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/inference/turn.ts

@@ -14,6 +14,7 @@ import type {
 import { ALL_TOOLS } from '../tools.js';
 import { resolveProjectRoot } from '../path_guard.js';
 import { maybeAutoNameChat } from '../auto_name.js';
+import { rewriteSearchQuery } from '../task-search-rewrite.js';
 import { getAgentById } from '../agents.js';
 import * as compaction from '../compaction.js';
 import type { Broker } from '../broker.js';
@@ -254,6 +255,16 @@ export async function runAssistantTurn(
     const webToolsEnabled =
       iterSession.web_search_enabled ?? iterProject.default_web_search_enabled ?? false;
 
+    if (stepNumber === 0 && webToolsEnabled && messages.length >= 2) {
+      const lastUserMsg = [...messages].reverse().find((m) => m.role === 'user');
+      if (lastUserMsg?.content) {
+        const hint = await rewriteSearchQuery(lastUserMsg.content);
+        if (hint && messages[0]?.role === 'system' && messages[0].content) {
+          messages[0].content += `\n\nThe user's search intent can be summarized as: "${hint}"`;
+        }
+      }
+    }
+
     const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, signal };
     const state: StreamPhaseState = { accumulated: '', startedAt: null };
     let result: StreamResult;