litellm/tests
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
..
agent_tests fix(a2a): keep the upstream status on card discovery failures and inject the card client in tests 2026-09-16 23:55:57 +00:00
audio_tests
base_sdk_tests fix(mcp): explain missing public client dependencies 2026-09-19 19:52:13 -07:00
basic_proxy_startup_tests
batches_tests
benchmarks
code_coverage_tests Merge pull request #42143 from BerriAI/litellm_e2e_changed_keep_pytest_log 2026-09-21 11:39:25 -07:00
documentation_tests fix(docs-test): restore line-anchored table regex in router settings check 2026-09-18 20:10:20 +00:00
e2e test(e2e-ui): check the MCP Tools tab against the upstream's own tools/list (#42397) 2026-09-21 20:35:30 -07:00
enterprise fix(projects): persist explicit budget cap clears 2026-09-12 13:43:55 -07:00
guardrails_tests Revert "Merge pull request #41220 from BerriAI/litellm_post_call_guardrail_context" 2026-09-19 17:45:15 +00:00
image_gen_tests test: remove fully commented-out test files that collect no tests 2026-09-17 20:05:27 +00:00
integration test(integration): chain a proxy-issued previous_response_id in the cost suite (#42396) 2026-09-21 20:36:53 -07:00
litellm-proxy-extras Merge remote-tracking branch 'origin/main' into litellm_v2_migration_startup 2026-09-18 20:55:05 -07:00
litellm_utils_tests Merge remote-tracking branch 'origin/main' into litellm_invalid_tool_choice_400 2026-09-19 02:35:29 -07:00
llm_responses_api_testing test: fix five tests left stale by #41311, #41337, #39996 and #41310 2026-09-16 17:47:27 -07:00
llm_translation test(bedrock): expect canonical session tags in the dynamic auth params propagation test 2026-09-18 11:17:34 -07:00
load_tests
local_testing fix(ci): let the install smoke test boot its key-less proxy config 2026-09-21 12:56:21 -07:00
logging_callback_tests Merge pull request #42071 from BerriAI/litellm_remove_dead_telemetry_flag 2026-09-19 21:48:02 -07:00
mcp_tests fix(mcp): preserve Python 3.10 imports and integration test seams 2026-09-21 12:58:06 -07:00
multi_instance_e2e_tests
ocr_tests test(ocr): replace per-provider OCR test classes with a declarative provider x auth x input matrix 2026-09-18 21:27:03 +00:00
openai_endpoints_tests test(responses): fix stale Anthropic smoke request 2026-09-11 13:56:27 -07:00
otel_tests test: fix stale budget-status and bad-database-url assertions 2026-09-21 15:00:54 -07:00
pass_through_tests fix(mcp): preserve legacy behavior on SDK2 and streamline verification 2026-09-18 22:28:31 -07:00
pass_through_unit_tests feat(proxy): add TinyFish Agent API passthrough with per-step billing (#41099) 2026-09-21 21:21:43 -07:00
proxy_admin_ui_tests
proxy_behavior Merge pull request #42026 from BerriAI/litellm_user_jwt_savings 2026-09-21 16:41:16 -07:00
proxy_e2e_anthropic_messages_tests fix(test): run the all-beta-headers bedrock cases on Claude Fable 5.1 2026-09-19 23:33:29 +00:00
proxy_migration_tests Merge remote-tracking branch 'origin/main' into litellm_v2_migration_startup 2026-09-19 23:59:26 -07:00
proxy_security_tests refactor(proxy): rename the local development override to dangerously_permit_weak_or_unset_master_key so the name says exactly what it permits 2026-09-19 18:53:14 -07:00
proxy_unit_tests fix(proxy): surface a database outage from the user read as 503 no_db_connection (#42399) 2026-09-21 20:52:41 -07:00
router_unit_tests Merge pull request #42283 from BerriAI/litellm_mid_stream_fallback_walks_full_list 2026-09-21 15:14:04 -07:00
rust-python-harness test: drop tests that pin provider-owned cost map values 2026-09-18 03:55:51 +00:00
search_tests test: remove fully commented-out test files that collect no tests 2026-09-17 20:05:27 +00:00
spend_tracking_tests
store_model_in_db_tests test(proxy): expect the sanitized unknown-model message in the spend-log error test 2026-09-11 19:18:10 -07:00
test_gateway feat(proxy): offload spend tracking to a pod-local collector sidecar (#40545) 2026-09-10 17:14:13 -07:00
test_litellm feat(proxy): add TinyFish Agent API passthrough with per-step billing (#41099) 2026-09-21 21:21:43 -07:00
test_litellm_rust feat(rust-bridge): add cache and secret migration foundations (#42328) 2026-09-22 03:41:04 +00:00
unified_google_tests test(google): boot the unified Google proxy fixture with a real master key 2026-09-20 08:48:39 +00:00
unit feat(rust-bridge): add cache and secret migration foundations (#42328) 2026-09-22 03:41:04 +00:00
vector_store_tests
windows_tests
__init__.py
_fake_openai_endpoint_server.py
_flush_vcr_cache.py
_live_test_helpers.py refactor(test): validate cost-map entries into a typed model 2026-09-16 14:32:08 -07:00
_openai_record_replay_proxy.py
_vcr_conftest_common.py
_vcr_redis_persister.py
_wait_helpers.py
_ws_vcr.py
AGENTS.md ci(tests): wire tests/unit into CircleCI and drain legacy unit shards green 2026-09-20 07:05:42 +00:00
eval_swe_bench.py
fake_openai_endpoint.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
pyrightconfig.json
README.MD
test_anthropic_compaction_usage.py
test_budget_management.py
test_callbacks_on_proxy.py
test_debug_warning.py
test_default_encoding_non_root.py
test_end_users.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: fix five tests left stale by #41311, #41337, #39996 and #41310 2026-09-16 17:47:27 -07:00
test_organizations.py
test_otel_thread_leak.py
test_presidio_latency.py
test_proxy_server_non_root.py
test_ratelimit.py
test_resource_cleanup.py
test_rust_python_harness.py refactor(rust): remove gateway, config, router, realtime, and trace-parity infrastructure 2026-09-16 16:00:07 +00:00
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.