* fix(test): add missing mocks for test_streamable_http_mcp_handler_mock
The test was missing mocks for extract_mcp_auth_context and set_auth_context,
causing the handler to fail silently in the except block instead of reaching
session_manager.handle_request. This mirrors the fix already applied to the
sibling test_sse_mcp_handler_mock.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix(ci): route OpenAI models through chat completions in pass-through tests
The test_anthropic_messages_openai_model_streaming_cost_injection test fails
because the OpenAI Responses API returns 400 for requests routed through the
Anthropic Messages endpoint. Setting LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES=true
routes OpenAI models through the stable chat completions path instead.
Cost injection still works since it happens at the proxy level.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix(ci): fix assemblyai custom auth and router wildcard test flakiness
1. custom_auth_basic.py: Add user_role='proxy_admin' so the custom auth
user can access management endpoints like /key/generate. The test
test_assemblyai_transcribe_with_non_admin_key was hidden behind an
earlier -x failure and was never reached before.
2. test_router_utils.py: Add flaky(retries=3) and increase sleep from 1s
to 2s for test_router_get_model_group_usage_wildcard_routes. The async
callback needs time to write usage to cache, and 1s is insufficient on
slower CI hardware.
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* ci: retrigger CI pipeline
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix(mypy): use LitellmUserRoles enum instead of raw string in custom_auth_basic
Fixes mypy error: Argument 'user_role' has incompatible type 'str'; expected 'LitellmUserRoles | None'
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
* fix: don't close HTTP/SDK clients on LLMClientCache eviction (#22926)
* fix: don't close HTTP/SDK clients on LLMClientCache eviction
Removing the _remove_key override that eagerly called aclose()/close()
on evicted clients. Evicted clients may still be held by in-flight
streaming requests; closing them causes:
RuntimeError: Cannot send a request, as the client has been closed.
This is a regression from commit fb72979432. Clients that are no longer
referenced will be garbage-collected naturally. Explicit shutdown cleanup
happens via close_litellm_async_clients().
Fixes production crashes after the 1-hour cache TTL expires.
* test: update LLMClientCache unit tests for no-close-on-eviction behavior
Flip the assertions: evicted clients must NOT be closed. Replace
test_remove_key_closes_async_client → test_remove_key_does_not_close_async_client
and equivalents for sync/eviction paths.
Add test_remove_key_removes_plain_values for non-client cache entries.
Remove test_background_tasks_cleaned_up_after_completion (no more _background_tasks).
Remove test_remove_key_no_event_loop variant that depended on old behavior.
* test: add e2e tests for OpenAI SDK client surviving cache eviction
Add two new e2e tests using real AsyncOpenAI clients:
- test_evicted_openai_sdk_client_stays_usable: verifies size-based eviction
doesn't close the client
- test_ttl_expired_openai_sdk_client_stays_usable: verifies TTL expiry
eviction doesn't close the client
Both tests sleep after eviction so any create_task()-based close would
have time to run, making the regression detectable.
Also expand the module docstring to explain why the sleep is required.
* docs(AGENTS.md): add rule — never close HTTP/SDK clients on cache eviction
* docs(CLAUDE.md): add HTTP client cache safety guideline
* [Fix] Install bsdmainutils for column command in security scans
The security_scans.sh script uses `column` to format vulnerability
output, but the package wasn't installed in the CI environment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: handle string callback values in prometheus multiproc setup
When callbacks are configured as a plain string (e.g., `callbacks: "my_callback"`)
instead of a list, the proxy crashes on startup with:
TypeError: can only concatenate str (not "list") to str
Normalize each callback setting to a list before concatenating.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* bump: version 1.82.2 → 1.82.3
* fix(test): update test_startup_fails_when_db_setup_fails for opt-in enforcement
The --enforce_prisma_migration_check flag is now required to trigger
sys.exit(1) on DB migration failure, after #23675 flipped the default
behavior to warn-and-continue.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(cost_calculator): use model name for per-request custom pricing when router_model_id has no pricing
When custom pricing is passed as per-request kwargs (input_cost_per_token/output_cost_per_token),
completion() registers pricing under the model name, but _select_model_name_for_cost_calc was
selecting the router deployment hash (which has no pricing data), causing response_cost to be 0.0.
Now checks whether the router_model_id entry actually has pricing before preferring it.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Replace gemini-pro with gemini-3-pro-preview in test_cost_discount_vertex_ai
(gemini-pro removed from cost map)
- Replace github/claude-3-5-sonnet-latest with github/claude-3-7-sonnet-20250219
in test_supports_function_calling_github_anthropic_alias (model removed)
- Add supports_multimodal, uses_embed_content, input/output_cost_per_token_above_256k_tokens
to JSON schema in test_utils.py (new properties added to model cost map)
Co-authored-by: yuneng-jiang <yuneng-jiang@users.noreply.github.com>
Pre-resolve CallTypes enum values into module-level frozensets to avoid
repeated .value attribute access in the elif chain. Inline the hot-path
_store_cost_breakdown_in_logging_obj as a direct dict literal. Remove
unnecessary cast(CallTypesLiteral, call_type) call. Guard
_get_additional_costs() with azure_ai-only check since no other provider
implements additional costs.
Line profile shows 20.5% reduction in completion_cost() total time
(7.14s → 5.68s across 6,006 calls). The four targeted bottlenecks
dropped from 2.82s to 0.28s combined.
When Gemini uses implicit caching, it returns cachedContentTokenCount but
NOT cacheTokensDetails. Previously, text_tokens was not adjusted in this case,
causing costs to be calculated as if all tokens were non-cached.
This fix subtracts cachedContentTokenCount from text_tokens when no
cacheTokensDetails is present (implicit caching), ensuring correct cost
calculation with the reduced cache_read pricing.
Azure audio models were charging audio output tokens at the text token
rate instead of the correct audio token rate. This resulted in costs
being ~6.65x lower than expected.
The fix replaces Azure's custom cost calculation logic with the generic
cost calculator that properly handles text, audio, cached, reasoning,
and image tokens.
Fixes#19764
- Add @lru_cache decorator to get_model_info() and _cached_get_model_info_helper()
- Update _invalidate_model_cost_lowercase_map() to clear these caches when model_cost changes
- Update test to call cache invalidation after modifying litellm.model_cost
Reduces get_model_cost_information from 46% to <1% of request handling time.
* fix(gemini): prevent negative text_tokens with explicit caching (#18750)
## Problem
When using Gemini with explicit caching (especially with images),
text_tokens would become negative (e.g., -3327) due to incorrectly
subtracting total cached_tokens from modality-specific text_tokens.
## Root Cause
The old code did:
```python
text_tokens = text_tokens - cached_tokens # 737 - 4064 = -3327
```
This was wrong because:
- cached_tokens includes ALL modalities (text + image + audio + video)
- text_tokens only contains text
- Subtracting total from specific caused negative values
## Solution
Parse cacheTokensDetails to get per-modality cached token breakdown:
```python
if "cacheTokensDetails" in usage_metadata:
cached_text_tokens = parse from cacheTokensDetails["TEXT"]
text_tokens = text_tokens - cached_text_tokens # Correct!
```
Now we subtract cached tokens per modality, preventing negatives.
## Changes
- Parse cacheTokensDetails field from Gemini response
- Calculate non-cached tokens per modality (text, image, audio)
- Remove incorrect global cached_tokens subtraction
- Add tests for explicit caching and implicit/no caching scenarios
## Testing
- Added test_gemini_cache_tokens_details_no_negative_values
- Added test_gemini_without_cache_tokens_details
- All existing Gemini caching tests pass
Fixes#18750
* feat: add cache_read_input_tokens to Usage object
Addresses reviewer feedback to include cached tokens at the top level
of the Usage object. This aligns with how Anthropic provider handles
cached tokens and ensures they are visible in the final usage response.
* fix: add cacheTokensDetails field to UsageMetadata TypedDict
Fixes mypy error where cacheTokensDetails was being accessed but not defined
in the UsageMetadata TypedDict type definition.
Added cache_read_input_token_cost (25% of regular input cost) to all 39 Gemini 2.x models
to properly support implicit context caching cost calculations. Previously, cached tokens
were being charged at full price instead of the discounted rate.
Fixes#11156
