indifferentketchup
203cfd2fa8
DeepSeek API: - @ai-sdk/deepseek provider replaces openai-compatible for deepseek-* models - Token tracking: cache_hit/reasoning tokens flow API → DB → WS frames → UI - thinking effort levels (off/low/medium/high/xhigh/max) via AGENTS.md frontmatter - V4 models: deepseek-v4-flash, deepseek-v4-pro - Wired for both chat and coder panes Whale lifts: - Tool input repair (schema-based type coercion, markdown link unwrapping) - Hooks system (6 lifecycle events, shell exec, JSON stdin/stdout contract) - Per-MCP-server permissions (allow/ask/deny) - token tracking UI (cache N, think N in message stats line) Infra: - New DB columns: messages.cache_tokens, messages.reasoning_tokens - New WS frame fields: cache_tokens, reasoning_tokens on message_complete - coder provider snapshot merges DeepSeek models alongside llama-swap
57 lines
1.9 KiB
TypeScript
57 lines
1.9 KiB
TypeScript
import type { FastifyInstance } from 'fastify';
|
|
import type { Config } from '../config.js';
|
|
import type { ModelInfo } from '../types/api.js';
|
|
|
|
interface ApiModelsResponse {
|
|
data?: ModelInfo[];
|
|
}
|
|
|
|
const DEEPSEEK_STATIC_MODELS: ModelInfo[] = [
|
|
{ id: 'deepseek-v4-flash', object: 'model', created: 0, owned_by: 'deepseek' },
|
|
{ id: 'deepseek-v4-pro', object: 'model', created: 0, owned_by: 'deepseek' },
|
|
];
|
|
|
|
export function registerModelRoutes(app: FastifyInstance, config: Config): void {
|
|
app.get('/api/models', async (_req, reply) => {
|
|
const models: ModelInfo[] = [];
|
|
|
|
// 1. Fetch llama-swap models
|
|
try {
|
|
const res = await fetch(`${config.LLAMA_SWAP_URL}/v1/models`);
|
|
if (res.ok) {
|
|
const parsed = (await res.json()) as ApiModelsResponse;
|
|
if (parsed.data) models.push(...parsed.data);
|
|
}
|
|
} catch {
|
|
// llama-swap unreachable — proceed with whatever we have
|
|
}
|
|
|
|
// 2. If DeepSeek is configured, fetch live models from their API
|
|
if (config.DEEPSEEK_API_KEY) {
|
|
try {
|
|
const baseURL = (config.DEEPSEEK_BASE_URL ?? 'https://api.deepseek.com').replace(/\/+$/, '');
|
|
const res = await fetch(`${baseURL}/v1/models`, {
|
|
headers: { Authorization: `Bearer ${config.DEEPSEEK_API_KEY}` },
|
|
signal: AbortSignal.timeout(5_000),
|
|
});
|
|
if (res.ok) {
|
|
const parsed = (await res.json()) as ApiModelsResponse;
|
|
if (parsed.data) models.push(...parsed.data);
|
|
} else {
|
|
// API call failed — fall back to static model list
|
|
models.push(...DEEPSEEK_STATIC_MODELS);
|
|
}
|
|
} catch {
|
|
// Network error — fall back to static model list
|
|
models.push(...DEEPSEEK_STATIC_MODELS);
|
|
}
|
|
}
|
|
|
|
if (models.length === 0) {
|
|
reply.code(502);
|
|
return { error: 'no models available from any provider' };
|
|
}
|
|
return models;
|
|
});
|
|
}
|