feat: add phase 3 prompt customization backend

- parse prompt model and argument-hint metadata and persist model on prompt invocations
- expand markdown-linked file context in scanned prompt and instruction bodies
- discover .claude/rules instructions and support Claude-style paths metadata
- discover customization roots up to the nearest parent repository and watch them for changes
- apply per-turn prompt model overrides before sidecar execution

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

tests/shared/models.test.ts

@@ -4,6 +4,7 @@ import type { SidecarModelCapability } from '@shared/contracts/sidecar';
 import {
   buildAvailableModelCatalog,
   findModel,
+  findModelByReference,
   normalizePatternModels,
   resolveReasoningEffort,
 } from '@shared/domain/models';
@@ -62,6 +63,13 @@ describe('dynamic model catalog', () => {
     expect(resolveReasoningEffort(model, 'high')).toBeUndefined();
   });
 
+  test('resolves model references by id or display name', () => {
+    const catalog = buildAvailableModelCatalog(availableModels);
+
+    expect(findModelByReference('gpt-5.4', catalog)?.id).toBe('gpt-5.4');
+    expect(findModelByReference('Claude Sonnet 4.5', catalog)?.id).toBe('claude-sonnet-4.5');
+  });
+
   test('normalizes pattern agents before runtime execution', () => {
     const normalized = normalizePatternModels(
       createPattern(),