feat: add v0.3 normalised comparison reasoning

Add explicit reasoning guidance for normalising counts by exposure/denominator,
distinguishing total count from rate, and avoiding correlation-as-causation errors.

Changes:
- prompts/reconstruct-v0.3.md: new prompt with normalisation discipline
- lib/reconstruction/prompt.js: v0.3 loader + env var override support
- lib/analysis.js: defer DEFAULT_PROMPT_VERSION to prompt module (defaults to v0.3)
- PROMPT_VERSIONS extended to [v0.1, v0.2, v0.3]
- tests/v03-reasoning.test.js: 34 focused tests covering prompt loading, schema validation, guidance completeness, and target scenario fixture
- playwright.config.js + tests/smoke.test.js: minimal UI smoke test for browser rendering
- package.json: add @playwright/test as devDependency

Default switches to v0.3; v0.2 selectable via promptVersion or RECONSTRUCTION_PROMPT_VERSION env var.

lib/analysis.js

@@ -5,14 +5,13 @@
 
 import { getConfig } from "../lib/config.js";
 import { getProvider } from "../lib/llm/provider.js";
-import { buildPrompt, PROMPT_VERSIONS } from "../lib/reconstruction/prompt.js";
+import { buildPrompt, PROMPT_VERSIONS, DEFAULT_PROMPT_VERSION } from "../lib/reconstruction/prompt.js";
 import {
   reconstructionV2Schema,
   reconstructionSchema as reconstructionV1Schema,
 } from "../lib/reconstruction/schema.js";
 
 const MAX_SCENARIO_LENGTH = 10000;
-const DEFAULT_PROMPT_VERSION = "v0.2";
 
 /**
  * Analyse a scenario string through the full pipeline.