* test: drop the cwd-relative sys.path.insert calls from the test suite
TQ003 stands at 1,077 across 1,058 files, and 1,015 of them are the same shape:
sys.path.insert(0, os.path.abspath("../..")) and its deeper siblings. The
argument resolves against the working directory rather than the file, so from
the repo root, where every job runs pytest, it inserts the directory two levels
above the checkout. It has never pointed at litellm. The package is installed
into the environment anyway, which is what actually makes the import work, and
what the rule's message has said all along.
Removing them leaves 1,634 imports of sys and os with no remaining reference,
and those go too, except where another test module imports the name back out of
the file. The rest of TQ003 is 62 call sites that resolve against __file__ or a
variable, which are a different question and are left alone.
Collection is identical either way: 45,871 tests and the same 51 pre-existing
collection errors before and after, and ruff reports no new undefined name.
* test: drop the duplicate imports the sys.path sweep exposed to F811
* test(pre-call-utils): restore the os import the new bedrock tests need
Azure rejects the legacy `max_tokens` key for the whole gpt-5 name family, but
`AzureOpenAIGPT5Config.is_model_gpt_5_model` deliberately excludes `gpt-5-chat*`
so those deployments fall through to `AzureOpenAIConfig`, which sends `max_tokens`
verbatim and gets a 400 back on every request that carries it, `/health` probes
included.
One predicate was answering two independent questions. Split it: the new
`AzureOpenAIConfig.requires_max_completion_tokens` covers the whole gpt-5 name
family and drives only the rename, while `is_model_gpt_5_model` keeps keying
reasoning_effort, the temperature clamp and the dropped penalties off the
reasoning question, so #13781 stays fixed.
Images nested inside an Anthropic `tool_result` block were dropped when the
request was adapted for an OpenAI-compatible provider, because the OpenAI tool
message shape only carried text. Hoist those images out of the tool result and
into a following user message so the model can still see them, and widen the
tool message content type to accept image parts.
* fix(anthropic): handle empty streaming tool calls (#28549)
Co-authored-by: shin-berri <shin-laptop@berri.ai>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
* [Feature][Bug Fix] Decouple Azure OpenAI Deployment ID from model name via base_model to fix gpt5 model routing (#28490)
* feat(azure): decouple deployment ID from model name via base_model
Azure OpenAI deployments have arbitrary names (deployment IDs) that may
not match the underlying model. Previously, model-type detection
(o-series, gpt-5, etc.) relied on substring matching against the
deployment name, causing misrouted configs and rejected params when
deployment names were non-standard (e.g. 'my-deployment-id' for gpt-5.2).
This change extends the existing base_model field to drive model-type
detection, config selection, supported param resolution, and param
mapping throughout the Azure call path:
- _get_azure_config() uses base_model for is_o_series/is_gpt_5 checks
- get_provider_chat_config() threads base_model for Azure
- get_supported_openai_params() accepts and uses base_model
- get_optional_params() accepts base_model and passes it to all Azure
config method calls (get_supported_openai_params, map_openai_params)
- azure.py completion handler uses base_model for GPT-5 detection
- Config internal methods (e.g. is_model_gpt_5_2_model) now receive
base_model so features like logprobs are correctly enabled
Fully backward compatible - when base_model is unset, behavior is
identical. Existing o_series/ and gpt5_series/ prefix workarounds
continue to work.
Usage in proxy config:
model_list:
- model_name: my-gpt5
litellm_params:
model: azure/my-deployment-id
model_info:
base_model: azure/gpt-5.2
Fixes: non-standard deployment names like 'prefix-gpt-5.2' rejecting
logprobs/top_logprobs despite the underlying model supporting them.
* Addressing Greptile comments.
* gemini-3.1-flash-lite pricing (#27933)
* feat(model_prices): add gemini-3.1-flash-lite pricing with standard/batch/flex/priority tiers
* fix pricing
* add service tier
---------
Co-authored-by: shin-berri <shin-laptop@berri.ai>
* fix(openai-responses): strip Anthropic cache_control from Responses API requests (#28431)
Squash-merged by litellm-agent from cwang-otto's PR.
* Treat None litellm_provider as wildcard in _check_provider_match (#28523)
Squash-merged by litellm-agent from adityasingh2400's PR.
* fix greptile
* fix: use _azure_detection_model in default Azure branch of get_supported_openai_params
Co-authored-by: Yassin Kortam <yassin@berri.ai>
* fix(openai-responses): strip cache_control on compact endpoint as well
Co-authored-by: Yassin Kortam <yassin@berri.ai>
---------
Co-authored-by: Felipe Garé <90070734+FelipeRodriguesGare@users.noreply.github.com>
Co-authored-by: shin-berri <shin-laptop@berri.ai>
Co-authored-by: yuneng-jiang <yuneng@berri.ai>
Co-authored-by: withomasmicrosoft <withomas@microsoft.com>
Co-authored-by: mubashir1osmani <mubashir.osmani777@gmail.com>
Co-authored-by: cwang-otto <chengxuan.wang@ottotheagent.com>
Co-authored-by: Aditya Singh <60082699+adityasingh2400@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Yassin Kortam <yassin@berri.ai>
Azure GPT-5.4+ models now get the same auto-routing treatment as OpenAI
when both `reasoning_effort` and `tools` are used in `litellm.completion()`.
Previously, `reasoning_effort` was silently dropped for Azure; now the
request is bridged to the Responses API which supports both parameters.
Fixes#23914
- Add _get_effort_level() to extract effective effort from string or dict
- Use effective_effort for xhigh validation, tool-drop, sampling, temperature guards
- Preserve dict format when it has summary/generate_summary for Responses API
- Add tests: xhigh-dict validation, none-dict for tools/sampling/temperature
- Update tests: dict-with-summary now preserved (not normalized)
Made-with: Cursor
* fix:fix: prompt_cache_key OAI + Azure OpenAI
* test_prompt_cache_key_supported
* test_azure_openai_with_prompt_cache_key
* fix: remove unnecessary async from test_azure_openai_with_prompt_cache_key
Addresses Greptile feedback: litellm.completion() is synchronous, so
async def is unnecessary and would silently pass without running.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove unused filter_and_transform_beta_headers imports
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test_azure_openai_with_prompt_cache_key
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(azure): add logprobs support for Azure OpenAI GPT-5 models
Azure OpenAI GPT-5 models (including gpt-5.2) support logprobs
parameters, unlike OpenAI's GPT-5 reasoning models. This fix
overrides the parent class restriction to enable logprobs for Azure.
Changes:
- Override get_supported_openai_params() in AzureOpenAIGPT5Config
- Add "logprobs" and "top_logprobs" to supported params
- Add comprehensive tests for logprobs functionality
Testing:
- Verified with direct Azure API calls to gpt-5.2
- API version: 2025-01-01-preview
- Successfully returns logprobs data
Related: #7974, #4022
* refactor: restrict logprobs support to gpt-5.2 only
Only gpt-5.2 has been verified to support logprobs on Azure.
Other gpt-5 variants (gpt-5, gpt-5.1) have not been tested.
Changes:
- Add conditional check for is_model_gpt_5_2_model()
- Update tests to be specific to gpt-5.2
- Add negative tests for gpt-5 and gpt-5.1
- Update documentation to reflect gpt-5.2 specificity
* fix(azure/chat/gpt_transformation.py): support api_version="preview"
Fixes https://github.com/BerriAI/litellm/issues/12945
* Fix anthropic passthrough logging handler model fallback for streaming requests (#13022)
* fix: anthropic passthrough logging handler model fallback for streaming requests
- Add fallback logic to retrieve model from logging_obj.model_call_details when request_body.model is empty
- Fixes issue #12933 where streaming requests to anthropic passthrough endpoints would crash due to missing model field
- Ensures downstream logging and cost calculation work correctly for all streaming scenarios
- Maintains backwards compatibility with existing non-streaming requests
* test: add minimal tests for anthropic passthrough logging handler model fallback
- Add unit tests for the model fallback logic in _handle_logging_anthropic_collected_chunks
- Test existing behavior when request_body.model is present
- Test fallback logic when request_body.model is empty but logging_obj.model_call_details has model
- Test edge cases where both sources are empty or missing
- Ensure backwards compatibility and graceful degradation
* fix(anthropic_passthrough_logging_handler.py): add provider to model name (accurate cost tracking)
* fix(anthropic_passthrough_logging_handler.py): don't reset custom llm provider, if already set
* fix: fix check
---------
Co-authored-by: Haggai Shachar <haggai.shachar@backline.ai>
* fix(utils.py): support non default params for audio transcription
allows passing provider specific params straight through on transcription calls
* fix(gpt_transformation.py): fix o_series model routing
call _transform_request on async event
* refactor: refactor tests
* test(test_azure_chat_o_series_transformation.py): add unit test for azure o series error
* test: update test
* test: update json
* fix: fix mutiple keyword error
