Add Claude Opus 4.6 entries for Anthropic, Bedrock Converse, and Vertex AI.
Align pricing and capability metadata with Anthropic docs, including
long-context rates, above-200k prompt-caching rates, prefill removal,
and tool-use system prompt token counts.
Register the Bedrock Converse model ID in constants and add targeted
tests to validate model map values and converse registration.
* _translate_openai_content_to_anthropic
* test_response_format_consistency
* test fixes unit tests
* test fix
* fix: use dict access for anthropic content blocks in tests (#20447)
The translate_openai_response_to_anthropic method returns dicts, not objects.
Changed .type/.text/.thinking attribute access to dict ['key'] access.
---------
Co-authored-by: shin-bot-litellm <shin-bot-litellm@berri.ai>
* fix(a2a): use text/event-stream SSE format for message/stream endpoint
The A2A gateway's streaming response was using application/x-ndjson
Content-Type and raw NDJSON body format. The A2A protocol spec requires
text/event-stream with SSE framing (data: ...\n\n).
The official a2a-sdk client validates the Content-Type header and raises
SSEError when it doesn't contain text/event-stream.
Changes:
- Changed media_type from application/x-ndjson to text/event-stream
- Updated response body to use SSE framing (data: prefix + \n\n suffix)
- Added tests validating Content-Type and SSE body format
Fixes#20278
* Potential fix for code scanning alert no. 4045: Information exposure through an exception
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* test(a2a): add manual SSE format validation script
Adds a manual test script that:
1. Starts a real A2A agent on port 10001
2. Starts LiteLLM proxy with the agent registered
3. Makes a streaming request to the proxy's A2A gateway
4. Validates Content-Type header is text/event-stream
5. Validates body uses SSE framing (data: ...\n\n)
Run: python tests/a2a_manual/test_a2a_sse_manual.py
---------
Co-authored-by: shin-bot-litellm <shin-bot-litellm@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
The unified guardrail's streaming iterator hook processes every Nth
chunk (sampling_rate, default 5). On each sampled chunk it calls
process_output_streaming_response, which combines all accumulated text
into the first chunk and clears all subsequent chunks to "".
The hook then yielded `processed_items[-1]` — the last item, whose
content had been cleared to "". This permanently lost every Nth
chunk's content, causing random missing words/tokens in the client
output (observed in Roo Code, Open WebUI, etc.).
Fix: deep-copy the current chunk before guardrail processing runs,
then yield the original (unmodified) chunk. The guardrail validation
still executes and can block if it detects a problem, but the stream
content is preserved.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: enforce team MCP permissions when using JWT authentication
Root cause: When JWT auth was used with teams in groups (via team_ids_jwt_field),
the team's MCP permissions were not being enforced because:
1. The default team_allowed_routes did not include mcp_routes
2. allowed_routes_check() failed for MCP endpoints like /mcp/tools/list
3. find_team_with_model_access() skipped the team due to failed route check
4. team_id was None in UserAPIKeyAuth
5. MCPRequestHandler._get_allowed_mcp_servers_for_team() returned empty list
Fix: Add 'mcp_routes' to the default team_allowed_routes in LiteLLM_JWTAuth.
This ensures that teams can access MCP endpoints by default, allowing the
team's MCP server permissions to be properly enforced.
Added tests:
- test_reproduce_jwt_mcp_enforcement_issue: Reproduces the exact bug scenario
- test_verify_mcp_routes_in_default_team_allowed_routes: Verifies fix
- test_mcp_route_check_passes_for_team: Verifies route check works
Co-authored-by: ishaan <ishaan@berri.ai>
* test: add comprehensive E2E tests for JWT + team MCP permission enforcement
Added tests:
- test_e2e_jwt_team_mcp_permissions_enforced: Full E2E test verifying JWT auth
with teams in groups properly sets team_id and MCPRequestHandler returns
the team's MCP servers
- test_e2e_jwt_without_team_no_mcp_servers: Verifies no MCP servers returned
when JWT has no teams
- test_e2e_jwt_team_mcp_key_intersection: Verifies intersection logic when
both key and team have MCP permissions (result = intersection)
These tests verify the complete flow:
1. JWT token with team in groups field
2. JWT auth properly sets team_id on UserAPIKeyAuth
3. MCPRequestHandler.get_allowed_mcp_servers() returns team's MCP servers
4. Key/team permission intersection works correctly
Co-authored-by: ishaan <ishaan@berri.ai>
* test: add simple tests for JWT + MCP permission enforcement
Simple, focused tests that validate:
1. test_simple_jwt_mcp_permissions_enforced: JWT user with team gets team's MCP servers
2. test_simple_jwt_no_team_no_mcp_servers: JWT user without team gets no MCP servers
3. test_simple_jwt_team_id_required_for_mcp_permissions: Verifies team_id is required
4. test_jwt_auth_sets_team_id_for_mcp_route: JWT auth sets team_id for MCP routes
These tests directly verify the core MCP permission enforcement logic works
when using JWT authentication with teams.
Co-authored-by: ishaan <ishaan@berri.ai>
* Add test: MCP route without model still returns team_id
Co-authored-by: ishaan <ishaan@berri.ai>
* Add 2 debug logs for JWT+MCP troubleshooting
- handle_jwt.py: Log team route check result (team_id, route, is_allowed)
- user_api_key_auth_mcp.py: Log team_id when looking up MCP permissions
Co-authored-by: ishaan <ishaan@berri.ai>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
AsyncHTTPHandler.__del__ was closing httpx clients still in use by
AsyncOpenAI/AsyncAzureOpenAI due to independent cache lifecycles.
Restores standalone httpx client creation for OpenAI/Azure providers.
* fix fail-open for grayswan; pass metadata to cygnal api endpoint; update docs
* pass litellm_metadata to cygnal in payload
* switch error msg to const, and clean exception handling.
* update pyproject.toml as requested
* Revert "update pyproject.toml as requested"
This reverts commit 4eece154d056ba33689a5584c86c8fc352bb7cdd.
* fix: check for model_response_choices before guardrail input
* test: add tests for responses api translation
* fix: protect other guardrail translations
* refactor: remove type ignores
* anthropic request body got mutated fix
* add warning when extra_body is provided but user is non premium
* fix: resolve mypy union-attr errors in anthropic guardrail handler
Cast choices[0] to Choices type before accessing .message attribute
to satisfy mypy's union type checking for Choices | StreamingChoices.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* add logger when model response has no choices for streaming /response and /messages
* update pyproject.toml as requested
* Revert "update pyproject.toml as requested"
This reverts commit 541a2b075a91b1b2d9efaf0407572f35bf5d4324.
* update pyproject.toml as requested
* Revert "update pyproject.toml as requested"
This reverts commit 716ea0caa1fee5e5f028d3f86479fedea2fac68b.
---------
Co-authored-by: Xiaohan Fu <xiaohan@grayswan.ai>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
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
