Background health checks now feed deployment health state into the
router candidate-filtering pipeline. Unhealthy deployments are excluded
proactively instead of waiting for request failures to trigger cooldown.
Gated by `enable_health_check_routing: true` in general_settings.
Off by default — zero behavior change for existing users.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove HTTP_PROXY/HTTPS_PROXY from blocklist (legitimately used in corporate envs)
- Add NO_PROXY/no_proxy to blocklist (prevents bypassing proxy monitoring)
- Remove dead code in _is_valid_user_id (space exception was unreachable)
- Update tests accordingly
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add input validation to get_user_id_from_request (length limit, control char rejection) and a blocklist of dangerous environment variable keys in _load_environment_variables to prevent PATH/LD_PRELOAD/PYTHONPATH override via config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wildcard openrouter/* deployments pass custom_llm_provider=openrouter with
the full openrouter/provider/model id; OpenRouter expects provider/model.
Strip the outer openrouter/ only when the remainder contains a slash so
native ids like openrouter/auto stay intact.
Adds regression test for proxy wildcard path.
Made-with: Cursor
Reset _ENABLE_TEAM_STALE_ALIAS_BYPASS to None in both test functions
to ensure test isolation and prevent ordering-dependent failures
Made-with: Cursor
- Cache LITELLM_ENABLE_TEAM_STALE_ALIAS_BYPASS at module level to avoid hot-path secret lookups
- Add clarifying comments for should_include_deployment team isolation logic
- Add negative assertion for update_team.assert_not_called() in test
- Add docstring clarification for _get_team_deployments helper pattern
- Add explicit assertion message in test_get_model_list_alias_optimization
Made-with: Cursor
- Add deduplication guard in _update_team_model_index to prevent duplicate indices
- Add wildcard comment in map_team_model for clarity
- Add monkeypatch to test_team_alias_stale_bypass_disabled_by_default for determinism
- Extract _get_team_deployments helper to centralize DB access pattern
- Add clarifying comments for team_public_model_name assignment ordering
Made-with: Cursor
- Use O(1) team index lookup instead of map_team_model in alias guard
- Fix MockPrismaClient to validate where clause filters
- Add comment explaining DB query trade-off for team deployments
Made-with: Cursor
- Skip model_aliases rewrite if model resolves to team deployments
- Add test coverage for sibling-preservation branch
- Update MockPrismaClient to support sibling deployment scenarios
Made-with: Cursor
- Add clarifying comments to test assertions
- Query prisma DB instead of in-memory router to avoid stale state
- Prevents incorrect deletion of old public name when siblings exist
Made-with: Cursor
Remove team model_alias rewrites and resolve team deployments by team_public_model_name with team_id so sibling deployments stay in the routing candidate pool, with explicit logs showing candidate selection before load balancing.
Made-with: Cursor
Use a deterministic internal model_name for team-scoped deployments so sibling deployments with the same public model share a routing group. This makes team alias writes idempotent and preserves multi-deployment failover/load balancing behavior.
Made-with: Cursor
- Add cancel/retrieve overrides in AzureOpenAIFineTuningAPI to normalize responses
- Expand _AZURE_STATUS_MAP to handle all known Azure statuses
- Add "pending" to OpenAIFileObject.status allowed values
- Fix async test mock to return awaitable LiteLLMFineTuningJob
- Add test_openai_file_object_accepts_pending_status
Made-with: Cursor
- Move trainingType injection to AzureOpenAIFineTuningAPI handler
- Guard normalization with is_azure flag to only apply to Azure responses
- Override acreate_fine_tuning_job in Azure handler to use is_azure=True
- Update test to directly test _ensure_training_type method
- Add test for OpenAI unchanged behavior
Made-with: Cursor
- Default trainingType=1 for Azure when omitted to avoid misleading "base model does not support fine-tuning" error
- Normalize Azure FineTuningJob responses (pending→queued, null fields→defaults) to match OpenAI schema
- Add pending status support to OpenAIFileObject for Azure file uploads
- Add test coverage for trainingType default and response normalization
Made-with: Cursor
Addresses Greptile review feedback: replace direct litellm.model_cost
lookup with the standard _supports_factory infrastructure used by
supports_reasoning, supports_native_streaming, etc.
- Add supports_native_structured_output() utility in litellm/utils.py
- Add supports_native_structured_output field to ModelInfoBase type
- Wire field into _get_model_info_helper return dict
- Delegate from Bedrock _supports_native_structured_outputs to utility
- Add field to JSON schema validator in test_utils.py
Wrap cost-map-dependent tests in try/finally to restore
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] and litellm.model_cost,
preventing test-ordering sensitivity.
Integration testing confirmed gemma-3 (4b/12b/27b) ignores the JSON
schema and returns free text, and nemotron-nano (9b/12b) errors with
"Tool calling is not supported in streaming mode" even on sync calls.
Remove the flag so these models fall back to the tool-call approach.
Also fix test assertions to match (nemotron-nano-3-30b is supported,
gemma-3 and nemotron-nano-12b are not).
Move the source of truth for which Bedrock models support native structured
outputs (outputConfig.textFormat) from a hardcoded substring set
(BEDROCK_NATIVE_STRUCTURED_OUTPUT_MODELS) to the cost JSON via a new
"supports_native_structured_output" flag. This makes it possible to add
support for new models (including Claude Sonnet 4.6, which was missing)
by updating the JSON alone, with no code changes needed.
Instead of returning a 400 error when return_to is passed without
control_plane_url configured, silently ignore it and proceed with
the normal same-origin SSO flow.
- Update test_anthropic_via_responses_api expected_events to include
CONTENT_PART_ADDED between OUTPUT_ITEM_ADDED and OUTPUT_TEXT_DELTA
- Add TestEnsureOutputItemContentPartAdded with 3 mock tests:
message item emits content_part.added, reasoning item does not,
and the event is only emitted once
Verify that spend_logs_metadata is correctly merged into combined_metadata
and flows through to Prometheus custom labels. Tests cover: basic extraction,
precedence when keys overlap, all three metadata sources combined, and None
handling.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Thread project_alias alongside project_id through the metadata pipeline so
callbacks receive the human-readable project name. DRY up duplicate metadata
dict construction in proxy_track_cost_callback and pass_through_endpoints by
reusing get_sanitized_user_information_from_key — future metadata fields only
need adding in one place.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Two independent bugs prevented post-call OpenAI Moderation guardrail
results from reaching downstream logging callbacks (Langfuse, Datadog).
Bug 1: process_output_response() created a throwaway request_data dict,
so guardrail info written by @log_guardrail_information was discarded.
Fixed by threading the real request_data from the unified guardrail
dispatcher through all 13 BaseTranslation handlers, with litellm_metadata
injection preserved for third-party guardrails (Zscaler, Prompt Security).
Also extended to process_output_streaming_response for consistency.
Bug 2: The @log_guardrail_information decorator collapsed the full
moderation API response (categories, scores, flagged status) to "allow".
Fixed by overriding _process_response/_process_error on
OpenAIModerationGuardrail to stash and log the full response, following
the established Model Armor pattern.
