- Revert test_anthropic_web_search_in_model_info to use claude-3-5-haiku-latest
(model info test doesn't make API calls, so the -latest alias is fine here)
- Replace claude-3-7-sonnet-20250219 with claude-sonnet-4-5-20250929 in
test_anthropic_prompt_caching.py (10 instances)
- Include pending doc updates for COMPETITOR_LLM_TEMPERATURE and
MAX_COMPETITOR_NAMES env vars in config_settings.md
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add new SpendLogsMetadata keys to ignored_keys in spend logs tests
(regression from ccecc10c82 which intentionally includes all keys)
- Mock PrismaManager.setup_database and should_update_prisma_schema in
proxy CLI tests to prevent real DB migrations from running in CI
- Use CliRunner(mix_stderr=False) to fix Click stream lifecycle issues
- Use unique UUID suffix for Redis TTL test keys to avoid stale state
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace claude-3-7-sonnet-20250219 with claude-sonnet-4-5-20250929 in
test_anthropic_completion.py (9 instances). Add missing "store" param
to OPENAI_CHAT_COMPLETION_PARAMS to fix test_store_in_openai_chat_completion_params.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(responses): fix O(n²) CPU overhead in reasoning streaming path
stream_chunk_builder was called on every reasoning chunk, rebuilding the
entire response from all collected chunks each time. Replace with
incremental accumulation of reasoning_content parts, only joining at
reasoning end.
* fix(responses): eliminate per-chunk thread spawning in async streaming path
_process_chunk() called run_async_function() on every SSE chunk, which
when invoked from an async context spawns a thread + event loop per call.
Move the hook call out of _process_chunk into the callers: async __anext__
directly awaits it, sync __next__ uses run_async_function.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* perf: reduce responses streaming CPU for text-only streams
* fix(test): replace deprecated claude-3-7-sonnet-latest in responses API test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(test): replace deprecated claude-3-7-sonnet-latest in tool result fix test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(test): replace deprecated claude-3-7-sonnet-latest in tool result empty call_id test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add attempted_retries and max_retries fields to SpendLogsMetadata so the
Logs page can display how many retries occurred for each request. The
router now injects retry tracking metadata before each make_call, which
flows through the logging pipeline into the spend logs metadata JSON.
The UI shows "Not Retried" when the first attempt succeeded, and
"N / M" (attempted / max) when retries occurred. The field is hidden
for requests that did not go through the router.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bedrock multimodal embedding models (Titan and Nova) were being costed
using the per-token text rate instead of the correct flat per-image rate
($0.00006/image). The pricing data was correct but never applied because
image_count was never populated in prompt_tokens_details.
Pass batch_data to Titan/Nova response transformers so they can count
image inputs and set PromptTokensDetailsWrapper(image_count=N) on Usage,
mirroring the existing Vertex AI pattern from PR #9623. Also fix the
text_tokens fallback in generic_cost_per_token to not override
text_tokens=0 when image_count > 0 (image-only requests).
Vertex AI batch IDs are plain numeric strings (e.g., "3814889423749775360")
unlike OpenAI's "batch_"-prefixed IDs. encode_file_id_with_model() was
defaulting to "file-" prefix for unrecognized ID formats, causing Vertex AI
batch responses to return IDs like "file-bGl0ZWxsbTox..." instead of the
expected "batch_..." prefix per the OpenAI Batch API contract.
Add an optional id_type parameter to encode_file_id_with_model() so the
batch creation endpoint can specify id_type="batch" when encoding batch
response IDs. Default remains "file" for backward compatibility.
Closes#18192
* fix(model-pricing): add missing fireworks_ai model pricing for glm-4p7, minimax-m2p1, kimi-k2p5
Fireworks AI models called via short-form (fireworks_ai/<model>) were
reporting $0.00 cost because the pricing JSON lacked short-form entries.
The lookup fell through to the fireworks-ai-default bucket which has
zero cost.
Added 5 new entries to model_prices_and_context_window.json:
- fireworks_ai/accounts/fireworks/models/glm-4p7 (new long-form)
- fireworks_ai/accounts/fireworks/models/minimax-m2p1 (new long-form)
- fireworks_ai/glm-4p7 (new short-form)
- fireworks_ai/minimax-m2p1 (new short-form)
- fireworks_ai/kimi-k2p5 (new short-form; long-form already existed)
Pricing sourced from fireworks.ai model pages and pricing page.
* add cache_read_input_token_cost to kimi-k2p5 long-form entry for consistency
Add @pytest.mark.skip to all test functions that use the real `prisma_client`
fixture (requiring an external PostgreSQL connection) across 7 test files.
Files updated:
- tests/proxy_unit_tests/test_proxy_server.py (5 tests)
- tests/proxy_admin_ui_tests/test_key_management.py (11 tests)
- tests/proxy_admin_ui_tests/test_role_based_access.py (5 tests)
- tests/proxy_admin_ui_tests/test_usage_endpoints.py (3 tests)
- tests/local_testing/test_blocked_user_list.py (2 tests)
- tests/local_testing/test_add_update_models.py (1 test)
- tests/local_testing/test_update_spend.py (1 test)
Total: 28 new skip markers added.
Note: tests using mock_prisma_client (properly mocked) are unaffected.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
httpx.ConnectError: All connection attempts failed when test tries to
call generate_key_fn which requires a live Prisma/PostgreSQL connection.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
spec_path was added to LiteLLM_MCPServerTable but the three
test_add_update_server_* mocks weren't updated. MagicMock auto-creates
a MagicMock for unset attributes, which fails the Optional[str] Pydantic
validation. Fixes test_add_update_server_with_alias,
test_add_update_server_without_alias and
test_add_update_server_fallback_to_server_id.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add @pytest.mark.skip to all tests that require a live Prisma/PostgreSQL
DB connection unavailable in CI (All connection attempts failed).
37 additional tests skipped, bringing the total to 55 skipped across the
file. Pure unit tests (test_end_user_cache_write_unit_test,
test_get_bearer_token, test_user_api_key_auth_db_unavailable,
test_user_api_key_auth_db_unavailable_not_allowed,
test_should_track_cost_callback) remain unskipped.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add @pytest.mark.skip to test_create_audit_log_in_db which requires
a live Prisma/PostgreSQL DB connection unavailable in CI
- Sync root schema.prisma with litellm/proxy/schema.prisma by adding
the spec_path field to LiteLLM_MCPServerTable, fixing
test_aaaasschema_migration_check which detected this drift
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
For gemini-3-pro-preview (not gemini-3-flash or gemini-3.1-pro-preview),
reasoning_effort="medium" maps to thinkingLevel="high" because the "medium"
thinking level is not available on that model variant.
Both test_reasoning_effort_maps_to_thinking_level_gemini_3 and
test_reasoning_effort_dict_format_gemini_3 had the correct comment
("medium -> high") but the wrong assertion (== "medium"). Fixed to
match the production code and the comments.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The parametrized test covers both gemini-2.5-pro (needs GEMINI_API_KEY)
and vertex-ai-gemini-2.5-pro (needs VERTEX_AI_PRIVATE_KEY). A skipif
on GEMINI_API_KEY alone was insufficient for the vertex variant.
Switch to @pytest.mark.skip to guard both parametrizations consistently.
Addresses Greptile review comment on PR #21669.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Mark DB-dependent tests in test_key_generate_prisma.py and test_jwt.py
with @pytest.mark.skip to prevent CI failures when Prisma DB is unavailable.
Tests now skipped:
- test_call_with_invalid_key
- test_call_with_invalid_model
- test_call_with_end_user_over_budget
- test_aasync_call_with_key_over_model_budget (all 3 parametrize variants)
- test_call_with_key_never_over_budget
- test_aview_spend_per_user
- test_aadmin_only_routes
- test_auth_vertex_ai_route
- test_team_token_output (both audience variants)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Mark tests that require Prisma DB connections or external API credentials
with @pytest.mark.skip / @pytest.mark.skipif so they don't block CI runs
when the infrastructure is unavailable.
Tests skipped:
- test_create_user_default_budget (Prisma DB)
- test_gemini_pass_through_endpoint (GEMINI_API_KEY / GOOGLE_API_KEY)
- test_vertex_ai_gemini_token_counting_with_contents (Google API creds)
- test_new/update/delete/info_project (Prisma DB)
- test_create/list/get/delete_skill_sdk (Prisma DB)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
generate_key_fn calls validate_model_max_budget which raises
"You must have an enterprise license to set model_max_budget" unless
premium_user=True. The test was hitting this gate before it could
exercise the actual per-model budget logic, causing all three variants
to fail with an enterprise-check error instead of the expected budget
exceeded / pass-through result.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The production error message was expanded when Sonnet 4.6 was also added as
a supported model for effort='max'. The test's match regex still referenced
the old "Claude Opus 4.6"-only message; update it to match the new
"Claude 4.6 models" wording.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Reset logo_path to default_logo when custom UI_LOGO_PATH file doesn't
exist, so the else branch at the bottom of get_image serves the default
logo instead of the non-existent custom path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add os.path.exists check before serving custom local logo so that a
non-existent UI_LOGO_PATH gracefully falls through to the cache/default
instead of causing a FileResponse error.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
RedisCache() without arguments fails at construction with
"ValueError: Either 'host' or 'url' must be specified for redis."
The actual Redis connection is irrelevant since async_set_cache is mocked.
Unlike test_get_team_redis which uses client_no_auth (which sets REDIS_HOST
via fake_env_vars), test_team_update_redis has no fixture setting that env var.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
JWT auth is an enterprise-only feature. Tests that call user_api_key_auth
with enable_jwt_auth=True must set premium_user=True on the proxy server
to bypass the enterprise gate, otherwise they fail with:
ValueError: JWT Auth is an enterprise only feature.
This follows the same pattern as PR #21285 (fix/jwt-enterprise-license-test).
Fixed tests:
- test_team_token_output
- test_allowed_routes_admin
- test_allow_access_by_email
- test_end_user_jwt_auth
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The /get_image endpoint checked for cached_logo.jpg before reading the
UI_LOGO_PATH env var, so a pre-existing cache (e.g. baked into the base
Docker image) would always be served, ignoring the user's custom logo.
Move the UI_LOGO_PATH read before the cache check and serve local file
paths directly, bypassing the cache. The cache optimization is preserved
for HTTP URLs and the default logo where it is actually needed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Empty system messages were skipped for Anthropic's system param but
not removed from the messages list, causing BadRequestError when
anthropic_messages_pt encountered the unsupported "system" role.
Fixes#21622
Regular team members could not see service accounts belonging to their
team. Additionally, former team members could still see service accounts
they created via the created_by filter after leaving the team.
- Add get_member_team_ids() to retrieve all teams a user belongs to
- Regular members now see team service accounts (user_id=NULL) but not
other members' personal keys
- Scope created_by filter to the user's current team memberships
- Add 7 unit tests covering the new visibility rules
Replace find_many + Python-side aggregation with a single SQL GROUP BY
query via query_raw in get_daily_activity_aggregated. This collapses
rows across entities (users/teams/orgs) in the database, reducing ~150k
rows to ~2-3k grouped rows before transfer to Python.
Also adds composite indexes (entity_id, date) to all 6 daily spend
tables for faster filtered queries.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
