- Allow per-request Phoenix project name via `metadata.phoenix_project_name`, falling back to PHOENIX_PROJECT_NAME env var
- Add missing `post_call_success_hook` to `/images/generations` endpoint so guardrails and OTEL tracing apply to image generation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Preserved nullable object fields by carrying schema properties
* Fix: _convert_schema_types
* Fix all mypy issues
* Add alert about email notifications
* fixing tests
* extending timeout for long running tests
* Text changes
* [Feat] MCP Oauth2 Fixes - Add support for MCP M2M Oauth2 support (#20788)
* add has_client_credentials
* MCPOAuth2TokenCache
* init MCP Oauth2 constants
* MCPOAuth2TokenCache
* resolve_mcp_auth
* test fixes
* docs fix
* address greptile review: min TTL, env-configurable constants, tests, docs
- Fix zero-TTL edge case: floor at MCP_OAUTH2_TOKEN_CACHE_MIN_TTL (10s)
- Make all MCP OAuth2 constants env-configurable via os.getenv()
- Move test file to follow 1:1 mapping convention (test_oauth2_token_cache.py)
- Add MCP OAuth doc page (mcp_oauth.md) with M2M and PKCE sections
- Update FAQ in mcp.md to reflect M2M support
- Add E2E test script and config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix mypy lint
* fix oauth2
* remove old files
* docs fix
* address greptile comments
* fix: atomic lock creation + validate JSON response shape
- Use dict.setdefault() for atomic per-server lock creation
- Add isinstance(body, dict) check before accessing token response fields
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: replace asserts with proper guards, wrap HTTP errors with context
- Replace `assert` statements with `if/raise ValueError` (asserts can be
disabled with python -O in production)
- Wrap `httpx.HTTPStatusError` to provide a clear error message with
server_id and status code
- Add tests for HTTP error and non-dict JSON response error paths
- Remove unused imports
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* [UI] M2M OAuth2 UI Flow (#20794)
* add has_client_credentials
* MCPOAuth2TokenCache
* init MCP Oauth2 constants
* MCPOAuth2TokenCache
* resolve_mcp_auth
* test fixes
* docs fix
* address greptile review: min TTL, env-configurable constants, tests, docs
- Fix zero-TTL edge case: floor at MCP_OAUTH2_TOKEN_CACHE_MIN_TTL (10s)
- Make all MCP OAuth2 constants env-configurable via os.getenv()
- Move test file to follow 1:1 mapping convention (test_oauth2_token_cache.py)
- Add MCP OAuth doc page (mcp_oauth.md) with M2M and PKCE sections
- Update FAQ in mcp.md to reflect M2M support
- Add E2E test script and config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix mypy lint
* fix oauth2
* ui feat fixes
* test M2M
* test fix
* ui feats
* ui fixes
* ui fix client ID
* fix: backend endpoints
* docs fix
* fixes greptile
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* [Fix] prevent shared backend model key from being polluted by per-deployment custom pricing (#20679)
* bug: custom price override for models
* added associated test
* fix(mcp): resolve OAuth2 root endpoints returning "MCP server not found" (#20784)
When MCP SDK hits root-level /register, /authorize, /token without
server name prefix, auto-resolve to the single configured OAuth2
server. Also fix WWW-Authenticate header to use correct public URL
behind reverse proxy.
* Add support for langchain_aws via litellm passthrough
* fix(proxy): return early instead of raising ValueError when standard_logging_payload is missing
The `_PROXY_VirtualKeyModelMaxBudgetLimiter.async_log_success_event` hook
raises `ValueError` when `standard_logging_payload` is `None`. This breaks
non-standard call types (e.g. vLLM `/classify`) that do not populate the
payload, and the resulting exception disrupts downstream success callbacks
like Langfuse.
Return early with a debug log instead, matching the existing pattern used
for missing `user_api_key_model_max_budget`.
Fixes#18986
---------
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Shivam Rawat <161387515+shivamrawat1@users.noreply.github.com>
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
* 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
OIDC providers like Logto may return opaque (non-JWT) access tokens,
which caused jwt.decode() to raise DecodeError and crash the SSO
callback with a 500 error. Catch DecodeError and skip JWT-based
extraction gracefully, since user info is already available from
the UserInfo endpoint.
Fixes#20724
* Add chat completion support for websearch
* Add chat completion tool calls support and response transformation
* Add new methods in chat completion
* Add chat completion tool format
* Add callback for websearch in completion method
* Add test for web search
* Potential fix for code scanning alert no. 4046: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Update litellm/integrations/websearch_interception/tools.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: empty guardrails/policies arrays should not trigger enterprise license check (#20567)
* fix: empty guardrails/policies arrays should not trigger enterprise license check (#20304)
The UI sends empty arrays for enterprise-only fields (guardrails, policies,
logging) even when the user has not configured these features. The backend
`is not None` check treated `[]` as a truthy intent to use the feature,
falsely requiring an enterprise license for basic team operations.
Backend: Add `and updated_kv[field] != [] and updated_kv[field] != {}`
guards in `_update_metadata_fields` so empty collections are skipped.
UI: Conditionally omit guardrails, logging, and policies from the
payload when empty instead of defaulting to `[]`.
Fixes#20304
* fix: allow clearing fields with empty collections while skipping enterprise check
Address PR review feedback:
1. Move the empty-collection guard into _update_metadata_field (singular)
so that empty lists/dicts skip only the premium license check but still
get written into metadata. This lets users intentionally clear a
previously-set field (e.g. guardrails: []) without being blocked, while
the UI's default empty arrays still don't trigger a false enterprise
error.
2. Remove sys.path hack from test file; use standard imports that work
with pytest discovery.
3. Add tests verifying that empty collections are moved into metadata
(field clearing works) even though they bypass the premium check.
Fixes#20304
* fix critical CVE vulnerabliltes (#20683)
* fix: add hook to handle db case (#20635)
* Add team policy mapping for zguard (#20608)
* support policy mapping on team key level
* update document
* update document
* address comments
* update document
* add unit test for new feature
* add more test case
* feat: add support for anthropic_messages call type in prompt caching (#19233)
* feat: add support for anthropic_messages call type in prompt caching
* test: move anthropic_messages prompt caching test to main router test file
* add tutorial on using claude code with prompt cache routing
* docs: add SDK proxy authentication (OAuth2/JWT auto-refresh) documentation (#20680)
Adds documentation for the litellm.proxy_auth feature that automatically
obtains and refreshes OAuth2/JWT tokens when connecting to a LiteLLM Proxy.
* Fixes#20582 (#20663)
* fix: show error details instead of Data Not Available for failed requests (#20656)
* fix(ui): add null guard for models in API keys table (#20655)
The VirtualKeysTable crashed when rendering keys with null or undefined
models field. The className expression tried to access .length on null,
throwing a TypeError that broke the entire keys table.
Added Array.isArray() guard before accessing .length on the models value.
Fixes#20611
* Fix: Spend logs pickle error with Pydantic models and redaction (#20685)
* docs: add callback registration optimization to v1.81.9 release notes (#20681)
* docs: add callback registration optimization to v1.81.9 release notes
* Update v1.81.9.md
---------
Co-authored-by: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
* Fix spend logs pickle error with Pydantic models
Replace copy.deepcopy() with Pydantic-safe serialization to avoid
"cannot pickle '_thread.RLock' object" errors when request/response
redaction is enabled.
Changes:
- Add _convert_to_json_serializable_dict() helper that uses
model_dump() for Pydantic models instead of pickle
- Replace copy.deepcopy() calls in request and response redaction
paths with the new helper function
- Recursively handles nested dicts, lists, and Pydantic models
Root cause: Pydantic v2 BaseModel instances contain internal
_thread.RLock objects for thread-safety. When copy.deepcopy()
attempts to pickle these objects, it fails because threading
primitives cannot be pickled.
Fixes#20647
* chore: remove unused copy import
Remove unused copy import that was causing lint failure. The copy.deepcopy()
calls were replaced with _convert_to_json_serializable_dict() helper function
in the previous commit, making the copy module no longer needed.
---------
Co-authored-by: ryan-crabbe <128659760+ryan-crabbe@users.noreply.github.com>
Co-authored-by: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
* fix(vertex_ai): propagate extra_headers anthropic-beta to request body (#20666)
Vertex AI requires Anthropic beta flags in the request body
(anthropic_beta array), not as HTTP headers. The Bedrock handler
already extracts user-specified beta headers from the headers dict,
but the Vertex handler was missing this, causing extra_headers like
interleaved-thinking-2025-05-14 to be silently dropped.
This extracts anthropic-beta values from optional_params extra_headers
and merges them into the anthropic_beta request body field, and also
removes extra_headers from the request body since the parent's
transform_request spreads optional_params into data.
* fix(streaming): preserve interleaved thinking/redacted blocks
* test(streaming): build thinking chunks with typed Delta/StreamingChoices
* Fix video list pagination cursors not encoded with provider metadata
first_id and last_id in the video list response were returned as raw
provider IDs while data[].id was properly wrapped with
encode_video_id_with_provider(). This caused pagination to break when
clients passed unencoded cursors back as the `after` parameter.
- Encode first_id/last_id in transform_video_list_response
- Decode the `after` param in transform_video_list_request via
extract_original_video_id()
- Add 6 unit tests covering encoding, decoding, passthrough, and
full round-trip pagination
Fixes#20708
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(responses): preserve streamed tool deltas when id is omitted
* fix(responses): guard ambiguous tool-call index reuse
* Add compaction for vertex ai
* Add all new feat for v1/messages
* Add inference_geo as supported messages param
* Add inference based costing
* Add inference_geo as supported messages param
* Add support for fast param
* Add fast mode for other providers
* Add documentation for Fast Mode
* add missing indexes on VerificationToken table
* Fix structured response of tool call
* Add tests for WebSearch interception with chat completions API
* Add doc for chat completion web search
* Fix: is_web_search_tool_chat_completion
* Fix double json import
* Add new vercel ai anthropic models
* Fix: base_model name for body and deplyment name in URL
* Add output_config as supported param
* Add response schema for vercel ai sonnet 4.5
* handle when litellm_parrams might be none
* Fix : litellm/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_bedrock_chat_invoke_transformations_anthropic_claude3_transformation.py
* fix: Missing return statement for async streaming
* Fix: get_supported_anthropic_messages_params
* Fix mypy issues
* Fix mypy issues
* Add support for extra fields in Generic SSO via GENERIC_USER_EXTRA_ATTRIBUTES
Enables extraction of additional fields from the Generic SSO userinfo endpoint response beyond the standard 8 fields (id, email, name, etc.). Custom handlers can now access these fields via CustomOpenID.extra_fields dict.
Changes:
- Add extra_fields: Optional[Dict[str, Any]] to CustomOpenID type
- Add GENERIC_USER_EXTRA_ATTRIBUTES env var (comma-separated field names)
- Extract specified fields using get_nested_value() with dot notation support
- Add 4 test cases covering basic, nested, and missing field scenarios
- Update custom_sso.py example showing how to access extra_fields
Backward compatible: extra_fields is None when env var not set
* docs: Add documentation for GENERIC_USER_EXTRA_ATTRIBUTES
Document the new GENERIC_USER_EXTRA_ATTRIBUTES environment variable for Generic SSO
- Add to admin_ui_sso.md: explanation and usage examples
- Add to config_settings.md: environment variable reference
- Add to custom_sso.md: code example showing how to access extra_fields
- Includes examples for nested field paths with dot notation
---------
Co-authored-by: Sameer Kankute <sameer@berri.ai>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Varun Chawla <34209028+veeceey@users.noreply.github.com>
Co-authored-by: Harshit Jain <48647625+Harshit28j@users.noreply.github.com>
Co-authored-by: jwang-gif <j.wang@zscaler.com>
Co-authored-by: nuernber <benjamin.nuernberger@jpl.nasa.gov>
Co-authored-by: Cesar Garcia <128240629+Chesars@users.noreply.github.com>
Co-authored-by: John Lathouwers <john.lathouwers@oracle.com>
Co-authored-by: ryan-crabbe <128659760+ryan-crabbe@users.noreply.github.com>
Co-authored-by: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
Co-authored-by: Elias Högbom Aronsson <elias.aronson@gmail.com>
Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
Co-authored-by: tshushan <tshushan@outbrain.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Carlo Alberto Ferraris <cafxx@mercari.com>
When MCP SDK hits root-level /register, /authorize, /token without
server name prefix, auto-resolve to the single configured OAuth2
server. Also fix WWW-Authenticate header to use correct public URL
behind reverse proxy.
* docs: add callback registration optimization to v1.81.9 release notes (#20681)
* docs: add callback registration optimization to v1.81.9 release notes
* Update v1.81.9.md
---------
Co-authored-by: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
* Fix spend logs pickle error with Pydantic models
Replace copy.deepcopy() with Pydantic-safe serialization to avoid
"cannot pickle '_thread.RLock' object" errors when request/response
redaction is enabled.
Changes:
- Add _convert_to_json_serializable_dict() helper that uses
model_dump() for Pydantic models instead of pickle
- Replace copy.deepcopy() calls in request and response redaction
paths with the new helper function
- Recursively handles nested dicts, lists, and Pydantic models
Root cause: Pydantic v2 BaseModel instances contain internal
_thread.RLock objects for thread-safety. When copy.deepcopy()
attempts to pickle these objects, it fails because threading
primitives cannot be pickled.
Fixes#20647
* chore: remove unused copy import
Remove unused copy import that was causing lint failure. The copy.deepcopy()
calls were replaced with _convert_to_json_serializable_dict() helper function
in the previous commit, making the copy module no longer needed.
---------
Co-authored-by: ryan-crabbe <128659760+ryan-crabbe@users.noreply.github.com>
Co-authored-by: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
* support policy mapping on team key level
* update document
* update document
* address comments
* update document
* add unit test for new feature
* add more test case
* fix: empty guardrails/policies arrays should not trigger enterprise license check (#20304)
The UI sends empty arrays for enterprise-only fields (guardrails, policies,
logging) even when the user has not configured these features. The backend
`is not None` check treated `[]` as a truthy intent to use the feature,
falsely requiring an enterprise license for basic team operations.
Backend: Add `and updated_kv[field] != [] and updated_kv[field] != {}`
guards in `_update_metadata_fields` so empty collections are skipped.
UI: Conditionally omit guardrails, logging, and policies from the
payload when empty instead of defaulting to `[]`.
Fixes#20304
* fix: allow clearing fields with empty collections while skipping enterprise check
Address PR review feedback:
1. Move the empty-collection guard into _update_metadata_field (singular)
so that empty lists/dicts skip only the premium license check but still
get written into metadata. This lets users intentionally clear a
previously-set field (e.g. guardrails: []) without being blocked, while
the UI's default empty arrays still don't trigger a false enterprise
error.
2. Remove sys.path hack from test file; use standard imports that work
with pytest discovery.
3. Add tests verifying that empty collections are moved into metadata
(field clearing works) even though they bypass the premium check.
Fixes#20304
The warning 'Semantic tool filter hook not initialized' was appearing on
every startup, even when the mcp_semantic_tool_filter feature was not
configured. This was confusing for users.
Now the function checks if the feature is actually configured and enabled
before proceeding with initialization. The warning will only appear if
the feature was explicitly enabled but failed to initialize.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Previously, PR #19818 (via #20205) removed the model_list check entirely,
causing Router to be created even with no models AND no search_tools.
This fix adds back a conditional check that creates the Router only when:
- There are models to route, OR
- There are search_tools configured
This preserves the PR #19818 goal (search-tools-only deployments) while
avoiding unnecessary Router creation when there's nothing to route.
Fixes test_add_and_delete_deployments[0-None]
Extract the allowed MCP servers resolution logic with IP filtering into
a dedicated helper function _resolve_allowed_mcp_servers_with_ip_filter.
This reduces the statement count in call_tool_rest_api from 51 to under
50, fixing the ruff PLR0915 (too many statements) lint error.
Co-authored-by: Shin <shin@openclaw.ai>
