forked from evanp/inference-coop-copilot
fix: cache model list and fire change event to avoid startup race
This commit is contained in:
1 file changed
+42
-18
+42
-18
@@ -3,30 +3,34 @@ import * as vscode from 'vscode';
|
|||||||
const BASE_URL = 'https://gateway.inference.coop/v1';
|
const BASE_URL = 'https://gateway.inference.coop/v1';
|
||||||
const PREFIX = 'inference-coop/';
|
const PREFIX = 'inference-coop/';
|
||||||
|
|
||||||
|
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) {
|
export function activate(context: vscode.ExtensionContext) {
|
||||||
const out = vscode.window.createOutputChannel('Inference Coop');
|
const out = vscode.window.createOutputChannel('Inference Coop');
|
||||||
context.subscriptions.push(out);
|
context.subscriptions.push(out);
|
||||||
out.appendLine('activate() called');
|
|
||||||
|
|
||||||
const provider: vscode.LanguageModelChatProvider = {
|
const changed = new vscode.EventEmitter<void>();
|
||||||
async provideLanguageModelChatInformation() {
|
context.subscriptions.push(changed);
|
||||||
out.appendLine('provideLanguageModelChatInformation: called');
|
|
||||||
|
|
||||||
const key = vscode.workspace
|
let cached: CoopModel[] = [];
|
||||||
.getConfiguration('inferenceCoop')
|
let lastFetch = 0;
|
||||||
.get<string>('apiKey');
|
|
||||||
if (!key) {return [];}
|
|
||||||
|
|
||||||
|
async function refresh(force = false): Promise<CoopModel[]> {
|
||||||
|
if (!force && Date.now() - lastFetch < 30_000 && cached.length) {return cached;}
|
||||||
|
const key = vscode.workspace.getConfiguration('inferenceCoop').get<string>('apiKey');
|
||||||
|
if (!key) {return cached;}
|
||||||
|
try {
|
||||||
const res = await fetch(`${BASE_URL}/models`, {
|
const res = await fetch(`${BASE_URL}/models`, {
|
||||||
headers: { Authorization: `Bearer ${key}` }
|
headers: { Authorization: `Bearer ${key}` }
|
||||||
});
|
});
|
||||||
out.appendLine(` /models status: ${res.status}`);
|
out.appendLine(`refresh: /models ${res.status}`);
|
||||||
if (!res.ok) {return [];}
|
if (!res.ok) {return cached;}
|
||||||
|
const body = (await res.json()) as { data: Array<{ id: string; mode?: string }> };
|
||||||
const body = (await res.json()) as {
|
const next: CoopModel[] = body.data
|
||||||
data: Array<{ id: string; mode?: string }>;
|
|
||||||
};
|
|
||||||
const models = body.data
|
|
||||||
.filter(m => !m.mode || m.mode === 'chat')
|
.filter(m => !m.mode || m.mode === 'chat')
|
||||||
.map(m => ({
|
.map(m => ({
|
||||||
id: `${PREFIX}${m.id}`,
|
id: `${PREFIX}${m.id}`,
|
||||||
@@ -37,8 +41,29 @@ export function activate(context: vscode.ExtensionContext) {
|
|||||||
maxOutputTokens: 8192,
|
maxOutputTokens: 8192,
|
||||||
capabilities: { toolCalling: true, imageInput: false }
|
capabilities: { toolCalling: true, imageInput: false }
|
||||||
}));
|
}));
|
||||||
out.appendLine(` returning ${models.length} models`);
|
lastFetch = Date.now();
|
||||||
return models;
|
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) {
|
||||||
@@ -222,7 +247,6 @@ function toOpenAIMessages(
|
|||||||
if (toolCalls.length) {m.tool_calls = toolCalls;}
|
if (toolCalls.length) {m.tool_calls = toolCalls;}
|
||||||
result.push(m);
|
result.push(m);
|
||||||
}
|
}
|
||||||
// OpenAI requires tool results to follow the assistant message that requested them.
|
|
||||||
result.push(...toolResults);
|
result.push(...toolResults);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
Reference in new issue
Block a user