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>

.env.example

@@ -11,6 +11,11 @@ POSTGRES_PASSWORD=CHANGE_ME
 # point BooCode at a different SearXNG instance.
 SEARXNG_URL=http://100.114.205.53:8888
 
+# Task model: lightweight model for auto-naming, search rewrite, etc.
+# Direct llama-server instance (NOT llama-swap). Falls back to LLAMA_SWAP_URL
+# with FAST_MODEL when unset.
+# TASK_MODEL_URL=http://100.90.172.55:7995
+
 # v1.13.15-tools: BOOCODE_TOOLS narrows the tool whitelist sent to the LLM.
 # Unset (default) → all tools (~21k schema). Useful primarily for single-purpose
 # sessions where the model only needs read-only filesystem access.

apps/server/src/config.ts

@@ -25,6 +25,8 @@ const ConfigSchema = z.object({
   // v2.0.5: cheaper model for titles, summaries, labeling. Falls back to
   // session model (auto_name) or DEFAULT_MODEL when unset.
   FAST_MODEL: z.string().optional(),
+  TASK_MODEL_URL: z.string().url().optional(),
+  LLAMA_SIDECAR_URL: z.string().url().optional(),
 });
 
 export type Config = z.infer<typeof ConfigSchema>;

apps/server/src/index.ts

@@ -28,7 +28,7 @@ import { cleanupTruncations } from './services/truncate.js';
 import { loadMcpConfig } from './services/mcp-config.js';
 import { initialize as initMcp, getTools as getMcpTools, shutdown as shutdownMcp } from './services/mcp-client.js';
 import { appendMcpTools } from './services/tools.js';
-import { refreshToolNames } from './services/agents.js';
+import { refreshToolNames, getAgentsForProject } from './services/agents.js';
 
 async function main() {
   const config = loadConfig();
@@ -91,6 +91,20 @@ async function main() {
   }
   app.addHook('onClose', async () => { await shutdownMcp(); });
 
+  // Boot-time guard: if any agent has llama_extra_args but LLAMA_SIDECAR_URL
+  // is unset, fail fast. Silent fallback would defeat per-agent flags.
+  if (!config.LLAMA_SIDECAR_URL) {
+    const { agents } = await getAgentsForProject('');
+    const offending = agents.find(a => a.llama_extra_args && a.llama_extra_args.length > 0);
+    if (offending) {
+      app.log.fatal(
+        { agent: offending.name },
+        `Agent "${offending.name}" has llama_extra_args but LLAMA_SIDECAR_URL is not set`,
+      );
+      process.exit(1);
+    }
+  }
+
   await app.register(fastifyWebsocket);
 
   app.get('/api/health', async () => {

apps/server/src/schema.sql

@@ -344,6 +344,7 @@ INSERT INTO settings (key, value) VALUES ('theme_mode', '"dark"') ON CONFLICT (k
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_system_prompt TEXT NOT NULL DEFAULT '';
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_web_search_enabled BOOLEAN NOT NULL DEFAULT false;
 ALTER TABLE sessions ADD COLUMN IF NOT EXISTS web_search_enabled BOOLEAN;
+ALTER TABLE sessions ADD COLUMN IF NOT EXISTS tags TEXT[] DEFAULT '{}';
 
 -- v1.11: anchored rolling compaction.
 --   compacted_at  — marks rows that are "behind the curtain" of the latest
@@ -366,3 +367,39 @@ ALTER TABLE messages ADD COLUMN IF NOT EXISTS summary BOOLEAN NOT NULL DEFAULT F
 ALTER TABLE messages ADD COLUMN IF NOT EXISTS tail_start_id UUID REFERENCES messages(id) ON DELETE SET NULL;
 ALTER TABLE chats ADD COLUMN IF NOT EXISTS needs_compaction BOOLEAN NOT NULL DEFAULT FALSE;
 CREATE INDEX IF NOT EXISTS idx_messages_chat_compacted ON messages (chat_id, compacted_at);
+
+-- tasks table (provider dispatch, arena)
+CREATE TABLE IF NOT EXISTS tasks (
+  id                UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  project_id        UUID NOT NULL REFERENCES projects(id) ON DELETE CASCADE,
+  session_id        UUID REFERENCES sessions(id) ON DELETE CASCADE,
+  parent_task_id    UUID REFERENCES tasks(id),
+  arena_id          UUID,
+  state             TEXT NOT NULL DEFAULT 'pending'
+                    CHECK (state IN ('pending','running','completed','failed','blocked','cancelled')),
+  input             TEXT NOT NULL,
+  output_summary    TEXT,
+  agent             TEXT,
+  model             TEXT,
+  mode_id           TEXT,
+  thinking_option_id TEXT,
+  feature_values    JSONB,
+  execution_path    TEXT CHECK (execution_path IS NULL OR execution_path IN ('native','acp','pty','qwen')),
+  worktree_path     TEXT,
+  cost_tokens       INTEGER,
+  started_at        TIMESTAMPTZ,
+  ended_at          TIMESTAMPTZ,
+  created_at        TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+
+-- Fix tasks FK to cascade on session delete (existing tables without CASCADE)
+DO $$ BEGIN
+  IF EXISTS (
+    SELECT 1 FROM pg_constraint WHERE conname = 'tasks_session_id_fkey'
+    AND confdeltype != 'c'
+  ) THEN
+    ALTER TABLE tasks DROP CONSTRAINT tasks_session_id_fkey;
+    ALTER TABLE tasks ADD CONSTRAINT tasks_session_id_fkey
+      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE;
+  END IF;
+END $$;

apps/server/src/services/__tests__/provider.test.ts

@@ -0,0 +1,58 @@
+import { describe, expect, it } from 'vitest';
+import { resolveRoute, upstreamModel } from '../inference/provider.js';
+
+describe('resolveRoute', () => {
+  it('routes to swap when agent is null', () => {
+    expect(resolveRoute(null)).toEqual({ route: 'swap', flags: null });
+  });
+
+  it('routes to swap when agent has no llama_extra_args', () => {
+    expect(resolveRoute({ llama_extra_args: null })).toEqual({ route: 'swap', flags: null });
+  });
+
+  it('routes to swap when agent has empty llama_extra_args', () => {
+    expect(resolveRoute({ llama_extra_args: [] })).toEqual({ route: 'swap', flags: null });
+  });
+
+  it('routes to sidecar when agent has llama_extra_args', () => {
+    const result = resolveRoute({ llama_extra_args: ['--top-k', '20'] });
+    expect(result.route).toBe('sidecar');
+    expect(result.flags).toEqual(['--top-k', '20']);
+  });
+});
+
+describe('upstreamModel', () => {
+  const swapConfig = { LLAMA_SWAP_URL: 'http://localhost:8401' };
+  const fullConfig = {
+    LLAMA_SWAP_URL: 'http://localhost:8401',
+    LLAMA_SIDECAR_URL: 'http://localhost:8402',
+  };
+
+  it('returns a model for swap route (no agent)', () => {
+    const model = upstreamModel(swapConfig, 'test-model');
+    expect(model).toBeDefined();
+    expect((model as any).modelId).toBe('test-model');
+  });
+
+  it('returns a model for swap route (agent without extra args)', () => {
+    const model = upstreamModel(swapConfig, 'test-model', { llama_extra_args: null });
+    expect(model).toBeDefined();
+  });
+
+  it('returns a model for sidecar route', () => {
+    const model = upstreamModel(fullConfig, 'test-model', { llama_extra_args: ['--top-k', '20'] });
+    expect(model).toBeDefined();
+    expect((model as any).modelId).toBe('test-model');
+  });
+
+  it('throws when sidecar route requested but URL missing', () => {
+    expect(() =>
+      upstreamModel(swapConfig, 'test-model', { llama_extra_args: ['--top-k', '20'] }),
+    ).toThrow(/LLAMA_SIDECAR_URL/);
+  });
+
+  it('routes to swap for empty llama_extra_args array', () => {
+    const model = upstreamModel(swapConfig, 'test-model', { llama_extra_args: [] });
+    expect(model).toBeDefined();
+  });
+});

apps/server/src/services/auto_name.ts

@@ -1,9 +1,10 @@
 import type { InferenceContext } from './inference/index.js';
+import { taskModelCompletion } from './task-model.js';
 
 const NAMING_SYSTEM_PROMPT =
-  'You name chat sessions based on what the assistant did. Summarize the topic or outcome — do NOT copy the first few words verbatim. Reply directly with no thinking, reasoning, or explanation. Output ONLY the title, 4 words max, no quotes, no punctuation, no prefix like "Title:".';
+  'You name chat sessions. Reply with ONLY the title. 4 to 6 words. No quotes, no punctuation, no prefix.';
 
-const MAX_TITLE_CHARS = 60;
+const MAX_TITLE_CHARS = 80;
 
 function cleanTitle(raw: string): string {
   let name = raw.trim();
@@ -18,27 +19,7 @@ function cleanTitle(raw: string): string {
   return name;
 }
 
-interface NamingResponse {
+// TODO: wire suggestTags after task model validation
-  choices?: Array<{
-    message?: {
-      content?: string;
-      reasoning_content?: string;
-    };
-  }>;
-}
-
-function pickTitleSource(data: NamingResponse): string {
-  const choice = data.choices?.[0]?.message;
-  if (!choice) return '';
-  if (choice.content && choice.content.trim().length > 0) return choice.content;
-  const reasoning = choice.reasoning_content ?? '';
-  if (reasoning.length === 0) return '';
-  const lines = reasoning
-    .split('\n')
-    .map((l) => l.trim())
-    .filter((l) => l.length > 0);
-  return lines[lines.length - 1] ?? '';
-}
 
 export async function maybeAutoNameChat(
   ctx: InferenceContext,
@@ -64,13 +45,6 @@ export async function maybeAutoNameChat(
   if (!chat) return;
   if (chat.name !== null && chat.name !== '') return;
 
-  const sessionRows = await ctx.sql<{ model: string }[]>`
-    SELECT model FROM sessions WHERE id = ${sessionId}
-  `;
-  // v2.0.5: prefer FAST_MODEL for cheap LLM calls (titles, summaries).
-  const model = ctx.config.FAST_MODEL ?? sessionRows[0]?.model;
-  if (!model) return;
-
   const assistantMsg = await ctx.sql<{ content: string }[]>`
     SELECT content FROM messages
     WHERE chat_id = ${chatId}
@@ -84,32 +58,12 @@ export async function maybeAutoNameChat(
 
   const assistantText = assistantMsg[0].content.slice(0, 2000);
 
-  const body = {
+  const raw = await taskModelCompletion({
-    model,
+    system: NAMING_SYSTEM_PROMPT,
-    messages: [
+    user: assistantText,
-      { role: 'system', content: NAMING_SYSTEM_PROMPT },
+    maxTokens: 30,
-      {
-        role: 'user',
-        content: assistantText,
-      },
-    ],
-    max_tokens: 30,
     temperature: 0.3,
-    stream: false,
-    chat_template_kwargs: { enable_thinking: false },
-  };
-
-  const res = await fetch(`${ctx.config.LLAMA_SWAP_URL}/v1/chat/completions`, {
-    method: 'POST',
-    headers: { 'Content-Type': 'application/json' },
-    body: JSON.stringify(body),
   });
-  if (!res.ok) {
-    const text = await res.text().catch(() => '');
-    throw new Error(`naming request failed: ${res.status} ${text.slice(0, 200)}`);
-  }
-  const data = (await res.json()) as NamingResponse;
-  const raw = pickTitleSource(data);
   const name = cleanTitle(raw);
   if (!name) {
     ctx.log.warn({ chatId, raw }, 'auto-name: empty title from model');

apps/server/src/services/inference/provider.ts

@@ -1,37 +1,84 @@
 import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
 import type { LanguageModel } from 'ai';
 
-// TODO: When per-agent llama-server flag overrides are added, route them
-// through validateExtraArgs (./llama-args-validator.ts) first.
-
 // v1.13.1-A: AI SDK provider against llama-swap. baseURL is threaded from
 // config.LLAMA_SWAP_URL at call time (not module-load) so tests can stub the
 // upstream without touching env vars. No apiKey — llama-swap is unauth in our
 // Tailscale topology and exposing it over the public internet is gated by
 // Authelia at the Caddy layer, not by API keys.
+//
+// v2.4.1-sidecar: when the agent has llama_extra_args, route through
+// llama-sidecar instead. A fresh provider is created per call (not cached)
+// because the X-Agent-Flags header varies per agent. The llama-swap path
+// stays cached since it has no per-request headers.
 
-const cache = new Map<string, ReturnType<typeof createOpenAICompatible>>();
+const swapCache = new Map<string, ReturnType<typeof createOpenAICompatible>>();
 
-function getProvider(baseURL: string): ReturnType<typeof createOpenAICompatible> {
+function getSwapProvider(baseURL: string): ReturnType<typeof createOpenAICompatible> {
-  let provider = cache.get(baseURL);
+  let provider = swapCache.get(baseURL);
   if (!provider) {
     provider = createOpenAICompatible({
       name: 'llama-swap',
       baseURL: baseURL.endsWith('/v1') ? baseURL : `${baseURL}/v1`,
-      // v1.13.7: @ai-sdk/openai-compatible defaults includeUsage=false, which
-      // omits `stream_options.include_usage` from the request body. Without
-      // it, llama.cpp / llama-swap never emits the trailing usage block, so
-      // `result.usage` resolves with inputTokens=outputTokens=undefined and
-      // tokens_used / ctx_used land as NULL in every messages row. Setting
-      // true here re-enables the per-stream usage payload across all models
-      // served via the llama-swap provider.
       includeUsage: true,
     });
-    cache.set(baseURL, provider);
+    swapCache.set(baseURL, provider);
   }
   return provider;
 }
 
-export function upstreamModel(baseURL: string, modelId: string): LanguageModel {
+function sidecarProvider(
-  return getProvider(baseURL).chatModel(modelId);
+  baseURL: string,
+  flags: string[],
+): ReturnType<typeof createOpenAICompatible> {
+  return createOpenAICompatible({
+    name: 'llama-sidecar',
+    baseURL: baseURL.endsWith('/v1') ? baseURL : `${baseURL}/v1`,
+    includeUsage: true,
+    headers: {
+      'X-Agent-Flags': flags.join(' '),
+    },
+  });
+}
+
+export type InferenceRoute = 'swap' | 'sidecar';
+
+export interface RoutingInfo {
+  route: InferenceRoute;
+  flags: string[] | null;
+}
+
+interface AgentLike {
+  llama_extra_args: string[] | null;
+}
+
+interface ConfigLike {
+  LLAMA_SWAP_URL: string;
+  LLAMA_SIDECAR_URL?: string;
+}
+
+export function resolveRoute(agent: AgentLike | null): RoutingInfo {
+  const flags = agent?.llama_extra_args;
+  if (flags && flags.length > 0) {
+    return { route: 'sidecar', flags };
+  }
+  return { route: 'swap', flags: null };
+}
+
+export function upstreamModel(
+  config: ConfigLike,
+  modelId: string,
+  agent?: AgentLike | null,
+): LanguageModel {
+  const { route, flags } = resolveRoute(agent ?? null);
+  if (route === 'sidecar') {
+    const url = config.LLAMA_SIDECAR_URL;
+    if (!url) {
+      throw new Error(
+        `Agent has llama_extra_args but LLAMA_SIDECAR_URL is not set`,
+      );
+    }
+    return sidecarProvider(url, flags!).chatModel(modelId);
+  }
+  return getSwapProvider(config.LLAMA_SWAP_URL).chatModel(modelId);
 }

apps/server/src/services/inference/stream-phase.ts

@@ -157,7 +157,8 @@ export async function streamCompletion(
   opts: StreamOptions,
   onDelta: (content: string) => void,
   onUsage: ((prompt: number | null, completion: number | null) => void) | undefined,
-  signal?: AbortSignal
+  signal?: AbortSignal,
+  agent?: Agent | null,
 ): Promise<StreamResult> {
   const aiMessages = toModelMessages(messages);
   const hasTools = opts.tools !== null && opts.tools.length > 0;
@@ -195,7 +196,7 @@ export async function streamCompletion(
   };
 
   const result = streamText({
-    model: upstreamModel(ctx.config.LLAMA_SWAP_URL, model),
+    model: upstreamModel(ctx.config, model, agent ?? null),
     messages: aiMessages,
     ...(aiTools
       ? { tools: aiTools, toolChoice: 'auto' as const, experimental_repairToolCall: repairToolCall }
@@ -458,7 +459,8 @@ export async function executeStreamPhase(
           }, USAGE_THROTTLE_MS - elapsed);
         }
       },
-      signal
+      signal,
+      agent,
     );
   } finally {
     if (pendingFlushTimer) {

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;

apps/server/src/services/system-prompt.ts

@@ -21,6 +21,7 @@ import { createHash } from 'node:crypto';
 import { readFile, stat } from 'node:fs/promises';
 import type { Agent, Project, Session } from '../types/api.js';
 import { getAgentsMtimes } from './agents.js';
+import { resolveRoute } from './inference/provider.js';
 
 const BASE_SYSTEM_PROMPT = (projectPath: string) =>
   `You are BooCode Chat, a code investigation assistant. The user is working on a project located at ${projectPath}. Use the file-read tools (view_file, list_dir, grep, find_files) to investigate code when needed. Be concise. Cite file paths and line numbers when discussing code. Do not hallucinate file contents — read the file first. Tool results may be truncated; if so, narrow your query rather than guessing.`;
@@ -98,6 +99,7 @@ export interface PrefixFingerprint {
   has_agent_system_prompt: boolean;
   has_session_override: boolean;
   has_project_override: boolean;
+  route: 'swap' | 'sidecar';
 }
 
 export interface PrefixDrift {
@@ -125,6 +127,7 @@ interface ObservedInputs {
   has_agent_system_prompt: boolean;
   has_session_override: boolean;
   has_project_override: boolean;
+  route: 'swap' | 'sidecar';
 }
 
 interface ObserverEntry {
@@ -183,6 +186,7 @@ export async function buildSystemPromptWithFingerprint(
     has_agent_system_prompt: !!(agent && agent.system_prompt.trim().length > 0),
     has_session_override: sessionPrompt.length > 0,
     has_project_override: projectPrompt.length > 0,
+    route: resolveRoute(agent).route,
   };
 
   const fingerprint: PrefixFingerprint = {
@@ -199,6 +203,7 @@ export async function buildSystemPromptWithFingerprint(
     has_agent_system_prompt: inputs.has_agent_system_prompt,
     has_session_override: inputs.has_session_override,
     has_project_override: inputs.has_project_override,
+    route: inputs.route,
   };
 
   let drift: PrefixDrift | null = null;

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

@@ -0,0 +1,68 @@
+import { loadConfig, type Config } from '../config.js';
+
+const TIMEOUT_MS = 10_000;
+
+export async function taskModelCompletion(opts: {
+  system: string;
+  user: string;
+  maxTokens?: number;
+  temperature?: number;
+  fallbackModel?: string;
+}): Promise<string> {
+  const config = loadConfig();
+  const maxTokens = opts.maxTokens ?? 30;
+  const temperature = opts.temperature ?? 0.3;
+
+  const { url, model } = resolveEndpoint(config, opts.fallbackModel);
+
+  try {
+    const res = await fetch(`${url}/v1/chat/completions`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({
+        model,
+        messages: [
+          { role: 'system', content: opts.system },
+          { role: 'user', content: opts.user },
+        ],
+        max_tokens: maxTokens,
+        temperature,
+        stream: false,
+        chat_template_kwargs: { enable_thinking: false },
+      }),
+      signal: AbortSignal.timeout(TIMEOUT_MS),
+    });
+    if (!res.ok) {
+      const text = await res.text().catch(() => '');
+      console.warn(`task-model: ${res.status} ${text.slice(0, 200)}`);
+      return '';
+    }
+    const data = (await res.json()) as {
+      choices?: Array<{
+        message?: { content?: string; reasoning_content?: string };
+      }>;
+    };
+    const choice = data.choices?.[0]?.message;
+    if (!choice) return '';
+    const content = (choice.content ?? '').trim();
+    if (content.length > 0) return content;
+    const reasoning = choice.reasoning_content ?? '';
+    if (reasoning.length === 0) return '';
+    const lines = reasoning.split('\n').map((l) => l.trim()).filter((l) => l.length > 0);
+    return lines[lines.length - 1] ?? '';
+  } catch (err) {
+    console.warn('task-model: request failed', err);
+    return '';
+  }
+}
+
+function resolveEndpoint(
+  config: Config,
+  fallbackModel?: string,
+): { url: string; model: string } {
+  if (config.TASK_MODEL_URL) {
+    return { url: config.TASK_MODEL_URL, model: 'gemma-3-270m-it' };
+  }
+  const model = config.FAST_MODEL ?? fallbackModel ?? config.DEFAULT_MODEL;
+  return { url: config.LLAMA_SWAP_URL, model };
+}

apps/server/src/services/task-search-rewrite.ts

@@ -0,0 +1,19 @@
+import { taskModelCompletion } from './task-model.js';
+
+const SYSTEM_PROMPT =
+  'You rewrite user messages into concise web search queries. Reply with ONLY the search query. 3 to 6 words. No quotes, no explanation.';
+
+const MAX_INPUT_CHARS = 500;
+const FALLBACK_CHARS = 60;
+
+export async function rewriteSearchQuery(userMessage: string): Promise<string> {
+  const input = userMessage.slice(0, MAX_INPUT_CHARS);
+  const result = await taskModelCompletion({
+    system: SYSTEM_PROMPT,
+    user: input,
+    maxTokens: 20,
+    temperature: 0.2,
+  });
+  if (result.length > 0) return result;
+  return userMessage.slice(0, FALLBACK_CHARS).trim();
+}

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,
+  });
+}

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

@@ -0,0 +1,22 @@
+import { taskModelCompletion } from './task-model.js';
+
+const SYSTEM_PROMPT =
+  'You tag chat sessions. Reply with 1 to 3 lowercase tags separated by commas. Tags should describe the topic. No explanation. Examples: "docker, deployment", "python, debugging", "react, styling".';
+
+export async function suggestTags(
+  userMessage: string,
+  assistantReply: string,
+): Promise<string[]> {
+  const input = `User: ${userMessage.slice(0, 300)}\nAssistant: ${assistantReply.slice(0, 300)}`;
+  const result = await taskModelCompletion({
+    system: SYSTEM_PROMPT,
+    user: input,
+    maxTokens: 30,
+    temperature: 0.3,
+  });
+  if (result.length === 0) return [];
+  return result
+    .split(',')
+    .map((t) => t.trim().toLowerCase())
+    .filter((t) => t.length > 0 && t.length <= 30);
+}

data/AGENTS.md

@@ -7,7 +7,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Reviews code for bugs, security issues, and maintainability. Read-only.
 ---
 You review code. Find real problems, not style nits.
@@ -46,7 +46,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Diagnoses bugs from error messages, logs, or described symptoms.
 ---
 You diagnose bugs. Form a hypothesis, prove it with evidence from the code.
@@ -72,7 +72,7 @@ top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
 steps: 5
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Proposes refactors for clarity, deduplication, or decoupling. Read-only — outputs plans, not edits.
 ---
 You propose refactors. You do not apply them. The user applies via OpenCode or Claude Code.
@@ -115,7 +115,7 @@ top_k: 20
 min_p: 0.0
 presence_penalty: 1.5
 steps: 20
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Designs new features, modules, or architectural changes. Outputs a build plan.
 ---
 You design. You produce build plans, not code.
@@ -157,7 +157,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Audits code for security vulnerabilities. Read-only.
 ---
 You audit for security issues. Concrete findings only, no generic warnings.
@@ -240,7 +240,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Discovers and maps unfamiliar codebases. Reads architecture, traces data flow, identifies key symbols.
 ---
 You map codebases. Start broad, then drill into specifics.

docker-compose.yml

@@ -11,6 +11,7 @@ services:
       CONTAINER_GUIDANCE_FILE: /app/BOOCHAT.md
       DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boochat
       BOOCODER_URL: http://100.114.205.53:9502
+      LLAMA_SIDECAR_URL: http://100.101.41.16:8402
     volumes:
       - /opt:/opt
       - /opt/projects:/opt/projects:rw