For multi-turn conversations, convert thinking_blocks on assistant
messages into content blocks prepended before the rest of the content,
so reasoning context is passed back to the hosted_vllm API.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Virtual keys only track created_at and updated_at, which don't indicate
when a key was last used. This adds a last_active field that gets updated
during the async batch spend update, giving admins visibility into which
keys are actively being used.
Changes:
- Add last_active DateTime? to VerificationToken and
DeletedVerificationToken in all 3 schema files and Python types
- Set last_active in the batch key spend update alongside spend increment
- Add Last Active column to virtual keys UI table with info popover
and hover tooltip showing full date/time with timezone
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix aviation safety topic filter: remove overly broad exceptions, add cockpit access block words
* fix airline brand protection filter: add identifier words, competitor/ops block words, tighten exceptions
* update policy templates with competitor pre/post guardrails and streaming enrichment
* sync policy_templates_backup.json with policy_templates.json
* add streaming enrichment endpoint, competitor variations, and model selection
* add streaming enrichPolicyTemplate networking function
* rewrite template parameter modal with streaming tags, AI/manual toggle, model selector
* update policies panel to pass enrichment options and show discovered competitors
* show discovered competitors as tags in guardrail selection modal
* use llm_router instead of litellm.acompletion, extract helpers, move constants
* validate competitors list size, cap variation prompt input
* add refinement instruction support for competitor discovery
* add instruction and existingCompetitors params to streaming enrichment
* add refinement input for iterating on competitor list with AI
* emit status events during variation generation so UI shows progress
* add onStatus callback to streaming enrichment
* show status spinner during variation generation, widen modal to 700px
* add tests for competitor enrichment helper functions
Add a new team member permission `/team/daily/activity` that allows
non-admin team members to see all team usage data, not just their own.
## Changes
- Add `TEAM_DAILY_ACTIVITY` to `KeyManagementRoutes` enum and available
team member permissions
- Add `_team_member_has_permission` helper in `common_utils.py`
- Modify `/team/daily/activity` endpoint to skip API key filtering when
the member has this permission
- Add permission description and method detection in the UI
- Add backend and frontend tests
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Four tests were broken by commit e00c181f0c (Mcp user permissions #21462):
1. test_list_tools_single_server_unprefixed_names: The commit changed
_get_tools_from_mcp_servers to always add server prefixes (add_prefix=True),
removing the conditional that skipped prefixing for single servers.
Updated assertion from "toolA" → "zapier-toolA".
2. test_mcp_get_prompt_success: mcp_get_prompt now extracts the server name
from a prefixed prompt name via split_server_prefix_from_name(). Passing
unprefixed "hello" returns server_name="" which matches no server → 403.
Updated call to use "server_a-hello" so the server lookup succeeds.
3. test_e2e_jwt_team_mcp_permissions_enforced &
4. test_e2e_jwt_team_mcp_key_intersection:
The commit replaced `from typing import List` with
`from litellm.proxy.proxy_server import general_settings` in
MCPRequestHandler.get_allowed_mcp_servers(). Both tests mock
litellm.proxy.proxy_server with a types.ModuleType that lacked
general_settings, causing ImportError. Added general_settings={} to
both mock modules.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Cast `guardrail` to `Dict[str, Any]` in `mcp_end_user_permission/__init__.py`
to fix "No overload variant of 'get' matches argument type 'str'" — the
`Guardrail` TypedDict's `.get()` overloads resolve the key type to `Never`
when chained with a `{}` default, making further `.get()` calls fail.
- Cast `fn` to `Dict[str, Any]` in `transformation.py`
`transform_chat_completion_tool_params_to_responses_api_tools` to fix
'"object" has no attribute "get"' — `tool.get("function")` on
`Union[ChatCompletionFunctionToolParam, OpenAIMcpServerTool]` returns
`object` because `"function"` is not a key in `OpenAIMcpServerTool`.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
test_complete_reload_flow and test_distributed_reload_check_function both
trigger code paths that assign a minimal stub dict to litellm.model_cost
(via the /reload/model_cost_map endpoint and _check_and_reload_model_cost_map).
Without restoring, subsequent tests in the same worker can't find gpt-4o
pricing and calculate spend=0.0 instead of the expected value.
Added try/finally save-and-restore of litellm.model_cost in both tests,
matching the pattern used in test_reload_model_cost_map_admin_access.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(schema.prisma): add object permissions for end users
allows controlling if end user can call specific mcp servers
* feat: cleanup for customer_endpoints support of object permission id
* fix: cleanup str
* feat(customers/): enforce end user can only call allowed mcps - if configured
* docs: document customer/end user object permission usage
* feat: enforce end user permissions on MCP tool calls
This commit implements end user permission enforcement for MCP servers:
1. Always add server prefixes to MCP tool names
- Removed conditional logic that only added prefixes when multiple servers existed
- Now always adds server prefix for consistent tool naming across all scenarios
- Updated 5 locations in server.py (list_tools, get_prompts, get_resources,
get_resource_templates, get_prompt)
2. Created MCP End User Permission Guardrail Hook
- New guardrail hook: litellm/proxy/guardrails/guardrail_hooks/mcp_end_user_permission.py
- Runs on post_call to validate tool calls in LLM responses
- Extracts MCP server name from tool names (splits on first '-')
- Checks if end_user_id has permissions for the MCP server
- Raises GuardrailRaisedException if end user lacks permission
- Supports both streaming and non-streaming responses
3. Added comprehensive tests
- Test file: tests/test_litellm/proxy/guardrails/guardrail_hooks/test_mcp_end_user_permission.py
- Tests cover: authorized/unauthorized tools, non-MCP tools, no end_user scenarios
- Tests permission checking logic and exception raising
The hook integrates with the existing MCPRequestHandler._get_allowed_mcp_servers_for_end_user
to fetch end user permissions and enforce access control at the response level.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* refactor: remove redundant add_prefix variable assignments
Simplified the code by removing intermediate `add_prefix` variable
assignments and passing `True` directly to function calls since
we now always add server prefixes.
Changes:
- Removed `add_prefix = True` variable assignments in 5 locations
- Changed `add_prefix=add_prefix` to `add_prefix=True` in function calls
- Added inline comments to clarify the behavior
This makes the code more concise and clearer in intent.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* feat(auth_utils.py): support safety_identifier as a valid way of passing the end user id for responses api
* feat(llms): ensure 'tools' is correctly updated for responses api
* fix: fix greptile feedback
* feat: transformation.py
proper responses api tool handling for guardrail translation layer
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
