Blueprint v1.0.4: Implemented AI Context Optimization & Token Management

- core/utils.py: Added estimate_tokens(), truncate_to_tokens(), get_ai_cache(), set_ai_cache(), make_cache_key() utilities
- story/writer.py: Applied truncate_to_tokens() to prev_content (2000 tokens) and prev_sum (600 tokens) context injections
- story/editor.py: Applied truncate_to_tokens() to summary (1000t), last_chapter_text (800t), eval text (7500t), propagation contexts (2500t/3000t)
- web/routes/persona.py: Added MD5-keyed in-memory cache for persona analyze endpoint; truncated sample_text to 750 tokens
- ai/models.py: Added pre-dispatch payload size estimation with 30k-token warning threshold

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

story/editor.py

@@ -59,7 +59,7 @@ def evaluate_chapter_quality(text, chapter_title, genre, model, folder):
     }}
     """
     try:
-        response = model.generate_content([prompt, text[:30000]])
+        response = model.generate_content([prompt, utils.truncate_to_tokens(text, 7500)])
         model_name = getattr(model, 'name', ai_models.logic_model_name)
         utils.log_usage(folder, model_name, response.usage_metadata)
         data = json.loads(utils.clean_json(response.text))
@@ -86,8 +86,8 @@ def check_pacing(bp, summary, last_chapter_text, last_chapter_data, remaining_ch
     TASK: Analyze pacing.
 
     CONTEXT:
-    - PREVIOUS_SUMMARY: {summary[-3000:]}
-    - CURRENT_CHAPTER: {last_chapter_text[-2000:]}
+    - PREVIOUS_SUMMARY: {utils.truncate_to_tokens(summary, 1000)}
+    - CURRENT_CHAPTER: {utils.truncate_to_tokens(last_chapter_text, 800)}
     - UPCOMING: {json.dumps([c['title'] for c in remaining_chapters[:3]])}
     - REMAINING_COUNT: {len(remaining_chapters)}
 
@@ -254,7 +254,7 @@ def check_and_propagate(bp, manuscript, changed_chap_num, folder, change_summary
         TASK: Summarize the key events and ending state of this chapter for continuity tracking.
 
         TEXT:
-        {changed_chap.get('content', '')[:10000]}
+        {utils.truncate_to_tokens(changed_chap.get('content', ''), 2500)}
 
         FOCUS:
         - Major plot points.
@@ -350,7 +350,7 @@ def check_and_propagate(bp, manuscript, changed_chap_num, folder, change_summary
         CHANGE_SUMMARY: {current_context}
 
         CHAPTER_TO_CHECK (Ch {target_chap['num']}):
-        {target_chap['content'][:12000]}
+        {utils.truncate_to_tokens(target_chap['content'], 3000)}
 
         DECISION_LOGIC:
         - If the chapter directly contradicts the change (references dead characters, items that no longer exist, events that didn't happen), status = REWRITE.

story/writer.py

@@ -71,7 +71,7 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None,
 
     prev_context_block = ""
     if prev_content:
-        trunc_content = prev_content[-3000:] if len(prev_content) > 3000 else prev_content
+        trunc_content = utils.truncate_to_tokens(prev_content, 2000)
         prev_context_block = f"\nPREVIOUS CHAPTER TEXT (For Tone & Continuity):\n{trunc_content}\n"
 
     chars_for_writer = [
@@ -238,7 +238,7 @@ def write_chapter(chap, bp, folder, prev_sum, tracking=None, prev_content=None,
         HARD_CONSTRAINTS:
         - TARGET_WORDS: ~{est_words} words (aim for this; ±20% is acceptable if the scene genuinely demands it — but do not condense beats to save space)
         - BEATS MUST BE COVERED: {json.dumps(chap.get('beats', []))}
-        - SUMMARY CONTEXT: {prev_sum[:1500]}
+        - SUMMARY CONTEXT: {utils.truncate_to_tokens(prev_sum, 600)}
 
         AUTHOR_VOICE:
         {persona_info}