scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-27 06:13:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 72
litellm/tests/unit/llms
History
Mateo Wang 91724bb0a7
fix(responses)!: count input tokens the way inference sends the request (#47363) 
* fix(count-tokens): translate chat tool use before Claude token counts

Responses and chat tool use (function tools, function_call items, tool messages) is now converted the way Claude chat inference converts it before the Anthropic, Azure AI and Vertex partner counters call count_tokens. Translation errors answer 400 before any provider call. Anthropic-shaped requests and /v1/messages/count_tokens keep their body as sent.

* test(count-tokens): compare Claude count bodies with inference for Responses tool use

* fix(responses): forward the caller's Responses body to OpenAI token counts

OpenAI deployments now get the caller's /v1/responses/input_tokens body as sent, minus LiteLLM-only fields, so OpenAI's own count and errors come back. previous_response_id is checked for ownership like inference and routes to the deployment that served it

* fix(responses)!: count Claude Responses bodies the way inference sends them

Non-native Responses counts now run the body through the inference bridge, so
text.format, tool_choice, reasoning, built-in tools, and file_search count the
way inference sends them on Anthropic, Azure AI, Vertex, and Bedrock. The
OpenAI native count body uses the drop_params-resolved tool fields.

* fix(responses): honor drop_params and replay previous turns in Claude counts

Claude input_tokens counts now read the same drop_params setting inference merges from the deployment, router defaults, and request, so a forced tool_choice downgrades to auto under drop_params. previous_response_id replays the stored turns through inference's session loader, and chat messages carrying fields beyond role and content go through the provider's chat translation

* fix(responses): keep proxy-only request keys out of OpenAI counts and map chat tools in Bedrock counts

* fix(count-tokens): import on Python 3.11 and keep stored prompts in OpenAI counts under drop_params

* fix(responses): leave tool_choice out of counts when drop_params drops every tool

* fix(count-tokens): count Mantle options, drop cache marks, and reject input inference cannot send

The Bedrock Mantle fallback now counts thinking, tool_choice and output_config
like the runtime count. Claude Responses counts leave out cache_control marks
again, so more than four marks count instead of failing. Counts answer 400
before any provider call for user blocks chat inference refuses and for
Responses tools with no Chat Completions equivalent, instead of dropping the
block or counting a placeholder tool. Adds the wire tests for these paths

* fix(count-tokens): count Responses tools the way the inference bridge sends them

A Claude count now hoists additional_tools input items into tools, strips a malformed tool flag under drop_params and rejects it without, and leaves tools out when the deployment lists tools in additional_drop_params, so the count matches the body Claude inference sends for the same request

* fix(count-tokens): keep Bedrock runtime counts option-free and send OpenAI the provider file id

* test(count-tokens): capture the Anthropic count request at the HTTP layer instead of patching the handler

* fix(count-tokens): ignore a caller-sent file id mapping and keep non-string file ids as sent
2026-10-20 15:13:59 +00:00
..
a2a chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
aiml chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
aiohttp_openai refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
anthropic fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
apiserpent test(unit): add package markers to migrated unit test directories 2026-09-20 11:53:14 +00:00
aws_polly refactor(sdk): separate core AWS and tokenizer dependencies (#44447) 2026-10-08 19:07:57 -07:00
azure fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348) 2026-10-19 20:35:27 +00:00
azure_ai fix(anthropic): json_schema envelope edge cases on the Anthropic json tool path (#47478) 2026-10-20 08:38:40 +00:00
base_llm fix(responses): keep strong refs to stream and websocket logging tasks (GC race) (#31074) 2026-10-20 09:26:25 +00:00
baseten fix(baseten): list current Model APIs instead of retired 2023 deployment IDs (#46945) 2026-10-19 16:40:13 +00:00
bedrock fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
bedrock_mantle fix(router)!: stop a chat-mode Mantle deployment from rewriting the shared Responses routing row (#46263) 2026-10-17 21:39:14 +00:00
black_forest_labs refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
brave chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
bytez test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
cerebras test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
chat fix(router): read the first stream chunk before returning so a failure before any token runs through the retry and fallback budget (#46493) 2026-10-14 14:19:25 -07:00
chatgpt fix(responses): keep the provider code and message on top-level stream error events (#46438) 2026-10-14 16:16:46 -07:00
clarifai refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
claude_code refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
cloudflare test: move offline logging, secret manager and provider tests from legacy dirs into tests/unit (#45554) 2026-10-09 09:48:10 -07:00
codex refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
cohere chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
cometapi chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
compactifai test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
crusoe fix(crusoe): update base URL to current endpoint (#33121) 2026-10-15 19:10:58 -07:00
custom_httpx fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466) 2026-10-20 01:51:51 +00:00
dashscope feat(dashscope): add separate explicit and implicit cache pricing (#45567) 2026-10-20 04:54:35 +00:00
databricks fix(databricks): stream Claude json_schema answers as text on every streaming path (#47424) 2026-10-20 02:41:55 +00:00
dataforseo chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
datarobot test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
deepagents 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
deepgram test: move the unit half of 126 mixed legacy files into tests/unit (#45090) 2026-10-07 14:07:43 -07:00
deepinfra refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
deepseek feat(search): add DeepSeek as a /v1/search provider (#47401) 2026-10-19 20:35:04 +00:00
docker_model_runner test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
duckduckgo chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
e2b refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
edenai test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
elevenlabs test: move the unit half of 126 mixed legacy files into tests/unit (#45090) 2026-10-07 14:07:43 -07:00
exa_ai fix(exa): return highlights, highlight scores, score and the response envelope from Exa search (#47423) 2026-10-19 15:45:56 -07:00
fal_ai chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
fastcrw fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
featherless_ai refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
firecrawl fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
fireworks_ai fix(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444) 2026-10-14 21:40:14 -07:00
friendliai fix(friendliai): drop litellm-internal message fields before sending (#45092) 2026-10-20 01:22:07 +00:00
gdc test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
gemini test: catch regressions in the validation lines #44798 added (#47420) 2026-10-20 01:06:37 +00:00
gigachat fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
github_copilot fix(anthropic): add the dangerous-tool-use beta when a /v1/messages request carries safeguards (#43955) 2026-10-17 16:46:25 +00:00
google_pse chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
gradient_ai fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
groq fix(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444) 2026-10-14 21:40:14 -07:00
heroku fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
hosted_vllm test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
huggingface test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
hyperbolic refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
inception refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
infinity chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
jina_ai fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
lambda_ai test: move the unit half of 126 mixed legacy files into tests/unit (#45090) 2026-10-07 14:07:43 -07:00
langflow fix(ci): stop stale CI reds, keep unit tests off the host env, retry CyberArk policy conflicts (#43294) 2026-09-26 09:25:13 -07:00
langgraph chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
laya feat: add Bespoke Nimble gateway and OSS classifier support (#44246) 2026-10-02 19:37:08 -07:00
lemonade chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
linkup fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
litellm_proxy fix(openai): send chat completions through client.post so the SDK's per-message param transform stops holding the event loop (#46967) 2026-10-16 18:06:01 -07:00
llamafile refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
lm_studio refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
manus test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
meta fix(realtime)!: keep turn_detection.type when a transcript guardrail disables auto-response (#44939) 2026-10-16 15:24:40 +00:00
meta_llama refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
microsoft_365_copilot fix(router)!: bound fake-streamed calls by the request timeout, not stream_timeout (#47162) 2026-10-17 22:08:02 +00:00
milvus test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
minimax feat(minimax): add MiniMax-H3 and H3-Max video generation via /v1/videos (#43705) 2026-10-15 05:48:36 -07:00
mistral fix(anthropic)!: answer 400 for a malformed tool_result text on /v1/messages and count_tokens (#47347) 2026-10-19 21:13:46 +00:00
modelscope fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
mongodb test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
moonshot fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
nadir test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
nebius test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
neosantara refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
nimble test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
nlp_cloud chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
novita test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
nscale test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
nvidia_nim fix(openai): send chat completions through client.post so the SDK's per-message param transform stops holding the event loop (#46967) 2026-10-16 18:06:01 -07:00
nvidia_riva test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
oci fix(oci): drop non-function tools under drop_params and gate reasoning_effort on declared levels (#40732) 2026-10-15 22:20:02 +00:00
ocr test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
ollama fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
oobabooga test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
openai fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
openai_like feat(openinfer): add OpenInfer as an OpenAI-compatible provider (#41034) 2026-10-17 23:22:19 +00:00
opencode 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
openrouter chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
opensandbox chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
ovhcloud chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
parallel_ai test: add __init__.py to phase 12 unit test directories 2026-09-20 12:36:15 +00:00
parasail refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
pass_through fix(bedrock)!: scan Claude invoke-with-response-stream passthrough output with post_call guardrails (#46524) 2026-10-17 01:17:19 -07:00
perplexity fix(openai): send chat completions through client.post so the SDK's per-message param transform stops holding the event loop (#46967) 2026-10-16 18:06:01 -07:00
pg_vector fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
pi feat(harness): add pi harness for litellm.agent() (#45467) 2026-10-20 09:01:40 +00:00
publicai test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
ragflow test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
recraft refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
reducto test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
replicate chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
runwayml test: add __init__.py to phase 12 unit test directories 2026-09-20 12:36:15 +00:00
s3_vectors test: add __init__.py to intermediate phase 12 unit test directories 2026-09-20 12:37:21 +00:00
sagemaker fix(sagemaker)!: parse every streamed record however SageMaker cuts the payload parts (#47495) 2026-10-20 09:36:49 +00:00
sail test(e2e): align completion, SAIL, and spend-log fixtures with supported contracts (#43902) 2026-09-30 14:21:22 -07:00
sambanova chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
sap fix(sap): correctly handle cache_control (#39122) 2026-10-06 08:54:06 -07:00
scaledown feat(scaledown): add native text provider support (#44168) 2026-10-10 14:01:17 -07:00
scaleway test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
searchapi chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
searxng chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
serper chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
snowflake fix(bedrock)!: keep reasoning, thinking blocks and the json_mode finish_reason on fake streams (#46863) 2026-10-16 17:27:57 +00:00
soniox feat(soniox): decode proxy form fields for context, translation and flags (#40605) 2026-10-16 06:37:34 +00:00
stability refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
strands_decider feat(strands_decider): call a Strands Decider on an AgentCore runtime ARN (#45678) 2026-10-09 22:51:19 -07:00
tavily fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
tencent refactor(anthropic): rename experimental_pass_through to pass_through (#43329) 2026-09-26 13:00:50 -07:00
tinyfish test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
together_ai fix(responses bridge): round-trip tool_search_call and tool_search_output items between turns (#46444) 2026-10-14 21:40:14 -07:00
tool_loop feat(harness): add Harness.TOOL_LOOP, a minimal in-process tool-calling loop (#44391) 2026-10-03 17:33:01 +00:00
topaz fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
triton test: move offline logging, secret manager and provider tests from legacy dirs into tests/unit (#45554) 2026-10-09 09:48:10 -07:00
v0 test: move the unit half of 126 mixed legacy files into tests/unit (#45090) 2026-10-07 14:07:43 -07:00
valkey test: migrate legacy provider tests to tests/unit (wave 2, phase 13) 2026-09-20 14:18:49 +00:00
vercel_ai_gateway refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
vertex_ai fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
vllm fix(vllm): write spend log rows for /vllm passthrough calls to router models (#45733) 2026-10-14 12:40:48 -07:00
volcengine fix(openai): send chat completions through client.post so the SDK's per-message param transform stops holding the event loop (#46967) 2026-10-16 18:06:01 -07:00
voyage fix(llms): sanitize trailing slashes in provider get_complete_url (#42887) 2026-10-15 02:59:46 -07:00
wandb test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
watsonx chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388) 2026-10-13 15:35:23 -07:00
xai fix: preserve explicit provider for async image, audio, and realtime routes (#36346) 2026-10-15 05:21:43 -07:00
xinference test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
you_com test: migrate phase 14 wave 2 provider tests to tests/unit 2026-09-20 11:01:40 +00:00
zai test: add __init__.py to every tests/unit directory this migration touches 2026-09-20 11:52:09 +00:00
__init__.py test(unit): add package markers to migrated unit test directories 2026-09-20 11:53:14 +00:00
test_cache_control_and_reasoning.py test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
test_custom_llm.py test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807) 2026-10-07 05:02:28 +00:00
test_file_content_block.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_file_search_responses.py fix(responses)!: count input tokens the way inference sends the request (#47363) 2026-10-20 15:13:59 +00:00
test_lifecycle_fix.py refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
test_oss_decision.py feat(decisions): add Laya and Bespoke providers to the Add Model form (#45260) 2026-10-14 08:11:11 -07:00
test_polling_url_origin_match.py test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199) 2026-09-25 17:10:13 -07:00
test_predibase_transformation.py fix(prompt-templates): treat initial_prompt_value and final_prompt_value as optional (#39762) 2026-10-16 10:30:59 +00:00