indifferentketchup
fcc7c5a86e
Task model infrastructure for cheap LLM calls (auto-naming, search rewrite, tags, summaries) via a dedicated llama-server instance at TASK_MODEL_URL, falling back to LLAMA_SWAP_URL with FAST_MODEL when unset. Replaces the inline fetch in auto_name.ts with taskModelCompletion. Adds search query rewriting: on step 0 when web tools are enabled, the user's message is summarized into a search intent hint appended to the system prompt, improving web_search relevance. Schema: tasks table for provider dispatch and arena, sessions.tags column. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
25 lines
646 B
TypeScript
25 lines
646 B
TypeScript
import { taskModelCompletion } from './task-model.js';
|
|
|
|
const SYSTEM_PROMPT =
|
|
'Summarize this conversation in one sentence, 15 words max. No quotes, no prefix.';
|
|
|
|
const MAX_INPUT_CHARS = 1000;
|
|
|
|
export async function oneLineSummary(
|
|
messages: Array<{ role: string; content: string }>,
|
|
): Promise<string> {
|
|
const lastPairs = messages.slice(-6);
|
|
let input = lastPairs
|
|
.map((m) => `${m.role}: ${m.content}`)
|
|
.join('\n');
|
|
if (input.length > MAX_INPUT_CHARS) {
|
|
input = input.slice(0, MAX_INPUT_CHARS);
|
|
}
|
|
return taskModelCompletion({
|
|
system: SYSTEM_PROMPT,
|
|
user: input,
|
|
maxTokens: 30,
|
|
temperature: 0.3,
|
|
});
|
|
}
|