fix(anthropic): handle tool_choice type 'none' in messages API

[BillionClaw]

Fixes #24443.

The Anthropic /v1/messages API accepts tool_choice={"type": "none"} to explicitly disable tool use. The translation layer in LiteLLMAnthropicMessagesAdapter.translate_anthropic_tool_choice_to_openai() was missing a handler for this case, causing it to fall through to a ValueError: Incompatible tool choice param submitted - {'type': 'none'}.

OpenAI's ChatCompletionToolChoiceValues accepts "none", so the fix is to add a branch that maps {"type": "none"} → "none".

Added a regression test in the existing test file.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
litellm	Ready	Preview, Comment	Mar 23, 2026 11:42pm

[greptile-apps]

Greptile Summary

Adds handling for tool_choice={"type": "none"} in translate_anthropic_tool_choice_to_openai, mapping it to the OpenAI string "none" instead of raising a ValueError. The fix is minimal and correct — "none" is already declared as a valid literal in the AnthropicMessagesToolChoice TypedDict, and the new branch sits naturally alongside the existing "auto", "any", and "tool" branches.

Confidence Score: 5/5

Safe to merge — minimal, targeted bugfix with a regression test and no side effects.

The change is a single two-line addition that fills a gap already expressed in the existing TypedDict. No existing behaviour is altered, no mocks are weakened, and the new test exercises exactly the fixed path.

No files require special attention.

Important Files Changed

Filename	Overview
litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py	Added elif tool_choice["type"] == "none": return "none" branch to translate_anthropic_tool_choice_to_openai; correctly fills the missing case already typed in AnthropicMessagesToolChoice.
tests/test_litellm/llms/anthropic/experimental_pass_through/adapters/test_anthropic_experimental_pass_through_adapters_transformation.py	Adds test_translate_anthropic_tool_choice_none regression test; existing test reformatted cosmetically (no logic change).

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A["translate_anthropic_tool_choice_to_openai(tool_choice)"] --> B{tool_choice type?}
    B -->|"any"| C["return 'required'"]
    B -->|"auto"| D["return 'auto'"]
    B -->|"tool"| E["truncate name\nreturn ChatCompletionToolChoiceObjectParam"]
    B -->|"none"| F["return 'none' ✅ NEW"]
    B -->|other| G["raise ValueError"]

Loading

_{Reviews (2): Last reviewed commit: "Merge branch 'litellm_oss_staging_04_22_..." | Re-trigger Greptile}

[codspeed-hq]

Merging this PR will not alter performance

✅ 16 untouched benchmarks

---

_{Comparing BillionClaw:clawoss/fix/24443-tool-choice-none (b3e5dd3) with main (63425b4)}

[BillionClaw]

This is BillionClaw. Happy to discuss the approach or make adjustments to the fix.

[lgx0319]

Friendly bump -- this PR has been open for a while. Happy to make any changes if needed, or close it if no longer relevant.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ BillionClaw
❌ krrish-berri-2
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[gitguardian]

⚠️ GitGuardian has uncovered 2 secrets following the scan of your pull request.

Please consider investigating the findings and remediating the incidents. Failure to do so may lead to compromising the associated services or software components.

Since your pull request originates from a forked repository, GitGuardian is not able to associate the secrets uncovered with secret incidents on your GitGuardian dashboard.
Skipping this check run and merging your pull request will create secret incidents on your GitGuardian dashboard.

🔎 Detected hardcoded secrets in your pull request

GitGuardian id	GitGuardian status	Secret	Commit	Filename
29203053	Triggered	Generic Password	f7bb810	.circleci/config.yml	View secret
29375658	Triggered	JSON Web Token	f7bb810	tests/test_litellm/proxy/auth/test_handle_jwt.py	View secret

🛠 Guidelines to remediate hardcoded secrets

1. Understand the implications of revoking this secret by investigating where it is used in your code.
2. Replace and store your secrets safely. Learn here the best practices.
3. Revoke and rotate these secrets.
4. If possible, rewrite git history. Rewriting git history is not a trivial act. You might completely break other contributing developers' workflow and you risk accidentally deleting legitimate data.

To avoid such incidents in the future consider

• following these best practices for managing and storing secrets including API keys and other credentials
• install secret detection on pre-commit to catch secret before it leaves your machine and ease remediation.

---

^{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}