litellm/tests/unit
paveln83 febd340120
fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
* fix(guardrails): keep the upstream error when a /v1/messages stream ends in one

Raw-SSE guardrail stream hooks assembled the whole stream, and the Anthropic
chunk parser raises on an error event, so a stream the upstream ended with
event: error failed assembly. tool_permission then blocked it with a 400 that
hid the upstream error, bedrock and model_armor emitted a could-not-assemble
block, and presidio skipped masking.

Assembly now leaves the error events out, so the delivered content is checked
as usual and a clean stream passes through with its error frame. A rewritten
stream ends with the upstream error instead of a message_delta and
message_stop the upstream never sent. tool_permission also passes a stream of
only error frames, which carries no tool call to check.

* fix(guardrails): do not close a block the failed upstream left open when re-emitting a rewritten stream

* fix(guardrails): check only the finished blocks of a stream cut off by an upstream error

tool_permission and Presidio now assemble an error-ended stream through the
error with an opt-in keyword, leaving out a tool call or thinking block the
upstream cut off. Logging, OpenTelemetry, Bedrock, and Model Armor keep the
old assembly. A rewrite drops the text block stop only when the upstream left
its text block open.

* fix(guardrails): keep a cut-off tool call from the client and stop each rewritten block before the next starts

A failed stream holding a cut-off tool_use is now re-emitted through the rewrite, which leaves the call out and keeps the upstream error, so a denied call never reaches the client. The rewrite leaves its text block open only when it is the last block, and keeps a message_delta the upstream sent before failing. The new tool_permission tests no longer patch should_run_guardrail.

* fix(guardrails): pass a cut-off stream with nothing denied through as sent, minus the cut-off tool call

Re-emitting such a stream through the rewrite sent an empty text block and stopped it, and Claude Code
does not retry a failed stream that shows a finished block, so it showed a mid-response error instead
of retrying. Dropping only the cut-off call's events keeps the stream as the upstream sent it.

* fix(guardrails): strip a cut-off tool call only from a stream the upstream failed

Assembly leaves unfinished blocks out of the check only when the stream carries an upstream error
event, so a stream with an unfinished but allowed tool call and no error frame now reaches the client
as sent instead of losing a call the check already read

* test(guardrails): type the parameters of the new stream error tests

* fix(guardrails): skip SSE data lines that are not JSON objects when reading a stream

A data line holding a bare JSON value such as 5 made the stream helpers call .get on an int, so tool_permission and Presidio answered 500 where main answered 400 or passed the stream through

* fix(anthropic): skip SSE data lines that are not JSON objects when assembling a stream

* test(guardrails): annotate the upstream error stream tests

* fix(anthropic): read a stream's non-object lines and named error frames the same way everywhere

Run the skip for a data line that is not a JSON object through extract_sse_data and the assembler loop, so the usage fallback keeps a stream's tokens and the chat handler keeps its contract.

Presidio now holds a leading non-object frame until the first object frame, so the rest of the stream is still masked or blocked. An event: error frame now counts by its name, so a rewrite keeps it.

* fix(guardrails): refuse an unreadable stream in Presidio and cut every kind of tool call

A non-object JSON line with no Anthropic frame after it now gets a 400 from
Presidio before any data byte, since passing it would send text main refused.
A frame named error stays a normal event when its data is another Anthropic
event. server_tool_use and mcp_tool_use cut off by an upstream error are
dropped like tool_use, and a leading frame with empty data is relayed at once.

* fix(guardrails): refuse what Presidio cannot read past a non-object line and keep non-string error types out of the frozenset

Presidio now refuses a stream assembly cannot read when it holds a non-object
data line, instead of relaying it unmasked. Non-string event types no longer
crash a rewrite, and a CRLF stream that opens with a typed error is no longer
read as one error, so its tool calls are still checked.

* fix(guardrails): refuse a first frame whose type is a list or dict in Presidio

Presidio passed PII at 200 where main answered 500 when the first read was
a JSON object with a list or dict type, or a JSON array with a character cut
at the end of the read. has_unreadable_json_event now reads both as data no
reader of these streams can take, so the first-frame check refuses them.

* test(guardrails): cover Presidio's refusal when a word or null line comes before a Gemini stream

The first read then holds the unreadable line behind one Presidio can pass,
so the check has to look at every frame in it.

* fix(guardrails): treat a stream as error-only only when every data frame is an error

A tool call split over data: lines beside one error frame read as error-only,
so tool_permission passed it, and an SDK joins those lines and reads the call.
The check now joins a frame's data lines and refuses anything but an error.

* fix(guardrails): refuse a stream past an upstream error when a client could read a frame differently

Run 8 of the live risk pass showed each stream reader imitating a client and missing a shape: a
whitespace-led data line, an error key with no type, a split tool call after a plain message_start.
An error frame now has to be plain, and assembly past an error returns None for any frame a client
could read differently, so those streams keep main's refusal.

* fix(guardrails): on a failed upstream, deliver only what tool_permission read

A failed stream now reaches the client through the rewrite that already
serves a denial, followed by the upstream error, even when nothing is
denied. Raw frames could carry a tool call the check never read in shapes
such as a reused block index, mixed line ends, a tool in message_start,
interleaved deltas, or a form feed, and each refusal rule only moved the
search to the next shape.

The error frame goes out as its event name and first data line. An error
is found at CR, LF and CRLF line ends, and the rewrite adds no finished
block when it read no text, so Claude Code still retries the stream.

* fix(guardrails): read an error frame's name as clients do and send the error alone when a rewrite cannot be built

A data-less event: error frame with junk after the name is an unknown event to both SDKs, so a healthy stream
stays raw. A finished tool call whose input is not JSON cannot be rebuilt, so a failed stream sends its upstream
error alone, and a healthy stream still raises as before.

* fix(guardrails): read an error frame as a client dispatches it and keep its JSON whole

Only the last event line of a frame a blank line ended names an error, so a
healthy stream with a later event line or an unterminated error is no failed
stream. Any rebuild failure on a failed stream now sends the upstream error
alone with a warning, a param rule denies an input nested too deep, and a raw
line break inside a JSON error stays escaped so every reader gets it whole.

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-10-31 02:56:20 -07:00
..
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 feat(accounting): add accounting contracts, PricingSnapshot and ledger schema (LIT-10193) (#48862) 2026-10-28 14:39:25 -07:00
anthropic_interface fix(proxy): send a real error event when a /v1/messages stream fails (#41826) 2026-09-25 15:36:35 -07:00
batch_completion test: move routing, caching and callback tests out of local_testing (#45761) 2026-10-10 09:33:09 -07:00
batches fix(hosted_vllm): accept the vLLM production-stack router's file and batch objects (#49068) 2026-10-30 23:11:34 -07:00
caching refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
completion_extras fix(streaming): rebuild each choice of an n>1 chat stream on its own (#49002) 2026-10-29 18:29:14 -07:00
compression test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
containers refactor(typing): clear 1181 basedpyright Any errors across 431 files (#47789) 2026-10-24 11:31:09 -07:00
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(decisions)!: honor a deployment's own supports_audio_input and supports_video_input flags (#49207) 2026-10-31 01:09:46 -07:00
endpoints feat(vertex-ai)!: support gemini 3.1 flash tts (#31915) 2026-10-21 04:18:42 +00:00
enterprise refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
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): wait for every worker in Scenario.model (#47277) 2026-10-18 14:49:25 -07:00
integrations fix(proxy): trace model list requests with the caller's traceparent (#49141) 2026-10-31 01:22:45 -07:00
interactions fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755) 2026-10-28 17:00:29 -07:00
litellm_core_utils fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192) 2026-10-31 02:53:59 -07:00
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 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088) 2026-10-31 02:56:20 -07:00
mcp_client refactor(mcp): drop the experimental label from the MCP server and client paths (#48513) 2026-10-27 17:47:50 +00:00
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 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088) 2026-10-31 02:56:20 -07:00
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(soniox): add realtime speech-to-text on /v1/realtime (#44822) 2026-10-29 07:58:38 -07:00
repositories refactor(proxy): inject gateway activity through a typed repository (#49116) 2026-10-30 16:25:11 -07:00
rerank_api test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
responses fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192) 2026-10-31 02:53:59 -07:00
router_strategy refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
router_utils refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
rust_bridge refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
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 feat(secret_managers): resolve oidc/google api_key references per request (#47703) 2026-10-29 08:44:46 -07:00
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 refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
text_completions fix(proxy)!: bill streamed /v1/completions without stream_options like chat (#45366) 2026-10-29 17:18:51 -07:00
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(hosted_vllm): accept the vLLM production-stack router's file and batch objects (#49068) 2026-10-30 23:11:34 -07:00
vector_stores fix(exceptions)!: honor status code when mapping OpenAI invalid_request_error exceptions (#32537) 2026-10-29 08:05:47 -07:00
videos test: migrate phase 16 legacy tests to tests/unit 2026-09-20 10:59:02 +00:00
__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 fix(llms): move later developer messages for models declared system-first (#48897) 2026-10-29 04:12:13 -07:00
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 fix(vertex_ai,azure_ai)!: auto-add the compaction, thinking display, and tool change betas on Claude routes (#44747) 2026-10-30 09:28:19 -07:00
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 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_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 feat(models): add Cerebras Llama 3.1 hyphenated aliases (cerebras/llama-3.1-8b, cerebras/llama-3.1-70b) (#48157) (#48158) 2026-10-24 17:16:33 -07:00
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 ci: gate undocumented POST routes in the proxy OpenAPI document (#45843) 2026-10-10 21:51:00 +00:00
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 test: isolate model cost maps in runtime registration tests (#47559) 2026-10-20 16:18:13 +00:00
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): preserve zero prices across batch, speech and search (#49294) 2026-10-30 15:05:32 -07:00
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 fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
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 feat(proxy): add LITELLM_OFFLINE_MODE, one switch for the fetches LiteLLM makes on its own (#48096) 2026-10-23 16:54:19 -07:00
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 test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
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_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(proxy)!: model family and access group entries in model_max_budget (#47722) 2026-10-28 15:40:57 -07:00
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 fix(ci): measure PR gates from the target branch's current tip (#49078) 2026-10-29 18:28:16 -07:00
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(logging): warn when drop_params drops a requested reasoning level on the remaining paths (#48933) 2026-10-30 08:48:43 -07:00
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 refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
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): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
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 refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
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: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
test_redis.py test: move routing, caching and callback tests out of local_testing (#45761) 2026-10-10 09:33:09 -07:00
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(register_model)!: keep bedrock geo deployments priced across price data reloads (#41523) 2026-10-17 19:10:04 +00:00
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): resume background response streams with stream and starting_after (#48819) 2026-10-29 02:31:22 -07:00
test_responses_streaming_container_ownership.py fix(responses): bill a background response once, on the first read or poll that sees it finished (#45703) 2026-10-15 11:00:14 -07:00
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: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
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 fix(anthropic)!: send /v1/messages PDF documents to OpenAI-shaped providers as file parts (#47166) 2026-10-29 08:06:12 -07:00
test_router_order_fallback.py fix(router): keep the prompt caching affinity pin alive as long as the prefix's cache_control ttl (#46084) 2026-10-14 21:10:09 -07:00
test_router_per_deployment_num_retries.py fix(images): honor max_retries and prevent Router retry amplification (#48705) 2026-10-28 10:46:47 -07:00
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 test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
test_router_retry_non_retryable_errors.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_policy_update.py fix(proxy): unset DB environment variables removed from the row on every worker by row revision (#46709) 2026-10-17 03:51:05 +00:00
test_router_silent_experiment.py fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs (#48888) 2026-10-29 05:12:50 -07:00
test_router_streaming_fallback_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_router_weighted_failover.py fix(router): let affinity pins yield to deployments that already failed this request (#32309) 2026-10-28 03:24:26 -07:00
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): remove a request's queue entry once it stops waiting (#43061) 2026-10-07 17:34:38 -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 test: move tests/test_litellm root and small trees into tests/unit (#43186) 2026-09-25 11:30:43 -07:00
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 refactor(cost-map): drop the legacy max_tokens field in favor of max_input_tokens and max_output_tokens (#48471) 2026-10-26 17:03:05 -07:00
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 fix(openrouter)!: list OpenRouter's live catalog for openrouter/* when check_provider_endpoint is on (#48820) 2026-10-30 12:19:51 -07:00
test_utils_get_model_info.py fix(bedrock): price claude_platform calls from their own cost map rows (#48150) 2026-10-24 13:54:18 -07:00
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