v2.5.0-task-model: lightweight task model services + tasks table

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>

apps/server/src/services/task-summary.ts

@@ -0,0 +1,24 @@
+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,
+  });
+}