mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-15 23:31:29 +00:00
b2c5b3267c
/vector_store/list (#25947) Vector stores declared under `vector_store_registry:` in proxy_config.yaml are loaded into `litellm.vector_store_registry` in memory only — they are never written to the `litellm_managedvectorstorestable` DB table. But `list_vector_stores` treats the DB as the source of truth and runs a reconcile step that deletes any in-memory entry missing from the DB, on the assumption that a disappeared DB row means the entry was deleted at runtime. That assumption doesn't hold for config-declared entries: they're *supposed* to live only in memory, so the reconcile step silently pruned them on every /vector_store/list call and the UI at `/ui/?page=vector-stores` always appeared empty, as reported in #25947. Fix: - Mark entries that came from `load_vector_stores_from_config` with `from_litellm_config=True` (new optional field on `LiteLLM_ManagedVectorStore`). - Teach `list_vector_stores` to skip the "missing from DB => delete" branch for those entries; they are included in the response and left untouched in the in-memory registry. - Stale *runtime* entries (API-created rows that the DB no longer knows about) are still pruned — that path is unchanged. Test coverage: - `test_load_vector_stores_from_config_marks_from_litellm_config` - `test_add_vector_store_to_registry_does_not_mark_from_litellm_config` - `test_list_vector_stores_returns_config_loaded_even_when_db_empty` (direct repro of #25947) - `test_list_vector_stores_still_prunes_stale_runtime_entries` (regression guard — the old behaviour is correct for non-config entries and must not regress) - `test_list_vector_stores_mixed_config_and_db` (config and DB entries coexist without masking each other) `pytest tests/test_litellm/vector_stores/test_vector_store_registry.py tests/test_litellm/proxy/vector_store_endpoints/test_vector_store_endpoints.py` — 53 passed (5 new + 48 pre-existing). Fixes #25947 |
||
|---|---|---|
| .. | ||
| agent_tests | ||
| audio_tests | ||
| basic_proxy_startup_tests | ||
| batches_tests | ||
| benchmarks | ||
| code_coverage_tests | ||
| documentation_tests | ||
| enterprise | ||
| guardrails_tests | ||
| image_gen_tests | ||
| litellm | ||
| litellm-proxy-extras | ||
| litellm_core_utils | ||
| litellm_utils_tests | ||
| llm_responses_api_testing | ||
| llm_translation | ||
| load_tests | ||
| local_testing | ||
| logging_callback_tests | ||
| mcp_tests | ||
| multi_instance_e2e_tests | ||
| ocr_tests | ||
| old_proxy_tests/tests | ||
| openai_endpoints_tests | ||
| otel_tests | ||
| pass_through_tests | ||
| pass_through_unit_tests | ||
| proxy_admin_ui_tests | ||
| proxy_e2e_anthropic_messages_tests | ||
| proxy_security_tests | ||
| proxy_unit_tests | ||
| router_unit_tests | ||
| scim_tests | ||
| search_tests | ||
| spend_tracking_tests | ||
| store_model_in_db_tests | ||
| test_litellm | ||
| unified_google_tests | ||
| vector_store_tests | ||
| windows_tests | ||
| __init__.py | ||
| gettysburg.wav | ||
| large_text.py | ||
| openai_batch_completions.jsonl | ||
| README.MD | ||
| test_budget_management.py | ||
| test_callbacks_on_proxy.py | ||
| test_config.py | ||
| test_debug_warning.py | ||
| test_default_encoding_non_root.py | ||
| test_end_users.py | ||
| test_entrypoint.py | ||
| test_fallbacks.py | ||
| test_gpt5_azure_temperature_support.py | ||
| test_health.py | ||
| test_keys.py | ||
| test_litellm_proxy_responses_config.py | ||
| test_logging.conf | ||
| test_models.py | ||
| test_new_vector_store_endpoints.py | ||
| test_openai_endpoints.py | ||
| test_organizations.py | ||
| test_otel_thread_leak.py | ||
| test_passthrough_endpoints.py | ||
| test_presidio_latency.py | ||
| test_proxy_server_non_root.py | ||
| test_ratelimit.py | ||
| test_resource_cleanup.py | ||
| test_service_logger_otel.py | ||
| test_spend_logs.py | ||
| test_team.py | ||
| test_team_logging.py | ||
| test_team_members.py | ||
| test_users.py | ||
In total litellm runs 1000+ tests
[02/20/2025] Update:
To make it easier to contribute and map what behavior is tested,
we've started mapping the litellm directory in tests/test_litellm
This folder can only run mock tests.