The test used a fixed side_effect list for time.time(), but the number
of calls varies by Python version, causing StopIteration on 3.12 and
AssertionError on 3.14. Replace with an infinite counter-based callable
and assert the timestamp was updated rather than checking for an exact
value.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(budget): fix timezone config lookup and replace hardcoded timezone map with ZoneInfo
* fix(budget): update stale docstring on get_budget_reset_time
* fix: feat: add litellm_system_prompt support
* feat: support new 'litellm_agent' model provider
* feat: ui/ - new agent builder ui
* fix(anthropic/chat/transformation.py): normalize max_tokens if decimal
* feat(agentbuilderview.tsx): run compliance datasets against litellm agent
* feat: new response rejection detector
* fix: multiple fixes
* feat: add mcp tools support to agent builder
create an agent with access to llm's + mcp servers
Replace Click CliRunner with standalone_mode=False to avoid
"I/O operation on closed file" errors caused by Click's stream
isolation in CI environments.
test_vertex_passthrough_with_default_credentials and
test_view_spend_logs_with_date_range_summarized fail intermittently when a
prior xdist worker sets master_key — auth then rejects the unauthenticated
test requests before the code under test is reached.
- mock user_api_key_auth in test_vertex_passthrough_with_default_credentials
(same pattern used for test_vertex_passthrough_with_no_default_credentials
in #21810)
- wrap test_view_spend_logs_with_date_range_summarized in
app.dependency_overrides[ps.user_api_key_auth] with try/finally cleanup
(same pattern used for the other spend log tests in #21810)
- TestSpendLogsPayload: save/restore litellm.cache in setup_method/teardown_method
so tests that run after a cache-setting test don't see a non-None cache and get
a hash instead of "Cache OFF" in the cache_key field
- test_use_prisma_db_push_flag_behavior: apply clean_env pattern (strip DATABASE_URL/DIRECT_URL,
then set DATABASE_URL to test value) inside the with block instead of using @patch.dict
decorator, matching the pattern from test_skip_server_startup to avoid Click 8.3.x
StreamMixer stream lifecycle issues in CI
Tests hardcode expected api_base as https://api.anthropic.com/v1/messages but
if ANTHROPIC_BASE_URL is set in the environment the recorded api_base changes,
causing a mismatch. Clear both env vars via monkeypatch at the start of each test.
* fix(tests): add app.dependency_overrides for auth in spend logs tests
test_ui_view_spend_logs_with_status, test_ui_view_spend_logs_with_model,
test_ui_view_spend_logs_with_model_id, and test_view_spend_logs_summarize_parameter
all send Bearer sk-test without mocking user_api_key_auth. When a prior test
in the same xdist worker sets master_key, the auth check fails for sk-test
and the test fails intermittently.
Fix: use app.dependency_overrides[ps.user_api_key_auth] to bypass auth,
same pattern as other tests in the same file.
* fix(tests): mock user_api_key_auth in test_vertex_passthrough_with_no_default_credentials
vertex_proxy_route calls user_api_key_auth internally. When a prior test in the
same xdist worker sets master_key, the auth check fails for the test request
and create_pass_through_route is never called, causing assert_called_once_with to fail.
Fix: patch user_api_key_auth as an AsyncMock in the with mock.patch() block.
* fix(test): remove deprecated Click mix_stderr param in test_use_prisma_db_push_flag_behavior
Click 8.2+ removed the mix_stderr parameter from CliRunner. Use CliRunner() without it.
* fix(test): use app.dependency_overrides for auth mock in test_role_mappings_stored_and_retrieved
monkeypatch.setattr doesn't affect FastAPI's Depends() resolution in parallel
test execution. Use app.dependency_overrides which is the proper FastAPI pattern.
Any PrismaError should be treated as a DB connection error for the
allow_requests_on_db_unavailable feature and 503 responses. The narrow
keyword-based check is now in is_database_transport_error, which is
what the reconnect logic in auth_checks.py should use.
Fixes test_delete_access_group_503_on_db_connection_error and
test_handle_authentication_error_db_unavailable failures caused by
PR #21706 narrowing is_database_connection_error.
* fix(tests): isolate flaky files endpoint tests from global proxy state
* test(secret_managers): add mocked unit test for write/read JSON secret cycle
* fix(tests): restore litellm.callbacks in TestSpendLogsPayload setup/teardown
* fix(tests): clear app.openapi_schema in TestSwaggerChatCompletions setup/teardown
* fix(tests): add flaky marker to test_async_increment_tokens_with_ttl_preservation
* fix(tests): isolate flaky files endpoint tests from global proxy state
* test(secret_managers): add mocked unit test for write/read JSON secret cycle
- Restore preserve_fields param for backward compatibility (deprecated)
- Use zip() instead of index-based iteration to prevent IndexError
- Add backward compatibility test
* fix: reset db_health_cache in source module to prevent stale cache hits
The test was reassigning db_health_cache via `global` in the test module,
which doesn't affect the _health_endpoints module's variable. When a prior
test set the cache to "connected" within 2 minutes, _db_health_readiness_check
returned early without calling health_check(), causing assert_called_once to fail.
Also use PrismaError with a connection message so it's properly recognized
as a connection error by PrismaDBExceptionHandler.is_database_connection_error.
* fix: replace asyncio.sleep with polling loop in spend logs tests
The GLOBAL_LOGGING_WORKER processes callbacks via an async queue, so
asyncio.sleep(1) is a race condition - under CI load the worker may not
have processed the queued task within 1 second. Replace with a polling
helper that waits up to 10 seconds for the mock to be called.
Also add metadata.attempted_retries and metadata.max_retries to
ignored_keys since these are new fields.
* fix: isolate test_skip_server_startup from CI environment
Remove mix_stderr=False (unsupported in some Click versions). Strip
DATABASE_URL/DIRECT_URL from environment during the test to prevent
real prisma operations when these are set in CI.
POST /access_group/new and PUT /access_group/{name}/update now accept an
optional model_ids list that targets specific deployments by their unique
model_id, instead of tagging every deployment that shares a model_name.
When model_ids is provided it takes priority over model_names, giving
API callers the same single-deployment precision that the UI already has
via PATCH /model/{model_id}/update.
Backward compatible: model_names continues to work as before.
Closes#21544
Add user_email field to LiteLLM_OrganizationMembershipTable with a model_validator
that populates it from the nested user object, and update the /organization/info
Prisma query to select user_email from the related user record.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add competitor name blocker guardrail
* fix: fix batch test endpoint for compliance playground
* fix(airline.py): add list of all known airlines to airline competitor name detector
prevent competitor discussion on company chatbot
* feat: ui tweaks for prod
* Add keyword-based topic blocker implementation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add embedding-based topic blocker using MiniLM
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add topic blocker package init with exports
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add synthetic engine eval set (34 cases)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add investment questions eval set (207 cases)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add engine eval synthetic policy config
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add engine keyword blocker eval results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add investment keyword blocker eval results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add investment embedding blocker eval results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add investment embedding MiniLM eval results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add investment embedding MPNet eval results (historical)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add investment TF-IDF eval results (historical)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add unified eval runner with confusion matrix reporting
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add benchmarks comparison table in markdown
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Clean up topic blocker: remove unused blockers, add phrase_patterns to content filter
- Remove embedding_blocker.py, api_embedding_blocker.py, nli_blocker.py,
tfidf_blocker.py, onnx_blocker.py (heavy deps not in Docker, inferior accuracy)
- Remove airline_off_topic_restriction policy template and its test
- Fix __init__.py to only export DeniedTopic and TopicBlocker (no eager import crash)
- Add phrase_patterns support to ContentFilterGuardrail for regex-based paraphrase detection
- Rewrite denied_financial_advice.yaml with conditional matching (identifier + block word),
always-block keywords, phrase patterns, and exception phrases
- Clean up test_eval.py: only keyword blocker + content filter tests remain (no network calls)
- All 207 eval cases pass at 100% F1, 0 FP, 0 FN, <0.1ms latency
Addresses all Greptile review comments:
- Eager import crash (embedding deps) → fixed
- Undeclared dependencies → fixed (files deleted)
- lru_cache memory leak → fixed (file deleted)
- Real network calls in tests → fixed (embedding tests removed)
- Unused Dict import → already fixed
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add LLM-as-judge eval and update BENCHMARKS.md
- Add TestInvestmentLlmJudgeGpt4oMini and TestInvestmentLlmJudgeClaude
test classes that use litellm.completion() to classify messages
- System prompt instructs LLM to act as airline chatbot content moderator
- Tests skip gracefully when API keys aren't set
- Update BENCHMARKS.md with production results table, historical comparison,
and instructions for running LLM judge evals
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Move evals and benchmarks to guardrail_benchmarks folder
Move eval runner, eval data (JSONL), and results from
tests/test_litellm/.../topic_blocker/ into the guardrail implementation
folder at litellm/.../litellm_content_filter/guardrail_benchmarks/.
This keeps benchmarks co-located with the guardrail code they test.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Remove standalone topic_blocker package, consolidate into content_filter
The standalone keyword_blocker.py was redundant with content_filter.py +
denied_financial_advice.yaml. Removed the entire topic_blocker/ package,
engine eval files, and old keyword blocker results. Simplified test_eval.py
to only test ContentFilter + LLM judge baselines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix compliance playground batch scoring bug, add display_name support
The compliance playground was sending all texts in a single batch API call,
but the content filter raises HTTPException on the first blocked text. This
caused a single blocked/allowed result to be applied to all rows, producing
incorrect scores (e.g. 41% instead of 100%). Fix by sending each text
individually to get per-text results with progressive UI updates.
Also add display_name field support for category YAML files so
denied_financial_advice shows as "Denied Financial / Investment Advice"
in the UI dropdown.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Add block_investment CSV eval set and update benchmark result JSON
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* address greptile review feedback (greploop iteration 1)
Fix stale test path in denied_financial_advice.yaml comment.
Other comments were on files already deleted in prior commits.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <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>
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>
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>
