v2.0.3: CLI client + human inbox + cost tracking + Boomerang new_task

Phase 7 of v2.0. BooCoder gains a terminal-driven UX and subagent
isolation primitive.

CLI (src/cli.ts): standalone entry point for terminal use.
- boocode run "task" [--agent x] [--model y] — create + stream output
- boocode ls [--state x] — formatted task table
- boocode attach <id> — WS stream of running task
- boocode send <id> "msg" — follow-up message to task session
Connects to BOOCODER_URL (default http://100.114.205.53:9502).

Human inbox (routes/inbox.ts): GET /api/inbox (failed/blocked tasks),
POST /api/inbox/:id/retry (reset to pending for re-dispatch).

Cost tracking: dispatcher aggregates tokens_used from all messages in
the task's session after completion, stores in tasks.cost_tokens.
GET /api/stats/costs?group_by=project|agent|day for aggregation.

Boomerang subagent isolation (3 new tools):
- new_task: creates child task with parent_task_id linkage, runs in
  fresh isolated session. Orchestrator sees only output_summary.
- list_tasks: query child tasks of current parent
- check_task_status: read task state + output_summary

The orchestrator pattern: an agent with tools: [new_task, list_tasks,
check_task_status] can ONLY dispatch — can't read files or MCP. This
is the Roo Code Boomerang Tasks capability-restriction principle.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/coder/src/services/tools/list_tasks.ts

@@ -0,0 +1,56 @@
+import { z } from 'zod';
+import type { ToolDef, ToolContext } from './types.js';
+import { getInferenceContext } from './inference_context.js';
+
+const ListTasksInput = z.object({
+  parent_task_id: z.string().uuid().optional().describe('Filter by parent task ID. Omit to list children of current task.'),
+});
+
+type ListTasksInputT = z.infer<typeof ListTasksInput>;
+
+export const listTasksTool: ToolDef<ListTasksInputT> = {
+  name: 'list_tasks',
+  description: 'List child tasks of the current task (or a specified parent). Returns id, state, input preview, and output_summary.',
+  inputSchema: ListTasksInput,
+  jsonSchema: {
+    type: 'function',
+    function: {
+      name: 'list_tasks',
+      description: 'List child tasks of the current task (or a specified parent).',
+      parameters: {
+        type: 'object',
+        properties: {
+          parent_task_id: { type: 'string', description: 'Filter by parent task ID. Omit to list children of current task.' },
+        },
+        required: [],
+      },
+    },
+  },
+
+  async execute(input: ListTasksInputT, _projectRoot: string, context: ToolContext): Promise<unknown> {
+    const { sql } = context;
+    const ctx = getInferenceContext();
+    const parentId = input.parent_task_id ?? ctx.taskId;
+
+    if (!parentId) {
+      return { tasks: [], note: 'No parent task context — not running inside a task.' };
+    }
+
+    const rows = await sql<{ id: string; state: string; input: string; output_summary: string | null }[]>`
+      SELECT id, state, input, output_summary
+      FROM tasks
+      WHERE parent_task_id = ${parentId}
+      ORDER BY created_at DESC
+      LIMIT 50
+    `;
+
+    return {
+      tasks: rows.map((r) => ({
+        id: r.id,
+        state: r.state,
+        input_preview: r.input.slice(0, 100),
+        output_summary: r.output_summary,
+      })),
+    };
+  },
+};