67 vercel_ai_gateway models were missing capability flags (supports_vision,
supports_function_calling, supports_tool_choice, supports_response_schema).
These capabilities were inferred from the corresponding direct provider entries
for the same models (e.g., vercel_ai_gateway/anthropic/claude-3.5-sonnet now has
the same capabilities as anthropic/claude-3.5-sonnet).
Models fixed include:
- Claude 3/3.5/3.7 (Anthropic)
- GPT-4/5 variants (OpenAI)
- Gemini 2.0/2.5 (Google)
- Grok 3/4 (xAI)
- Mistral/Mixtral variants
- Qwen models
- DeepSeek models
- And more
This ensures consistent capability reporting across providers for the same
underlying models.
Co-authored-by: krauckbot <krauckbot123@gmail.com>
Adds litellm.proxy_auth to automatically obtain and refresh OAuth2/JWT
tokens when connecting to LiteLLM Proxy or any OAuth2-protected endpoint.
- Add ProxyAuthHandler for token lifecycle (obtain, cache, refresh)
- Add AzureADCredential wrapper for azure-identity credentials
- Add GenericOAuth2Credential for any OAuth2 provider (Okta, Auth0, etc)
- Auto-inject Authorization headers in completion() and embedding()
Closes#19834
* docs: add Prisma migration troubleshooting guide
Add troubleshooting documentation for common Prisma migration errors
encountered when upgrading/downgrading LiteLLM proxy versions.
Covers:
- 'relation does not exist' errors after version rollback
- Blocked migrations from previous failures
- Migration state mismatch after version rollback
- General tips for prisma migrate resolve, db push, and migrate deploy
* docs: simplify prisma migration troubleshooting - focus on delete + restart
Add the following SCIM v2 discovery endpoints per RFC 7643/7644:
- GET /scim/v2 - Base resource discovery (ListResponse of ResourceTypes)
- GET /scim/v2/ResourceTypes - List all supported resource types
- GET /scim/v2/ResourceTypes/{id} - Get a specific resource type (User/Group)
- GET /scim/v2/Schemas - List all supported schemas
- GET /scim/v2/Schemas/{uri} - Get a specific schema by URI
These endpoints are required by identity providers (Okta, Azure AD, etc.)
for SCIM resource discovery. Previously, GET /scim/v2 returned 404.
Also adds SCIMResourceType, SCIMSchema, and SCIMSchemaAttribute Pydantic
models to the SCIM types module.
Fixes#20295
* fix: strip stale mcp-session-id header to prevent 'Session not found' error loop
When VSCode reconnects to LiteLLM's MCP endpoint after a reload, it sends
a stale mcp-session-id header. The session was already cleaned up, causing
a 404 'Session not found' error. VSCode retries with the same stale ID,
creating an infinite error loop.
Before forwarding requests to the StreamableHTTP session manager, check if
the mcp-session-id header references a valid session. If the session doesn't
exist, strip the header so a new session is created automatically.
Fixes#20292
* refactor: extract stale session handling into _strip_stale_mcp_session_header helper
Add moonshot/kimi-k2.5 model with:
- Input cost: $0.60/M tokens (6e-07)
- Output cost: $3.00/M tokens (3e-06)
- Cache read cost: $0.10/M tokens (1e-07)
- 256K context window
- Vision, function calling, tool choice, web search support
Reference: https://huggingface.co/moonshotai/Kimi-K2.5
Note: K2.5 thinking mode is controlled via API parameters, not a separate model ID.
Co-authored-by: krauckbot <krauckbot123@gmail.com>
