* feat(bedrock): add DeepSeek V3.2 pricing and region support
* feat(bedrock): add minimax.minimax-m2.1 pricing and region support
* feat(bedrock): add moonshotai.kimi-k2.5 pricing and region support
* feat(bedrock): add qwen.qwen3-coder-next
pricing and region support
* add some sanity unit tests for the bedrock beta models added
* --amend
* resolve greptileai comments and suggestions
* docs: add reference to example_openai_endpoint repo for self-hosting fake OpenAI proxy (#21006)
- Updated benchmarks.md with a section on setting up fake OpenAI endpoints
- Updated load_test.md to mention the self-hosted option
- Updated load_test_advanced.md with a tip box about the example repo
Reference: https://github.com/BerriAI/example_openai_endpoint
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* MCP fixes
* fix(oldteams.tsx): show policies when creating
* fix(proxy/_types.py): ensure mcp rest endpoints can be called by virtual key
ensures UI works with virtual key testing mcp endpoints
* refactor: migrate get object permissions table logic to happen in user api key auth - allows functions to trust user api key object they receive has what they need
* fix(rest_endpoints.py): filter for allowed tools based on what key has access to
* fix(mcp_server_manager.py): ensure only allowed MCP's are returned to the user, via rest endpoints
* Guardrails - add toxic/abusive content filter guardrails
* fix(streaming): preserve usage data from post-finish_reason chunks in OpenAI-compatible streaming
Fixes#16112
OpenRouter and other OpenAI-compatible providers send a usage chunk after
the finish_reason='stop' chunk when stream_options.include_usage is True.
The OpenAIChatCompletionStreamingHandler.chunk_parser() was not passing
the usage field to ModelResponseStream, causing real token counts from the
provider to be lost and falling back to inaccurate estimates.
* fix: resolve merge conflict in test file
- Fix typo in test method name (extra space)
- Move test_prompt_cache_key_in_optional_params to its own class
---------
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(vertex_ai): forward extra_body to completion transformation handler
The responses() function accepted extra_body as a named parameter but
did not pass it to response_api_handler when responses_api_provider_config
was None (completion transformation path), silently dropping it.
Also adds deep-merge support for extra_body in Vertex AI Gemini
transformation, so dict values like generationConfig are merged rather
than replaced.
* refactor(vertex_ai): extract _merge_extra_body to fix PLR0915 lint
Move the extra_body merge loop into a helper function to keep
_transform_request_body under the 50-statement limit.
* feat: add curated MCP server registry for discovery UI
Curated list of 31 well-known MCP servers with names, icons,
categories, transport config, and registry URLs. Includes HTTP
endpoints for GitHub, Atlassian, Sentry, Snowflake, and Cloudflare.
* feat: add GET /v1/mcp/discover endpoint for MCP discovery
Admin-only endpoint that serves the curated MCP registry with
optional query and category filters. Used by the UI discovery modal.
* feat: add DiscoverableMCPServer types for MCP discovery
* feat: add fetchDiscoverableMCPServers network function
* feat: add MCP discovery modal component
Compact list-row layout with category filters, search, and
grouped server list. Follows dev-tool aesthetic.
* feat: wire MCP discovery modal into server management page
Add MCP Server button now opens discovery modal. Card click
pre-fills the create form. Custom Server opens blank form.
* feat: add prefill from discovery and back-to-registry link
Create form accepts prefillData from discovery selection and
shows a Browse MCP Registry link to return to discovery modal.
* test: add unit tests for MCP discovery endpoint and registry
Tests for registry JSON structure validation and endpoint
query/category filtering logic. 15 tests total.
* fix: sync registry with official MCP API and fix stdio prefill
- Updated transport types and URLs from registry.modelcontextprotocol.io API
- GitHub: streamable-http at api.githubcopilot.com/mcp/
- GitLab: streamable-http at gitlab.com/api/v4/mcp (remote only)
- Atlassian: SSE at mcp.atlassian.com/v1/sse (remote only)
- Linear: SSE at mcp.linear.app/sse (remote only)
- Notion: SSE at mcp.notion.com/sse (remote only)
- Stripe: streamable-http at mcp.stripe.com (remote only)
- Exa: streamable-http at mcp.exa.ai/mcp (remote only)
- Cloudflare: SSE at bindings.mcp.cloudflare.com/sse (remote only)
- Sentry: stdio via @sentry/mcp-server (npm, correct package)
- Snowflake: stdio via snowflake-labs-mcp (pypi/uvx, not npm)
- Brave Search: stdio via @brave/brave-search-mcp-server (correct package)
- Fixed stdio prefill to generate stdio_config JSON instead of separate fields
- Discovery modal matches create modal width and header style
- Back arrow positioned on left of create modal header
* Update ui/litellm-dashboard/src/components/mcp_tools/mcp_discovery.tsx
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Update litellm/proxy/management_endpoints/mcp_management_endpoints.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: address Greptile review feedback
- Move `import json` and `import os` to module top level
- Move mcp_registry.json into litellm/proxy/ for pip distribution
- Fix `Text` component: destructure from antd Typography instead of deprecated Tremor
- Update test fixture path to match new registry location
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix: inject NPM_CONFIG_CACHE into STDIO MCP subprocess env for Docker
npm/npx needs a writable cache directory. In containers the default
(~/.npm) may not exist or be read-only, causing STDIO MCP servers
launched via npx to fail with ENOENT. Inject NPM_CONFIG_CACHE=/tmp/.npm_mcp_cache
into the subprocess env when not already set.
* test: add unit test for NPM_CONFIG_CACHE injection in STDIO MCP
Verifies that NPM_CONFIG_CACHE is auto-injected when not set, and
preserved when explicitly provided. Also moves the import to module
level per code style rules.
* Update litellm/constants.py
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Apply suggestion from @greptile-apps[bot]
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>
Fixes AT&T customer issue where API keys are returned in plain text
in error responses.
Changes:
1. user_api_key_auth.py: Mask the API key in the AssertionError when a
key doesn't start with 'sk-' (e.g. key with leading space). Shows
first 4 + last 4 chars with **** in between instead of the full key.
2. key_management_endpoints.py: Same masking for the key format
validation error when creating keys with invalid prefix.
3. presidio.py: Sanitize exceptions from Presidio analyze/anonymize
calls to prevent leaking original request text (which may contain
API keys) in error responses. Error messages now show only the
exception type, not the full payload.
* Add http support to custom code guardrails + Unified guardrails for MCP + Agent guardrail support (#20619)
* fix: fix styling
* fix(custom_code_guardrail.py): add http support for custom code guardrails
allows users to call external guardrails on litellm with minimal code changes (no custom handlers)
Test guardrail integrations more easily
* feat(a2a/): add guardrails for agent interactions
allows the same guardrails for llm's to be applied to agents as well
* fix(a2a/): support passing guardrails to a2a from the UI
* style(code-editor): allow editing custom code guardrails on ui + add examples of pre/post calls for custom code guardrails
* feat(mcp/): support custom code guardrails for mcp calls
allows custom code guardrails to work on mcp input
* feat(chatui.tsx): support guardrails on mcp tool calls on playground
* fix(mypy): resolve missing return statements and type casting issues (#20618)
* fix(mypy): resolve missing return statements and type casting issues
* fix(pangea): use elif to prevent UnboundLocalError and handle None messages
Address Greptile review feedback:
- Make branches mutually exclusive using elif to prevent input_messages from being overwritten
- Handle case where data.get('messages') returns None to avoid passing invalid payload to Pangea API
---------
Co-authored-by: Shin <shin@openclaw.ai>
* [Feat] MCP Gateway - Allow setting MCP Servers as Private/Public available on Internet (#20607)
* update MCPAuthenticatedUser
* add available_on_public_internet for MCPs
* update claude.md
* init IPAddressUtils
* init available_on_public_internet
* add on REST endpoints
* filter with IP
* TestIsInternalIp
* _extract_mcp_headers_from_request
* init get_mcp_client_ip
* _get_general_settings
* allowed_server_ids
* address PR comments
* get_mcp_server_by_name fix
* fix server
* fix review comments
* get_public_mcp_servers
* address _get_allowed_mcp_servers
* fixing user_id
* [Feat] IP-Based Access Control for MCP Servers (#20620)
* update MCPAuthenticatedUser
* add available_on_public_internet for MCPs
* update claude.md
* init IPAddressUtils
* init available_on_public_internet
* add on REST endpoints
* filter with IP
* TestIsInternalIp
* _extract_mcp_headers_from_request
* init get_mcp_client_ip
* _get_general_settings
* allowed_server_ids
* address PR comments
* get_mcp_server_by_name fix
* fix server
* fix review comments
* get_public_mcp_servers
* address _get_allowed_mcp_servers
* test fix
* fix linting
* inint ui types
* add ui for managing MCP private/public
* add ui
* fixes
* add to schema
* add types
* fix endpoint
* add endpoint
* update manager
* test mcp
* dont use external party for ip address
* Add OpenAI/Azure release test suite with HTTP client lifecycle regression detection (#20622)
* docs (#20626)
* docs
* fix(mypy): resolve type checking errors in 5 files (#20627)
- a2a_protocol/exception_mapping_utils.py: Fix type ignore comment for None assignment
- caching/redis_cache.py: Add type ignore for async ping return type
- caching/redis_cluster_cache.py: Add type ignore for async ping return type
- llms/deprecated_providers/palm.py: Add type ignore for palm.generate_text
- proxy/auth/handle_jwt.py: Add type ignore for jwt.decode options argument
All changes add appropriate type: ignore comments to handle library typing inconsistencies.
* fix(test): update deprecated gemini embedding model (#20621)
Replace text-embedding-004 with gemini-embedding-001.
The old model was deprecated and returns 404:
'models/text-embedding-004 is not found for API version v1beta'
Co-authored-by: Shin <shin@openclaw.ai>
* ui new buil
* fix(http_handler): bypass cache when shared_session is provided for aiohttp tracing
When users pass a shared_session with trace_configs to acompletion(),
the get_async_httpx_client() function was ignoring it and returning
a cached client without the user's tracing configuration.
This fix bypasses the cache when shared_session is provided, ensuring
the user's ClientSession (with its trace_configs, connector settings, etc.)
is actually used for the request.
Fixes#20174
---------
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: Shin <shin@openclaw.ai>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com>
Co-authored-by: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
Co-authored-by: shin-bot-litellm <shin-bot-litellm@users.noreply.github.com>
* 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(proxy): add regression tests for #20441 - ensure <script> tags in LLM messages are not blocked
The 403 Forbidden error when sending messages containing `<script>` is caused
by external WAF/reverse proxy infrastructure (confirmed by the standard nginx
HTML 403 response format), not by LiteLLM's own content filtering. However,
these regression tests ensure that:
1. The content filter guardrail's built-in patterns do not match HTML tags
2. Messages containing <script> and other HTML tags pass through the content
filter unchanged when no explicit HTML-blocking rules are configured
3. The HTTP request body parser correctly handles JSON payloads containing
HTML content without modification
These tests guard against accidentally introducing HTML/XSS filtering that
would break legitimate LLM API usage (e.g., discussing HTML/JavaScript code).
Closes#20441
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
When an OpenAI-compatible upstream provider emits minimal streaming event
payloads that omit required fields (e.g. created_at, output, output_index,
content_index), Pydantic raises a ValidationError crashing the SSE stream
and returning HTTP 500.
Fall back to model_construct() on ValidationError, consistent with the
existing pattern in transform_response_api_response for non-streaming.
Fixes https://github.com/BerriAI/litellm/issues/20570
Signed-off-by: Varun Chawla <varun_6april@hotmail.com>
* Fix MCP health check CancelledError handling for parallel test execution
Add asyncio.CancelledError handler in health_check_server() and missing
@pytest.mark.asyncio decorator on test_mcp_server_manager_config_integration_with_database.
In Python 3.8+, CancelledError inherits from BaseException, not Exception,
so it bypassed the generic exception handler when pytest-xdist cancels
running tasks after a failure.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Regenerate poetry.lock to resolve merge conflict markers
The lock file had unresolved conflict markers from a previous merge,
causing poetry to fail with "Invalid statement (at line 8534, column 1)".
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Fix skip condition to detect claude models (was only checking for
"anthropic" in model name, missing "claude-haiku-4-5")
- Add missing skip for OpenAI tests when OPENAI_API_KEY is not set
- Fix TypeError in utils.py when metadata is explicitly None instead
of missing (use `or {}` fallback)
HuggingFace Text Embeddings Inference (TEI) returns embeddings as raw
arrays [[0.1, 0.2, ...]] instead of wrapped format {"embedding": [...]}.
This change handles both formats:
- Raw array: [[...]] (TEI, some HF models)
- Wrapped: {"embedding": [[...]]} (standard HF format)
Fixes SagemakerError: "HF response missing 'embedding' field" when using
TEI containers on SageMaker.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix(oldteams.tsx): show policies when creating
* fix(proxy/_types.py): ensure mcp rest endpoints can be called by virtual key
ensures UI works with virtual key testing mcp endpoints
* refactor: migrate get object permissions table logic to happen in user api key auth - allows functions to trust user api key object they receive has what they need
* fix(rest_endpoints.py): filter for allowed tools based on what key has access to
* fix(mcp_server_manager.py): ensure only allowed MCP's are returned to the user, via rest endpoints
* 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
