Add usage example with concrete model entry, explanation of load-time
expansion, and cross-reference to model_alias_map to clarify the
difference between the two features.
The _list_has_thinking guard only checked for type == "thinking" but
Anthropic can also return redacted_thinking blocks (safety-filtered).
These are also accumulated in thinking_blocks, so the same duplication
bug would occur with redacted thinking content.
* fix(streaming): map unknown finish_reason values to finish_reason_unspecified
Some LLM providers return non-standard finish_reason values that are not
in the OpenAIChatCompletionFinishReason Literal (e.g. ZhipuAI/GLM returns
'network_error' when a streaming error occurs mid-response).
Previously map_finish_reason() fell through with return finish_reason,
passing the unknown value directly to Choices.__init__() which calls
Pydantic validation. This caused a ValidationError that was caught by
stream_chunk_builder() and re-raised as the misleading:
litellm.APIError: Error building chunks for logging/streaming usage calculation
Fix: after all known provider-specific mappings, check if the value is in
the valid set (stop, length, tool_calls, content_filter, function_call,
guardrail_intervened, eos, finish_reason_unspecified, malformed_function_call).
Any value not in this set is mapped to 'finish_reason_unspecified' instead
of being returned as-is.
This is consistent with how other unknown stop reasons (e.g. Vertex AI's
FINISH_REASON_UNSPECIFIED) are already handled.
* refactor: use get_args(OpenAIChatCompletionFinishReason) for valid set
Per code review feedback: replace the hardcoded _valid_finish_reasons set
with a module-level frozenset derived dynamically from the source-of-truth
Literal type via typing.get_args(). This ensures the valid-reason check
stays in sync automatically when new finish reasons are added to the Literal,
and avoids recreating the set on every streaming chunk call.
* test(map_finish_reason): add unit tests and warning log for unknown finish reasons
- Add TestMapFinishReason class in test_core_helpers.py covering:
- All known OpenAI-native values pass through unchanged (parametrized)
- Provider-specific mappings: Anthropic, Cohere, Vertex AI
- Unknown/provider-specific values map to 'finish_reason_unspecified'
- Regression test for ZhipuAI/GLM-5 'network_error' case
- Add verbose_logger.warning() in map_finish_reason() when an unknown
finish_reason is encountered, so operators can track which providers
return non-standard values
When assistant content is already a list containing thinking blocks
inline (not str/None), SEQUENTIAL MODE was still prepending all
thinking_blocks from provider_specific_fields, causing duplication
and breaking Anthropic's position-dependent signature verification.
Now detects if the content list already has thinking blocks and skips
the extend(thinking_blocks) to preserve the original interleaved order.
Addresses the correctness gap identified by Greptile review where
list-content messages bypass INTERLEAVED MODE.
Fixes: https://github.com/BerriAI/litellm/issues/23047
* fix: add missing indexes for top CPU-consuming queries
Add indexes to eliminate full table scans on two of the top 5 queries
by CPU usage:
1. LiteLLM_VerificationToken(key_alias) — for ORDER BY key_alias ASC
queries when listing verification tokens
2. LiteLLM_SpendLogs(user, startTime) — for WHERE user = $1 AND
startTime BETWEEN $2 AND $3 GROUP BY queries on the spend logs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use CREATE INDEX CONCURRENTLY to avoid table locks
Both indexes are now created with CONCURRENTLY and IF NOT EXISTS
to avoid blocking writes on large production tables.
Uses -- SkipTransactionBlock for Prisma migrate compatibility.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Gemini 2.0+ natively accepts JSON Schema in tool parameters, including
bare {} (TYPE_UNSPECIFIED), anyOf with null, and lowercase types. The
existing _build_vertex_schema pipeline was coercing {} to {"type": "object"},
breaking JsonValue/Any field semantics (issue #22391).
Add _build_vertex_schema_for_gemini_2() that only resolves $ref (which
Gemini doesn't support in tools) and filters unsupported fields. Use it
for Gemini 2.0+ models, keeping the full transform for Gemini 1.5.
When a fetch fails, the button now exits the loading state instead of
staying stuck on "Fetching" indefinitely.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Show a Fetch/Fetching button next to "Showing X of Y results" that acts as
both a manual refetch trigger and a loading indicator. The "Loading keys..."
message now only appears on initial load; subsequent refetches keep the table
visible with stale data (via React Query's keepPreviousData).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix case-insensitive tool name matching in _tool_name_matches() so that
OpenAPI operationIds (camelCase) match lowercase registered tool names
when filtering by allowed_tools
- Fix get_base_url() to resolve relative server URLs (e.g. /api/v3) by
deriving full base URL from spec_path when OpenAPI spec has relative URLs
- Add tests for case-insensitive matching and filter_tools_by_allowed_tools
Made-with: Cursor
`all_models = user_api_key_dict.models` was creating an alias, so
`_get_models_from_access_groups` (which uses `.pop()`/`.extend()`) would
mutate the cached object in-place. Now both `.models` and `.team_models`
assignments create copies via `list()`.
Added test to verify the input is not mutated.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds dedup to get_key_models and get_team_models to prevent duplicate
entries when access group member models overlap with proxy_model_list.
Removes dead assignment of all_models in get_team_models.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a team has "all-proxy-models", the model list expansion now includes
model access group names so they appear in the UI key creation form.
Also fixes get_key_models not forwarding include_model_access_groups to
_get_models_from_access_groups, and removes unused _unfurl_all_proxy_models.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix perform_redaction to handle dict representation of ModelResponse (from model_dump())
- Preserve full choices structure when redacting, redact content/audio in place
- Add _redact_standard_logging_object helper for standard_logging_object field
- Update test_logging_redaction_e2e_test assertions to expect choices format
- Add charity_engine to provider_endpoints_support.json
Fixes: test_standard_logging_payload, test_standard_logging_payload_audio
Made-with: Cursor
Extend the "Proxy database access" section with guidelines to prevent
common DB performance issues, tailored to actual Prisma usage patterns
in the litellm codebase: N+1 queries, client-side processing, batching
writes, bounding result sets, select on wide tables, index coverage,
and schema file sync.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
