yuneng-jiang 8ca744036a [Fix] Malformed messages returning 500 instead of 400 ...

The existing AttributeError detection in proxy error handling only
checked one level deep in the exception chain (__cause__, __context__,
original_exception). In practice, the AttributeError from malformed
messages gets wrapped in multiple layers (AttributeError ->
OpenAIException -> APIConnectionError), so the check never found it.

Extracted the check into _has_attribute_error_in_chain() which walks
the full exception chain recursively (depth-capped at 10 to prevent
infinite loops from circular references).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-12 23:01:25 -07:00

..

_experimental/mcp_server

fix(ci): skip tests requiring openai>=2.x and MCP M2M oauth2_flow

2026-03-13 01:09:56 +00:00

agent_endpoints

fix(tests): restore litellm_params=None on mock agent in a2a invoke test (#23125)

2026-03-09 07:16:02 -07:00

anthropic_endpoints

…

auth

merge: resolve conflicts with upstream staging (bedrock + mcp tests)

2026-03-12 13:40:16 -03:00

client

…

common_utils

Merge pull request #20688 from BerriAI/litellm_budget_tier_enforcement_for_keys

2026-03-06 20:44:58 -08:00

db

Revert "feat(proxy): add Prisma DB pool and engine health metrics to Promethe…"

2026-03-09 14:55:11 -07:00

discovery_endpoints

Support auto_redirect_ui_login_to_sso in config.yaml general_settings

2026-03-11 11:34:17 -07:00

experimental/mcp_server

…

google_endpoints

…

guardrails

merge: resolve conflicts between main and litellm_oss_staging_03_11_2026

2026-03-12 09:38:31 -03:00

health_endpoints

Prisma DB Failure Detection and Self-Healing (#21059)

2026-03-05 13:44:49 -08:00

hooks

fix(proxy): make async_post_call_response_headers_hook consistent across all endpoints (#22985)

2026-03-12 08:51:00 -07:00

image_endpoints

…

management_endpoints

fix: stabilize 5 CI test failures

2026-03-13 01:03:35 +00:00

management_helpers

[Docs] Fix "Page Not Found" link for Anthropic endpoint (#23349)

2026-03-11 20:17:41 +05:30

middleware

…

openai_files_endpoint

CircleCI test stability (#23055)

2026-03-07 15:19:39 -08:00

pass_through_endpoints

fix: stabilize 5 CI test failures

2026-03-13 01:03:35 +00:00

policy_engine

…

prompts

…

public_endpoints

…

rag_endpoints

…

realtime_endpoints

address greptile review feedback (greploop iteration 2)

2026-03-12 18:53:22 +05:30

response_api_endpoints

…

spend_tracking

merge: resolve conflicts with upstream staging (bedrock + mcp tests)

2026-03-12 13:40:16 -03:00

test_configs

…

ui_crud_endpoints

[Fix] PATCH /update/ui_settings now merges with existing record instead of overwriting

2026-03-05 15:49:40 -08:00

vector_store_endpoints

…

__init__.py

…

conftest.py

…

test_aiohttp_cleanup_closed.py

…

test_api_key_masking_in_errors.py

…

test_audio_speech_prometheus_hooks.py

…

test_batch_expiry.py

fix(proxy): improve team expiry enforcement validation

2026-03-03 17:29:39 -08:00

test_batch_metadata_none_fix.py

…

test_caching_routes.py

…

test_chat_completion_metadata.py

…

test_common_request_processing.py

[Fix] Malformed messages returning 500 instead of 400

2026-03-12 23:01:25 -07:00

test_custom_proxy.py

…

test_empty_model_list.py

…

test_enforce_user_param.py

…

test_fallback_management_endpoints.py

…

test_fastapi_offline_routes.py

…

test_health_check_functions.py

…

test_health_check_max_tokens.py

…

test_litellm_pre_call_utils.py

Bug Fix: auto-inject prompt caching support for Gemini models (#21881)

2026-03-03 20:25:35 -08:00

test_model_dump_with_preserved_fields.py

…

test_model_id_header_propagation.py

…

test_openapi_schema_validation.py

Reapply "feat: add model_cost aliases expansion support"

2026-03-12 13:36:57 -03:00

test_prometheus_cleanup.py

…

test_proxy_cli.py

merge: resolve conflicts between main and litellm_oss_staging_03_11_2026

2026-03-12 09:38:31 -03:00

test_proxy_server.py

…

test_proxy_types.py

…

test_proxy_utils.py

[Feat[ extends OAuth2 M2M authentication support to info routes (/key/info, /team/info, /user/info, /model/info) (#22713)

2026-03-06 17:29:25 -08:00

test_pyroscope.py

…

test_response_model_sanitization.py

feat(azure_ai): show actual model used in Azure Model Router response

2026-03-12 11:41:19 +05:30

test_route_a2a_models.py

…

test_route_llm_request.py

…

test_shared_health_check.py

…

test_spend_log_cleanup.py

Fix spend log cleanup: lock tracking, integer retention, skip log level

2026-03-03 10:12:08 -08:00

test_swagger_chat_completions.py

…

test_team_member_update.py

…

test_tools_allowlist_enforcement.py

Bug Fix: auto-inject prompt caching support for Gemini models (#21881)

2026-03-03 20:25:35 -08:00

test_update_llm_router_resilience.py

…