feat: Implement ai_blueprint_v2.md — Exp 5, 6 & 7 (persona validation, mid-gen consistency, two-pass drafting)

Exp 6 — Iterative Persona Validation (story/style_persona.py + cli/engine.py):
- Added validate_persona(): generates ~200-word sample in persona voice, scores 1–10 via
  lightweight voice-quality prompt; accepts if ≥ 7/10
- cli/engine.py retries create_initial_persona() up to 3× until validation passes
- Expected: -20% Phase 3 voice-drift rewrites

Exp 5 — Mid-gen Consistency Snapshots (cli/engine.py):
- analyze_consistency() called every 10 chapters inside the writing loop
- Issues logged as ⚠️ warnings; non-blocking; score and summary emitted
- Expected: -30% post-generation continuity error rate

Exp 7 — Two-Pass Drafting (story/writer.py):
- After Flash rough draft, Pro model (model_logic) polishes prose against a strict
  checklist: filter words, deep POV, active voice, AI-isms, chapter hook
- max_attempts reduced 3 → 2 since polished prose needs fewer rewrite cycles
- Expected: +0.3 HQS with no increase in per-chapter cost

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

story/writer.py

@@ -362,7 +362,51 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None,
         utils.log("WRITER", f"⚠️ Failed Ch {chap['chapter_number']}: {e}")
         return f"## Chapter {chap['chapter_number']} Failed\n\nError: {e}"
 
-    max_attempts = 3
+    # Exp 7: Two-Pass Drafting — Polish the rough draft with the logic (Pro) model
+    # before evaluation. Produces cleaner prose with fewer rewrite cycles.
+    if current_text:
+        utils.log("WRITER", f"  -> Two-pass polish (Pro model)...")
+        guidelines = get_style_guidelines()
+        fw_list = '", "'.join(guidelines['filter_words'])
+        polish_prompt = f"""
+        ROLE: Senior Fiction Editor
+        TASK: Polish this rough draft into publication-ready prose.
+
+        AUTHOR_VOICE:
+        {persona_info}
+
+        GENRE: {genre}
+        TARGET_WORDS: ~{est_words}
+        BEATS (must all be covered): {json.dumps(chap.get('beats', []))}
+
+        POLISH_CHECKLIST:
+        1. FILTER_REMOVAL: Remove all filter words [{fw_list}] — rewrite each to show the sensation directly.
+        2. DEEP_POV: Ensure the reader is inside the POV character's experience at all times — no external narration.
+        3. ACTIVE_VOICE: Replace all 'was/were + -ing' constructions with active alternatives.
+        4. SENTENCE_VARIETY: No two consecutive sentences starting with the same word. Vary length for rhythm.
+        5. STRONG_VERBS: Delete adverbs; replace with precise verbs.
+        6. NO_AI_ISMS: Remove: 'testament to', 'tapestry', 'palpable tension', 'azure', 'cerulean', 'bustling', 'a sense of'.
+        7. CHAPTER_HOOK: Ensure the final paragraph ends on unresolved tension, a question, or a threat.
+        8. PRESERVE: Keep all narrative beats, approximate word count (±15%), and chapter header.
+
+        ROUGH_DRAFT:
+        {current_text}
+
+        OUTPUT: Complete polished chapter in Markdown.
+        """
+        try:
+            resp_polish = ai_models.model_logic.generate_content(polish_prompt)
+            utils.log_usage(folder, ai_models.model_logic.name, resp_polish.usage_metadata)
+            polished = resp_polish.text
+            if polished:
+                polished_words = len(polished.split())
+                utils.log("WRITER", f"  -> Polished: {polished_words:,} words.")
+                current_text = polished
+        except Exception as e:
+            utils.log("WRITER", f"  -> Polish pass failed: {e}. Proceeding with raw draft.")
+
+    # Reduced from 3 → 2 attempts since polish pass already refines prose before evaluation
+    max_attempts = 2
     SCORE_AUTO_ACCEPT = 8
     # Adaptive passing threshold: lenient for early setup chapters, strict for climax/resolution.
     # chapter_position=0.0 → setup (SCORE_PASSING=6.5), chapter_position=1.0 → climax (7.5)