mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-29 06:33:28 +00:00
95e321cc75
ZAIChatConfig.get_supported_openai_params omitted response_format, so litellm either raised UnsupportedParamsError or, under drop_params, dropped the schema and returned HTTP 200 with prose. The silent variant is the damaging one: the failure only surfaces in a downstream JSON parser. GLM ignores response_format upstream but does honour a forced tool call, which is what BaseConfig._add_response_format_to_tools already builds for azure and fireworks_ai. Wiring zai into it is not enough on its own: that helper sets the internal json_mode flag, and zai reaches the OpenAI SDK handler, which passed the flag straight through to Completions.create() as an unexpected keyword argument. azure solved the same problem by popping json_mode and threading convert_tool_call_to_json_mode into its response conversion, so openai.py now does the same and the tool call is unwrapped back into message.content. The translation is skipped when it could not be unwrapped again: streaming responses, and requests that already carry caller-supplied tools, where forcing json_tool_call would hijack them. In both cases response_format is left to pass through as before. Also stops _add_response_format_to_tools mutating the caller's tools list. _map_openai_params aliases that list into optional_params, so the previous setdefault plus append wrote into the list the caller passed to completion(), accumulating a duplicate json_tool_call on every turn of an agent loop. azure and fireworks_ai were exposed to this too. Fixes: BerriAI/litellm#37720 Signed-off-by: Alexander Chernov <alexander@chernov.it> |
||
|---|---|---|
| .. | ||
| agent_tests | ||
| audio_tests | ||
| base_sdk_tests | ||
| basic_proxy_startup_tests | ||
| batches_tests | ||
| benchmarks | ||
| code_coverage_tests | ||
| documentation_tests | ||
| e2e | ||
| enterprise | ||
| guardrails_tests | ||
| image_gen_tests | ||
| integration | ||
| litellm/proxy/_experimental/mcp_server | ||
| litellm-proxy-extras | ||
| litellm_utils_tests | ||
| llm_responses_api_testing | ||
| llm_translation | ||
| load_tests | ||
| local_testing | ||
| logging_callback_tests | ||
| mcp_tests | ||
| multi_instance_e2e_tests | ||
| ocr_tests | ||
| openai_endpoints_tests | ||
| otel_tests | ||
| pass_through_tests | ||
| pass_through_unit_tests | ||
| proxy_admin_ui_tests | ||
| proxy_behavior | ||
| proxy_e2e_anthropic_messages_tests | ||
| proxy_migration_tests | ||
| proxy_security_tests | ||
| proxy_unit_tests | ||
| router_unit_tests | ||
| search_tests | ||
| spend_tracking_tests | ||
| store_model_in_db_tests | ||
| test_litellm | ||
| unified_google_tests | ||
| vector_store_tests | ||
| windows_tests | ||
| __init__.py | ||
| _fake_openai_endpoint_server.py | ||
| _flush_vcr_cache.py | ||
| _live_test_helpers.py | ||
| _openai_record_replay_proxy.py | ||
| _vcr_conftest_common.py | ||
| _vcr_redis_persister.py | ||
| _wait_helpers.py | ||
| _ws_vcr.py | ||
| eval_swe_bench.py | ||
| fake_openai_endpoint.py | ||
| gettysburg.wav | ||
| large_text.py | ||
| openai_batch_completions.jsonl | ||
| pyrightconfig.json | ||
| README.MD | ||
| test_anthropic_compaction_usage.py | ||
| test_budget_management.py | ||
| test_callbacks_on_proxy.py | ||
| test_debug_warning.py | ||
| test_default_encoding_non_root.py | ||
| test_end_users.py | ||
| test_fallbacks.py | ||
| test_gpt5_azure_temperature_support.py | ||
| test_health.py | ||
| test_keys.py | ||
| test_litellm_proxy_responses_config.py | ||
| test_logging.conf | ||
| test_models.py | ||
| test_new_vector_store_endpoints.py | ||
| test_openai_endpoints.py | ||
| test_organizations.py | ||
| test_otel_thread_leak.py | ||
| test_presidio_latency.py | ||
| test_proxy_server_non_root.py | ||
| test_ratelimit.py | ||
| test_resource_cleanup.py | ||
| test_service_logger_otel.py | ||
| test_spend_logs.py | ||
| test_team.py | ||
| test_team_logging.py | ||
| test_team_members.py | ||
| test_users.py | ||
In total litellm runs 1000+ tests
[02/20/2025] Update:
To make it easier to contribute and map what behavior is tested,
we've started mapping the litellm directory in tests/test_litellm
This folder can only run mock tests.