scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-20 00:11:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 76
litellm/tests/test_litellm
History
yucheng-berri 7a81ae98e6
fix(model_armor): handle Anthropic Messages and Responses streams in post_call (#39181) 
* fix(model_armor): handle Anthropic Messages and Responses streams in post_call

The post_call streaming hook buffered every chunk and fed it to
stream_chunk_builder, which only understands chat-completion deltas.
/v1/messages streams raw Anthropic SSE bytes and /v1/responses streams
typed Responses events, so both raised litellm.APIError and surfaced to
the client as a 500 on every streamed request.

Assemble each surface with its own reader, frame guardrail failures as
terminal items in that surface's wire format, and pass the stream
through unscanned when it cannot be assembled instead of raising.

* fix(model_armor): classify the stream surface and fail closed when it cannot be assembled

Decide the wire format explicitly instead of inferring it from a boolean pair, so an
opaque raw SSE stream (the Google :streamGenerateContent route) is never refused in
Anthropic framing, and a stream that cannot be assembled is blocked rather than
released unscanned unless fail_on_error is disabled.

Also scan Responses tool-call arguments, read the body only off a terminal Responses
event, and record the applied guardrail on the fail-closed path.

* test(model_armor): pin the error-only stream predicate against content-carrying streams

is_sse_error_stream decides whether a buffered stream is forwarded to the client
untouched, so a stream that still carries content must not qualify: the frames-only
join drops typed chunks, an empty stream is not a refusal, and a content event may
carry an empty error field.

* fix(model_armor): let a streamed de-identify match mask instead of blocking

A de-identify template reports MATCH_FOUND for every redaction it makes. The
streaming block check omitted allow_sanitization, so with mask_response_content
enabled that match read as a refusal and the client got a 400 where the
non-streaming sibling returned the redacted text. Pass the flag through, as the
non-streaming hook already does, and stamp the logged status from the same
decision so the spend row agrees with what the client received.

Also drop Any from the chat-completion assembler's parameter; stream_chunk_builder
takes a bare list, so list[object] carries the mutability requirement without
erasing the element type.

* fix(model_armor): fail closed when a streamed de-identify match cannot be applied

Allowing sanitization past the streaming block check is a promise to apply the
redaction Model Armor asked for. Two paths broke that promise and released the
buffered original instead: a match that comes back with no sanitized text, and a
surface with no assembled body to rewrite.

The outcome is now resolved once, before it is recorded, so the status stamped on
request metadata agrees with what the client receives rather than reporting the
success the block check alone would have implied.

* fix: scan the deltas when a Responses stream ends without a body

response.failed and response.incomplete are terminal events like
response.completed, but a turn that broke mid-generation reports an empty
output while the deltas ahead of it already spelled the answer out to the
client. Reading only the terminal body found nothing to scan there, and the
empty-content shortcut then forwarded every buffered delta past the guardrail.

Fall back to the text the delta events carry whenever a Responses stream
assembles to nothing.

* fix: read the Responses delta event types off the event enum

The hand-listed set left out response.mcp_call_arguments.delta, so a turn that
streamed only MCP tool arguments and then reported an empty body still took the
no-content shortcut and forwarded those chunks unscanned.

Deriving the set from ResponsesAPIStreamEvents keeps it complete as the enum
grows, and the str guard in the reader already covers any event whose delta is
not text.

* fix(model_armor): scan responses deltas alongside the terminal body

A /v1/responses stream spells out reasoning summaries and tool-call arguments in
delta events that its terminal body never repeats, so scanning the body alone
handed every summary delta to the client unscanned whenever the body carried text.

* fix(model_armor): scan responses delta fields apart from each other

A Responses turn spells out its reasoning summary, its visible answer and its tool-call
arguments in separate delta events. Joining every delta into one string let a finding form
across the boundary between two fields that each carry nothing to find, so a safe stream
could be blocked. Group the deltas by the field they belong to, join a field's own deltas
as they streamed, and keep the fields apart.

* fix(model_armor): scan each responses field once, not twice

Separating delta fields stopped the terminal body from matching the delta text, so a turn
with two visible fields sent Model Armor both copies. Only the delta fields the body does not
already carry are appended now.

---------

Co-authored-by: yassin <yassin@berri.ai>
2026-09-02 19:15:14 -07:00
..
a2a_protocol feat(agentcore-a2a): derive runtime session id from A2A message.contextId (#39371) 2026-09-02 12:40:24 -07:00
anthropic_interface Merge pull request #39334 from BerriAI/litellm_rust_opt_in_configuration 2026-09-02 16:26:36 -07:00
batches test(batches): cover decoding a model-encoded error file id 2026-08-24 19:34:16 -04:00
caching fix(redis): coerce env var string types and fix param discovery through decorator wrappers (#30644) 2026-08-31 20:51:31 -07:00
completion_extras fix(anthropic): carry tool_reference tool results through the guardrail translation round trip 2026-08-26 22:35:46 -07:00
compression fix(guardrails/headroom): stop compressing the turn the model must act on (#35294) 2026-07-30 18:53:31 -07:00
containers fix(router): pass container create/list through when model names no deployment 2026-09-01 23:39:42 +00:00
endpoints fix(speech): honor pcm response_format for Gemini TTS and reject unsupported containers 2026-08-29 16:36:34 -07:00
enterprise Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_keyless_key_managed_resource_owner 2026-08-29 11:33:08 -07:00
expected_fine_tuning_api refactor: refactor testing 2026-03-28 18:39:32 -07:00
expected_responses_api_request test(responses): replace perma-skip azure shell e2e with offline coverage (#32444) 2026-07-08 10:01:41 -07:00
experimental_mcp_client fix(mcp): follow tools/list pagination from upstream servers (#39172) 2026-09-01 14:34:14 -07:00
fixtures/together_ai_sync feat(models): add daily Together AI model registry sync script and workflow 2026-08-25 13:12:06 -07:00
google_genai refactor(google_genai): pick the stream logging endpoint type at construction 2026-08-26 17:18:44 -07:00
images test(images): pin scalar-array edit params survive as repeated multipart fields 2026-08-24 12:49:54 -07:00
integrations feat(azure): support credential chain for storage (#39229) 2026-09-02 18:55:22 -07:00
interactions fix(interactions): poll queued background creates and drop the poll's deployment identity 2026-08-22 17:35:19 -07:00
litellm_core_utils fix(proxy): stop leaking internal exception details to clients (#39380) 2026-09-02 17:32:00 -07:00
llms feat(azure): support credential chain for storage (#39229) 2026-09-02 18:55:22 -07:00
models fix(proxy): serialize model block responses 2026-08-29 21:22:17 -07:00
ocr Merge pull request #39334 from BerriAI/litellm_rust_opt_in_configuration 2026-09-02 16:26:36 -07:00
passthrough fix(passthrough): map sync streaming errors, keep router streaming responses unwrapped, and resolve gigachat from api base 2026-08-31 13:16:40 -07:00
proxy fix(model_armor): handle Anthropic Messages and Responses streams in post_call (#39181) 2026-09-02 19:15:14 -07:00
rag fix(rag): store-wins merge, single lookup, allowlisted search params 2026-09-01 12:52:45 -07:00
realtime_api test(realtime): pin mode-only transcription detection and correct a stale docstring 2026-08-26 12:33:46 -07:00
repositories fix(budgets): drop the bespoke access group cache TTL and format the repository 2026-08-29 14:00:56 -07:00
rerank_api fix(rerank): adopt declared authenticating providers in arerank instead of resolving them 2026-09-01 14:47:59 -07:00
responses fix(responses): keep provider response headers in streaming logging callbacks (#38131) 2026-09-02 17:40:13 -07:00
router_strategy fix(proxy): keep SpendLogs and callback session ids in sync when the request has none (#39450) 2026-09-02 18:28:06 -07:00
router_utils fix(proxy): keep SpendLogs and callback session ids in sync when the request has none (#39450) 2026-09-02 18:28:06 -07:00
rust_bridge Merge pull request #39334 from BerriAI/litellm_rust_opt_in_configuration 2026-09-02 16:26:36 -07:00
sandbox test: say whether a match= pattern is a regex or a literal (ruff RUF043) 2026-08-21 16:25:33 -07:00
secret_managers test(aws): type the new partition test parameters 2026-08-29 02:27:18 -07:00
test_router fix(logging): stop pinning large request payloads past request end (#33455) 2026-07-15 15:28:37 -07:00
types feat(mcp): let a resolved OAuth token target a custom upstream header (#38456) 2026-08-27 14:32:01 -07:00
vector_stores test(vector_stores): package the suite dir to avoid test_main basename collision 2026-09-01 13:15:51 -07:00
videos test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
__init__.py
conftest.py test: invalidate memoized model-cost lookups between unit tests 2026-08-23 09:23:35 +00:00
log.txt
readme.md
test_a2a_registry_lookup.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_acompletion_session_reuse_e2e.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_add_deployment_no_master_key.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_aembedding_session_reuse_e2e.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_anthropic_beta_headers_filtering.py chore(oss): litellm oss staging 120626 (#30292) 2026-06-12 09:49:25 -07:00
test_anthropic_skills_transformation.py fix: encode upstream URL path identifiers 2026-04-29 22:02:39 -07:00
test_anthropic_sonnet_1hr_cache_pricing.py test(model_prices): pin claude 3 1h cache write rates to 2x base input 2026-08-25 14:05:07 +00:00
test_assert_ci_coverage.py ci: run the keyless caching tests that ran in no job (#37790) 2026-08-22 22:56:43 -07:00
test_assert_workflow_dir_hygiene.py feat(ci): assert .github/workflows holds only workflows, correctly named (#37616) 2026-08-20 21:36:26 +00:00
test_audio_transcription_rust_bridge.py perf(bedrock): audio transcription via rust core (py->rust bridge) (#33990) 2026-07-20 14:09:41 -07:00
test_azure_ad_token_credential_resolution.py test(router): cover s3_output_bucket_name surviving the trusted credential snapshot 2026-08-17 14:51:10 -07:00
test_azure_ai_grok_4_3_model_metadata.py feat(azure-ai): add Grok 4.3 model metadata (#27932) 2026-08-13 17:25:17 -07:00
test_azure_audio_price_aliases.py fix(pricing): add undated azure aliases for gpt-audio-mini and gpt-realtime-mini (#37867) 2026-08-21 18:44:19 -07:00
test_batch_completion_models_all_responses.py test(batches): move orphan tests into tests/test_litellm for CI coverage (#30510) 2026-06-16 10:20:59 -07:00
test_bedrock_anthropic_1hr_cache_pricing.py Litellm oss staging 030626 (#29578) 2026-06-03 11:01:51 -07:00
test_bedrock_batch_pricing.py fix(model_prices): add Gemini live-translate, Voyage 4 series, Perplexity contextualized embeddings; absorb Fireworks + Bedrock batch registry PRs 2026-08-20 19:14:11 +00:00
test_bedrock_extended_beta_models.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_bedrock_nemotron_super.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_bedrock_usgov_haiku_1hr_cache.py Litellm OSS Staging 010626 (#29422) 2026-06-01 21:42:51 -07:00
test_bedrock_usgov_pricing.py fix(models): add the us-gov. geo inference profile keys for Claude Sonnet 5 and Opus 4.8 2026-09-02 10:30:14 -07:00
test_budget_ratchet_check.py fix(lint): let the ratchet guard recognise a graduated rule 2026-08-07 23:11:23 -07:00
test_chat_ui_responses_session.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_check_licenses.py fix(ci): retry transient PyPI license lookups 2026-08-23 09:23:35 +00:00
test_check_migrations_no_data_rewrites.py fix: keep a schema-qualified call inside an index expression from reading as a relation 2026-08-24 16:04:38 -07:00
test_check_py310_typing_imports.py fix: keep litellm importable on Python 3.10 and guard 3.11-only typing imports in CI (#39448) 2026-09-02 18:27:19 -07:00
test_check_test_quality.py feat(ci): gate patching of SDK internals in tests as TQ008 (#37787) 2026-08-22 22:54:30 -07:00
test_check_type_discipline.py perf(ci): fan the budget checkers out across cores (#37784) 2026-08-22 22:44:58 -07:00
test_circleci_path_filter.py perf(ci): gate the lint, MCP and dashboard jobs on the pull request's file list (#37559) 2026-08-19 18:32:21 -07:00
test_circleci_rust_toolchain.py fix(ci): pin workflow toolchain dependencies 2026-09-02 12:16:25 -07:00
test_claude_fable_5_config.py feat(anthropic): gate forced tool_choice for Fable 5.1 behind supports_forced_tool_use 2026-09-01 18:46:03 +00:00
test_claude_haiku_4_5_config.py feat(anthropic): add Claude Opus 4.8 and prune reasoning-effort flags (#29238) 2026-05-28 18:50:33 -07:00
test_claude_opus_4_6_config.py fix(azure_ai): advertise 1M context window for Claude Opus 4.6+ on Foundry 2026-07-24 21:53:12 +00:00
test_claude_opus_4_8_config.py fix: omit thinking.type=disabled for always-on thinking Claude models (#37510) 2026-08-21 10:27:26 -07:00
test_claude_opus_5_config.py fix: omit thinking.type=disabled for always-on thinking Claude models (#37510) 2026-08-21 10:27:26 -07:00
test_claude_sonnet_4_6_config.py feat(anthropic): add Claude Opus 4.8 and prune reasoning-effort flags (#29238) 2026-05-28 18:50:33 -07:00
test_claude_sonnet_5_config.py fix: omit thinking.type=disabled for always-on thinking Claude models (#37510) 2026-08-21 10:27:26 -07:00
test_cloudflare_workers_ai_model_metadata.py fix(models): add cloudflare whisper transcription pricing and pin govcloud pricing tests 2026-09-02 15:28:53 +00:00
test_command_r7b_pricing.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_completion_timeout_resolution.py fix(router): honor litellm_settings.request_timeout as an independent per-attempt timeout (#31119) 2026-06-23 14:22:54 -07:00
test_component_entrypoint.py fix(docker): honor USE_DDTRACE in the componentized gateway and backend images (#35490) 2026-08-01 14:12:59 -07:00
test_compression.py Prompt Compression - add it to the proxy (#25729) 2026-04-20 15:08:00 -07:00
test_conftest.py test: trim the PROXY_BASE_URL fixture and regression docstrings 2026-08-19 00:56:37 -07:00
test_conftest_isolation.py test: roll back live router replay membership between tests (#36278) 2026-08-08 10:45:43 -07:00
test_constants.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_container_router.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_cost_calculation_log_level.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_cost_calculator.py fix(cost_calculator): scope region_name to response-derived model names 2026-08-28 12:19:14 -07:00
test_count_tokens_public_api.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_dashscope_image_generation.py feat(dashscope): support qwen-image-3.0 and qwen-image-3.0-pro image generation 2026-08-27 01:59:51 +00:00
test_daybreak_model_metadata.py fix: mark daybreak-blue-latest and gpt-5.6-sol as supporting computer use 2026-08-20 16:20:40 -07:00
test_deepseek_model_metadata.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_detect_changes.py perf(ci): gate the lint, MCP and dashboard jobs on the pull request's file list (#37559) 2026-08-19 18:32:21 -07:00
test_dockerfile_apk_repository.py fix(docker): add public Wolfi apk repo to runtime image (#39033) 2026-09-01 15:11:15 -07:00
test_dockerfile_bedrock_realtime_extra.py fix(docker): install bedrock-realtime extra in monolith proxy images (#39223) 2026-09-01 17:51:55 -07:00
test_dockerfile_non_root.py fix(docker.non_root): use numeric UID 65534 for K8s runAsNonRoot (#26268) 2026-04-22 18:00:04 -07:00
test_e2e_egress_sentinel.py ci(e2e): record the e2e suite weekly and replay it on weekdays with zero egress (#38163) 2026-08-24 23:49:03 -04:00
test_eager_tiktoken_load.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_env_key_doc_gate.py fix(ci): make the env-key doc gate see bare get_secret and get_secret_str reads (#35996) 2026-08-05 14:49:55 -07:00
test_exception_exports.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_exception_header_preservation.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_exception_mapping_request_attribute.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_filter_out_litellm_params.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_fireworks_serverless_model_costs.py Registry audit: Fireworks DeepSeek V4 Flash 0731 pricing, Databricks DeepSeek V4 entries, provider deprecation dates 2026-09-01 13:15:22 +00:00
test_friendli_glm_5_3_flash_model_metadata.py fix(friendli): declare GLM-5.3-Flash reasoning efforts as explicit levels 2026-08-31 13:25:51 -07:00
test_friendli_glm_5_3_model_metadata.py fix(friendli): track GLM-5.3 discounted live pricing and declare effort levels 2026-08-31 13:26:37 -07:00
test_gate_slot_lock.py fix(make): acquire the gate slot before lint setup deps 2026-08-14 21:17:14 -07:00
test_gemini_3_1_flash_lite_image_pricing.py fix(model_cost): dedupe gemini-3.1-flash-lite-image and correct its capabilities 2026-08-21 17:23:47 -07:00
test_gemini_tts_native_audio_pricing.py test: restore model cost map via monkeypatch 2026-08-26 15:34:25 -07:00
test_get_blog_posts.py test(lint): ban blind pytest.raises(Exception) with ruff B017 (#37731) 2026-08-20 18:09:42 -07:00
test_git_hooks.py chore(hooks): enforce Conventional Commits and Conventional Branches (#30174) 2026-06-11 10:00:23 -07:00
test_github_close_low_quality_prs.py test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769) 2026-08-20 20:24:49 -07:00
test_github_review_gate.py feat(agent-shin): automated PR/issue triage, low-quality auto-close, and review-gate label lifecycle (#30433) 2026-06-17 20:42:27 -07:00
test_github_triage_with_llm.py test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769) 2026-08-20 20:24:49 -07:00
test_github_triage_workflows.py chore(ci): close the test-census blind spots and move scripts out of workflows/ (#37586) 2026-08-20 10:07:14 -07:00
test_gpt_5_4_model_metadata.py fix(pricing): correct gpt-5.4-mini and gpt-5.4-nano token limits 2026-07-30 02:43:54 +00:00
test_gpt_5_5_model_metadata.py chore: litellm oss staging160626 (#30527) 2026-06-16 18:23:13 -07:00
test_gpt_image_cost_calculator.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_gpt_realtime_mode.py fix(pricing): add undated azure aliases for gpt-audio-mini and gpt-realtime-mini (#37867) 2026-08-21 18:44:19 -07:00
test_groq_streaming_encoding.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_guardrail_exception_status_codes.py Litellm oss staging (#28161) 2026-05-18 16:27:44 -07:00
test_lazy_imports.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_litellm_params_reserved_keys.py fix(snowflake): transform tool_choice string to object format (#23268) 2026-03-11 01:41:24 +05:30
test_logging.py fix(logging): redact credential query params from the uvicorn access log (#39293) 2026-09-02 15:10:36 -07:00
test_lowest_latency_zero_tokens.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_main.py feat(streaming): carry final response cost on streamed usage by default 2026-08-31 21:47:13 -07:00
test_main_module_header.py Add main module header comment 2026-05-06 00:26:17 +00:00
test_mistral_medium_3_5_model_metadata.py fix: omit thinking.type=disabled for always-on thinking Claude models (#37510) 2026-08-21 10:27:26 -07:00
test_mistral_small_4_0_model_metadata.py fix(model_prices): restore supports_vision on Mistral Small 4.0 entries 2026-08-20 13:54:03 -07:00
test_mistral_zai_glm_5_2_model_metadata.py fix(mistral): correct zai-glm-5-2 limits, add cached-input price and glm-5-2 alias 2026-08-20 10:45:24 -07:00
test_model_block_unblock.py fix(proxy): serialize model reconciles so concurrent model writes stop evicting each other (#36687) 2026-08-12 13:42:26 -07:00
test_model_cost_aliases.py [Feat] - Ishaan main merge branch (#23596) 2026-03-14 09:40:00 -07:00
test_model_param_helper.py style: black format test_model_param_helper.py 2026-04-15 18:18:52 -07:00
test_model_prices_schema.py fix(model_cost): dedupe gemini-3.1-flash-lite-image and correct its capabilities 2026-08-21 17:23:47 -07:00
test_model_response_normalization.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_muse_spark_1_1_model_metadata.py Revert "chore(ci): sync litellm_internal_staging into daily OSS branch (#33337)" (#33339) 2026-07-14 19:32:25 -07:00
test_muse_spark_1_2_model_metadata.py fix: omit thinking.type=disabled for always-on thinking Claude models (#37510) 2026-08-21 10:27:26 -07:00
test_muse_spark_1_3_model_metadata.py feat(model_prices): add meta/muse-spark-1.3 and its contributor tier 2026-09-02 22:05:17 +00:00
test_mutation_report.py fix(ci): stop the mutation report publishing a score it never measured (#37825) 2026-08-21 20:15:52 -07:00
test_nested_drop_params.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_non_chat_routes_open_llm_spans.py fix(otel): emit LLM Call spans for speech, image, moderation, ocr and transcription (#37752) 2026-08-22 11:11:21 -07:00
test_openai_embedding_encoding_format_default.py test(embeddings): move legacy intercepts to the wire for the omitted-format path 2026-08-29 12:04:44 -07:00
test_openai_service_tier_long_context_pricing.py fix(models): absorb open registry PRs: govcloud bedrock and mantle, azure gov, openai tiered long-context, scaleway, together qwen3.8, azure ai cache and kimi k2.7 code, azure mai deprecations 2026-09-02 14:48:51 +00:00
test_pre_commit_lint.py feat(scripts): queue heavy gates behind a machine-wide slot lock 2026-08-14 17:22:32 -07:00
test_prisma_generate_if_needed.py fix(lint): generate the prisma client into the gate-owned venv 2026-08-06 01:54:26 -07:00
test_project_alias_tracking.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_project_tags_pydantic.py test(lint): ban blind pytest.raises(Exception) with ruff B017 (#37731) 2026-08-20 18:09:42 -07:00
test_proxy_auth.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_rag_openai_ingestion.py chore: litellm oss staging (#30745) 2026-06-18 13:55:35 -07:00
test_rate_limit_error_unification.py test(rate-limits): drop the removed data kwarg from the v3 dynamic limiter raise-branch test 2026-07-30 15:20:44 -07:00
test_redact_string_in_error_paths.py fix(proxy): stop leaking internal exception details to clients (#39380) 2026-09-02 17:32:00 -07:00
test_redis.py fix(redis): coerce env var string types and fix param discovery through decorator wrappers (#30644) 2026-08-31 20:51:31 -07:00
test_register_model_custom_pricing.py fix(cost): bill off-peak rates for deployments that set only off_peak_pricing 2026-09-01 12:14:46 -07:00
test_register_model_zero_cost_persistence.py chore(oss): litellm oss staging 150626 (#30463) 2026-06-16 12:06:41 -07:00
test_replicate_model_key_format.py fix(model-prices): correct replicate model key typo (#34800) 2026-08-05 16:37:44 -07:00
test_responses_api_bridge_non_stream.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_responses_id_security.py test(responses): drive streamed-id regression via production ResponseCompletedEvent shape 2026-08-26 01:52:01 -07:00
test_responses_streaming_container_ownership.py chore(oss): litellm oss staging 150626 (#30463) 2026-06-16 12:06:41 -07:00
test_retrieve_batch_bedrock_dispatch.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router.py Merge pull request #39239 from BerriAI/litellm_lit_6342_claude_subagent_router 2026-09-02 17:05:55 -07:00
test_router_block_helpers.py feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00
test_router_exception_redaction.py test(router): let monkeypatch own expose_router_debug_in_errors (#37848) 2026-08-22 09:02:40 -07:00
test_router_google_genai.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_router_model_cost_isolation.py fix(cost-map): retry transient boot fetch failures and recover config deployments dropped by a stale cost map (#39230) 2026-09-01 17:49:06 -07:00
test_router_order_fallback.py test(router): inject the upstream client instead of mutating litellm.aclient_session 2026-09-01 15:14:56 -07:00
test_router_per_deployment_num_retries.py fix(router): honor request-level num_retries over a deployment's litellm_params value (#35483) 2026-08-01 13:51:29 -07:00
test_router_redis_init.py fix: handle deprecated 'redis_db' arg to prevent crash (#19808) 2026-02-02 18:18:05 +05:30
test_router_retry_backoff_headers.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_router_retry_non_retryable_errors.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router_retry_policy_update.py fix: preserve shared optional callbacks 2026-09-02 03:28:04 +00:00
test_router_silent_experiment.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_router_streaming_fallback_metadata.py chore: litellm oss staging (#30968) 2026-06-23 07:31:44 -07:00
test_router_weighted_failover.py test(lint): ban blind pytest.raises(Exception) with ruff B017 (#37731) 2026-08-20 18:09:42 -07:00
test_ruff_strict_gate.py refactor(lint): graduate the 35 zero-violation strict rules into ruff.toml 2026-08-07 23:10:33 -07:00
test_sambanova_model_metadata.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_secret_redaction.py fix(proxy): stop leaking internal exception details to clients (#39380) 2026-09-02 17:32:00 -07:00
test_select_ui_test_scope.py fix(ci): run the full dashboard suite when a change reaches outside src/ (#37563) 2026-08-19 23:09:03 -07:00
test_service_logger.py fix: missing span for guardrail passthrough (#29552) 2026-06-03 01:25:15 +00:00
test_setup_wizard.py test: test 2026-03-28 19:17:38 -07:00
test_shared_session_integration.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_ssl_verify_unit.py refactor(bedrock): remove the dead BedrockLLM invoke code path 2026-07-29 20:25:36 -07:00
test_stream_chunk_builder_annotations.py fix: merge annotations from all streaming chunks in stream_chunk_builder 2026-03-15 14:20:45 +05:30
test_stream_chunk_builder_citations.py fix(streaming): join block-list citation deltas without extra nesting 2026-08-28 13:56:07 -07:00
test_stream_chunk_builder_images.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_streaming_connection_cleanup.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_sync_together_ai_models.py fix(together_ai): stop writing context_length as max_output_tokens in the serverless sync 2026-08-29 15:26:44 -07:00
test_system_message_format_bug.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_test_quality_gate.py feat(ci): gate patching of SDK internals in tests as TQ008 (#37787) 2026-08-22 22:54:30 -07:00
test_thinking_enabled.py test: drop restating comment and wrap long call in thinking tests 2026-08-18 19:55:22 -07:00
test_together_ai_model_metadata.py Merge pull request #38820 from BerriAI/litellm_fix_together_sync_output_ceiling 2026-08-29 16:44:56 -07:00
test_type_check_gate.py fix(lint): retire the single-slot base-counts cache 2026-08-06 02:23:52 -07:00
test_type_discipline_gate.py fix(lint): pick the merge-aware base so in-progress merges are not blamed for base drift 2026-08-04 17:58:41 -07:00
test_utils.py refactor(utils): remove the dead get_api_key provider-key resolver (#39260) 2026-09-02 15:06:36 -07:00
test_utils_module_docstring.py Add utils module docstring 2026-05-06 00:42:49 +00:00
test_uuid_helper.py
test_vcr_safe_body_matcher.py test: stabilize batch VCR coverage and stop live upload/network leaks (#29477) 2026-06-02 16:11:52 -07:00
test_video_generation.py fix(registry): add vertex veo 3.1 resolution tier pricing per vertex pricing page 2026-09-01 10:15:18 -07:00
test_with_dashboard_node.py fix(bootstrap): fail fast when nvm cannot activate the pinned node 2026-08-04 21:18:58 -07:00
test_xai_grok_4_3_model_metadata.py feat(xai): add grok-4.3 and grok-4.3-latest to model_prices_and_conte… (#27154) 2026-05-07 09:06:56 -07:00
test_xai_responses_auto_routing.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00

readme.md

Testing for litellm/

This directory 1:1 maps the the litellm/ directory, and can only contain mocked tests.

The point of this is to:

  1. Increase test coverage of litellm/
  2. Make it easy for contributors to add tests for the litellm/ package and easily run tests without needing LLM API keys.

File name conventions

  • litellm/proxy/test_caching_routes.py maps to litellm/proxy/caching_routes.py
  • test_<filename>.py maps to litellm/<filename>.py