Custom user-added routes (e.g. /ldap/ngs/ready) used with Depends(user_api_key_auth) were being rejected as admin-only after _run_post_custom_auth_checks was introduced in commit 14badde13c.
The route authorization check in common_checks is designed for LiteLLM's own management routes. Custom auth flows that add their own routes should be trusted since the custom auth function already validated the request. Budget and expiry checks still run.
Add skip_route_check parameter to common_checks() and pass skip_route_check=True from _run_post_custom_auth_checks() to skip route authorization while preserving budget/team/model checks.
Regression test added: test_common_checks_skip_route_check_for_custom_auth
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Extract duplicated batch ID encoding logic into a shared helper
encode_batch_response_ids() in common_utils.py. Use it in create_batch,
retrieve_batch, and cancel_batch. Also add encoding to list_batches
when x-litellm-model is used.
The provider returns raw IDs in the retrieve response (output_file_id,
error_file_id). These need to be encoded with model info so the client
can use them for subsequent file download calls through the proxy.
When create_batch routes via x-litellm-model header, the response batch_id
was returned raw without model routing info. This meant retrieve_batch could
not determine which provider/credentials to use, defaulting to "openai"
instead of the correct provider (e.g., VLLM).
Now encodes batch_id, output_file_id, and error_file_id with model info
(same pattern as the model-embedded file_id flow in Scenario 1), so
retrieve_batch can decode and route back to the correct provider.
Fixes#22646
Adds pricing for DashScope models that were missing from the cost map,
causing $0 spend tracking in the proxy dashboard:
- dashscope/qwen3-max-2026-01-23 (tiered, same as qwen3-max)
- dashscope/qwen3-next-80b-a3b-instruct ($0.15/$1.20 per 1M)
- dashscope/qwen3-next-80b-a3b-thinking ($0.15/$1.20 per 1M)
- dashscope/qwen3-vl-235b-a22b-instruct ($0.40/$1.60 per 1M)
- dashscope/qwen3-vl-235b-a22b-thinking ($0.40/$4.00 per 1M)
- dashscope/qwen3-vl-32b-instruct ($0.16/$0.64 per 1M)
- dashscope/qwen3-vl-32b-thinking ($0.16/$2.87 per 1M)
Fixes#22609
Adds pricing for OpenRouter models that were routing correctly but
returning $0 for spend tracking due to missing cost map entries:
- openrouter/anthropic/claude-sonnet-4.6 ($3.00/$15.00 per 1M tokens)
- openrouter/google/gemini-3.1-pro-preview ($2.00/$12.00 per 1M tokens)
- openrouter/openai/gpt-5.1-codex-max ($1.25/$10.00 per 1M tokens)
- openrouter/qwen/qwen3-coder-plus ($1.00/$5.00 per 1M tokens)
- openrouter/z-ai/glm-5 ($0.80/$2.56 per 1M tokens)
* feat(guardrails): team-based guardrail registration and approval workflow
Add team-based guardrail submission system where teams can register
Generic Guardrail API guardrails for admin review. Includes:
- POST /guardrails/register endpoint for team-scoped submissions
- Admin review endpoints (list/get/approve/reject submissions)
- Team Guardrails tab in the UI dashboard
- extra_headers support for forwarding client headers to guardrail APIs
- Prisma schema migration for status, submitted_at, reviewed_at fields
- Documentation for team-based guardrails and static/dynamic headers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(guardrails): address review feedback - SSRF, silent failure, redundant query
- Validate api_base URL scheme (http/https only) and hostname in
register_guardrail to prevent SSRF via team submissions
- Return warning field in approve response when in-memory initialization
fails so admins know the guardrail won't work until next sync cycle
- Eliminate redundant DB query in list_guardrail_submissions by fetching
all team guardrails once and deriving both filtered list and summary
counts from the single result set
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(guardrails): add pending_review status guard to reject endpoint
Prevent rejecting already-active or already-rejected guardrails, which
would create a DB/memory inconsistency (active in memory but rejected
in DB). Now mirrors the approve endpoint's status check.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
OpenRouter supports the Responses API at /api/v1/responses with
encrypted_content for multi-turn stateless reasoning workflows.
Without native registration, requests fall through to the chat
completion bridge, which uses a different format (reasoning_details)
and drops encrypted_content entirely.
This adds OpenRouterResponsesAPIConfig to route requests directly to
OpenRouter's Responses API endpoint, preserving encrypted_content.
Fixes https://github.com/BerriAI/litellm/issues/22189
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
The _resolve_jwks_url method checks response.status_code != 200, but
MagicMock returns a MagicMock object for status_code which is always
truthy (!= 200). Explicitly set mock_response.status_code = 200 so the
tests exercise the intended code path.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
