filter_helpers.ts was not populating the Organization ID filter dropdown
(always empty). TeamVirtualKeysTable was showing the team's org for all
keys instead of each key's own org.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add proxy-admin-configurable toggles to restrict internal users (and optionally
team admins) from accessing agent and vector store management features.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The /key/list API returns `org_id` (the Pydantic field name), but the UI
was reading `organization_id`, causing the Organization field to always
show "Not Set" and the Organization ID filter to never match.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a localStorage-based toggle to hide the bouncing 🌑 icon next to
the version tag in the navbar, following the same pattern used for
hiding prompts, usage indicator, new feature badges, and blog posts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(gemini): ensure image token accumulation in usage metadata
Fixed an issue where image tokens were being overwritten instead of accumulated in Gemini responses. Added support for both camelCase and snake_case token count keys. Fixes#22082.
* test: add regression test for image token accumulation and cleanup files
* fix(gemini): ensure consistent accumulation for responseTokensDetails
* fix(gemini): harden token count parsing and add vertex accumulation test
Parse tokenCount/token_count as int-safe values to satisfy mypy and avoid None/object arithmetic. Add regression test for duplicate modality accumulation in Vertex _calculate_usage.
mask was missing from get_supported_openai_params, causing it to be
dropped before reaching transform_image_edit_request where it is
already handled correctly for flux-pro-1.0-fill inpainting.
- Propagate timeout to each polling GET request to prevent indefinite hangs
- Validate HTTP status code of initial POST before parsing JSON
- Fix inline import and add 60s timeout to image URL download in _read_image_bytes
- Remove required validation for models field in create_key_button.tsx
- Update help text to clarify models are optional
- If no models selected, key will have access to all models
- This allows users to create keys for MCP-only access without selecting LLM models
- Fixes LIT-1791: Cannot create virtual key without LLM provider if user only has MCP access
Backend already supports empty models list (defaults to all models).
This change only updates the UI source to match backend behavior.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
- Added showSearch prop to enable search input in MCP server selector
- Added filterOption to search across server name, alias, server_id, and description
- Search is case-insensitive and filters in real-time
- Added test to verify search input appears when dropdown opens
- Updated tsconfig.json with Next.js auto-configuration (jsx: react-jsx)
Fixes issue where MCP server search was not working in the playground.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
Document the `summary` optional field in the `thinking` object for the
Anthropic `/v1/messages` adapter, and add a section on summary preservation
when routing to non-Anthropic providers via the adapter.
- Fix F821: add BaseTokenCounter TYPE_CHECKING import in gpt_transformation.py
- Remove duplicate auth invocation in count_response_input_tokens endpoint
- Preserve `strict` field during chat→Responses API tool conversion
- Fix docs tools example to use chat completions format (not Responses API format)
- Return None early for system-only messages to avoid noisy error logs
* fix: complexity_router fails on list-format message content (OpenAI multi-part messages)
When a client sends messages with list-format content
(e.g. [{"type": "text", "text": "..."}] as used by the OpenAI JS SDK
and other clients), the complexity_router's async_pre_routing_hook
skipped those messages because it only handled str content. This caused
user_message to be None, the hook returned None, and the router fell
through to selecting the complexity_router deployment itself
(model="auto_router/complexity_router") which litellm cannot dispatch,
resulting in LiteLLMUnknownProvider.
Fixes:
- Extract text from list-format content parts (type=text) before
classifying
- Return default_model instead of None when no user message can be
extracted, preventing the crash fallthrough
- Loosen PreRoutingHookResponse.messages type from Dict[str, str] to
Dict[str, Any] to accommodate list-format content values
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: update messages type annotation in async_pre_routing_hook to Dict[str, Any]
Consistent with PreRoutingHookResponse.messages type change and the
list-format content support added in the previous commit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: normalize None content to empty string in complexity_router message parsing
msg.get("content", "") returns None when the key exists with value None
(e.g. assistant messages with tool calls). Use `or ""` to normalize
None to an empty string explicitly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: strip whitespace from joined list content parts in complexity_router
Prevents leading/trailing spaces when some content parts have empty
text values (e.g. " ".join(["", "hello"]) → " hello").
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The OpenAPI-to-MCP feature (PR #21575) added spec_path to the code
(_types.py, mcp_server_manager.py) but missed adding the column to
the Prisma schema files. This causes "Could not find field spec_path"
errors when creating OpenAPI-based MCP servers via the UI or API.
Adds `spec_path String?` to LiteLLM_MCPServerTable in all three
schema files (root, litellm/proxy, litellm-proxy-extras).
Made-with: Cursor
