feat(ai-anthropic): computer use on the Claude 5.5 models, with the computer toolset, computer_20251124, and SDK 0.135 by AlemTuzlak · Pull Request #1834 · TanStack/ai

AlemTuzlak · 2026-10-19T17:08:30Z

Computer use now works on Claude Opus 5.5, Sonnet 5.5, and Haiku 5.5, through computer_toolset_20260801. computerUseTool() also takes computer_20251124. One execute works for every version. TypeScript now rejects a version that the model does not take. The PR upgrades @anthropic-ai/sdk to 0.135.0, the first version with the toolset types. It is stacked on #1832 (the computer use beta header), so its diff starts after that PR.

🎯 Changes

The computer toolset. computerUseTool({ type: 'computer_toolset_20260801', configs? }) sends one entry with no name and no beta header. Claude calls each action as its own tool (left_click, screenshot, and more) with toolset_name: 'computer'. Then the adapter does three things:
1. It joins each call into one computer call with the action in input.action. The joined arguments stream at the end of the block.
2. It sends each call back to Claude in the form that Claude sent it.
3. It adds toolset_name to each result.
computer_20251124. It goes out with the computer-use-2025-11-24 beta. Each earlier version now maps to its own beta header.
Each model takes only its versions. There are three tool kinds in model-meta.ts: computer_use (computer_20241022, computer_20250124), computer_use_20251124, and computer_toolset. Each model gets the kinds from the Anthropic compatibility table. The model sync now gives a new Claude model computer_toolset.
SDK 0.135.0. The upgrade broke two things, and the PR fixes both. FileMetadata is now BetaFileMetadata. The @anthropic-ai/sdk-v112 test alias is gone: it checked an SDK newer than the old 0.97.1, and 0.135.0 is newer than it. Two more changes come with the new types:
- The SDK now types mid-conversation system messages, so the local type and the cast are gone.
- A toolset entry has no name, so two reads of tool.name check for it first.
- The SDK now sends the files-api-2025-04-14 header once. The old SDK sent it twice, so auth-parity.test.ts now expects one header.
Docs and tests. The computerUseTool section has a version table and a full loop with execute, and the support matrix has the new versions. There are unit tests and an E2E wire spec for the toolset loop.

The lockfile changes because of the SDK upgrade. The @google/genai entry of ai-vertex stays as on main. When the install moved it to a copy with zod@4.6.5, the mock in the ai-vertex test missed the copy that ai-gemini loads.

✅ Checklist

I have followed the steps in the Contributing guide.
I have tested code changes locally with pnpm run test:pr, or these tests do not apply to this pull request.
I fully understand the code in this pull request, including any code generated with AI assistance.
Docs: I updated docs/ for this change, or this change is not user-facing.
Changeset: I added a changeset (pnpm changeset), or this PR does not change a published package.

🚀 Release Impact

This change affects published code, and I have generated a changeset.
This change is docs/CI/dev-only (no release).

Testing

Commands run:

A pnpm build of the dependencies of ai-anthropic, then vite build and publint of ai-anthropic.
test:types and test:oxlint of ai-anthropic (no new warnings), oxfmt --check on every changed file, pnpm test:sherif, and pnpm test:docs.
Vitest with --maxWorkers=2 on 13 ai-anthropic files: the new computer-toolset and computer-use-beta tests, and the tests of tools, betas, files, the client type, prompt caching, mid-conversation changes, replay, and model meta. 178 tests pass. The model-sync test (scripts/model-sync/provider-supports.test.ts) passes too.
kiira check on docs/adapters/anthropic.md and docs/tools/provider-tools.md: 30 snippets pass.
After CI failed on ai-anthropic:test:lib and ai-vertex:test:lib: the full ai-anthropic unit suite (26 files, 307 tests) and the ai-vertex unit suite (12 tests). All pass after the fix commit.
The two new E2E routes type-check with the TypeScript of testing/e2e. The two new specs type-check on their own.

Not run locally: the E2E suite, pnpm test:pr, knip, coverage, and the typecheck of examples/ts-react-chat and all of testing/e2e (they need a build of every package). CI runs them.

Manual test:

Run pnpm --dir packages/ai-anthropic exec vitest run tests/computer-toolset.test.ts tests/tools-per-model-type-safety.test.ts.
Open tests/computer-toolset.test.ts. The second test streams left_click and screenshot as toolset calls. execute gets { action: 'left_click', coordinate: [500, 300] } and { action: 'screenshot' }. The next request sends both calls back with toolset_name: 'computer'.
With a real key, run the sample in docs/adapters/anthropic.md#computerusetool on claude-opus-5-5 with your own screen functions.

How this PR makes testing easy: tests/computer-toolset.test.ts drives a full toolset loop through chat() with a mocked client. testing/e2e/tests/anthropic-computer-toolset-wire.spec.ts runs the same loop against a custom fetch and checks each request on the wire. tests/tools-per-model-type-safety.test.ts checks which versions each model takes.

Risk / rollback

Medium:

The SDK moves from 0.97.1 to 0.135.0. The unit tests mock the SDK. The E2E suite in CI runs the real SDK.
Type errors on some models. A call that type-checked before can fail to compile now: for example, computer_20250124 on claude-opus-4-6. Anthropic rejects that pair at runtime, so only broken code stops compiling.

To undo, revert this PR.

Public API change

Before

// claude-opus-5-5 took no computer use version.
// computer_20250124 type-checked on claude-opus-4-6, and Anthropic rejected it.
computerUseTool({
  type: 'computer_20250124',
  name: 'computer',
  display_width_px: 1024,
  display_height_px: 768,
})

After

const computer = {
  ...computerUseTool({ type: 'computer_toolset_20260801' }),
  execute: async (input: { action: string }) => runOnMyScreen(input),
}

chat({
  adapter: anthropicText('claude-opus-5-5'),
  messages,
  tools: [computer],
  toolExecution: 'sequential',
})

Upgrade @anthropic-ai/sdk to 0.135.0. Add computer_20251124 with its computer-use-2025-11-24 beta, and computer_toolset_20260801 for the Claude 5.5 models. A toolset call runs as one computer call with the action in input.action, and goes back to Claude in the form that it sent. Each model now takes only the computer use versions that it supports.

Also add the changeset and format the changed files.

changeset-bot · 2026-10-19T17:08:36Z

🦋 Changeset detected

Latest commit: 7fac2ac

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package

Name	Type
@tanstack/ai-anthropic	Minor

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

socket-security · 2026-10-19T17:09:22Z

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	npm/@anthropic-ai/sdk@0.97.1 ⏵ 0.135.0			⁺¹²

View full report

nx-cloud · 2026-10-19T17:12:46Z

View your CI Pipeline Execution ↗ for commit 7fac2ac

Command	Status	Duration	Result
`nx run-many --targets=build --exclude=examples/...`	✅ Succeeded	4s	View ↗

☁️ Nx Cloud last updated this comment at 2026-10-20 08:26:50 UTC

pkg-pr-new · 2026-10-19T17:15:14Z

Open in StackBlitz

@tanstack/ai

npm i https://pkg.pr.new/@tanstack/ai@1834

@tanstack/ai-acp

npm i https://pkg.pr.new/@tanstack/ai-acp@1834

@tanstack/ai-angular

npm i https://pkg.pr.new/@tanstack/ai-angular@1834

@tanstack/ai-anthropic

npm i https://pkg.pr.new/@tanstack/ai-anthropic@1834

@tanstack/ai-bedrock

npm i https://pkg.pr.new/@tanstack/ai-bedrock@1834

@tanstack/ai-byteplus

npm i https://pkg.pr.new/@tanstack/ai-byteplus@1834

@tanstack/ai-claude-code

npm i https://pkg.pr.new/@tanstack/ai-claude-code@1834

@tanstack/ai-client

npm i https://pkg.pr.new/@tanstack/ai-client@1834

@tanstack/ai-cloudflare

npm i https://pkg.pr.new/@tanstack/ai-cloudflare@1834

@tanstack/ai-code-mode

npm i https://pkg.pr.new/@tanstack/ai-code-mode@1834

@tanstack/ai-code-mode-snippets

npm i https://pkg.pr.new/@tanstack/ai-code-mode-snippets@1834

@tanstack/ai-codex

npm i https://pkg.pr.new/@tanstack/ai-codex@1834

@tanstack/ai-cohere

npm i https://pkg.pr.new/@tanstack/ai-cohere@1834

@tanstack/ai-compaction

npm i https://pkg.pr.new/@tanstack/ai-compaction@1834

@tanstack/ai-devtools-core

npm i https://pkg.pr.new/@tanstack/ai-devtools-core@1834

@tanstack/ai-durable-stream

npm i https://pkg.pr.new/@tanstack/ai-durable-stream@1834

@tanstack/ai-elevenlabs

npm i https://pkg.pr.new/@tanstack/ai-elevenlabs@1834

@tanstack/ai-event-client

npm i https://pkg.pr.new/@tanstack/ai-event-client@1834

@tanstack/ai-fal

npm i https://pkg.pr.new/@tanstack/ai-fal@1834

@tanstack/ai-gemini

npm i https://pkg.pr.new/@tanstack/ai-gemini@1834

@tanstack/ai-grok

npm i https://pkg.pr.new/@tanstack/ai-grok@1834

@tanstack/ai-grok-build

npm i https://pkg.pr.new/@tanstack/ai-grok-build@1834

@tanstack/ai-groq

npm i https://pkg.pr.new/@tanstack/ai-groq@1834

@tanstack/ai-isolate-cloudflare

npm i https://pkg.pr.new/@tanstack/ai-isolate-cloudflare@1834

@tanstack/ai-isolate-daytona

npm i https://pkg.pr.new/@tanstack/ai-isolate-daytona@1834

@tanstack/ai-isolate-e2b

npm i https://pkg.pr.new/@tanstack/ai-isolate-e2b@1834

@tanstack/ai-isolate-node

npm i https://pkg.pr.new/@tanstack/ai-isolate-node@1834

@tanstack/ai-isolate-quickjs

npm i https://pkg.pr.new/@tanstack/ai-isolate-quickjs@1834

@tanstack/ai-isolate-quickjs-bun

npm i https://pkg.pr.new/@tanstack/ai-isolate-quickjs-bun@1834

@tanstack/ai-llmgateway

npm i https://pkg.pr.new/@tanstack/ai-llmgateway@1834

@tanstack/ai-lovable

npm i https://pkg.pr.new/@tanstack/ai-lovable@1834

@tanstack/ai-mcp

npm i https://pkg.pr.new/@tanstack/ai-mcp@1834

@tanstack/ai-memory

npm i https://pkg.pr.new/@tanstack/ai-memory@1834

@tanstack/ai-mistral

npm i https://pkg.pr.new/@tanstack/ai-mistral@1834

@tanstack/ai-octane

npm i https://pkg.pr.new/@tanstack/ai-octane@1834

@tanstack/ai-ollama

npm i https://pkg.pr.new/@tanstack/ai-ollama@1834

@tanstack/ai-ollaya

npm i https://pkg.pr.new/@tanstack/ai-ollaya@1834

@tanstack/ai-openai

npm i https://pkg.pr.new/@tanstack/ai-openai@1834

@tanstack/ai-opencode

npm i https://pkg.pr.new/@tanstack/ai-opencode@1834

@tanstack/ai-openrouter

npm i https://pkg.pr.new/@tanstack/ai-openrouter@1834

@tanstack/ai-perplexity

npm i https://pkg.pr.new/@tanstack/ai-perplexity@1834

@tanstack/ai-persistence

npm i https://pkg.pr.new/@tanstack/ai-persistence@1834

@tanstack/ai-preact

npm i https://pkg.pr.new/@tanstack/ai-preact@1834

@tanstack/ai-react

npm i https://pkg.pr.new/@tanstack/ai-react@1834

@tanstack/ai-react-ui

npm i https://pkg.pr.new/@tanstack/ai-react-ui@1834

@tanstack/ai-reactor

npm i https://pkg.pr.new/@tanstack/ai-reactor@1834

@tanstack/ai-remix

npm i https://pkg.pr.new/@tanstack/ai-remix@1834

@tanstack/ai-sandbox

npm i https://pkg.pr.new/@tanstack/ai-sandbox@1834

@tanstack/ai-sandbox-blaxel

npm i https://pkg.pr.new/@tanstack/ai-sandbox-blaxel@1834

@tanstack/ai-sandbox-boxd

npm i https://pkg.pr.new/@tanstack/ai-sandbox-boxd@1834

@tanstack/ai-sandbox-cloudflare

npm i https://pkg.pr.new/@tanstack/ai-sandbox-cloudflare@1834

@tanstack/ai-sandbox-daytona

npm i https://pkg.pr.new/@tanstack/ai-sandbox-daytona@1834

@tanstack/ai-sandbox-docker

npm i https://pkg.pr.new/@tanstack/ai-sandbox-docker@1834

@tanstack/ai-sandbox-e2b

npm i https://pkg.pr.new/@tanstack/ai-sandbox-e2b@1834

@tanstack/ai-sandbox-local-process

npm i https://pkg.pr.new/@tanstack/ai-sandbox-local-process@1834

@tanstack/ai-sandbox-railway

npm i https://pkg.pr.new/@tanstack/ai-sandbox-railway@1834

@tanstack/ai-sandbox-sprites

npm i https://pkg.pr.new/@tanstack/ai-sandbox-sprites@1834

@tanstack/ai-sandbox-upstash-box

npm i https://pkg.pr.new/@tanstack/ai-sandbox-upstash-box@1834

@tanstack/ai-sandbox-vercel

npm i https://pkg.pr.new/@tanstack/ai-sandbox-vercel@1834

@tanstack/ai-skills

npm i https://pkg.pr.new/@tanstack/ai-skills@1834

@tanstack/ai-solid

npm i https://pkg.pr.new/@tanstack/ai-solid@1834

@tanstack/ai-solid-ui

npm i https://pkg.pr.new/@tanstack/ai-solid-ui@1834

@tanstack/ai-svelte

npm i https://pkg.pr.new/@tanstack/ai-svelte@1834

@tanstack/ai-typesafe

npm i https://pkg.pr.new/@tanstack/ai-typesafe@1834

@tanstack/ai-utils

npm i https://pkg.pr.new/@tanstack/ai-utils@1834

@tanstack/ai-vercel-gateway

npm i https://pkg.pr.new/@tanstack/ai-vercel-gateway@1834

@tanstack/ai-vertex

npm i https://pkg.pr.new/@tanstack/ai-vertex@1834

@tanstack/ai-vue

npm i https://pkg.pr.new/@tanstack/ai-vue@1834

@tanstack/ai-vue-ui

npm i https://pkg.pr.new/@tanstack/ai-vue-ui@1834

@tanstack/ai-worldlabs

npm i https://pkg.pr.new/@tanstack/ai-worldlabs@1834

@tanstack/openai-base

npm i https://pkg.pr.new/@tanstack/openai-base@1834

@tanstack/preact-ai-devtools

npm i https://pkg.pr.new/@tanstack/preact-ai-devtools@1834

@tanstack/react-ai-devtools

npm i https://pkg.pr.new/@tanstack/react-ai-devtools@1834

@tanstack/solid-ai-devtools

npm i https://pkg.pr.new/@tanstack/solid-ai-devtools@1834

@tanstack/svelte-ai-devtools

npm i https://pkg.pr.new/@tanstack/svelte-ai-devtools@1834

commit: 7fac2ac

coderabbitai · 2026-10-19T17:23:52Z

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Repository: TanStack/ai/.coderabbit.yaml
Review profile: CHILL
Plan: Advanced
Run ID: 51278ec0-11e4-487a-becf-f44332dd7aa0

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands.}

…les beta header The SDK install moved the @google/genai of ai-vertex to a copy with zod 4.6.5, so its test mock missed the copy that ai-gemini loads. SDK 0.135.0 sends the files-api beta header once, where 0.97.1 sent it twice.

github-actions · 2026-10-19T17:37:47Z

Coverage

✅ Coverage held across 68 compared package(s).

Each package is measured twice in this job — on this PR and on its merge-base with main — and compared. A metric fails only when it is at or above 60% on the merge-base and under 60% on this PR. Other drops are listed but do not fail. Packages your PR doesn't affect are not measured and not listed.

package	statements	branches	functions	lines
ai	91.66% (0.00)	85.47% (0.00)	92.42% (0.00)	93.28% (0.00)	ok
ai-acp	78.41% (0.00)	66.79% (0.00)	70.27% (0.00)	80.13% (0.00)	ok
ai-angular	74.10% (0.00)	62.20% (0.00)	61.65% (0.00)	75.60% (0.00)	ok
ai-anthropic	92.17% (+0.13)	87.13% (+0.33)	95.72% (+0.11)	92.56% (+0.11)	ok
ai-bedrock	90.11% (0.00)	82.82% (0.00)	94.20% (0.00)	91.33% (0.00)	ok
ai-byteplus	97.06% (0.00)	91.66% (0.00)	98.27% (0.00)	98.49% (0.00)	ok
ai-claude-code	88.93% (0.00)	76.88% (0.00)	86.88% (0.00)	90.40% (0.00)	ok
ai-client	87.96% (0.00)	80.38% (0.00)	87.13% (0.00)	90.26% (0.00)	ok
ai-cloudflare	85.55% (0.00)	76.44% (0.00)	85.48% (0.00)	86.79% (0.00)	ok
ai-code-mode	91.71% (0.00)	83.12% (0.00)	86.27% (0.00)	92.63% (0.00)	ok
ai-code-mode-snippets	87.13% (0.00)	75.67% (0.00)	91.11% (0.00)	88.39% (0.00)	ok
ai-codex	94.55% (0.00)	85.10% (0.00)	89.28% (0.00)	95.56% (0.00)	ok
ai-cohere	88.97% (0.00)	88.37% (0.00)	85.71% (0.00)	91.80% (0.00)	ok
ai-compaction	97.38% (0.00)	92.79% (0.00)	100.00% (0.00)	98.88% (0.00)	ok
ai-devtools	83.13% (0.00)	72.77% (0.00)	87.07% (0.00)	85.22% (0.00)	ok
ai-durable-stream	86.70% (0.00)	82.25% (0.00)	92.30% (0.00)	88.72% (0.00)	ok
ai-elevenlabs	74.68% (0.00)	69.59% (0.00)	59.13% (0.00)	75.46% (0.00)	ok
ai-event-client	56.83% (0.00)	46.87% (0.00)	68.96% (0.00)	57.89% (0.00)	ok
ai-fal	91.10% (0.00)	82.63% (0.00)	92.40% (0.00)	91.60% (0.00)	ok
ai-gemini	68.33% (0.00)	67.88% (0.00)	64.62% (0.00)	68.93% (0.00)	ok
ai-grok	48.85% (0.00)	53.49% (0.00)	56.46% (0.00)	49.67% (0.00)	ok
ai-grok-build	79.19% (0.00)	63.56% (0.00)	77.39% (0.00)	81.02% (0.00)	ok
ai-groq	52.54% (0.00)	47.73% (0.00)	67.39% (0.00)	54.66% (0.00)	ok
ai-isolate-cloudflare	94.11% (0.00)	70.66% (0.00)	100.00% (0.00)	93.96% (0.00)	ok
ai-isolate-daytona	90.25% (0.00)	81.34% (+0.75)	100.00% (0.00)	90.15% (0.00)	ok
ai-isolate-e2b	92.11% (0.00)	81.48% (0.00)	97.36% (0.00)	95.05% (0.00)	ok
ai-isolate-node	84.00% (0.00)	43.39% (0.00)	100.00% (0.00)	83.78% (0.00)	ok
ai-isolate-quickjs	89.07% (0.00)	76.41% (0.00)	90.90% (0.00)	90.30% (0.00)	ok
ai-isolate-quickjs-bun	7.76% (0.00)	8.08% (0.00)	5.00% (0.00)	8.33% (0.00)	ok
ai-llmgateway	97.67% (0.00)	100.00% (0.00)	88.88% (0.00)	97.67% (0.00)	ok
ai-lovable	73.21% (0.00)	55.63% (0.00)	85.07% (0.00)	73.96% (0.00)	ok
ai-mcp	96.91% (0.00)	92.43% (0.00)	97.33% (0.00)	98.72% (0.00)	ok
ai-memory	73.87% (0.00)	52.70% (0.00)	79.74% (0.00)	76.04% (0.00)	ok
ai-mistral	84.82% (0.00)	79.88% (0.00)	92.59% (0.00)	85.46% (0.00)	ok
ai-octane	90.67% (0.00)	67.74% (0.00)	86.66% (0.00)	90.79% (0.00)	ok
ai-ollama	92.73% (0.00)	78.15% (0.00)	90.62% (0.00)	92.68% (0.00)	ok
ai-ollaya	86.84% (0.00)	89.28% (0.00)	85.71% (0.00)	91.66% (0.00)	ok
ai-openai	65.34% (0.00)	65.72% (0.00)	66.66% (0.00)	65.63% (0.00)	ok
ai-opencode	69.04% (0.00)	60.82% (0.00)	65.26% (0.00)	70.87% (0.00)	ok
ai-openrouter	87.88% (0.00)	73.00% (0.00)	90.78% (0.00)	89.79% (0.00)	ok
ai-perplexity	91.34% (0.00)	90.43% (0.00)	100.00% (0.00)	93.87% (0.00)	ok
ai-persistence	91.36% (0.00)	81.23% (0.00)	97.45% (0.00)	94.87% (0.00)	ok
ai-preact	85.62% (0.00)	70.81% (0.00)	85.96% (0.00)	87.02% (0.00)	ok
ai-react	72.95% (0.00)	51.89% (0.00)	73.77% (0.00)	73.07% (0.00)	ok
ai-reactor	94.91% (0.00)	83.33% (0.00)	93.33% (0.00)	96.55% (0.00)	ok
ai-remix	36.70% (0.00)	22.69% (0.00)	34.18% (0.00)	39.04% (0.00)	ok
ai-sandbox	77.53% (+0.07)	82.84% (+0.04)	74.58% (+0.11)	78.03% (+0.05)	ok
ai-sandbox-blaxel	87.64% (0.00)	77.18% (0.00)	82.26% (0.00)	89.71% (0.00)	ok
ai-sandbox-boxd	95.86% (0.00)	87.12% (0.00)	95.31% (0.00)	98.17% (0.00)	ok
ai-sandbox-cloudflare	67.91% (0.00)	57.47% (0.00)	71.79% (0.00)	69.62% (0.00)	ok
ai-sandbox-daytona	82.70% (0.00)	81.89% (0.00)	67.14% (0.00)	85.18% (0.00)	ok
ai-sandbox-docker	80.15% (0.00)	71.49% (0.00)	77.38% (0.00)	82.13% (0.00)	ok
ai-sandbox-e2b	94.42% (0.00)	88.97% (0.00)	93.24% (0.00)	98.63% (0.00)	ok
ai-sandbox-local-process	68.00% (0.00)	53.59% (0.00)	75.86% (0.00)	68.88% (0.00)	ok
ai-sandbox-railway	94.75% (0.00)	92.68% (0.00)	90.90% (0.00)	97.59% (0.00)	ok
ai-sandbox-sprites	73.23% (0.00)	59.70% (0.00)	73.83% (0.00)	76.17% (0.00)	ok
ai-sandbox-upstash-box	94.82% (0.00)	91.52% (0.00)	91.04% (0.00)	97.76% (0.00)	ok
ai-sandbox-vercel	44.67% (0.00)	38.18% (0.00)	35.18% (0.00)	45.76% (0.00)	ok
ai-skills	80.38% (0.00)	64.05% (0.00)	84.86% (0.00)	82.44% (0.00)	ok
ai-solid	52.13% (0.00)	38.29% (0.00)	49.82% (0.00)	56.87% (0.00)	ok
ai-svelte	73.76% (0.00)	54.59% (0.00)	69.15% (0.00)	78.33% (0.00)	ok
ai-typesafe	78.04% (0.00)	84.61% (0.00)	66.66% (0.00)	82.05% (0.00)	ok
ai-utils	75.34% (0.00)	74.00% (0.00)	85.71% (0.00)	75.38% (0.00)	ok
ai-vercel-gateway	75.97% (0.00)	55.63% (0.00)	85.41% (0.00)	79.38% (0.00)	ok
ai-vertex	96.77% (0.00)	97.22% (0.00)	100.00% (0.00)	96.77% (0.00)	ok
ai-vue	60.07% (0.00)	34.10% (0.00)	59.34% (0.00)	61.04% (0.00)	ok
ai-worldlabs	79.62% (0.00)	71.50% (0.00)	91.42% (0.00)	82.66% (0.00)	ok
openai-base	90.31% (0.00)	78.28% (0.00)	97.66% (0.00)	92.36% (0.00)	ok

AlemTuzlak added 3 commits October 19, 2026 18:48

test(e2e): check the computer toolset loop on the wire

575855a

Also add the changeset and format the changed files.

feat(ai-anthropic): export the computer use config and tool types

854320e

AlemTuzlak requested a review from a team as a code owner October 19, 2026 17:08

andrewmcgivery mentioned this pull request Oct 19, 2026

feat(ai-anthropic): server-side refusal fallback, and refusals finish with content_filter #1835

Open

6 of 7 tasks

github-actions Bot assigned jherr Oct 20, 2026

github-actions Bot requested a review from jherr October 20, 2026 00:23

github-actions Bot added the waiting-on: maintainer The ball is in the maintainers’ court label Oct 20, 2026

docs(ai-anthropic): drop the as const in the computer use sample

7fac2ac

Navigation Menu

Repository navigation

feat(ai-anthropic): computer use on the Claude 5.5 models, with the computer toolset, computer_20251124, and SDK 0.135 - #1834

feat(ai-anthropic): computer use on the Claude 5.5 models, with the computer toolset, computer_20251124, and SDK 0.135#1834
AlemTuzlak wants to merge 5 commits into
fix/anthropic-computer-use-betafrom
feat/anthropic-computer-toolset

AlemTuzlak commented Oct 19, 2026 •

edited

Loading

Uh oh!

changeset-bot Bot commented Oct 19, 2026 •

edited

Loading

Uh oh!

socket-security Bot commented Oct 19, 2026 •

edited

Loading

Uh oh!

nx-cloud Bot commented Oct 19, 2026 •

edited

Loading

Uh oh!

pkg-pr-new Bot commented Oct 19, 2026 •

edited

Loading

Uh oh!

coderabbitai Bot commented Oct 19, 2026 •

edited

Loading

Review skipped

Uh oh!

github-actions Bot commented Oct 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

AlemTuzlak commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🎯 Changes

✅ Checklist

🚀 Release Impact

Testing

Risk / rollback

Public API change

Uh oh!

changeset-bot Bot commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🦋 Changeset detected

Uh oh!

socket-security Bot commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

nx-cloud Bot commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pkg-pr-new Bot commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

coderabbitai Bot commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Uh oh!

github-actions Bot commented Oct 19, 2026

Coverage

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

AlemTuzlak commented Oct 19, 2026 •

edited

Loading

changeset-bot Bot commented Oct 19, 2026 •

edited

Loading

socket-security Bot commented Oct 19, 2026 •

edited

Loading

nx-cloud Bot commented Oct 19, 2026 •

edited

Loading

pkg-pr-new Bot commented Oct 19, 2026 •

edited

Loading

coderabbitai Bot commented Oct 19, 2026 •

edited

Loading