21 04:18:42 +00:00
enterprise fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
expected_fine_tuning_api test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
expected_responses_api_request test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199) 2026-09-25 17:10:13 -07:00
experimental_mcp_client fix(mcp): load deprecated package aliases on demand (#48615) 2026-10-27 19:46:19 +00:00
extraction feat(extraction): add /v1/extraction with Cloudflare Clairic support (#47473) 2026-10-20 15:51:45 -07:00
files fix(hosted_vllm): accept the vLLM production-stack router's file and batch objects (#49068) 2026-10-30 23:11:34 -07:00
fine_tuning fix(fine_tuning): stop forwarding api_version to the OpenAI client (#44995) 2026-10-21 01:58:25 +00:00
fixtures test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
gateway fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039) 2026-10-29 10:25:14 -07:00
google_genai fix(google_genai): read one-object and null spellings of repeated fields in countTokens and generateContent (#48771) 2026-10-28 21:46:06 -07:00
harness fix(streaming)!: send the include_usage chunk with an empty choices array (#47109) 2026-10-21 02:26:05 +00:00
images feat(dashscope): add image edits and text-to-speech (#48998) 2026-10-29 17:48:38 -07:00
integration_support test(integration): stop the wire peer from dropping requests whose bytes arrive late (#49889) 2026-11-05 09:24:05 -08:00
integrations fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
interactions 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
litellm_core_utils fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385) 2026-11-06 03:54:34 -08:00
litellm_proxy_extras feat(proxy): replace the pre-migration row check with a rolled-back dry run of the pending migrations (#48961) 2026-10-29 09:39:26 -07:00
llms feat(proxy): mixed Codex model picker and LiteLLM routing on native codex routes (#49408) 2026-11-06 11:14:47 -08:00
mcp_client feat(mcp): add an opt-in per-server setting to skip MCP tool output validation (#49961) 2026-11-03 20:42:10 -08:00
models fix(proxy): allow model instances in LiteLLM_EndUserTable validation (#41677) 2026-10-15 10:57:26 -07:00
ocr test(rust-bridge): relocate dispatch tests before routing changes (#46926) 2026-10-16 12:29:33 -07:00
passthrough fix(vllm): send the pass-through key as a bearer on both /vllm routes (#46861) 2026-10-30 08:57:48 -07:00
proxy feat(proxy): mixed Codex model picker and LiteLLM routing on native codex routes (#49408) 2026-11-06 11:14:47 -08:00
rag fix(rag)!: use team provider credentials and allow viewer and JWT team access (#45497) 2026-10-17 23:51:48 +00:00
realtime_api feat(realtime)!: support latest OpenAI audio models (#35600) 2026-11-03 07:27:52 +00:00
redis feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
repositories feat(skills): add sortable Skills Hub catalog and publication audit (#50195) 2026-11-06 00:57:33 +00:00
rerank_api test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
responses feat(proxy): mixed Codex model picker and LiteLLM routing on native codex routes (#49408) 2026-11-06 11:14:47 -08:00
router_rust feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
router_strategy feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
router_utils feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
rust_bridge feat: add OpenRouter-style -latest model aliases for first-party providers (#50315) 2026-11-06 18:22:38 +08:00
sandbox fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755) 2026-10-28 17:00:29 -07:00
search fix(search): price Tavily advanced and Linkup deep searches at their own cost map entries (#47411) 2026-10-19 23:32:31 -07:00
secret_managers fix(proxy): let a config license unlock enterprise settings and spell "environment" right in license errors (#49745) 2026-11-03 09:56:08 +00:00
skills feat(skills): add a litellm-setup agent skill (#47731) 2026-10-28 15:44:43 -07:00
systemone fix(databricks): reuse base OAuth for decisions (#48395) (#48527) 2026-10-26 20:18:16 -07:00
telemetry feat(telemetry): add AggregatingSink, fixed-bucket histograms, Report and HttpExporter (#45487) 2026-10-13 18:33:01 -07:00
test_router fix(router): count embedding batches per input in pre-call checks (#49851) 2026-11-06 11:32:08 -08:00
text_completions feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393) 2026-11-02 13:26:29 -08:00
tracing fix(proxy): cooldown errors carry 429, Sentry starts at boot without request bodies, tracing failures log at ERROR, exporter counters exported (#46344) 2026-10-16 00:53:52 +00:00
types fix(types): define the responses compact call types for during_call guardrails and deployment hooks (#50274) 2026-11-05 16:09:49 -08:00
vector_stores fix(exceptions)!: honor status code when mapping OpenAI invalid_request_error exceptions (#32537) 2026-10-29 08:05:47 -07:00
videos feat(videos): serve custom_provider_map BaseVideoConfig providers on /v1/videos (#49785) 2026-11-02 21:28:46 -08:00
__init__.py test(unit): add package markers to migrated unit test directories 2026-09-20 11:53:14 +00:00
AGENTS.md feat(vector_stores): add OpenSearch k-NN search as a vector store provider (#47759) 2026-10-29 08:15:05 -07:00
conftest.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
create_mock_standard_logging_payload.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_a2a_registry_lookup.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_acompletion_session_reuse_e2e.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_add_deployment_no_master_key.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_aembedding_session_reuse_e2e.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_anthropic_beta_gated_fields.py fix(anthropic)!: drop beta-gated body fields under drop_params (#48793) 2026-10-29 06:25:31 -07:00
test_anthropic_beta_headers_filtering.py feat(anthropic): pick the beta allowlist row per deployment and surface input_transformations (#49689) 2026-11-03 01:55:26 +00:00
test_anthropic_skills_transformation.py feat(anthropic): workload identity federation and pluggable identity sources (#44448) 2026-10-03 17:08:30 -07:00
test_assert_ci_coverage.py docs(agents): keep directory rules in nested AGENTS.md and pin integration tests to CircleCI (#46796) 2026-10-16 14:57:49 -07:00
test_assert_secret_absent.py ci: run the integration groups on GitHub Actions (#48985) 2026-10-29 12:50:08 -07:00
test_assert_workflow_dir_hygiene.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_audio_transcription_rust_bridge.py fix(bedrock): omit system prompt from audio transcription and report its token usage (#41565) 2026-10-28 19:23:15 -07:00
test_azure_ad_token_credential_resolution.py feat(proxy)!: only let clients pick S3 buckets the admin allowed (#47496) 2026-11-06 02:50:15 +00:00
test_azure_ai_grok_4_3_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_azure_ai_grok_4_6_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_baseten_glm_5_3_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_batch_completion_models_all_responses.py test: move routing, caching and callback tests out of local_testing (#45761) 2026-10-10 09:33:09 -07:00
test_bedrock_marengo_embed_3_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_build_core_distribution.py test: move packaging and install checks off CircleCI build_and_test (#45757) 2026-10-10 09:33:51 -07:00
test_cerebras_llama_model_metadata.py chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974) 2026-11-03 16:23:06 -08:00
test_chat_ui_responses_session.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_check_licenses.py feat(proxy): embed enterprise LiteAdmin MCP in LiteLLM images (#44610) 2026-10-05 15:24:34 -07:00
test_check_mcp_operation_boundary.py refactor(mcp): drop the experimental label from the MCP server and client paths (#48513) 2026-10-27 17:47:50 +00:00
test_check_migrations_lock_timeout.py fix(proxy-extras): bound migration lock waits with SET LOCAL lock_timeout in the migration SQL (#46329) 2026-10-13 20:51:03 -07:00
test_check_migrations_no_data_rewrites.py fix(proxy-extras): build the SpendLogs indexes in the migration job instead of in migrations (#43948) 2026-10-01 14:12:22 -07:00
test_check_openapi_docs.py feat(skills): upload local skill ZIPs from the dashboard (#50008) 2026-11-04 00:56:40 -08:00
test_check_py310_typing_imports.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_check_test_quality.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_check_type_discipline.py ci(lint): gate every rule on its merge-base count and cap Anys at a fixed total (#40193) 2026-10-08 05:39:29 +00:00
test_check_unbounded_in_lists.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_check_windows_wheel_install.py test: move packaging and install checks off CircleCI build_and_test (#45757) 2026-10-10 09:33:51 -07:00
test_circleci_checkout.py ci(circleci): clone the public repo over HTTPS so main jobs stop failing at checkout (#49394) 2026-10-31 02:53:54 -07:00
test_circleci_path_filter.py refactor(mcp): drop the experimental label from the MCP server and client paths (#48513) 2026-10-27 17:47:50 +00:00
test_circleci_run_migration_tests.py test: migrate proxy security, schema migration and MCP legacy tests (#45937) 2026-10-11 16:17:24 -07:00
test_circleci_rust_toolchain.py test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
test_claude_fable_5_config.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_claude_haiku_5_5_config.py fix(model_prices): consolidate claude-haiku-5-5 over-100k pricing and capability flags (#45151) 2026-10-07 14:14:47 -07:00
test_claude_opus_4_6_config.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_claude_opus_4_8_config.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_claude_opus_5_config.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_claude_sonnet_5_config.py refactor(cost-map): remove openrouter rows, part 5 of 5 (#45669) 2026-10-09 22:48:55 +00:00
test_cloudflare_workers_ai_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_completion_timeout_resolution.py fix(router)!: bound fake-streamed calls by the request timeout, not stream_timeout (#47162) 2026-10-17 22:08:02 +00:00
test_component_entrypoint.py feat(prometheus): cap series per metric for every labeled metric (#44420) 2026-10-06 01:28:44 +00:00
test_compression.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_conftest_isolation.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_constants.py fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054) 2026-10-29 20:32:04 -07:00
test_container_router.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_cost_calculation_log_level.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_cost_calculator.py fix(cost_calculator): keep regional and speed multipliers for per-call custom prices and log the billed per-call entry (#50063) 2026-11-04 15:47:57 -08:00
test_cost_map_guard.py fix(cost_map): mark fireworks_ai/minimax-m3 as vision and pin capabilities verified against live calls (#43390) 2026-10-29 00:23:11 -07:00
test_count_tokens_public_api.py chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974) 2026-11-03 16:23:06 -08:00
test_dashscope_image_generation.py feat(dashscope): add image edits and text-to-speech (#48998) 2026-10-29 17:48:38 -07:00
test_daybreak_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_deepseek_model_metadata.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
test_default_branch.py feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex (#48949) 2026-10-29 18:15:44 -07:00
test_detect_changes.py ci: render lint, unit and smoke checks as <tier> / <job> with one collector per tier (#45480) 2026-10-09 04:28:41 +00:00
test_docker_no_network_on_deploy.py test: migrate local_testing SDK and provider tests out of build_and_test (#45760) 2026-10-10 23:14:25 +00:00
test_dockerfile_apk_repository.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_dockerfile_bedrock_realtime_extra.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_dockerfile_non_root.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_drop_params_env_var.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_e2e_egress_sentinel.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_eager_tiktoken_load.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_elevenlabs_tts_pricing.py fix(cost-map): rolling registry audit, add elevenlabs api rates, together minimax-m3.1-flash, mistral voxtral 3 and azure_ai phi-4 dates (#47623) 2026-10-23 14:57:35 -07:00
test_empty_mock_response.py fix: honor empty mock completion responses (#48162) (#48266) 2026-10-28 00:56:45 +00:00
test_env_key_doc_gate.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_exception_exports.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_exception_header_preservation.py fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079) 2026-10-29 23:30:02 -07:00
test_exception_mapping_request_attribute.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_fake_openai_endpoint.py test: migrate local_testing SDK and provider tests out of build_and_test (#45760) 2026-10-10 23:14:25 +00:00
test_filter_out_litellm_params.py fix(params): validate stream_chunk_size once, before any provider call (#43222) 2026-09-26 23:01:20 +00:00
test_fireworks_serverless_model_costs.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_gate_slot_lock.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_gemini_3_1_flash_lite_image_pricing.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_gemini_4_argon_model_metadata.py feat(gemini)!: auto-continue gemini-4-argon long decodes with continuationToken (#46240) 2026-10-15 22:54:23 +00:00
test_gemini_tts_native_audio_pricing.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_get_blog_posts.py chore(blog): refresh the bundled blog posts backup with the latest 50 posts from the docs RSS feed (#49971) 2026-11-03 23:41:15 +00:00
test_git_hooks.py chore(hooks): drop Conventional Branches pre-push hook in favor of litellm_ prefix (#44951) 2026-10-20 00:35:39 +00:00
test_gpt_5_4_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_gpt_5_5_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_gpt_image_cost_calculator.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_gpt_realtime_mode.py chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974) 2026-11-03 16:23:06 -08:00
test_groq_streaming_encoding.py fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755) 2026-10-28 17:00:29 -07:00
test_guardrail_exception_status_codes.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_guardrails.py Add guardrails.apply SDK helper (#49217) (#49469) 2026-10-31 23:37:45 +00:00
test_integration_run.py test(integration): isolate every multi-worker integration suite by default (#46027) 2026-10-12 03:46:06 -07:00
test_internal_context.py feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
test_lazy_imports.py fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233) 2026-10-29 00:40:02 -07:00
test_lint_base_counts.py revert(lint-gates): accept an empty base scan again, since zero violations is a legitimate count (#45319) 2026-10-08 08:40:08 +00:00
test_lint_workflow_diff_gates.py ci(unit): stop the full history clone on the db-and-spend shard, fetch the schema merge base by sha (#50120) 2026-11-04 22:40:38 +00:00
test_litellm_cli.py fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039) 2026-10-29 10:25:14 -07:00
test_litellm_overhead.py test(unit): wait on the work itself instead of fixed sleeps (#46261) 2026-10-13 12:41:06 -07:00
test_litellm_params_reserved_keys.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_logging.py feat(proxy)!: add suppress_startup_output to turn off startup prints (#47708) 2026-10-29 03:47:04 -07:00
test_lowest_latency_zero_tokens.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_main.py fix(github-copilot): send the GitHub token directly instead of exchanging it (#50126) 2026-11-05 09:45:17 -08:00
test_main_module_header.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_mistral_large_4_model_metadata.py fix(cost-map): price Mistral Large 4 at its list price now that the launch sale ended (#48825) 2026-10-28 18:12:55 +00:00
test_mistral_medium_3_5_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_mistral_small_4_0_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_mistral_zai_glm_5_2_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_model_block_unblock.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_model_cost_aliases.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_model_param_helper.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
test_model_prices_and_context_window.py fix(vertex-ai): sync tier prices and retirement floors (#49964) 2026-11-04 00:03:54 +00:00
test_model_response_normalization.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_muse_spark_1_1_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_muse_spark_1_2_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_muse_spark_1_3_model_metadata.py refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
test_mutation_report.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_nested_drop_params.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_no_top_level_test_invocations.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_non_chat_routes_open_llm_spans.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_openai_embedding_encoding_format_default.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_record_replay_proxy.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_openai_service_tier_long_context_pricing.py fix(cost_calculator): bill ultrafast prompts above 272k at the ultrafast long-context rates (#43764) 2026-09-30 07:32:16 -07:00
test_openapi_docs_gate.py fix(ci): build base native extension for OpenAPI lint (#49136) 2026-10-29 16:56:44 -07:00
test_package_layout.py test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
test_package_metadata.py chore(deps): require anyio>=4.14.0 to rule out the lock-waiter deadlock (#47378) 2026-10-19 12:37:47 -07:00
test_pre_commit_lint.py ci: run the dashboard API types and Terraform endpoint checks on every change that can alter the spec (#49022) 2026-10-29 07:19:06 -07:00
test_prisma_generate_if_needed.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_private_usage_aliases.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_process_helpers.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_project_alias_tracking.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_project_tags_pydantic.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_proxy_auth.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_pydantic_namespaces.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_rag_openai_ingestion.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_rate_limit_error_unification.py feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
test_read_rc_version.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_redact_string_in_error_paths.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_redis.py feat(redis): serve the proxy's common Redis call with Rust stores (#50170) 2026-11-06 06:01:11 +00:00
test_redis_credential_provider.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_register_model_custom_pricing.py fix(main)!: carry the full per-call price entry on the logging object instead of writing litellm.model_cost (#49532) 2026-11-03 16:03:34 -08:00
test_register_model_zero_cost_persistence.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_replicate_model_key_format.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_repo_agent_skills.py feat(skills): add a litellm-setup agent skill (#47731) 2026-10-28 15:44:43 -07:00
test_responses_api_bridge_non_stream.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
test_responses_id_security.py fix(responses)!: authorize and decode comparison response IDs (#49402) 2026-11-03 03:40:46 +00:00
test_responses_streaming_container_ownership.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_retrieve_batch_bedrock_dispatch.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_router_block_helpers.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_exception_redaction.py fix(streaming)!: map stream read timeouts to litellm.Timeout on chat, messages, and responses (#47198) 2026-10-18 13:58:34 +00:00
test_router_get_settings.py ci(circleci): test Redis behavior against local Redis and print short tracebacks (#44062) 2026-10-01 13:00:54 -07:00
test_router_google_genai.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_router_model_cost_isolation.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_router_order_fallback.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_per_deployment_num_retries.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_redis_init.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_router_retry_backoff_headers.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_retry_non_retryable_errors.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_retry_policy_update.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_silent_experiment.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_streaming_fallback_metadata.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_router_weighted_failover.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_ruff_strict_gate.py ci(lint): gate every rule on its merge-base count and cap Anys at a fixed total (#40193) 2026-10-08 05:39:29 +00:00
test_sambanova_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_scaledown_model_prices.py feat(scaledown): add native text provider support (#44168) 2026-10-10 14:01:17 -07:00
test_scheduler.py fix(scheduler): read shared queue from Redis so expired dead-replica entries stop blocking waiters (#49387) 2026-10-31 11:43:46 -07:00
test_secret_redaction.py refactor(rust-bridge): require the native extension (#48852) 2026-10-28 13:16:56 -07:00
test_seed_tracing_fixtures.py refactor(lens): connect LiteLLM to the independent Lens service (#45529) 2026-10-09 16:17:05 -07:00
test_select_ui_test_scope.py fix(ci): measure PR gates from the target branch's current tip (#49078) 2026-10-29 18:28:16 -07:00
test_service_logger.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_setup_wizard.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_shared_session_integration.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_socket_policy.py test(unit): block external sockets at import time and add a socket policy regression test 2026-09-20 08:07:50 +00:00
test_spend_logs_guard.py fix(ci): flag any schema.prisma change inside model LiteLLM_SpendLogs in the spend logs guard (LIT-10240) (#48905) 2026-10-28 15:52:15 -07:00
test_ssl_verify_unit.py test(unit): stop test modules from putting their own directory on sys.path (#43421) 2026-09-28 12:20:20 -07:00
test_stream_chunk_builder_annotations.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_stream_chunk_builder_citations.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_stream_chunk_builder_images.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_streaming_connection_cleanup.py refactor(router): delete the python router core, the rust core is the only core (#50178) 2026-11-05 10:40:46 -08:00
test_system_message_format_bug.py fix(prompt_templates): do not mutate messages in-place in function_call_prompt (#41676) 2026-10-15 14:37:11 -07:00
test_test_quality_gate.py ci(lint): gate every rule on its merge-base count and cap Anys at a fixed total (#40193) 2026-10-08 05:39:29 +00:00
test_thinking_enabled.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_together_ai_model_metadata.py chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974) 2026-11-03 16:23:06 -08:00
test_tool_loop.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_type_check_gate.py ci(lint): gate every rule on its merge-base count and cap Anys at a fixed total (#40193) 2026-10-08 05:39:29 +00:00
test_type_discipline_gate.py ci(lint): gate every rule on its merge-base count and cap Anys at a fixed total (#40193) 2026-10-08 05:39:29 +00:00
test_typesafe_model_metadata.py fix(cost): price typesafe/jev-1.14.0 (#46594) 2026-10-14 20:27:35 -07:00
test_unit_shard_missing_paths.py ci: render lint, unit and smoke checks as <tier> / <job> with one collector per tier (#45480) 2026-10-09 04:28:41 +00:00
test_unit_shard_per_test_timeout.py ci: render lint, unit and smoke checks as <tier> / <job> with one collector per tier (#45480) 2026-10-09 04:28:41 +00:00
test_utils.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_utils_get_model_info.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_utils_get_optional_params.py fix(openai): warn when the GPT-5 reasoning effort gate drops a level under drop_params (#47761) 2026-10-29 04:46:29 -07:00
test_utils_module_docstring.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_uuid_helper.py fix: support Python 3.15 (#48359) 2026-10-26 16:00:11 +00:00
test_vcr_classification.py test: move offline logging, secret manager and provider tests from legacy dirs into tests/unit (#45554) 2026-10-09 09:48:10 -07:00
test_vcr_conftest_common_banner.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_vcr_filters.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_vcr_leak_guard.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_vcr_redis_persister.py test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
test_vcr_safe_body_matcher.py fix(tests): stop VCR recording and replaying a test's own localhost upstream (#43346) 2026-09-26 15:49:39 -07:00
test_version.py feat(sdk): build core from an independent packaging manifest (#44340) 2026-10-08 18:40:14 -07:00
test_vertex_ai_xai_grok_prompt_caching_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_video_generation.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_with_dashboard_node.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_ws_vcr.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_xai_grok_4_3_model_metadata.py test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_xai_responses_auto_routing.py fix(router)!: stop a chat-mode Mantle deployment from rewriting the shared Responses routing row (#46263) 2026-10-17 21:39:14 +00:00