scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-13 23:11:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 152
litellm/tests/test_litellm/proxy
History
Exact
Yassin Kortam a8b94b9a87
Some checks failed
Agent Shin — rollout heads-up (one-shot) / heads-up (push) Has been cancelled
Details
fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is unreliable (#30684) 
Budget enforcement reads spend from the cross-pod Redis counter via get_current_spend, which trusted the counter whenever Redis returned a value. A Redis instance that restarts and reloads an older RDB snapshot (the customer's logs repeat "Redis is loading the dataset in memory") comes back with a stale-low counter; that read is a hit, not a clean miss, so the existing DB reseed never ran and a key kept getting admitted even though its recorded spend was already over max_budget. The symptom was recorded spend sitting above the limit while requests kept succeeding.

Read-time enforcement: get_current_spend takes an optional max_budget and, when the counter would admit the request but reads below this caller's last-known recorded spend, re-reads the authoritative spend and enforces against the higher value. The authoritative source depends on the counter: key/team/user/org/team-member read the DB row, per-window budgets aggregate spend logs, and end-user/tag have no DB row so the caller's freshly-loaded recorded spend is used. Healthy primary counters and freshly reset keys stay off the DB path, and the value is cached in-process for a few seconds, so a persistently stale counter drives at most one read per counter per window. When the DB value is higher, the counter is repaired with a monotonic, atomic set-max (RedisCache.async_set_max) so every worker reads the corrected total and a concurrent increment is never clobbered.

Reconcile no longer fails open: when the post-call reservation reconcile found the counter missing or an adjustment that would drive it negative, it deleted the counter and continued (the deletion is what left counters nil/unenforced after a Redis reload). It now reseeds from the DB's lagging authoritative floor instead of deleting; the monotonic set-max can only raise a stale-low counter, and the read-time floor converges to the true total as the spend buffer flushes. The pre-call admission resize path keeps its original fail-closed behavior.

Opt-in strict enforcement: general_settings.fail_closed_budget_enforcement (default False) makes the authoritative re-check run for every budgeted entity (closing the gap where a stale-low counter and a stale-low cached fallback would otherwise both pass the cheap guard), and rejects a request with 503 when the spend backing an admit decision can be verified against neither Redis nor the database. Default behavior is unchanged; the re-check stays bounded by the in-process cache.

Resolves LIT-3772
2026-06-18 10:35:41 -07:00
..
_experimental/mcp_server chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
a2a feat(a2a): well-known agent-card discovery + LangGraph Platform mode (#28860) 2026-05-29 20:50:42 -07:00
agent_endpoints fix(a2a): forward agent_extra_headers through completion bridge (#28277) 2026-06-11 21:56:18 -07:00
anthropic_endpoints chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
auth fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is unreliable (#30684) 2026-06-18 10:35:41 -07:00
client feat(cli): per-agent lite claude / codex / opencode commands that wrap coding agents through the proxy (#29850) 2026-06-10 13:52:26 -07:00
common_utils fix(callbacks): forward callback_settings to callback initializers and guard consumers against non-dict values (#30161) 2026-06-10 15:22:00 -07:00
db chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
discovery_endpoints chore: litellm oss staging160626 (#30527) 2026-06-16 18:23:13 -07:00
experimental/mcp_server
google_endpoints chore: litellm oss staging160626 (#30527) 2026-06-16 18:23:13 -07:00
guardrails feat(guardrails): surface OpenAI moderation violation_categories on guardrail traces (#30659) 2026-06-17 09:44:19 -07:00
health_endpoints chore(oss): litellm oss staging 120626 (#30292) 2026-06-12 09:49:25 -07:00
hooks feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00
image_endpoints fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232) 2026-06-09 22:10:23 +02:00
management_endpoints chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
management_helpers feat(mcp): per-server env vars with global + per-user scopes (#28917) 2026-06-05 20:15:11 -07:00
memory Litellm memory improvements v2 (#26541) 2026-04-25 19:03:43 -07:00
middleware fix(proxy): point /metrics 401 at the opt-out flag 2026-05-08 18:09:14 -07:00
openai_files_endpoint fix(proxy): resolve list files credentials from team BYOK deployments (#30495) 2026-06-17 10:32:52 -07:00
pass_through_endpoints chore(lint): remove PLR0915 too-many-statements ruff rule (#30574) 2026-06-16 16:52:49 -07:00
policy_engine fix(guardrails): return HTTP 400 for litellm content filter blocks (#28418) 2026-05-30 14:28:46 -07:00
prompts style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
proxy_server fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is unreliable (#30684) 2026-06-18 10:35:41 -07:00
public_endpoints chore: litellm oss staging160626 (#30527) 2026-06-16 18:23:13 -07:00
rag_endpoints fix: harden /key/update authorization checks (#27878) 2026-05-14 04:16:04 +00:00
realtime_endpoints chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
response_api_endpoints Litellm websocket improvements (#29563) 2026-06-03 11:48:35 -07:00
shutdown feat(proxy): native /health/drain preStop hook for graceful shutdown (#29439) 2026-06-02 16:30:44 -07:00
spend_tracking fix(anthropic): price and surface response service_tier in cost tracking (#30558) 2026-06-17 06:33:51 -07:00
test_configs
types_utils chore(proxy): also scrub guardrail callbacks / module paths from DB overlay 2026-05-14 01:24:51 +00:00
ui_crud_endpoints feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796) 2026-06-09 17:45:42 -07:00
utils chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
vector_store_endpoints Title: fix(proxy): resolve vector store file list credentials from team deployments (#29739) 2026-06-06 12:36:05 -07:00
__init__.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
conftest.py feat(proxy): native /health/drain preStop hook for graceful shutdown (#29439) 2026-06-02 16:30:44 -07:00
test_aiohttp_cleanup_closed.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_aiohttp_session_recovery.py fix: use AsyncMock for concurrent test consistency 2026-03-18 00:54:23 +00:00
test_api_key_masking_in_errors.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_audio_speech_prometheus_hooks.py fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232) 2026-06-09 22:10:23 +02:00
test_batch_expiry.py fix(proxy): strip LiteLLM policy tracking from OpenAI batch metadata (#28425) 2026-05-26 11:35:42 -07:00
test_batch_metadata_none_fix.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_batch_retrieve_bedrock.py fix(proxy/batches): forward model to retrieve_batch for bedrock 2026-04-29 22:48:03 +02:00
test_batch_x_litellm_model_encoding.py test(batches): move orphan tests into tests/test_litellm for CI coverage (#30510) 2026-06-16 10:20:59 -07:00
test_budget_reservation.py fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is unreliable (#30684) 2026-06-18 10:35:41 -07:00
test_caching_routes.py Litellm oss staging 040626 (#29671) 2026-06-04 11:07:20 -07:00
test_chat_completion_metadata.py fix: propagate JWT auth metadata to OTEL spans (#19627) 2026-01-23 21:21:23 -08:00
test_common_request_processing.py fix(guardrails): return 400 not 500 when AIM blocks a request (#30573) 2026-06-16 18:56:14 -07:00
test_component_allowlists.py chore(oss): litellm oss staging 120626 (#30292) 2026-06-12 09:49:25 -07:00
test_cors_config.py refactor: extract _get_cors_config() for testability, fix no-op CORS tests 2026-04-11 22:24:04 +05:30
test_custom_proxy.py
test_dynamic_mcp_route.py Litellm oss staging 040626 (#29671) 2026-06-04 11:07:20 -07:00
test_empty_model_list.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_enforce_user_param.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_fallback_management_endpoints.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_fastapi_offline_routes.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_filter_models_by_team_access_group.py fix: resolve access group names in _filter_models_by_team_id (#25224) 2026-05-01 11:55:36 +05:30
test_health_check_functions.py feat(proxy): skip disable_background_health_check models on GET /health when flag set (#27716) 2026-05-13 09:49:05 -07:00
test_health_check_max_tokens.py fix(health): correct bedrock embedding health checks (#30583) 2026-06-17 14:34:09 -07:00
test_langfuse_passthrough_security.py chore(callbacks): guard dynamic integration hosts 2026-04-30 14:27:19 -07:00
test_lazy_openapi_snapshot.py [Fix] Tests: Move Misplaced Import in Lazy OpenAPI Snapshot Test 2026-05-01 14:24:53 -07:00
test_litellm_pre_call_utils.py fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is unreliable (#30684) 2026-06-18 10:35:41 -07:00
test_max_budget_env_var.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_mcp_asgi_response.py fix(mcp): surface upstream 401 for token-forwarding MCP servers (#27847) 2026-05-13 12:03:36 -07:00
test_model_based_routing_files_batches.py test(batches): move orphan tests into tests/test_litellm for CI coverage (#30510) 2026-06-16 10:20:59 -07:00
test_model_dump_with_preserved_fields.py Fix_mapped tests part 2 2026-02-26 12:43:39 +05:30
test_model_id_header_propagation.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_model_info_default_limits.py fix(proxy): align /v1/model/info with router deployments (#30025) 2026-06-10 19:38:21 -07:00
test_model_level_guardrails.py fix(guardrails): run pre_call hook once for model-level guardrails (#30543) 2026-06-16 11:17:03 -07:00
test_model_list_healthy_only.py feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00
test_openapi_schema_validation.py fix(proxy): preserve HTTP operations when injecting WebSocket stubs into OpenAPI schema 2026-05-06 00:28:42 +02:00
test_pricing_field_strip.py chore: litellm oss staging160626 (#30527) 2026-06-16 18:23:13 -07:00
test_prometheus_cleanup.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_provider_url_destination_guard.py chore(proxy): move URL-valued model/file_id guard from SDK to proxy 2026-05-02 02:17:46 +00:00
test_proxy_cli.py feat(proxy): add --max_requests_before_restart_jitter to stagger worker restarts (#30601) 2026-06-17 11:28:48 -07:00
test_proxy_logging_hook_detection.py perf: reduce per-request and per-chunk overhead across Anthropic streaming hot paths (#28289) 2026-05-23 12:15:59 -07:00
test_proxy_server.py fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is unreliable (#30684) 2026-06-18 10:35:41 -07:00
test_proxy_types.py fix(proxy): add default=None to LiteLLM_TeamMembership.litellm_budget_table (#29684) 2026-06-04 12:13:11 -07:00
test_proxy_utils.py chore: litellm oss 170626 (#30637) 2026-06-17 21:11:12 -07:00
test_pyroscope.py Implement normalize_nonempty_secret_str function to trim whitespace from secrets and treat empty values as unset. Update proxy_server to use this function for Grafana credentials. Enhance tests to validate the new normalization behavior. 2026-05-04 18:17:31 +00:00
test_redis_auth_cache_flag.py refactor(proxy): replace DualCache with UserApiKeyCache for user API key management 2026-04-28 19:15:03 +00:00
test_response_model_sanitization.py perf: eliminate per-request callback scanning on proxy hot path (#27858) 2026-05-14 09:28:31 -07:00
test_route_a2a_models.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_route_llm_request.py feat(proxy): fix vector store retrieve/list/update/delete without model (#27929) 2026-05-15 04:37:59 -07:00
test_sensitive_route_auth.py chore(proxy): guard sensitive public endpoints 2026-04-30 11:52:47 -07:00
test_shared_health_check.py feat(proxy): skip disable_background_health_check models on GET /health when flag set (#27716) 2026-05-13 09:49:05 -07:00
test_spend_log_cleanup.py feat(spend_logs): opt-in native Postgres partitioning for SpendLogs retention (#29466) 2026-06-11 11:02:42 -07:00
test_swagger_chat_completions.py fix(proxy): avoid misleading multi-method operation ids 2026-04-30 20:44:14 -07:00
test_team_member_update.py feat(ui): add budget duration to edit team member form (#29717) 2026-06-06 17:24:55 -07:00
test_team_org_move.py fix(team_endpoints): auto-add SSO team members to org on move (proxy admin only) (#26377) 2026-04-24 08:36:25 -07:00
test_tools_allowlist_enforcement.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
test_update_llm_router_resilience.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00