* fix:fix: prompt_cache_key OAI + Azure OpenAI
* test_prompt_cache_key_supported
* test_azure_openai_with_prompt_cache_key
* fix: remove unnecessary async from test_azure_openai_with_prompt_cache_key
Addresses Greptile feedback: litellm.completion() is synchronous, so
async def is unnecessary and would silently pass without running.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove unused filter_and_transform_beta_headers imports
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test_azure_openai_with_prompt_cache_key
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: _should_use_api_key_header
* test_azure_ai_validate_environment_with_api_key
* fix: remove unused top-level RouteChecks import
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add missing env keys to config_settings reference
Add MODEL_COST_MAP_MIN_MODEL_COUNT, MODEL_COST_MAP_MAX_SHRINK_RATIO,
and MAX_POLICY_ESTIMATE_IMPACT_ROWS to the environment variables
reference table.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
PermissionDeniedError (403) is defined in litellm/exceptions.py but was
never added to the import block in litellm/__init__.py. This makes it
the only standard HTTP error exception not accessible as
litellm.PermissionDeniedError, forcing users to import from
litellm.exceptions directly.
Fixes#20959
1. Cross-account false match: Added _parse_arn_account_and_role_name()
helper that compares partition + account ID + role name (not just
role name) to prevent same-name-different-account false matches.
2. SSL verify: _is_already_running_as_role() now passes ssl_verify to
the STS client via self._get_ssl_verify(), consistent with all other
boto3 client creation in this module.
3. Overbroad AccessDenied fallback: The catch in _auth_with_aws_role now
only falls back to ambient credentials when _is_already_running_as_role
positively confirms the caller is the target role. Genuine trust-policy
or permission misconfigurations are re-raised.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
When aws_role_name is configured but the environment (ECS task role, EC2 instance
profile) is already running as that role, AssumeRole is unnecessary and can fail
with AccessDenied. This adds same-role detection for ECS/EC2 (extending existing
IRSA support) and a fallback to ambient credentials when AssumeRole returns
AccessDenied.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Arize Phoenix and Arize loggers now create dedicated TracerProviders
instead of fighting over the global singleton, and the otel callback
dedup check no longer incorrectly matches Arize subclasses.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: redaction headers ignored when sent via proxy
When requests go through the proxy, `litellm_params["litellm_metadata"]`
is always set (even when `None`), so `get_metadata_variable_name_from_kwargs`
always returns "litellm_metadata". The redaction code then reads `None`
instead of the actual metadata dict that contains the headers.
Add a fallback to read from `metadata` when `litellm_metadata` is not a
dict, so `x-litellm-enable-message-redaction` and related headers work
correctly in the proxy flow.
Fixes#20739
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: normalize non-dict metadata after fallback in redact_messages
After falling back from litellm_metadata to metadata, ensure the value
is always a dict so .get("headers") never raises on None/non-dict inputs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(batch_completion): submit all model futures before waiting
* test: add batch_completion all responses concurrency regression
* fix(batch_completion): continue collecting responses on per-model failures
* fix(batch_completion): handle empty and string models in all responses
* test(batch_completion): avoid blocking wait in concurrency regression
The provider-prefixed entries (deepseek/deepseek-chat, deepseek/deepseek-reasoner)
in the model cost map were missing supports_response_schema, supports_system_messages,
supports_native_streaming, supports_parallel_function_calling, and had stale
max_input_tokens / max_output_tokens values. This caused supports_response_schema()
to return False for DeepSeek models regardless of calling convention.
Changes:
- Sync deepseek/deepseek-chat and deepseek/deepseek-reasoner entries with
their canonical bare-name counterparts in both JSON files
- Add a bare-model-name fallback in _supports_factory so that when a
provider-prefixed entry is missing a capability field, the bare model
entry is consulted before returning False
- Fix pre-existing unused-import lint error (F401) in policy_resolve_endpoints.py
- Add 14 regression tests covering data consistency, API-level correctness,
and the new fallback logic
* init schema with TAGS
* ui: add policy test
* resolvePoliciesCall
* add_policy_sources_to_metadata + headers
* types Policy
* preview Impact
* def _describe_match_reason(
* match based on TAGs
* TestTagBasedAttachments
* test fixes
* add policy_resolve_router
* add_guardrails_from_policy_engine
* TestMatchAttribution
* refactor
* fix
* fix: address Greptile review feedback on policy resolve endpoints
- Track unnamed keys/teams as separate counts instead of inflating
affected_keys_count with duplicate "(unnamed key)" placeholders.
Added unnamed_keys_count and unnamed_teams_count to response.
- Push alias pattern matching to DB via _build_alias_where() which
converts exact patterns to Prisma "in" and suffix wildcards to
"startsWith" filters.
- Gate sync_policies_from_db/sync_attachments_from_db behind
force_sync query param (default false) to avoid 2 DB round-trips
on every /policies/resolve request.
- Remove worktree-only conftest.py that cleared sys.modules at import
time — no longer needed since code moved to main repo.
- Rename MAX_ESTIMATE_IMPACT_ROWS → MAX_POLICY_ESTIMATE_IMPACT_ROWS.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: eliminate duplicate DB queries and fix header delimiter ambiguity
- Fetch teams table once in estimate_attachment_impact and reuse for
both tag-based and alias-based lookups (was querying teams twice when
both tag_patterns and team_patterns were provided).
- Convert tag/team filter functions from async DB queries to sync
filters that operate on pre-fetched data (_filter_keys_by_tags,
_filter_teams_by_tags).
- Fix comma ambiguity in x-litellm-policy-sources header: use '; '
as entry delimiter since matched_via values can contain commas.
- Use '+' as the within-value separator in matched_via reason strings
(e.g. "tag:healthcare+team:health-team") to avoid conflict with
header delimiters.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Update litellm/proxy/policy_engine/policy_resolve_endpoints.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* feat(guardrail_hooks/): add guardrail logging to all unified guardrails
ensures unified guardrails use the 'log_guardrail_information' decorator for logging
* fix(custom_guardrail.py): don't log inputs on guardrail response - just emit state
* refactor: don't double log bedrock guardrail information
* feat: add in-product nudges for contributing + trying community custom code guardrails
allows users to contribute / share custom code guardrails
* fix(aiohttp): respect ssl_verify with shared sessions
* fix(aiohttp): resolve mypy error for ssl parameter type
Pass ssl kwarg conditionally to aiohttp request() only when explicitly
configured, since None is not a valid value for the ssl parameter
(expected SSLContext | bool | Fingerprint).
When OpenTelemetry is configured via the UI, only OTEL_ENDPOINT and
OTEL_HEADERS are set, but OTEL_EXPORTER is not specified. This caused
the exporter to default to "console", meaning traces were printed to
stdout instead of being sent to the configured endpoint.
This fix adds logic in OpenTelemetryConfig.__post_init__ to automatically
infer "otlp_http" as the exporter when an endpoint is specified but the
exporter is still the default "console".
Fixes issue reported by Elastic team where traces weren't being sent
to their OTEL endpoint when configured through the LiteLLM UI.
* fix:Parse embedded JSON in the message field of logs
* Update litellm/_logging.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
