litellm/tests
ryan-crabbe-berri 4f538f48c8
fix(anthropic): keep signed empty thinking blocks and honor thinking.block_binding (#46342)
* fix(anthropic): treat adaptive thinking as enabled when mapping response_format

is_thinking_enabled only recognised thinking.type=enabled, so a request that
paired thinking.type=adaptive with response_format took the synthetic JSON
tool path with a forced tool_choice, which Anthropic rejects alongside
thinking. The same check also gates the Bedrock Converse and Databricks
forced tool_choice downgrades, so they now see adaptive thinking too.

* fix(anthropic): keep signed thinking blocks with empty text on chat completions

Models that default to display: omitted return signed thinking blocks whose
text is empty, and Anthropic rejects the next turn when they are not replayed
unchanged. is_unsignable_thinking_block dropped them along with unsigned
blocks, and the inline content path required non-empty text, so a tool-use
turn on Opus 4.7+ or the 5 families lost its thinking blocks and 400ed on the
tool-result turn. Only a missing signature now drops a block, and the
mid-conversation system placement mirrors that rule. The /v1/messages strip
helper is left to #41362.

* fix(anthropic): skip the thinking-strip retry when block_binding asks for an error

The /v1/messages retry loop strips thinking blocks and resends on any
invalid-thinking 400, including the binding mismatch a caller opted into
with thinking.block_binding.prefix_mismatch_behavior: error. The retry
decision now sees the request body and surfaces that 400 instead of
overriding the caller's choice. #42888 covers the litellm_params side.

* fix(bedrock): carry thinking.block_binding through the Invoke thinking rebuilds

Bedrock Invoke rebuilt the thinking param from scratch when display: updates
was requested, on both the /v1/messages and chat completions paths, and the
legacy enabled-to-adaptive translation plus the clear_thinking injection did
the same, so thinking.block_binding never reached Bedrock. Every rebuild now
spreads the caller's thinking and only overrides the keys it owns, and
AnthropicThinkingParam types block_binding. The thinking-binding-controls
beta was already on the Bedrock allowlist.

* fix(anthropic): keep forcing the response_format tool under adaptive thinking

This reverts ad9e861ae7. Anthropic, Bedrock Invoke and Vertex all accept a
forced tool_choice next to thinking.type=adaptive and only reject it with
type=enabled, so counting adaptive as enabled fixed no live failure. It did
drop the forced JSON tool, so Claude answered response_format requests in
prose, and it downgraded a required tool_choice to auto on Bedrock Converse

* test(e2e): drop the adaptive thinking tool round trip case

With adaptive thinking the model often skips thinking on the weather prompt, so
turn 1 carries no signed empty block and the case fails before the replay it is
meant to cover. Anthropic also answers the replay with a 200 whether or not the
block is forwarded, so the case could not tell the fix from main. The factory
unit tests pin the outgoing shape instead

* fix(anthropic): only skip the thinking-strip retry for a binding mismatch 400

prefix_mismatch_behavior: error asks Anthropic to reject a block bound to
another conversation. It says nothing about unrelated bad blocks such as a
null signature, so those still get the strip-and-retry self-heal. Also trims
the empty-thinking docstrings to what the code guarantees and types the new
test parameters

* refactor(anthropic): narrow thinking fields with the mapping validator instead of typing.cast

typing.cast is banned by the strict ruff gate (TID251), so the three new casts pushed that rule one over its merge-base count. The existing pydantic mapping validator gives the same typed view without an unchecked cast, and it now has a generic name since it is no longer only used for Claude Code payloads

* refactor(anthropic): read thinking settings through the validated mapping so basedpyright stays at its merge-base count

The Bedrock clear_thinking rewrite still narrowed with a cast and an untyped dict fallback, which added two reportUnknownVariableType errors. It now uses the same pydantic mapping validator, made public for that reuse, and the retry hook validates the request body itself so the handler passes a typed dict instead of an untyped one

---------

Co-authored-by: yuneng-jiang <yuneng@berri.ai>
(cherry picked from commit f470e418ea)
2026-10-19 22:42:04 -07:00
..
_support fix(params): validate stream_chunk_size once, before any provider call (#43222) 2026-09-26 23:01:20 +00:00
agent_tests/local_only_agent_tests test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
audio_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
base_sdk_tests refactor(sdk): separate core AWS and tokenizer dependencies (#44447) 2026-10-08 19:07:57 -07:00
basic_proxy_startup_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
batches_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
benchmarks refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
code_coverage_tests docs(proxy): describe /v1/decisions and /v1/systemone in Swagger UI (#45838) 2026-10-10 16:30:24 -07:00
documentation_tests fix(s3_v2): upload fresh events first, drop terminal failures and hour-old retries by default, opt-in adaptive concurrency (#43022) 2026-09-26 14:58:28 -07:00
e2e test(e2e): backport three stale e2e test fixes from main to rc/1.106.0 (#47229) 2026-10-17 20:22:41 -07:00
e2e_harness ci: render lint, unit and smoke checks as <tier> / <job> with one collector per tier (#45480) 2026-10-09 04:28:41 +00:00
guardrails_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
harness_e2e feat: add litellm.agent() to run claude code, codex, opencode and deep agents through the ai gateway (#43885) 2026-10-01 22:27:49 +00:00
image_gen_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
integration fix(responses): fold bridged Responses output into one chat choice (#46099) 2026-10-19 22:27:55 -07:00
litellm_utils_tests test: delete 34 legacy tests already covered by e2e (#45340) 2026-10-08 09:43:56 -07:00
llm_translation test: make 38 legacy live base-class translation tests offline (#45351) 2026-10-08 23:18:25 +00:00
load_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
local_testing test: delete 34 legacy tests already covered by e2e (#45340) 2026-10-08 09:43:56 -07:00
logging_callback_tests test: replace 61 live logging and otel tests with offline unit and integration coverage (#45362) 2026-10-08 15:55:57 -07:00
mcp_tests feat(mcp): add portable catalog pagination (#44446) 2026-10-06 18:54:50 -07:00
multi_instance_e2e_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
ocr_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
openai_endpoints_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
otel_tests test: replace 61 live logging and otel tests with offline unit and integration coverage (#45362) 2026-10-08 15:55:57 -07:00
pass_through_tests test: delete 34 legacy tests already covered by e2e (#45340) 2026-10-08 09:43:56 -07:00
pass_through_unit_tests test: delete 34 legacy tests already covered by e2e (#45340) 2026-10-08 09:43:56 -07:00
proxy_admin_ui_tests test: move the unit half of 126 mixed legacy files into tests/unit (#45090) 2026-10-07 14:07:43 -07:00
proxy_behavior test: realign stale decisions and lens tests with merged behaviour (#45346) 2026-10-08 09:44:18 -07:00
proxy_e2e_anthropic_messages_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
proxy_migration_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
proxy_security_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
proxy_unit_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
router_unit_tests test: make 77 legacy live tests offline in litellm_utils, router_unit and responses dirs (#45298) 2026-10-08 02:37:55 -07:00
rust-python-harness test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
search_tests test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
store_model_in_db_tests fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
test_litellm refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_litellm_rust fix(ci): import seed_tracing_fixtures from the pytest scripts path in rust trace tests (#45485) 2026-10-08 19:41:22 -07:00
unified_google_tests test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
unit fix(anthropic): keep signed empty thinking blocks and honor thinking.block_binding (#46342) 2026-10-19 22:42:04 -07:00
vector_store_tests refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
windows_tests fix(packaging): keep wheel paths under Windows MAX_PATH for Store Python (#43903) 2026-09-30 22:20:36 +00:00
__init__.py refactor: expose core private helpers under public names (#44871) 2026-10-07 00:05:27 +00:00
_fake_openai_endpoint_server.py
_flush_vcr_cache.py
_live_test_helpers.py
_master_key.py fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
_openai_record_replay_proxy.py
_process_helpers.py test: count a zombie grandchild as gone in the migrate deploy timeout test (#42570) 2026-09-22 14:59:26 -07:00
_vcr_conftest_common.py fix(tests): stop VCR recording and replaying a test's own localhost upstream (#43346) 2026-09-26 15:49:39 -07:00
_vcr_redis_persister.py
_wait_helpers.py
_ws_vcr.py
AGENTS.md test(e2e): move the harness self-tests out of tests/e2e (#45172) 2026-10-07 22:20:02 +00:00
capturing_transport.py test(vcr): guard leaked cassette patches and make injected-transport embedding tests immune (#42542) 2026-09-22 14:20:18 -07:00
eval_swe_bench.py
fake_openai_endpoint.py
gettysburg.wav
large_text.py
openai_batch_completions.jsonl
pyrightconfig.json
README.MD test: finish the non-proxy half of tests/test_litellm (#43281) 2026-09-25 22:43:41 -07:00
test_debug_warning.py
test_keys.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_litellm_proxy_responses_config.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_logging.conf
test_models.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_new_vector_store_endpoints.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_openai_endpoints.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_proxy_server_non_root.py
test_rust_python_harness.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_service_logger_otel.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_spend_logs.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
test_team_logging.py fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
test_users.py test: move 76 live top-level tests to offline unit and integration coverage (#45352) 2026-10-08 10:33:35 -07:00
white_100x100.png test: stop CI tests from downloading tokenizer files and images (#43257) 2026-09-25 19:27:48 -07:00

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/unit

This folder can only run mock tests.