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>
115 lines
3.3 KiB
TypeScript
115 lines
3.3 KiB
TypeScript
import type { InferenceContext } from './inference/index.js';
|
||
import { taskModelCompletion } from './task-model.js';
|
||
|
||
const NAMING_SYSTEM_PROMPT =
|
||
'You name chat sessions. Reply with ONLY the title. 4 to 6 words. No quotes, no punctuation, no prefix.';
|
||
|
||
const MAX_TITLE_CHARS = 80;
|
||
|
||
function cleanTitle(raw: string): string {
|
||
let name = raw.trim();
|
||
const quotes = ['"', "'", '`', '‘', '’', '“', '”'];
|
||
while (name.length >= 2 && quotes.includes(name[0]!) && quotes.includes(name[name.length - 1]!)) {
|
||
name = name.slice(1, -1).trim();
|
||
}
|
||
name = name.replace(/^title\s*:\s*/i, '').trim();
|
||
if (name.length > MAX_TITLE_CHARS) {
|
||
name = name.slice(0, MAX_TITLE_CHARS).trim();
|
||
}
|
||
return name;
|
||
}
|
||
|
||
// TODO: wire suggestTags after task model validation
|
||
|
||
export async function maybeAutoNameChat(
|
||
ctx: InferenceContext,
|
||
chatId: string,
|
||
sessionId: string
|
||
): Promise<void> {
|
||
const counts = await ctx.sql<{ n: number }[]>`
|
||
SELECT COUNT(*)::int AS n
|
||
FROM messages
|
||
WHERE chat_id = ${chatId}
|
||
AND role = 'assistant'
|
||
AND status = 'complete'
|
||
AND content <> ''
|
||
`;
|
||
if ((counts[0]?.n ?? 0) < 1) return;
|
||
|
||
const chatRows = await ctx.sql<
|
||
{ id: string; name: string | null; session_id: string }[]
|
||
>`
|
||
SELECT id, name, session_id FROM chats WHERE id = ${chatId}
|
||
`;
|
||
const chat = chatRows[0];
|
||
if (!chat) return;
|
||
if (chat.name !== null && chat.name !== '') return;
|
||
|
||
const assistantMsg = await ctx.sql<{ content: string }[]>`
|
||
SELECT content FROM messages
|
||
WHERE chat_id = ${chatId}
|
||
AND role = 'assistant'
|
||
AND status = 'complete'
|
||
AND content <> ''
|
||
ORDER BY created_at ASC
|
||
LIMIT 1
|
||
`;
|
||
if (!assistantMsg[0]) return;
|
||
|
||
const assistantText = assistantMsg[0].content.slice(0, 2000);
|
||
|
||
const raw = await taskModelCompletion({
|
||
system: NAMING_SYSTEM_PROMPT,
|
||
user: assistantText,
|
||
maxTokens: 30,
|
||
temperature: 0.3,
|
||
});
|
||
const name = cleanTitle(raw);
|
||
if (!name) {
|
||
ctx.log.warn({ chatId, raw }, 'auto-name: empty title from model');
|
||
return;
|
||
}
|
||
|
||
const updated = await ctx.sql<{ id: string; name: string; session_id: string; updated_at: string }[]>`
|
||
UPDATE chats
|
||
SET name = ${name}, updated_at = clock_timestamp()
|
||
WHERE id = ${chatId}
|
||
AND (name IS NULL OR name = '')
|
||
RETURNING id, name, session_id, updated_at
|
||
`;
|
||
if (updated.length === 0) return;
|
||
|
||
ctx.publish(sessionId, {
|
||
type: 'chat_renamed',
|
||
chat_id: chatId,
|
||
name,
|
||
});
|
||
ctx.publishUser({
|
||
type: 'chat_updated',
|
||
chat_id: chatId,
|
||
session_id: sessionId,
|
||
name,
|
||
updated_at: updated[0]!.updated_at,
|
||
});
|
||
ctx.log.info({ chatId, name }, 'chat auto-named');
|
||
|
||
// Propagate to the parent session if it's still on its default name.
|
||
// The WHERE guard makes the check atomic — if the user has already
|
||
// renamed (or a prior chat already propagated), this UPDATE matches
|
||
// zero rows and we do nothing. First chat wins; manual renames win.
|
||
const renamedSession = await ctx.sql<{ id: string; name: string }[]>`
|
||
UPDATE sessions
|
||
SET name = ${name}
|
||
WHERE id = ${sessionId} AND name = 'New session'
|
||
RETURNING id, name
|
||
`;
|
||
if (renamedSession.length > 0) {
|
||
ctx.publishUser({
|
||
type: 'session_renamed',
|
||
session_id: sessionId,
|
||
name,
|
||
});
|
||
ctx.log.info({ sessionId, name }, 'session auto-named from chat');
|
||
}
|
||
}
|