* 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.
When litellm_metadata is explicitly set to None in litellm_params,
`dict.get("litellm_metadata", {})` returns None (not the default {}),
because the key exists. The subsequent .get() call on None raises
`AttributeError: 'NoneType' object has no attribute 'get'`.
Use `or {}` instead, consistent with line 4924 in the same file.
Fixes#15836
* fix: allow Management keys to access user/daily/activity and team/daily/activity
* feat(vertex): surface trafficType via generic provider_specific_fields in Responses API
Extract Vertex AI's trafficType from usageMetadata in both streaming and
non-streaming paths, storing it in _hidden_params["provider_specific_fields"].
The Responses API transformation layer generically passes any
_hidden_params["provider_specific_fields"] dict to the ResponsesAPIResponse,
avoiding provider-specific logic in the bridge.
Also fix stream_chunk_builder to propagate _hidden_params from the last
streaming chunk to the rebuilt ModelResponse, ensuring provider metadata
survives the chunk→response rebuild.
---------
Co-authored-by: naaa760 <neh6a683@gmail.com>
Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com>
* docs: add native thinking param examples for Claude Opus 4.6
Add documentation for using the native `thinking` parameter directly
with adaptive thinking and explicit budgets for Claude Opus 4.6.
* docs: add note about reasoning_effort mapping to adaptive for Opus 4.6
OAuth tokens (sk-ant-oat*) require Authorization: Bearer header per
Anthropic's OAuth specification, but were being sent via x-api-key
which Anthropic rejects with 'invalid x-api-key'.
- optionally_handle_anthropic_oauth: detect OAuth tokens in api_key
param (standard chat flow), not just Authorization header
- get_anthropic_headers: use Authorization: Bearer + required OAuth
headers for OAuth tokens, x-api-key for regular API keys
- Passthrough messages: skip x-api-key when Authorization is set
- Add oauth-2025-04-20 to beta headers whitelist config
* 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>
Fixes#20990
PR #19943 added logging when the proxy overrides model names to prevent
internal provider prefixes from leaking to clients. The behavior works
correctly but logs a WARNING on every request with model mismatch.
For high-traffic customers using model aliases or provider prefixes,
this creates millions of warnings per day, flooding logs and causing
disk space issues.
Changed log level from WARNING to DEBUG since:
- The model mismatch is expected behavior when using aliases
- The override happens correctly regardless of log level
- Operators can still enable with LITELLM_LOG=DEBUG for debugging
Changes:
- common_request_processing.py: 2 warnings -> debug (non-streaming)
- proxy_server.py: 1 warning -> debug (streaming)
