forked from evanp/inference-coop-copilot
233 lines
7.4 KiB
TypeScript
233 lines
7.4 KiB
TypeScript
import * as vscode from 'vscode';
|
|
|
|
const BASE_URL = 'https://gateway.inference.coop/v1';
|
|
const PREFIX = 'inference-coop/';
|
|
|
|
export function activate(context: vscode.ExtensionContext) {
|
|
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 key = vscode.workspace
|
|
.getConfiguration('inferenceCoop')
|
|
.get<string>('apiKey');
|
|
if (!key) {return [];}
|
|
|
|
const res = await fetch(`${BASE_URL}/models`, {
|
|
headers: { Authorization: `Bearer ${key}` }
|
|
});
|
|
out.appendLine(` /models status: ${res.status}`);
|
|
if (!res.ok) {return [];}
|
|
|
|
const body = (await res.json()) as {
|
|
data: Array<{ id: string; mode?: string }>;
|
|
};
|
|
const models = body.data
|
|
.filter(m => !m.mode || m.mode === 'chat')
|
|
.map(m => ({
|
|
id: `${PREFIX}${m.id}`,
|
|
name: m.id,
|
|
family: 'inference-coop',
|
|
version: '1.0.0',
|
|
maxInputTokens: 131072,
|
|
maxOutputTokens: 8192,
|
|
capabilities: { toolCalling: true, imageInput: false }
|
|
}));
|
|
out.appendLine(` returning ${models.length} models`);
|
|
return models;
|
|
},
|
|
|
|
async provideLanguageModelChatResponse(model, messages, options, progress, token) {
|
|
out.appendLine(`provideLanguageModelChatResponse: ${model.id}`);
|
|
out.appendLine(` tools offered: ${options.tools?.length ?? 0}`);
|
|
|
|
const key = vscode.workspace
|
|
.getConfiguration('inferenceCoop')
|
|
.get<string>('apiKey');
|
|
|
|
const body: Record<string, unknown> = {
|
|
model: model.id.replace(PREFIX, ''),
|
|
stream: true,
|
|
messages: toOpenAIMessages(messages, out)
|
|
};
|
|
|
|
if (options.tools?.length) {
|
|
body.tools = options.tools.map(t => ({
|
|
type: 'function',
|
|
function: {
|
|
name: t.name,
|
|
description: t.description,
|
|
parameters: t.inputSchema ?? { type: 'object', properties: {} }
|
|
}
|
|
}));
|
|
body.tool_choice = 'auto';
|
|
}
|
|
|
|
const res = await fetch(`${BASE_URL}/chat/completions`, {
|
|
method: 'POST',
|
|
headers: {
|
|
Authorization: `Bearer ${key}`,
|
|
'Content-Type': 'application/json'
|
|
},
|
|
body: JSON.stringify(body),
|
|
signal: token.isCancellationRequested ? AbortSignal.abort() : undefined
|
|
});
|
|
out.appendLine(` /chat/completions status: ${res.status}`);
|
|
if (!res.ok || !res.body) {
|
|
throw new Error(`Inference Coop: HTTP ${res.status} — ${await res.text()}`);
|
|
}
|
|
|
|
const reader = res.body.getReader();
|
|
const decoder = new TextDecoder();
|
|
let buf = '';
|
|
let textChunks = 0;
|
|
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 || '{}');
|
|
} catch {
|
|
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
|
|
)
|
|
);
|
|
}
|
|
pending.clear();
|
|
};
|
|
|
|
while (true) {
|
|
const { done, value } = await reader.read();
|
|
if (done) {break;}
|
|
buf += decoder.decode(value, { stream: true });
|
|
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;}
|
|
const data = line.slice(5).trim();
|
|
if (data === '[DONE]') {
|
|
if (pending.size) {flushTools();}
|
|
out.appendLine(` done, ${textChunks} text chunks`);
|
|
return;
|
|
}
|
|
let json: any;
|
|
try {
|
|
json = JSON.parse(data);
|
|
} catch {
|
|
continue;
|
|
}
|
|
const choice = json.choices?.[0];
|
|
const delta = choice?.delta;
|
|
if (!delta) {continue;}
|
|
|
|
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: '' };
|
|
acc.id = tc.id ?? acc.id;
|
|
acc.name = tc.function?.name ?? acc.name;
|
|
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();}
|
|
out.appendLine(` stream ended, ${textChunks} text chunks`);
|
|
},
|
|
|
|
async provideTokenCount() {
|
|
return 0;
|
|
}
|
|
};
|
|
|
|
context.subscriptions.push(
|
|
vscode.lm.registerLanguageModelChatProvider('inference-coop', provider)
|
|
);
|
|
|
|
context.subscriptions.push(
|
|
vscode.commands.registerCommand('inference-coop-copilot.helloWorld', () => {
|
|
vscode.window.showInformationMessage('Inference Coop extension loaded.');
|
|
})
|
|
);
|
|
}
|
|
|
|
function toOpenAIMessages(
|
|
messages: readonly vscode.LanguageModelChatRequestMessage[],
|
|
out: vscode.OutputChannel
|
|
): object[] {
|
|
const result: object[] = [];
|
|
|
|
for (const msg of messages) {
|
|
const text: string[] = [];
|
|
const toolCalls: object[] = [];
|
|
const toolResults: object[] = [];
|
|
|
|
for (const part of msg.content ?? []) {
|
|
if (part instanceof vscode.LanguageModelTextPart) {
|
|
text.push(part.value);
|
|
} else if (part instanceof vscode.LanguageModelToolCallPart) {
|
|
toolCalls.push({
|
|
id: part.callId,
|
|
type: 'function',
|
|
function: { name: part.name, arguments: JSON.stringify(part.input ?? {}) }
|
|
});
|
|
} else if (part instanceof vscode.LanguageModelToolResultPart) {
|
|
toolResults.push({
|
|
role: 'tool',
|
|
tool_call_id: part.callId,
|
|
content: part.content
|
|
.map((c: unknown) =>
|
|
c instanceof vscode.LanguageModelTextPart ? c.value : JSON.stringify(c)
|
|
)
|
|
.join('\n')
|
|
});
|
|
}
|
|
}
|
|
|
|
const role =
|
|
msg.role === vscode.LanguageModelChatMessageRole.Assistant
|
|
? 'assistant'
|
|
: msg.role === vscode.LanguageModelChatMessageRole.User
|
|
? 'user'
|
|
: 'system';
|
|
|
|
if (text.length || toolCalls.length) {
|
|
const m: Record<string, unknown> = {
|
|
role,
|
|
content: text.length ? text.join('\n') : null
|
|
};
|
|
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);
|
|
}
|
|
|
|
out.appendLine(` translated ${result.length} messages`);
|
|
return result;
|
|
}
|
|
|
|
export function deactivate() {} |