litellm/tests/test_litellm/proxy
Zachary Lyon 19c13ac971
feat(proxy): add TinyFish Agent API passthrough with per-step billing (#41099)
* feat(proxy): add TinyFish Agent API passthrough with per-step billing

* chore(ui): regenerate dashboard API types for /tinyfish passthrough

* fix(proxy): satisfy strict lint budget for tinyfish passthrough

* style: ruff format tinyfish passthrough handler

* test(proxy): exercise tinyfish route through the app with a faked upstream

* refactor(proxy): make cross-module tinyfish billing hooks public

* fix(proxy): tolerate transient tinyfish poll failures instead of dropping the charge

* fix(proxy): defer billing for disconnected tinyfish SSE runs to the background poller

* Revert "fix(proxy): defer billing for disconnected tinyfish SSE runs to the background poller"

This reverts commit ef0bcfb4a0.

* fix(proxy): bill tinyfish SSE runs via detached poller and only COMPLETED runs

Disconnected run-sse clients previously left completed runs unbilled: the stream-end
handler saw a still-RUNNING run and logged $0. The poller now spawns from the streaming
path on the first run_id frame, outlives the disconnect, and writes the one spend row when
the run turns terminal; the stream-end path only logs the $0 fallback for run_id-less
streams. Costs now apply only to COMPLETED runs ($0 for FAILED/CANCELLED, matching the
upstream invoice), spend rows carry the request's litellm_call_id (previously NULL
request_ids collided and were silently dropped), and the GET /v1/runs listing is blocked
so callers behind the shared key cannot discover each other's runs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* fix(proxy): drop GET /v1/runs from the tinyfish allowlist error message

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* chore(proxy): sync openapi artifacts for tinyfish docstring, suppress LIT011 on flag write

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* style(proxy): ruff-format the sse poller flag write

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* style(proxy): keep the rebind-ok suppression on the flag write's own line

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* fix(proxy): harden tinyfish billing paths from review findings

Skip failure dispatch when the SSE poller owns billing (a failure row collided with the
poller's billed row on request_id and dropped the charge), late-spawn the poller for
run_ids that arrive in unterminated frames instead of mispricing RUNNING runs at $0,
thread litellm_params into poller-billed standard logging objects so SLO consumers see
attribution, untype the run error field so upstream error-shape drift cannot void a
billable run, normalize a schemeless TINYFISH_AGENT_API_BASE, extend the poll budget to
cover queue wait (3600s) with ~60s outage tolerance, and log poller cancellation.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* chore(proxy): satisfy ratcheted BLE001/LIT002 budgets from main in tinyfish handler

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* style(proxy): drop stray blank line from merge resolution

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* fix(proxy): reject passthrough envelope controls on tinyfish route, raise blocking-run timeout

The generic passthrough unwraps a caller-supplied custom_body as the forwarded request and
honors a caller stream flag, so custom_body.use_vault bypassed the credentialed-run 403 and
stream: true flipped a blocking run into the streaming pipeline. The route now 400s the
envelope fields (custom_body, stream, query_params); streaming comes from the endpoint.
Blocking runs also get a 1500s default timeout covering the upstream 1200s run cap, unless
the operator configured pass_through_request_timeout.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* style(proxy): resolve operator timeout without a dict-literal default

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pxz11TQKYvCXvKawNUa2g4

* test(passthrough): list the TinyFish route among protocol-constrained pass-through routes

* chore(proxy): regenerate the lazy OpenAPI snapshot after merging main

* chore(proxy): keep the lazy OpenAPI snapshot as CI's Python 3.12 renders it

* fix(proxy): reject TinyFish POST bodies that are not a JSON object

A form-encoded or text body carried stream and use_vault past both field
gates, because the gates only saw fields the body parsed to as JSON. The
route now checks the content type before reading the body and answers 400
for anything that is not a JSON object.

* fix(tinyfish): reject submit paths with extra slashes so run-async always bills

The allowlist dropped empty path segments, so POST /v1/automation/run-async/
was forwarded upstream while the billing dispatch only recognises the exact
path and would have logged the submit at $0 without starting the poller.
Any path with a trailing or doubled slash now returns 403 before forwarding.

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-09-21 21:21:43 -07:00
..
_experimental/mcp_server fix(proxy): surface a database outage from the user read as 503 no_db_connection (#42399) 2026-09-21 20:52:41 -07:00
a2a fix(a2a): reject malformed protocolVersion suffixes while keeping semver prereleases 2026-07-21 13:24:58 -07:00
agent_endpoints fix(proxy): scope agent permissions to invoking caller 2026-09-21 22:32:32 +00:00
analytics_endpoints fix(proxy): attribute gate-rejected requests to their endpoint in cache analytics (#40824) 2026-09-12 16:03:38 -07:00
anthropic_endpoints feat(proxy): opt-in litellm_call_id in JSON error bodies (#42391) 2026-09-21 19:17:18 -07:00
auth fix(proxy): surface a database outage from the user read as 503 no_db_connection (#42399) 2026-09-21 20:52:41 -07:00
batches_endpoints chore: merge main into fix/batch-retrieve-model-group 2026-09-19 16:25:39 -07:00
client fix(cli): serialize footer installs and tolerate unknown versions 2026-09-21 16:48:08 -07:00
common_utils feat(proxy): opt-in litellm_call_id in JSON error bodies (#42391) 2026-09-21 19:17:18 -07:00
config_resolvers test: drop two inert type: ignore comments 2026-09-19 14:22:19 -07:00
container_endpoints fix(containers): page upstream until a non-admin container list fills its limit 2026-09-02 21:26:34 -07:00
credential_endpoints fix(credentials): answer 409 on a name collision, let PATCH resolve values from model_id 2026-09-15 10:41:43 -07:00
db Merge pull request #42026 from BerriAI/litellm_user_jwt_savings 2026-09-21 16:41:16 -07:00
discovery_endpoints chore(proxy): drop explanatory docstrings from credentials hint helper and tests 2026-09-14 19:29:30 +00:00
enterprise_billing feat(proxy): push-based OTLP billable-request metering for enterprise deployments (#31592) 2026-07-15 12:12:52 -07:00
experimental/mcp_server test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
fine_tuning_endpoints test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
google_endpoints test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
guardrails test(guardrails): gate the video e2e on a chat probe so a miss starts at most one paid job 2026-09-21 23:20:29 +00:00
health_endpoints Merge pull request #40814 from BerriAI/litellm_gate_health_services_alert_tests 2026-09-12 21:13:30 -07:00
hooks Merge pull request #42062 from BerriAI/litellm_pr38499_batch_retrieve_model_group 2026-09-19 18:23:06 -07:00
image_endpoints Merge remote-tracking branch 'origin/main' into litellm_fix_image_edits_bracketed_alias 2026-09-17 14:49:54 -07:00
list_api feat: page the public model hub table off /public/v1/model_hub, keeping every filter (#39691) 2026-09-03 22:36:16 -07:00
logging_endpoints fix(usage): recover aliases for v1.99 double-hashed spend keys 2026-09-03 14:21:25 +00:00
management_endpoints fix(proxy): drop cost-map metadata echoed back on model save (#41944) 2026-09-21 19:33:16 -07:00
management_helpers Merge remote-tracking branch 'origin/main' into litellm_jev_autorouter_launch_1789767495 2026-09-19 17:35:42 +00:00
memory feat(proxy): add a search param to key, memory, audit, and spend log listings 2026-09-03 15:20:13 -07:00
middleware fix(proxy): release unclaimed budget reservations at request end (#42304) 2026-09-21 19:51:12 -07:00
ocr_endpoints fix(ocr): validate body req_format in the proxy endpoint and run its tests in CI 2026-08-17 18:29:35 +00:00
openai_files_endpoint fix(files): keep an explicit target_storage on its old path and refuse litellm_db as a caller choice 2026-09-19 13:20:02 -07:00
pass_through_endpoints feat(proxy): add TinyFish Agent API passthrough with per-step billing (#41099) 2026-09-21 21:21:43 -07:00
policy_engine fix(policy_engine): resolve policies once and apply fallback semantics in get_matching_policies 2026-09-21 17:36:03 +00:00
prompts fix(prompts): accept a string prompt_version and carry the viewed environment into code snippets 2026-08-29 12:55:34 -07:00
proxy_server feat(proxy): opt-in litellm_call_id in JSON error bodies (#42391) 2026-09-21 19:17:18 -07:00
public_endpoints test: keep the Qwen brand missing-key tests off the network and split the ChatGPT fields test back out 2026-09-21 12:54:23 -07:00
rag_endpoints test(rag): drop the docstrings from the registered-store ingest tests 2026-09-19 04:10:49 -07:00
realtime_endpoints refactor(proxy): replace configurable model access denied message with a fixed clean client message 2026-09-16 01:44:36 +00:00
rerank_endpoints fix(proxy): carry litellm_call_id through endpoint specific error logs and failure responses 2026-09-16 02:29:26 +00:00
response_api_endpoints test(proxy): expect 422 for per-model budget rejections on cursor route 2026-09-20 06:10:16 +00:00
shutdown refactor(proxy): inject scheduled job shutdown timeouts 2026-09-21 19:37:28 +00:00
spend_tracking fix(proxy): release unclaimed budget reservations at request end (#42304) 2026-09-21 19:51:12 -07:00
test_configs
types_utils feat(proxy): unified custom_key_policy hook for key generate, update and regenerate 2026-09-12 16:09:24 -07:00
ui_crud_endpoints Merge remote-tracking branch 'origin/main' into litellm_config_read_source 2026-09-21 15:54:52 -07:00
utils Merge pull request #41634 from BerriAI/litellm_agent_access_groups 2026-09-21 19:13:46 -05:00
vector_store_endpoints fix(vector_stores): run the full model grant check on caller-supplied model hints 2026-09-19 00:54:41 -07:00
vector_store_files_endpoints test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
video_endpoints fix(videos): forward uploaded source file on /v1/videos/edits to the provider 2026-08-24 15:34:21 -07:00
__init__.py
conftest.py test(proxy): isolate the agent read-through singleton between unknown-agent tests 2026-09-22 01:34:31 +00:00
test__types.py feat(auth): breached password detection, self-service change-password and forced password reset 2026-09-21 18:48:35 +00:00
test_aiohttp_cleanup_closed.py
test_aiohttp_session_recovery.py
test_api_key_masking_in_errors.py
test_audio_speech_prometheus_hooks.py fix(proxy): match /v1/audio/speech content-type to the returned audio format 2026-08-29 13:44:43 -07:00
test_batch_expiry.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_batch_metadata_none_fix.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_batch_retrieve_bedrock.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_batch_x_litellm_model_encoding.py fix(proxy): apply model grants to unified file and batch ids on batch routes 2026-09-10 18:10:18 -04:00
test_blocked_response_usage.py fix(guardrails): remove the module-global translation mapping that leaked between tests 2026-09-03 03:28:52 -07:00
test_budget_reservation.py test(proxy): restore pipeline methods on expiring Redis fake after merge 2026-09-20 08:59:46 +00:00
test_caching_routes.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_chat_completion_metadata.py
test_claude_code_marketplace.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -07:00
test_collector.py feat(proxy): offload spend tracking to a pod-local collector sidecar (#40545) 2026-09-10 17:14:13 -07:00
test_common_request_processing.py feat(proxy): opt-in litellm_call_id in JSON error bodies (#42391) 2026-09-21 19:17:18 -07:00
test_component_allowlists.py fix(gateway): serve /debug/memory/summary on the data plane so the memory regression test can read each gateway's RSS 2026-09-10 18:12:40 -07:00
test_conftest.py test(proxy): stop monkeypatch.undo re-planting fixture-mocked prisma_client 2026-08-13 20:11:06 -07:00
test_cors_config.py
test_custom_proxy.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_dynamic_mcp_route.py fix(proxy): serve aggregate MCP endpoint on bare /mcp instead of 307-redirecting (#34845) 2026-08-14 17:04:32 -07:00
test_empty_model_list.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_enforce_user_param.py test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769) 2026-08-20 20:24:49 -07:00
test_fallback_management_endpoints.py
test_fastapi_offline_routes.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_filter_models_by_team_access_group.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_health_check_functions.py fix(health): skip background health check DB writes when the latest-row read fails 2026-09-14 23:03:30 +00:00
test_health_check_max_tokens.py feat(auto-router): integrate JEV context and usage accounting 2026-09-18 21:38:15 +00:00
test_init_litellm_callbacks.py test: run the 30 test files stranded in the second mirror (#37595) 2026-08-20 10:59:43 -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 refactor(proxy): type the snapshot fragments and wrap a long test line 2026-08-26 14:39:51 -07:00
test_litellm_pre_call_utils.py fix(proxy): forward a client's anthropic-beta and anthropic-version headers to bedrock_mantle 2026-09-19 20:11:14 -07:00
test_max_budget_env_var.py
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_deprecations_endpoint.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_model_dump_with_preserved_fields.py
test_model_id_header_propagation.py feat(proxy): add x-litellm-model-name response header with deployment model string (#33698) 2026-07-17 20:29:42 -07:00
test_model_info_default_limits.py perf(proxy): serialize /model/info listing once with orjson 2026-09-14 19:47:51 +00:00
test_model_level_guardrails.py fix(proxy): apply key/team router_settings.model_group_alias (#35486) 2026-08-03 22:09:47 +00:00
test_model_list_healthy_only.py perf(proxy): serialize /model/info listing once with orjson 2026-09-14 19:47:51 +00:00
test_modify_response_streaming_passthrough.py fix(proxy): use e.request_data for logging_obj in ModifyResponseException streaming passthrough (#30800) 2026-06-18 23:29:08 -07:00
test_openai_ws_passthrough_routes.py fix(proxy): keep the token's team model list in the websocket passthrough gate without a database 2026-09-04 19:05:35 -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_plugin_routes.py refactor(proxy): resolve config and DB settings precedence in one SettingsStore 2026-09-17 23:36:27 -07:00
test_pointfive_dashboard_config.py feat(pointfive): add pointfive to the dashboard logging integrations 2026-09-10 14:02:35 +03:00
test_pointfive_ui_callback.py feat(pointfive): list pointfive in the proxy callback registry 2026-09-10 14:02:35 +03:00
test_pricing_field_strip.py fix(proxy): fold litellm_metadata into metadata on chat routes so tag routing sees merged tags 2026-08-29 00:42:43 -07:00
test_prisma_engine_watchdog.py fix(proxy): recreate the Prisma client when the writer session turns read-only (#40610) 2026-09-10 13:53:42 -07:00
test_prisma_migration.py fix(proxy): run migrations through python -m prisma when the prisma console script is not on PATH 2026-09-09 18:17:12 -07:00
test_prometheus_cleanup.py feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform (#40163) 2026-09-08 13:31:07 -07:00
test_prometheus_metrics_server.py feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform (#40163) 2026-09-08 13:31:07 -07:00
test_provider_url_destination_guard.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_proxy_cli.py fix(proxy): only warn about the deprecated flag when it came from the CLI 2026-09-20 01:22:31 -07:00
test_proxy_logging_hook_detection.py fix(proxy): keep queued moderation running past a V1 pre_call guardrail 2026-09-18 23:33:29 +00:00
test_proxy_server.py Merge pull request #42122 from BerriAI/litellm_db_callback_redaction_settings 2026-09-21 16:03:44 -07:00
test_proxy_types.py fix(router): honor team and key provider weights 2026-09-14 23:31:52 -07:00
test_proxy_utils.py Merge remote-tracking branch 'origin/main' into litellm_v1_models_alias_metadata 2026-09-18 20:23:06 +00:00
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_read_model_list.py feat: add minimal rust router + axum ai-gateway calling router.realtime (2/2) (#31135) 2026-06-23 19:16:34 -07:00
test_redis_auth_cache_flag.py fix(proxy): share per-model budget counters across replicas through the spend counter cache (#39375) 2026-09-02 12:40:59 -07:00
test_response_model_sanitization.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_route_a2a_models.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_route_llm_request.py test(proxy): isolate the agent read-through singleton between unknown-agent tests 2026-09-22 01:34:31 +00:00
test_route_priority.py perf(proxy): register liveness and core inference routes first (#40687) 2026-09-11 17:10:38 +00:00
test_sensitive_route_auth.py chore(proxy): guard sensitive public endpoints 2026-04-30 11:52:47 -07:00
test_shared_health_check.py fix(proxy): derive auto-router health from its underlying models (#38174) 2026-08-26 16:41:54 -07:00
test_spend_log_cleanup.py Merge pull request #41213 from BerriAI/litellm_spend_log_cleanup_cancel_outcome 2026-09-21 17:03:25 -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 fix(team): schedule membership audit writes after commit and lock the roster on role updates 2026-09-19 22:33:22 +00:00
test_team_org_move.py test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769) 2026-08-20 20:24:49 -07:00
test_tools_allowlist_enforcement.py fix(anthropic): close hybrid tool-name allowlist gap and keep native tools through guardrails 2026-08-26 20:37:11 -07:00
test_update_llm_router_resilience.py fix(proxy): keep the no-model_list guard to absent reads so model_list: [] still evicts 2026-09-16 23:14:52 +00:00