computer: Provide ai-sdk, pi-ai and tanstack-ai compatible tools - #191
Merged
Merged
Conversation
馃 Changeset detectedLatest commit: d810bea The changes in this PR will be included in the next version bump. This PR includes changesets to release 4 packages
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 |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
Comment on lines
+60
to
+75
| const fetch = async (_input: RequestInfo | URL, init?: RequestInit): Promise<Response> => { | ||
| const input = JSON.parse(bodyText(init?.body)) as Record<string, unknown>; | ||
| const name = typeof input.model === "string" ? input.model : undefined; | ||
| if (!name) throw new TypeError("Workers AI pi request is missing its model"); | ||
| delete input.model; | ||
| return runBinding.run(name, input, { | ||
| returnRawResponse: true, | ||
| ...(init?.signal ? { signal: init.signal } : {}), | ||
| }); | ||
| }; | ||
|
|
||
| const api = openAICompletionsApi(); | ||
| const streams: ProviderStreams = { | ||
| stream: (m, context, options) => | ||
| api.stream(m, context, { ...options, fetch } as ApiStreamOptions<string>), | ||
| streamSimple: (m, context, options) => api.streamSimple(m, context, { ...options, fetch }), |
There was a problem hiding this comment.
馃攳 Workers AI transport remains untested
The local pi run replaces Workers AI with a scripted model, so it never exercises workersAI against the binding. A deployed smoke test would check whether pi can consume its streamed response.
Was this helpful? React with 馃憤 or 馃憥 to provide feedback.
Comment on lines
+106
to
+110
| const { task } = (await request.json()) as { task?: string }; | ||
| if (!task) return new Response("body needs a task\n", { status: 400 }); | ||
|
|
||
| const agent = env.PiAgent.get(env.PiAgent.idFromName("demo")); | ||
| return new Response(`${await agent.run(task)}\n`); |
There was a problem hiding this comment.
馃煡 Unauthenticated tasks control the shared workspace
Any caller can POST a task to PiAgent without authentication. Every request uses the same demo object, exposing its files and shell to unauthorized callers.
Was this helpful? React with 馃憤 or 馃憥 to provide feedback.
Comment on lines
+79
to
+83
| const { task } = (await request.json()) as { task?: string }; | ||
| if (!task) return new Response("body needs a task\n", { status: 400 }); | ||
|
|
||
| const agent = env.TanStackAgent.get(env.TanStackAgent.idFromName("demo")); | ||
| return new Response(`${await agent.run(task)}\n`); |
There was a problem hiding this comment.
馃煡 Unauthenticated tasks share the TanStack workspace
Any caller can POST a task to TanStackAgent without authentication. The fixed demo object exposes its persistent files and shell to every caller.
Was this helpful? React with 馃憤 or 馃憥 to provide feedback.
Split each tool into a framework-neutral core under tools/common (schema, description, executor; zod only) and an adapter per agent library. tools/ai-sdk wraps the core with `tool()` from `ai`; tools/pi-ai and tools/tanstack-ai build their own shapes from the same core without importing their libraries, so each entry point pulls in only what it uses. createAITools stays exported from @cloudflare/computer/tools. The exec core keeps the current options: a `shell` with a backend map and a default backend. All three tool sets resolve options through the same resolveToolOptions, so they offer the same tools. The pi and TanStack adapters come from #149. Co-authored-by: aron <263346377+aron-cf@users.noreply.github.com>
Two one-shot agents on a Worker-shell Workspace: pi-ai, where `run` is the whole loop, and tanstack-ai, where chat() owns it. Both pass the one worker shell to `exec` through `shell`. `npm run local` drives each loop in Node with a scripted model, through a small shim for `cloudflare:workers`. Bumps the libraries to current releases (pi-ai 0.99, @tanstack/ai 0.63, @tanstack/ai-cloudflare 0.2) and adds both to the CI examples matrix. Docs, READMEs, and a changeset cover the two entry points. The examples come from #149. Co-authored-by: aron <263346377+aron-cf@users.noreply.github.com>
chat() passes a tool result to the adapter as multimodal content only when it is a ContentPart array. The read tool returned an image or PDF as a plain object, which TanStack JSON-stringified, so the model got the base64 as text. It now returns a text part plus an image or document part, and the test checks the shape with TanStack's own isContentPartArray. Also covers a failed pi publish, which already comes back as an error result.
Renames createPiAITools to createPiTools and createTanStackAITools to createTanStackTools, with their option and result types. The entry points stay tools/pi-ai and tools/tanstack-ai. pi checks tool arguments with TypeBox, which also compiles plain JSON Schema, so the pi tools need only zod for their own schemas. pi 0.99 also closes a constrainedSampling schema itself when the provider runs it strict. The adapter used to close read, write, and edit up front, which made every optional field required in the schema pi validates against. A provider that fell back to ordinary tool calling and left `offset` out of a read failed pi's own validateToolCall. The declarations now stay open, and execute drops a null only on an optional field that cannot take one. Tests check the declarations against pi's validateToolCall and makeStrictJsonSchema.
aron-cf
force-pushed
the
split/tools-main
branch
from
October 2, 2026 11:04
d64fb73 to
d810bea
Compare
commit: |
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR was extracted from #186 so it can land on main but leaves out the changes to exec that are still on the container path.