Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

tool use without auto execution#162

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Open
jingyun19 wants to merge8 commits intowebmachinelearning:main
base:main
Choose a base branch
Loading
fromjingyun19:patch-1

Conversation

@jingyun19
Copy link

@jingyun19jingyun19 commentedNov 19, 2025•
edited by pr-previewbot
Loading

Update explainer and spec to support tool use functionalities without automatic execution.

Explainer: added an example and explained how to make tool calls
Spec: reflect IDL changes inhttps://chromium-review.googlesource.com/c/chromium/src/+/7092943

Preview |Diff

Added detailed explanations for tool use modes, including examples for open loop and closed loop execution.
Updated README to clarify tool-call and tool-result usage.
Added new types and enums for tool calls and responses.
@jingyun19
Copy link
Author

Copy link
Contributor

@tomayactomayac left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Tried to make the code samples more readable and correct. Maybe consider running them all through a tool likeprettier, which catches typos like missing commas or parentheses.

As general feedback, could the explainer outline why developers would choose closed vs. open?

Comment on lines +180 to +185
awaitsession.append([
{role:"user", content:"What is the weather in Seattle?"},
{role:"tool-call", content: {type:"tool-call", value: {callID:" get_weather_1", name:"get_weather", arguments: {location:"Seattle"}}},
{role:"tool-result", content: {type:"tool-response", value: {callID:"get_weather_1", name:"get_weather", result: [{type:"object", value: {temperature:"55F", humidity:"67%"}}]}},
{role:"assistant", content:"The temperature in Seattle is 55F and humidity is 67%"},
]);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
await session.append([
{role: "user", content: "What is the weather in Seattle?"},
{role: "tool-call", content: {type: "tool-call", value: {callID:" get_weather_1", name: "get_weather", arguments: {location:"Seattle"}}},
{role: "tool-result", content: {type: "tool-response", value: {callID: "get_weather_1", name: "get_weather", result: [{type:"object", value: {temperature: "55F", humidity: "67%"}}]}},
{role: "assistant", content: "The temperature in Seattle is 55F and humidity is 67%"},
]);
await session.append([
{ role: "user", content: "What is the weather in Seattle?" },
{
role: "tool-call",
content: {
type: "tool-call",
value: {
callID: " get_weather_1",
name: "get_weather",
arguments: { location: "Seattle" },
},
},
},
{
role: "tool-result",
content: {
type: "tool-response",
value: {
callID: "get_weather_1",
name: "get_weather",
result: [
{ type: "object", value: { temperature: "55F", humidity: "67%" } },
],
},
},
},
{
role: "assistant",
content: "The temperature in Seattle is 55F and humidity is 67%",
},
]);

]);
```
Note that "role" and "type" now supports "tool-call" and "tool-result".
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
Note that "role" and "type" nowsupports"tool-call" and "tool-result".
Note that`"role"` and`"type"` nowsupport`"tool-call"` and`"tool-result"`.

Comment on lines +200 to +212
sessionOptions=structuredClone(options);
sessionOptions.expectedOutputs.push(["tool-call"]);
session=awaitLanguageModel.create(sessionOptions);

var result=awaitsession.prompt("What is the weather in Seattle?");
if (result.type=="tool-call") {
if (result.name=="get_weather") {
consttool_result=getWeather(result.arguments.location);
result=session.prompt([{role:"tool-result", content: {type:"tool-result", value: {callId:result.callID, name:result.name, result: [{type:"object", value: tool_result}]}}}])
}
}else{
console.log(result)
}
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
sessionOptions = structuredClone(options);
sessionOptions.expectedOutputs.push(["tool-call"]);
session = await LanguageModel.create(sessionOptions);
var result = await session.prompt("What is the weather in Seattle?");
if (result.type=="tool-call") {
if (result.name == "get_weather") {
const tool_result = getWeather(result.arguments.location);
result = session.prompt([{role:"tool-result", content: {type: "tool-result", value: {callId: result.callID, name: result.name, result: [{type:"object", value: tool_result}]}}}])
}
} else{
console.log(result)
}
sessionOptions = structuredClone(options);
sessionOptions.expectedOutputs.push(["tool-call"]);
session = await LanguageModel.create(sessionOptions);
var result = await session.prompt("What is the weather in Seattle?");
if (result.type == "tool-call") {
if (result.name == "get_weather") {
const tool_result = getWeather(result.arguments.location);
result = session.prompt([
{
role: "tool-result",
content: {
type: "tool-result",
value: {
callId: result.callID,
name: result.name,
result: [{ type: "object", value: tool_result }],
},
},
},
]);
}
} else {
console.log(result);
}

#### Closed Loop:
To enable automatic execution, add a`execute` function for each tool's implementation, and add a`toolUseConfig` to indicate that execution is enabled and pose a max number of tool calls invoked in a single session generation:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
To enable automatic execution, adda`execute` function for each tool's implementation, and add a`toolUseConfig` to indicate that execution is enabled and pose a max number of tool calls invoked in a single session generation:
To enable automatic execution, addan`execute` function for each tool's implementation, and add a`toolUseConfig` to indicate that execution is enabled and pose a max number of tool calls invoked in a single session generation:

sessionOptions.expectedOutputs.push(["tool-call"]);
session=awaitLanguageModel.create(sessionOptions);

var result=awaitsession.prompt("What is the weather in Seattle?");
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
var result = await session.prompt("What is the weather in Seattle?");
let result = await session.prompt("What is the weather in Seattle?");

Example:
```js
sessionOptions=structuredClone(options);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
sessionOptions = structuredClone(options);
constsessionOptions = structuredClone(options);

```js
sessionOptions=structuredClone(options);
sessionOptions.expectedOutputs.push(["tool-call"]);
session=awaitLanguageModel.create(sessionOptions);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Suggested change
session = await LanguageModel.create(sessionOptions);
constsession = await LanguageModel.create(sessionOptions);

jingyun19and others added5 commitsNovember 26, 2025 09:08
Co-authored-by: Thomas Steiner <tomac@google.com>
Co-authored-by: Thomas Steiner <tomac@google.com>
Added explanation about automatic execution and constraints in planner loop.
@jingyun19
Copy link
Author

jingyun19 commentedDec 1, 2025•
edited
Loading

I added a new section to describe use cases where open loop is preferred. cc@tomayac

@reillyeon
Copy link
Member

I hadn't previously considered the context compression use case. That's interesting and motivating to enable developers to manipulate the conversation at this low level.

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

1 more reviewer

@tomayactomayactomayac left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@jingyun19@reillyeon@tomayac
[8]ページ先頭
©2009-2025 Movatter.jp