Inconsistent node ID generation and invalid complexity values from parallel LLM subagents in a codebase analysis tool.

## Problem

When `/understand --full` dispatches parallel file-analyzer subagents, there is no deterministic enforcement of node ID format or complexity enum values. The prompt specifies the correct formats, but the assembly pipeline trusts LLM output without validation — so inconsistent batches silently corrupt the final graph.

## Issue 1: No runtime enforcement of node ID format

The file-analyzer prompt (`skills/understand/file-analyzer-prompt.md`, lines 219–227) specifies:

| Node Type | Required Format | Example |
|---|---|---|
| File | `file:` | `file:src/index.ts` |
| Function | `func::` | `func:src/utils.ts:formatDate` |
| Class | `class::` | `class:src/models/User.ts:User` |

However, the Zod schema only validates `id: z.string()` (`packages/core/src/schema.ts`, line 13) — any string passes. Neither Phase 3 (ASSEMBLE) nor the `GraphBuilder` (`packages/core/src/analyzer/graph-builder.ts`, line 84) validates ID prefix format on merged batch output.

Since subagents are LLMs writing JSON directly to `batch-.json` files, they can produce:
- Project-name-prefixed IDs: `myproject:backend/main.py`
- Double-prefixed IDs: `myproject:service:docker-compose.yml`
- Bare paths with no prefix: `frontend/src/utils/constants.ts`

**Evidence from a 226-file project run:**
```jsonc
// Batch 1 — correct
{ "id": "file:backend/app/api/audit.py" }

// Batch 4 — project name prefixed
{ "id": "noora-health-res-cms:backend/main.py"...