fix: Add structured output fallback for non-Claude models in app spec generation

This fixes the app spec generation failing for non-Claude models (Cursor, Gemini,
OpenCode, Copilot) that don't support structured output capabilities.

Changes:
- Add `supportsStructuredOutput()` utility function in @automaker/types to
  centralize model capability detection
- Update generate-features-from-spec.ts:
  - Add explicit JSON instructions for non-Claude/Codex models
  - Define featuresOutputSchema for structured output
  - Pre-extract JSON from text responses using extractJsonWithArray
  - Handle both structured_output and text responses properly
- Update generate-spec.ts:
  - Replace isCursorModel with supportsStructuredOutput for consistency
- Update sync-spec.ts:
  - Add techStackOutputSchema for structured output
  - Add JSON extraction fallback for text responses
  - Handle both structured_output and text parsing
- Update validate-issue.ts:
  - Use supportsStructuredOutput for cleaner capability detection

The fix follows the same pattern used in generate-spec.ts where non-Claude models
receive explicit JSON formatting instructions in the prompt and responses are
parsed using extractJson utilities.

Fixes #669

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

apps/server/src/routes/github/routes/validate-issue.ts

@@ -23,6 +23,7 @@ import {
   isCodexModel,
   isCursorModel,
   isOpencodeModel,
+  supportsStructuredOutput,
 } from '@automaker/types';
 import { resolvePhaseModel } from '@automaker/model-resolver';
 import { extractJson } from '../../../lib/json-extractor.js';
@@ -124,8 +125,9 @@ async function runValidation(
     const prompts = await getPromptCustomization(settingsService, '[ValidateIssue]');
     const issueValidationSystemPrompt = prompts.issueValidation.systemPrompt;
 
-    // Determine if we should use structured output (Claude/Codex support it, Cursor/OpenCode don't)
-    const useStructuredOutput = isClaudeModel(model) || isCodexModel(model);
+    // Determine if we should use structured output based on model type
+    // Claude and Codex support it; Cursor, Gemini, OpenCode, Copilot don't
+    const useStructuredOutput = supportsStructuredOutput(model);
 
     // Build the final prompt - for Cursor, include system prompt and JSON schema instructions
     let finalPrompt = basePrompt;