mirror of https://github.com/tiennm99/litellm.git synced 2026-08-04 16:26:30 +00:00

Files

T

504c70f4e0 fix(responses-api): return finish_reason='tool_calls' when response.completed contains function_call items (#19745 )

When using the Responses API (e.g., Azure gpt-5.1-codex-mini), the response.completed
event was always returning finish_reason='stop', even when the response contained
function_call items in its output. This caused agents like OpenCode to incorrectly
conclude the stream ended without tools to execute, breaking tool/function calling
workflows.

The fix inspects the response.output field in the response.completed event to determine
the correct finish_reason:
- 'tool_calls' when output contains function_call items
- 'stop' otherwise (text-only responses)

Added tests to verify:
- response.completed with function_call output returns finish_reason='tool_calls'
- response.completed with message-only output returns finish_reason='stop'
- response.completed with empty output returns finish_reason='stop' (backward compat)

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>

2026-02-16 09:19:57 -08:00

a2a_protocol

[Fix] A2a Agent Gateway Fixes - A2A agents deployed with localhost/internal URLs in their agent cards (e.g., http://0.0.0.0:8001/) (#20604 )

2026-02-06 15:02:34 -08:00

anthropic_interface/exceptions

[bug fix] do not fallback to token counter if disable_token_counter is enabled (#19041 )

2026-01-13 16:53:38 -08:00

caching

fix(cache): prevent DualCache async batch check-then-act race (#20986 )

2026-02-13 18:32:41 +05:30

completion_extras

fix(responses-api): return finish_reason='tool_calls' when response.completed contains function_call items (#19745 )

2026-02-16 09:19:57 -08:00

containers

Fix test_error_handling_integration for parallel test execution

2026-02-15 13:08:47 -03:00

enterprise

fix(tests): Fix sendgrid email tests to properly mock httpx client (#20628 )

2026-02-07 09:19:02 -08:00

expected_responses_api_request

[Feat] Adds support for server-side compaction on the OpenAI Responses API context_management (#21058 )

2026-02-12 10:00:30 -08:00

experimental_mcp_client

fix: FLAKY tests

2026-01-24 11:13:44 -08:00

google_genai

litellm_fix_mapped_tests_core: fix test isolation and mock injection issues (#20209 )

2026-01-31 17:53:54 -08:00

images

…

integrations

fix(test): restore Langfuse client counter in test cleanup

2026-02-15 14:11:24 -03:00

interactions

…

litellm_core_utils

refactor: simplify cache clearing to avoid over-engineering

2026-02-15 20:36:24 -03:00

llms

Merge pull request #21217 from BerriAI/fix/anthropic-structured-output-test

2026-02-15 20:20:49 -03:00

passthrough

…

proxy

Generic Guardrails: Add a configurable fallback to handle generic guardrail endpoint connection failures (#21245 )

2026-02-16 08:34:21 -08:00

responses

fix: preserve metadata for custom callbacks on codex/responses path (… (#21243 )

2026-02-16 08:59:38 -08:00

router_strategy

fix(router): remove repeated provider parsing in budget limiter hot path (#21043 )

2026-02-12 20:05:55 -08:00

router_utils

…

secret_managers

Merge pull request #20481 from Harshit28j/litellm_aws_rotation_fix

2026-02-12 09:36:10 +05:30

test_router

feat: enforce model-level TPM/RPM limits (enforce_model_rate_limits) … (#19230 )

2026-02-02 18:18:46 +05:30

types

Add pipeline flow builder UI for guardrail policies (#21188 )

2026-02-13 20:06:03 -08:00

vector_stores

litellm_fix_mapped_tests_core: fix test isolation and mock injection issues (#20209 )

2026-01-31 17:53:54 -08:00

__init__.py

…

conftest.py

…

log.txt

…

readme.md

…

test_a2a_registry_lookup.py

[Feat] Use A2A registered agents with /chat/completions (#20362 )

2026-02-03 15:25:38 -08:00

test_acompletion_session_reuse_e2e.py

…

test_add_deployment_no_master_key.py

…

test_aembedding_session_reuse_e2e.py

…

test_anthropic_beta_headers_filtering.py

Make tests run with local beta header mapping json

2026-02-13 22:31:42 +05:30

test_azure_video_router.py

…

test_claude_haiku_4_5_config.py

…

test_claude_opus_4_6_config.py

Fix merge conflicts

2026-02-06 18:29:14 +05:30

test_constants.py

[Release - 02/10/2026] v1.81.10-nightly

2026-02-10 16:26:30 -08:00

test_container_router.py

…

test_cost_calculation_log_level.py

…

test_cost_calculator.py

Merge branch 'main' into litellm_oss_staging_01_28_2026

2026-01-29 17:39:42 +05:30

test_deepseek_model_metadata.py

fix(model-info): sync DeepSeek model metadata and add bare-name fallback (#20885 )

2026-02-11 12:48:10 +05:30

test_eager_tiktoken_load.py

fix(main): use local tiktoken cache in lazy loading (#19774 )

2026-01-27 18:16:58 -08:00

test_exception_exports.py

fix: export PermissionDeniedError from litellm.__init__

2026-02-11 13:39:19 +01:00

test_exception_header_preservation.py

fix: preserve llm_provider-* headers in error responses (#19020 )

2026-01-14 22:49:39 +05:30

test_exception_mapping_request_attribute.py

…

test_filter_out_litellm_params.py

…

test_gpt_image_cost_calculator.py

Fix gpt-image-1.5 cost calculation not including output image tokens (#19515 )

2026-01-22 19:42:15 -08:00

test_groq_streaming_encoding.py

…

test_lazy_imports.py

…

test_logging.py

fix:Parse embedded JSON in the message field of logs (#20366 )

2026-02-10 16:13:33 +05:30

test_lowest_latency_zero_tokens.py

…

test_main.py

refactor(test): remove redundant cache flush from test_openai_env_base

2026-02-15 14:24:38 -03:00

test_model_param_helper.py

perf: cache _get_relevant_args_to_use_for_logging() at module level (#20077 )

2026-02-02 10:54:49 -08:00

test_model_response_normalization.py

Normalize OpenAI SDK BaseModel choices/messages to avoid Pydantic serializer warnings (#18972 )

2026-01-14 03:40:11 +05:30

test_nested_drop_params.py

…

test_redis.py

…

test_responses_api_bridge_non_stream.py

fix: Pydantic will fail to parse it because cached_tokens is required but not provided

2026-01-28 11:51:26 +05:30

test_responses_id_security.py

fix(ui): use non-streaming method for endpoint v1/a2a/message/send in… (#19025 )

2026-01-14 03:29:10 +05:30

test_router_google_genai.py

…

test_router_model_cost_isolation.py

[Fix] prevent shared backend model key from being polluted by per-deployment custom pricing (#20679 )

2026-02-09 19:38:44 -08:00

test_router_per_deployment_num_retries.py

Bugfix/19481 num retries env var type (#19507 )

2026-01-22 19:39:58 -08:00

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_silent_experiment.py

litellm_fix(test): fix router silent experiment tests to properly mock async functions (#20140 )

2026-01-31 07:39:05 -08:00

test_router.py

fix(router): propagate model-level tags from config to SpendLogs (#20769 )

2026-02-10 15:52:52 -08:00

test_shared_session_integration.py

…

test_ssl_verify_unit.py

BUMP Enterprise PIP

2026-02-14 13:40:48 -08:00

test_system_message_format_bug.py

…

test_utils.py

[Fix] handle metadata=None in SDK path retry/error logic (utils.py) (#20873 )

2026-02-10 22:03:33 -08:00

test_uuid_helper.py

…

test_video_generation.py

fix(test): add mock isolation for test_video_content_handler_uses_get_for_openai

2026-02-15 13:34:19 -03:00

test_xai_responses_auto_routing.py

Add routing of xai chat completions to responses when web search options is present

2026-01-30 14:15:35 +05:30

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:

Increase test coverage of litellm/
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

readme.md

Testing for litellm/

File name conventions

Testing for `litellm/`