Compare commits
19
Commits
v0.1.0
..
ac9e439191
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ac9e439191 | ||
|
|
215ec19ba1 | ||
|
|
e74d97f4ae | ||
|
|
b5c2924886 | ||
|
|
892151ef92 | ||
|
|
503273f17d | ||
|
|
bbf1b56a76 | ||
|
|
9b6e78e9f5 | ||
|
|
4e50c28def | ||
|
|
8f1d71d913 | ||
|
|
e9a060af0f | ||
|
|
46b8d7e888 | ||
|
|
0460305327 | ||
|
|
c4bb02a7a2 | ||
|
|
f295cb8535 | ||
|
|
55e2764480 | ||
|
|
cb23c502aa | ||
|
|
4eeace6ce3 | ||
|
|
713a1c1d75 |
No files matched your search
+98
-12
@@ -1,30 +1,116 @@
|
||||
# Changelog
|
||||
|
||||
## [0.0.1] - 2026-11-06
|
||||
<!-- markdownlint-configure-file { "MD024": { "siblings_only": true } } -->
|
||||
|
||||
Initial development release. Not yet functional for chat.
|
||||
All notable changes to this project will be documented in this file.
|
||||
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
|
||||
and this project adheres to
|
||||
[Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Added
|
||||
|
||||
- Set `baseContentUrl` in package.json to the Gitea raw URL, so LICENSE and
|
||||
NOTICE links in the README resolve correctly on the Marketplace.
|
||||
- Added an npm `publish` script running `vsce publish`, with `@vscode/vsce`
|
||||
as a dev dependency, for releasing to the VS Code Marketplace.
|
||||
- Added `language-models` and `chat` Marketplace tags, so the extension
|
||||
appears in the "Install Language Models" discovery flow. The tags take
|
||||
effect when the next version is published.
|
||||
- Added an extension icon rendered from the Inference Coop logo, shown on
|
||||
the Marketplace listing and in the Extensions view.
|
||||
- Added Marketplace keywords for search discoverability.
|
||||
- Changed the Marketplace category from "Other" to "AI".
|
||||
|
||||
### Removed
|
||||
|
||||
- Removed the unused `inferenceCoop.baseUrl` setting. The extension only
|
||||
ever talked to the hardcoded `https://gateway.inference.coop/v1` gateway;
|
||||
keeping a configurable URL would let a modified setting redirect the
|
||||
stored API key to a hostile endpoint.
|
||||
|
||||
## [0.3.0] - 2026-11-08
|
||||
|
||||
### Changed
|
||||
|
||||
- Removed the "(unofficial)" disclaimer from the package description and
|
||||
NOTICE, and the README; the project is now official, maintained in the
|
||||
co-op's Git at `code/inference-coop-copilot`.
|
||||
- Updated the repository URL to `https://git.inference.coop/code/inference-coop-copilot.git`
|
||||
in package.json and CHANGELOG links.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Abort in-flight chat requests on cancellation: an `AbortController` wired
|
||||
to `token.onCancellationRequested` closes the SSE connection as soon as
|
||||
the user stops the request, instead of the server continuing to generate
|
||||
until the response ends.
|
||||
|
||||
## [0.2.2] - 2026-11-06
|
||||
|
||||
### Fixed
|
||||
|
||||
- Correct the publisher in package.json.
|
||||
|
||||
## [0.2.1] - 2026-11-06
|
||||
|
||||
### Fixed
|
||||
|
||||
- Correct instructions for setting the API key in README.
|
||||
|
||||
## [0.2.0] - 2026-11-06
|
||||
|
||||
### Added
|
||||
|
||||
- "Inference Coop: Set API Key" and "Inference Coop: Sign Out" commands.
|
||||
- Model list caching with `onDidChangeLanguageModelChatInformation`, so the
|
||||
picker refreshes when models change instead of requiring a restart.
|
||||
|
||||
### Changed
|
||||
|
||||
- **Breaking:** the API key is now stored in VS Code `SecretStorage` instead
|
||||
of the `inferenceCoop.apiKey` setting. Run "Inference Coop: Set API Key"
|
||||
once after upgrading; the gateway base URL is now the only setting.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Models intermittently missing from the Copilot Chat model picker when the
|
||||
provider's initial model fetch lost a race with chat activation.
|
||||
|
||||
## [0.1.0] - 2026-11-06
|
||||
|
||||
First release usable for chat.
|
||||
|
||||
### Added
|
||||
|
||||
- Streaming chat responses via `provideLanguageModelChatResponse`, with
|
||||
text streamed to the UI as it arrives.
|
||||
- Tool calling: tool schemas are sent to the gateway, streamed tool-call
|
||||
fragments are reassembled, and tool results are translated back into the
|
||||
conversation. Verified end to end in agent mode against
|
||||
`tinfoil/gpt-oss-120b`.
|
||||
- Extension scaffold with esbuild build pipeline and ESLint/tsc checks.
|
||||
- Registration of a `LanguageModelChatProvider` under the `inference-coop`
|
||||
vendor, discoverable via `contributes.languageModelChatProviders`.
|
||||
- Model discovery: fetches `GET https://gateway.inference.coop/v1/models`
|
||||
and filters to chat-capable models, excluding image-generation and
|
||||
audio endpoints.
|
||||
- `inferenceCoop.apiKey` setting (plain text, temporarily).
|
||||
- "Inference Coop" output channel logging provider activation, model
|
||||
enumeration, and HTTP status codes.
|
||||
|
||||
### Known issues
|
||||
### Changed
|
||||
|
||||
- Models appear in the Language Models panel but not in the Copilot Chat
|
||||
model picker. Under investigation; suspected upstream VS Code issue.
|
||||
- `provideLanguageModelChatResponse` sends a streaming request but has not
|
||||
been verified end to end from the chat UI.
|
||||
- No tool calling, image input, or token counting (returns 0).
|
||||
- API key is stored in settings rather than `SecretStorage`.
|
||||
- Adopted the Apache License 2.0.
|
||||
|
||||
### Not yet published
|
||||
## [0.0.1] - 2026-11-06
|
||||
|
||||
- No Marketplace publisher registered; installed from a local `.vsix`.
|
||||
Initial development release. Not functional for chat.
|
||||
|
||||
[Unreleased]: https://git.inference.coop/code/inference-coop-copilot/compare/v0.3.0...HEAD
|
||||
[0.3.0]: https://git.inference.coop/code/inference-coop-copilot/compare/v0.2.2...v0.3.0
|
||||
[0.2.2]: https://git.inference.coop/code/inference-coop-copilot/compare/v0.2.1...v0.2.2
|
||||
[0.2.1]: https://git.inference.coop/code/inference-coop-copilot/compare/v0.2.0...v0.2.1
|
||||
[0.2.0]: https://git.inference.coop/code/inference-coop-copilot/compare/v0.1.0...v0.2.0
|
||||
[0.1.0]: https://git.inference.coop/code/inference-coop-copilot/releases/tag/v0.1.0
|
||||
@@ -1,4 +1,4 @@
|
||||
Inference Coop Copilot (unofficial)
|
||||
Inference Coop Copilot
|
||||
Copyright 2026 Evan Prodromou
|
||||
|
||||
Licensed under the Apache License, Version 2.0.
|
||||
@@ -1,14 +1,38 @@
|
||||
# Inference Coop (unofficial)
|
||||
# Inference Coop for Copilot Chat
|
||||
|
||||
Community-built model provider for [inference.coop](https://inference.coop),
|
||||
usable in GitHub Copilot Chat. Not affiliated with or endorsed by the
|
||||
Inference Cooperative.
|
||||

|
||||
|
||||
Official model provider for [inference.coop](https://inference.coop), usable
|
||||
in GitHub Copilot Chat. An official project of the Inference Cooperative,
|
||||
maintained in the co-op's Git at
|
||||
[code/inference-coop-copilot](https://git.inference.coop/code/inference-coop-copilot).
|
||||
|
||||
## Requirements
|
||||
|
||||
- VS Code 1.145 or newer
|
||||
- GitHub Copilot Chat, installed and signed in
|
||||
- A co-op membership and API key
|
||||
|
||||
Copilot Business/Enterprise: your administrator must leave "Bring Your Own
|
||||
Language Model Key" enabled, or these models will not appear.
|
||||
|
||||
## Setup
|
||||
|
||||
1. Set `inferenceCoop.apiKey` in your settings to your co-op API key.
|
||||
2. Open Copilot Chat and pick an `inference-coop/…` model.
|
||||
1. Run **Inference Coop: Set API Key** from the Command Palette and paste
|
||||
your co-op key. It is stored in VS Code's secret storage, not in settings.
|
||||
2. Open Copilot Chat, click the model name, and pick an `inference-coop/…`
|
||||
model. Tool calling works, so agent mode is usable.
|
||||
|
||||
## Status
|
||||
To sign out, run **Inference Coop: Sign Out**.
|
||||
|
||||
Early development. Text chat only so far; tool calling is not implemented.
|
||||
## Limitations
|
||||
|
||||
- No image input; models are advertised as text-and-tools only.
|
||||
- Token counts are estimated rather than computed with a real tokenizer, so
|
||||
context budgeting is approximate.
|
||||
- No inline code completions. Copilot does not support third-party providers
|
||||
for completions; this extension only adds chat models.
|
||||
|
||||
## License
|
||||
|
||||
Apache-2.0. See [LICENSE](LICENSE) and [NOTICE](NOTICE).
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
@@ -0,0 +1,25 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 130 130">
|
||||
<rect width="130" height="130" rx="24" fill="#faf8f5"/>
|
||||
<circle cx="65" cy="14" r="5" fill="#5b8c5a"/>
|
||||
<circle cx="58" cy="30" r="6" fill="#7ab87a"/>
|
||||
<circle cx="74" cy="30" r="4" fill="#6ba86b"/>
|
||||
<circle cx="51.5" cy="46" r="6.5" fill="#5b8c5a"/>
|
||||
<circle cx="65" cy="46" r="5" fill="#7ab87a"/>
|
||||
<circle cx="81" cy="46" r="4" fill="#6ba86b"/>
|
||||
<circle cx="44" cy="62" r="7" fill="#6ba86b"/>
|
||||
<circle cx="61" cy="62" r="5.5" fill="#5b8c5a"/>
|
||||
<circle cx="76" cy="62" r="4.5" fill="#7ab87a"/>
|
||||
<circle cx="89.5" cy="62" r="3.5" fill="#6ba86b"/>
|
||||
<circle cx="36.5" cy="78" r="7.5" fill="#5b8c5a"/>
|
||||
<circle cx="54" cy="78" r="6" fill="#7ab87a"/>
|
||||
<circle cx="70" cy="78" r="5" fill="#6ba86b"/>
|
||||
<circle cx="84" cy="78" r="4" fill="#5b8c5a"/>
|
||||
<circle cx="97.5" cy="78" r="3.5" fill="#7ab87a"/>
|
||||
<circle cx="44" cy="94" r="6.5" fill="#6ba86b"/>
|
||||
<circle cx="61" cy="94" r="5.5" fill="#5b8c5a"/>
|
||||
<circle cx="76" cy="94" r="4.5" fill="#7ab87a"/>
|
||||
<circle cx="89.5" cy="94" r="3.5" fill="#6ba86b"/>
|
||||
<circle cx="51.5" cy="110" r="5.5" fill="#5b8c5a"/>
|
||||
<circle cx="65" cy="110" r="4.5" fill="#7ab87a"/>
|
||||
<circle cx="81" cy="110" r="3.5" fill="#6ba86b"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 1.2 KiB |
Generated
+1461
-2
File diff suppressed because it is too large.
Load diff
+35
-21
@@ -1,19 +1,33 @@
|
||||
{
|
||||
"name": "inference-coop-copilot",
|
||||
"displayName": "inference-coop-copilot",
|
||||
"description": "Inference.coop models for Copilot Chat (unofficial)",
|
||||
"version": "0.1.0",
|
||||
"description": "Inference.coop models for Copilot Chat",
|
||||
"version": "0.3.0",
|
||||
"icon": "images/icon.png",
|
||||
"engines": {
|
||||
"vscode": "^1.145.0"
|
||||
},
|
||||
"publisher": "inference-coop",
|
||||
"publisher": "evanp",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://git.inference.coop/evanp/inference-coop-copilot.git"
|
||||
"url": "https://git.inference.coop/code/inference-coop-copilot.git",
|
||||
"baseContentUrl": "https://git.inference.coop/code/inference-coop-copilot/raw/branch/main"
|
||||
},
|
||||
"license": "Apache-2.0",
|
||||
"categories": [
|
||||
"Other"
|
||||
"AI"
|
||||
],
|
||||
"tags": [
|
||||
"language-models",
|
||||
"chat"
|
||||
],
|
||||
"keywords": [
|
||||
"inference-coop",
|
||||
"inference.coop",
|
||||
"copilot",
|
||||
"chat",
|
||||
"language model",
|
||||
"AI"
|
||||
],
|
||||
"activationEvents": [],
|
||||
"main": "./dist/extension.js",
|
||||
@@ -26,8 +40,12 @@
|
||||
],
|
||||
"commands": [
|
||||
{
|
||||
"command": "inference-coop-copilot.helloWorld",
|
||||
"title": "Hello World"
|
||||
"command": "inferenceCoop.setKey",
|
||||
"title": "Inference Coop: Set API Key"
|
||||
},
|
||||
{
|
||||
"command": "inferenceCoop.clearKey",
|
||||
"title": "Inference Coop: Sign Out"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -43,32 +61,28 @@
|
||||
"pretest": "npm run compile-tests && npm run compile && npm run lint",
|
||||
"check-types": "tsc --noEmit",
|
||||
"lint": "eslint src",
|
||||
"publish": "vsce publish",
|
||||
"test": "vscode-test"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/vscode": "^1.145.0",
|
||||
"@types/mocha": "^10.0.10",
|
||||
"@types/node": "24.x",
|
||||
"typescript-eslint": "^8.61.1",
|
||||
"eslint": "^10.5.0",
|
||||
"@types/vscode": "^1.145.0",
|
||||
"@vscode/test-cli": "^0.0.15",
|
||||
"@vscode/test-electron": "^3.0.0",
|
||||
"@vscode/vsce": "^4.1.0",
|
||||
"esbuild": "^0.28.1",
|
||||
"eslint": "^10.5.0",
|
||||
"npm-run-all": "^4.1.5",
|
||||
"typescript": "^6.0.3",
|
||||
"@vscode/test-cli": "^0.0.15",
|
||||
"@vscode/test-electron": "^3.0.0"
|
||||
"typescript-eslint": "^8.61.1"
|
||||
},
|
||||
"overrides": {
|
||||
"diff": "^8.0.4",
|
||||
"serialize-javascript": "^7.0.6"
|
||||
},
|
||||
"configuration": {
|
||||
"title": "Inference Coop",
|
||||
"properties": {
|
||||
"inferenceCoop.apiKey": {
|
||||
"type": "string",
|
||||
"default": "",
|
||||
"description": "API key from the Inference Cooperative dashboard."
|
||||
}
|
||||
}
|
||||
"allowScripts": {
|
||||
"@vscode/vsce-sign@2.1.0": true,
|
||||
"esbuild@0.28.2": true
|
||||
}
|
||||
}
|
||||
+212
-75
@@ -1,125 +1,198 @@
|
||||
import * as vscode from 'vscode';
|
||||
import * as vscode from "vscode";
|
||||
|
||||
const BASE_URL = 'https://gateway.inference.coop/v1';
|
||||
const PREFIX = 'inference-coop/';
|
||||
const BASE_URL = "https://gateway.inference.coop/v1";
|
||||
const PREFIX = "inference-coop/";
|
||||
const SECRET_KEY = "inferenceCoop.apiKey";
|
||||
|
||||
type CoopModel = {
|
||||
id: string;
|
||||
name: string;
|
||||
family: string;
|
||||
version: string;
|
||||
maxInputTokens: number;
|
||||
maxOutputTokens: number;
|
||||
capabilities: { toolCalling: boolean; imageInput: boolean };
|
||||
};
|
||||
|
||||
export function activate(context: vscode.ExtensionContext) {
|
||||
const out = vscode.window.createOutputChannel('Inference Coop');
|
||||
const out = vscode.window.createOutputChannel("Inference Coop");
|
||||
context.subscriptions.push(out);
|
||||
out.appendLine('activate() called');
|
||||
|
||||
const provider: vscode.LanguageModelChatProvider = {
|
||||
async provideLanguageModelChatInformation() {
|
||||
out.appendLine('provideLanguageModelChatInformation: called');
|
||||
const changed = new vscode.EventEmitter<void>();
|
||||
context.subscriptions.push(changed);
|
||||
|
||||
const key = vscode.workspace
|
||||
.getConfiguration('inferenceCoop')
|
||||
.get<string>('apiKey');
|
||||
if (!key) {return [];}
|
||||
let cached: CoopModel[] = [];
|
||||
let lastFetch = 0;
|
||||
|
||||
async function refresh(force = false): Promise<CoopModel[]> {
|
||||
if (!force && Date.now() - lastFetch < 30_000 && cached.length) {
|
||||
return cached;
|
||||
}
|
||||
const key = await context.secrets.get(SECRET_KEY);
|
||||
if (!key) {
|
||||
return cached;
|
||||
}
|
||||
try {
|
||||
const res = await fetch(`${BASE_URL}/models`, {
|
||||
headers: { Authorization: `Bearer ${key}` }
|
||||
headers: { Authorization: `Bearer ${key}` },
|
||||
});
|
||||
out.appendLine(` /models status: ${res.status}`);
|
||||
if (!res.ok) {return [];}
|
||||
|
||||
out.appendLine(`refresh: /models ${res.status}`);
|
||||
if (!res.ok) {
|
||||
return cached;
|
||||
}
|
||||
const body = (await res.json()) as {
|
||||
data: Array<{ id: string; mode?: string }>;
|
||||
};
|
||||
const models = body.data
|
||||
.filter(m => !m.mode || m.mode === 'chat')
|
||||
.map(m => ({
|
||||
const next: CoopModel[] = body.data
|
||||
.filter((m) => !m.mode || m.mode === "chat")
|
||||
.map((m) => ({
|
||||
id: `${PREFIX}${m.id}`,
|
||||
name: m.id,
|
||||
family: 'inference-coop',
|
||||
version: '1.0.0',
|
||||
family: "inference-coop",
|
||||
version: "1.0.0",
|
||||
maxInputTokens: 131072,
|
||||
maxOutputTokens: 8192,
|
||||
capabilities: { toolCalling: true, imageInput: false }
|
||||
capabilities: { toolCalling: true, imageInput: false },
|
||||
}));
|
||||
out.appendLine(` returning ${models.length} models`);
|
||||
return models;
|
||||
lastFetch = Date.now();
|
||||
if (JSON.stringify(next) !== JSON.stringify(cached)) {
|
||||
cached = next;
|
||||
changed.fire();
|
||||
out.appendLine(`refresh: ${cached.length} models, fired change event`);
|
||||
}
|
||||
return cached;
|
||||
} catch (e) {
|
||||
out.appendLine(`refresh failed: ${e}`);
|
||||
return cached;
|
||||
}
|
||||
}
|
||||
|
||||
const provider: vscode.LanguageModelChatProvider = {
|
||||
onDidChangeLanguageModelChatInformation: changed.event,
|
||||
|
||||
async provideLanguageModelChatInformation() {
|
||||
out.appendLine("provideLanguageModelChatInformation: called");
|
||||
if (cached.length) {
|
||||
void refresh(); // refresh in background, answer now
|
||||
return cached;
|
||||
}
|
||||
return await refresh(true); // first call: must wait
|
||||
},
|
||||
|
||||
async provideLanguageModelChatResponse(model, messages, options, progress, token) {
|
||||
async provideLanguageModelChatResponse(
|
||||
model,
|
||||
messages,
|
||||
options,
|
||||
progress,
|
||||
token,
|
||||
) {
|
||||
out.appendLine(`provideLanguageModelChatResponse: ${model.id}`);
|
||||
out.appendLine(` tools offered: ${options.tools?.length ?? 0}`);
|
||||
|
||||
const key = vscode.workspace
|
||||
.getConfiguration('inferenceCoop')
|
||||
.get<string>('apiKey');
|
||||
const key = await context.secrets.get(SECRET_KEY);
|
||||
|
||||
const body: Record<string, unknown> = {
|
||||
model: model.id.replace(PREFIX, ''),
|
||||
model: model.id.replace(PREFIX, ""),
|
||||
stream: true,
|
||||
messages: toOpenAIMessages(messages, out)
|
||||
messages: toOpenAIMessages(messages, out),
|
||||
};
|
||||
|
||||
if (options.tools?.length) {
|
||||
body.tools = options.tools.map(t => ({
|
||||
type: 'function',
|
||||
body.tools = options.tools.map((t) => ({
|
||||
type: "function",
|
||||
function: {
|
||||
name: t.name,
|
||||
description: t.description,
|
||||
parameters: t.inputSchema ?? { type: 'object', properties: {} }
|
||||
}
|
||||
parameters: t.inputSchema ?? { type: "object", properties: {} },
|
||||
},
|
||||
}));
|
||||
body.tool_choice = 'auto';
|
||||
body.tool_choice = "auto";
|
||||
}
|
||||
|
||||
if (token.isCancellationRequested) {
|
||||
out.appendLine(" request cancelled before it started");
|
||||
return;
|
||||
}
|
||||
|
||||
// Abort the request as soon as the user cancels, so a cancelled chat
|
||||
// stops generating (and stops billing) server-side.
|
||||
const abort = new AbortController();
|
||||
const cancelSubscription = token.onCancellationRequested(() =>
|
||||
abort.abort(),
|
||||
);
|
||||
|
||||
try {
|
||||
const res = await fetch(`${BASE_URL}/chat/completions`, {
|
||||
method: 'POST',
|
||||
method: "POST",
|
||||
headers: {
|
||||
Authorization: `Bearer ${key}`,
|
||||
'Content-Type': 'application/json'
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
signal: token.isCancellationRequested ? AbortSignal.abort() : undefined
|
||||
signal: abort.signal,
|
||||
});
|
||||
out.appendLine(` /chat/completions status: ${res.status}`);
|
||||
if (!res.ok || !res.body) {
|
||||
throw new Error(`Inference Coop: HTTP ${res.status} — ${await res.text()}`);
|
||||
throw new Error(
|
||||
`Inference Coop: HTTP ${res.status} — ${await res.text()}`,
|
||||
);
|
||||
}
|
||||
|
||||
const reader = res.body.getReader();
|
||||
const decoder = new TextDecoder();
|
||||
let buf = '';
|
||||
let buf = "";
|
||||
let textChunks = 0;
|
||||
const pending = new Map<number, { id?: string; name: string; args: string }>();
|
||||
const pending = new Map<
|
||||
number,
|
||||
{ id?: string; name: string; args: string }
|
||||
>();
|
||||
|
||||
const flushTools = () => {
|
||||
for (const call of pending.values()) {
|
||||
let input: object = {};
|
||||
try {
|
||||
input = JSON.parse(call.args || '{}');
|
||||
input = JSON.parse(call.args || "{}");
|
||||
} catch {
|
||||
out.appendLine(` WARN bad tool args for ${call.name}: ${call.args}`);
|
||||
out.appendLine(
|
||||
` WARN bad tool args for ${call.name}: ${call.args}`,
|
||||
);
|
||||
}
|
||||
out.appendLine(` tool call: ${call.name} ${JSON.stringify(input)}`);
|
||||
progress.report(
|
||||
new vscode.LanguageModelToolCallPart(
|
||||
call.id ?? `call_${Math.random().toString(36).slice(2)}`,
|
||||
call.name,
|
||||
input
|
||||
)
|
||||
input,
|
||||
),
|
||||
);
|
||||
}
|
||||
pending.clear();
|
||||
};
|
||||
|
||||
while (true) {
|
||||
if (token.isCancellationRequested) {
|
||||
out.appendLine(" cancelled mid-stream; aborting request");
|
||||
abort.abort(); // close the connection so the gateway stops generating
|
||||
return;
|
||||
}
|
||||
const { done, value } = await reader.read();
|
||||
if (done) {break;}
|
||||
if (done) {
|
||||
break;
|
||||
}
|
||||
buf += decoder.decode(value, { stream: true });
|
||||
const frames = buf.split('\n\n');
|
||||
buf = frames.pop() ?? '';
|
||||
const frames = buf.split("\n\n");
|
||||
buf = frames.pop() ?? "";
|
||||
|
||||
for (const frame of frames) {
|
||||
for (const line of frame.split('\n')) {
|
||||
if (!line.startsWith('data:')) {continue;}
|
||||
for (const line of frame.split("\n")) {
|
||||
if (!line.startsWith("data:")) {
|
||||
continue;
|
||||
}
|
||||
const data = line.slice(5).trim();
|
||||
if (data === '[DONE]') {
|
||||
if (pending.size) {flushTools();}
|
||||
if (data === "[DONE]") {
|
||||
if (pending.size) {
|
||||
flushTools();
|
||||
}
|
||||
out.appendLine(` done, ${textChunks} text chunks`);
|
||||
return;
|
||||
}
|
||||
@@ -131,52 +204,110 @@ export function activate(context: vscode.ExtensionContext) {
|
||||
}
|
||||
const choice = json.choices?.[0];
|
||||
const delta = choice?.delta;
|
||||
if (!delta) {continue;}
|
||||
if (!delta) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (typeof delta.content === 'string' && delta.content) {
|
||||
if (typeof delta.content === "string" && delta.content) {
|
||||
textChunks++;
|
||||
progress.report(new vscode.LanguageModelTextPart(delta.content));
|
||||
}
|
||||
|
||||
for (const tc of delta.tool_calls ?? []) {
|
||||
const i = tc.index ?? 0;
|
||||
const acc = pending.get(i) ?? { id: undefined, name: '', args: '' };
|
||||
const acc = pending.get(i) ?? {
|
||||
id: undefined,
|
||||
name: "",
|
||||
args: "",
|
||||
};
|
||||
acc.id = tc.id ?? acc.id;
|
||||
acc.name = tc.function?.name ?? acc.name;
|
||||
acc.args += tc.function?.arguments ?? '';
|
||||
acc.args += tc.function?.arguments ?? "";
|
||||
pending.set(i, acc);
|
||||
}
|
||||
|
||||
if (choice?.finish_reason) {
|
||||
out.appendLine(` finish_reason: ${choice.finish_reason}`);
|
||||
if (pending.size) {flushTools();}
|
||||
if (pending.size) {
|
||||
flushTools();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if (pending.size) {flushTools();}
|
||||
}
|
||||
if (pending.size) {
|
||||
flushTools();
|
||||
}
|
||||
out.appendLine(` stream ended, ${textChunks} text chunks`);
|
||||
} catch (e) {
|
||||
// A cancellation aborts fetch (before headers) or the pending stream
|
||||
// read (mid-response) - both surface as AbortError. That is the user
|
||||
// pressing stop, not a failure: stop quietly instead of erroring.
|
||||
if (
|
||||
token.isCancellationRequested ||
|
||||
(e instanceof Error && e.name === "AbortError")
|
||||
) {
|
||||
out.appendLine(" stream aborted after cancellation");
|
||||
return;
|
||||
}
|
||||
throw e;
|
||||
} finally {
|
||||
cancelSubscription.dispose();
|
||||
}
|
||||
},
|
||||
|
||||
async provideTokenCount() {
|
||||
return 0;
|
||||
}
|
||||
},
|
||||
};
|
||||
|
||||
context.subscriptions.push(
|
||||
vscode.lm.registerLanguageModelChatProvider('inference-coop', provider)
|
||||
vscode.lm.registerLanguageModelChatProvider("inference-coop", provider),
|
||||
);
|
||||
|
||||
context.subscriptions.push(
|
||||
vscode.commands.registerCommand('inference-coop-copilot.helloWorld', () => {
|
||||
vscode.window.showInformationMessage('Inference Coop extension loaded.');
|
||||
})
|
||||
vscode.commands.registerCommand("inference-coop-copilot.helloWorld", () => {
|
||||
vscode.window.showInformationMessage("Inference Coop extension loaded.");
|
||||
}),
|
||||
);
|
||||
|
||||
context.subscriptions.push(
|
||||
vscode.commands.registerCommand("inferenceCoop.setKey", async () => {
|
||||
const key = await vscode.window.showInputBox({
|
||||
title: "Inference Coop API key",
|
||||
prompt: "Paste your key from the co-op dashboard.",
|
||||
password: true,
|
||||
ignoreFocusOut: true,
|
||||
validateInput: (v) =>
|
||||
v.trim().length < 16
|
||||
? "That looks too short to be an API key."
|
||||
: undefined,
|
||||
});
|
||||
if (!key) {return;}
|
||||
await context.secrets.store(SECRET_KEY, key.trim());
|
||||
cached = [];
|
||||
lastFetch = 0;
|
||||
await refresh(true);
|
||||
vscode.window.showInformationMessage(
|
||||
`Inference Coop: signed in, ${cached.length} models available.`,
|
||||
);
|
||||
}),
|
||||
);
|
||||
|
||||
context.subscriptions.push(
|
||||
vscode.commands.registerCommand("inferenceCoop.clearKey", async () => {
|
||||
await context.secrets.delete(SECRET_KEY);
|
||||
cached = [];
|
||||
lastFetch = 0;
|
||||
changed.fire();
|
||||
vscode.window.showInformationMessage("Inference Coop: signed out.");
|
||||
}),
|
||||
);
|
||||
}
|
||||
|
||||
function toOpenAIMessages(
|
||||
messages: readonly vscode.LanguageModelChatRequestMessage[],
|
||||
out: vscode.OutputChannel
|
||||
out: vscode.OutputChannel,
|
||||
): object[] {
|
||||
const result: object[] = [];
|
||||
|
||||
@@ -191,38 +322,44 @@ function toOpenAIMessages(
|
||||
} else if (part instanceof vscode.LanguageModelToolCallPart) {
|
||||
toolCalls.push({
|
||||
id: part.callId,
|
||||
type: 'function',
|
||||
function: { name: part.name, arguments: JSON.stringify(part.input ?? {}) }
|
||||
type: "function",
|
||||
function: {
|
||||
name: part.name,
|
||||
arguments: JSON.stringify(part.input ?? {}),
|
||||
},
|
||||
});
|
||||
} else if (part instanceof vscode.LanguageModelToolResultPart) {
|
||||
toolResults.push({
|
||||
role: 'tool',
|
||||
role: "tool",
|
||||
tool_call_id: part.callId,
|
||||
content: part.content
|
||||
.map((c: unknown) =>
|
||||
c instanceof vscode.LanguageModelTextPart ? c.value : JSON.stringify(c)
|
||||
c instanceof vscode.LanguageModelTextPart
|
||||
? c.value
|
||||
: JSON.stringify(c),
|
||||
)
|
||||
.join('\n')
|
||||
.join("\n"),
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
const role =
|
||||
msg.role === vscode.LanguageModelChatMessageRole.Assistant
|
||||
? 'assistant'
|
||||
? "assistant"
|
||||
: msg.role === vscode.LanguageModelChatMessageRole.User
|
||||
? 'user'
|
||||
: 'system';
|
||||
? "user"
|
||||
: "system";
|
||||
|
||||
if (text.length || toolCalls.length) {
|
||||
const m: Record<string, unknown> = {
|
||||
role,
|
||||
content: text.length ? text.join('\n') : null
|
||||
content: text.length ? text.join("\n") : null,
|
||||
};
|
||||
if (toolCalls.length) {m.tool_calls = toolCalls;}
|
||||
if (toolCalls.length) {
|
||||
m.tool_calls = toolCalls;
|
||||
}
|
||||
result.push(m);
|
||||
}
|
||||
// OpenAI requires tool results to follow the assistant message that requested them.
|
||||
result.push(...toolResults);
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user