fix(book-pipeline): inference hints + LLM-filled context vars + roster roundtable

- book_research.yml: add inference hint when genre_name/genre_audience/research_focus are empty
- book_outline.yml: add inference hint for genre/audience; change package schema to ask LLM
  to FILL genre_name/genre_audience/prose_style/chapter_target_words from the outline text
  (was using {template_vars} which stay empty unless planning sets them)
- devon/agent.yml: add chapter_roundtable to supported_templates
- lane/agent.yml: add chapter_roundtable to supported_templates
  (all three editors now participate in roundtable — roster-driven, not hardcoded)

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

agents/devon/agent.yml

@@ -21,4 +21,5 @@ manages: []
 department: editorial
 supported_templates:
   - chapter_review
+  - chapter_roundtable
   - book_editorial

agents/lane/agent.yml

@@ -20,3 +20,4 @@ manages: []
 department: editorial
 supported_templates:
   - chapter_review
+  - chapter_roundtable

templates/book_outline.yml

@@ -30,8 +30,9 @@ steps:
     hint: |
       You are {agent.name}. This is round {task.iteration} of the creative boardroom.
 
-      GENRE: {genre_name}  |  AUDIENCE: {genre_audience}
+      GENRE: {genre_name|[infer from project description if blank]}
-      STRUCTURE GUIDE: {outline_structure}
+      AUDIENCE: {genre_audience|[infer from project description if blank]}
+      STRUCTURE GUIDE: {outline_structure|[use standard 3-act structure with chapter hooks if blank]}
 
       The room is deciding on ONE book concept to write. The trend research
       is in the DELIVERABLES and RAG above — everyone has read it.
@@ -145,15 +146,21 @@ steps:
       You are the Project Manager. The outline above describes a multi-chapter book.
       Convert EVERY chapter in the outline into a sequential create_task action for Iris.
 
+      CRITICAL — Fill in these values from the outline document you just wrote:
+        - genre_name: the exact genre (e.g., "YA Romance", "Science Fiction", "Literary Fiction")
+        - genre_audience: the target audience (e.g., "Young adults 14–18", "Adult romance readers")
+        - prose_style: copy the 3-sentence Voice & Tone Guide from the outline exactly
+        - chapter_target_words: the target word count per chapter as a number string (e.g., "3500")
+        - chapter_ref: zero-padded two-digit chapter number, e.g. "ch-01", "ch-02", ... "ch-18"
+
       Rules:
-      - One action per chapter (minimum {chapter_count} chapters)
+      - One action per chapter (minimum {chapter_count|10} chapters)
       - task_name format: "Write Chapter N: [Chapter Title]"
       - agent_name: always "Iris"
       - task_type: always "book_chapter"
       - description: Include the chapter summary, POV character, emotional beat, and cliffhanger from the outline.
         Start with: "You are writing Chapter N of [Book Title]. [chapter summary]. POV: [character name]."
       - depends_on: the exact task_name of the PREVIOUS chapter (empty string for Chapter 1)
-      - chapter_ref: zero-padded two-digit chapter number, e.g. "ch-01", "ch-02", ... "ch-18"
 
       The depends_on chain creates sequential writing — each chapter waits for the previous to be committed.
     schema:
@@ -165,10 +172,10 @@ steps:
           description: "string"
           depends_on: "string"
           context:
-            genre_name: "{genre_name}"
+            genre_name: "string"
-            genre_audience: "{genre_audience}"
+            genre_audience: "string"
-            prose_style: "{prose_style}"
+            prose_style: "string"
-            chapter_target_words: "{chapter_target_words}"
+            chapter_target_words: "string"
             chapter_ref: "string"
 
   - type: close

templates/book_research.yml

@@ -26,14 +26,17 @@ builders:
 steps:
   - type: think
     hint: |
-      You are researching the current {genre_name} fiction landscape.
+      You are researching the current fiction landscape for this book project.
 
-      TARGET AUDIENCE: {genre_audience}
+      GENRE: {genre_name|[infer from the project description above]}
-      GENRE: {genre_name}
+      TARGET AUDIENCE: {genre_audience|[infer from the project description above]}
-      RESEARCH FOCUS: {research_focus}
+      RESEARCH FOCUS: {research_focus|[infer: what trends, tropes, and reader expectations matter most for this project?]}
+
+      NOTE: If GENRE, TARGET AUDIENCE, or RESEARCH FOCUS are blank above, read the
+      PROJECT DESCRIPTION section and infer them from the project's stated goal.
 
       Your mission: identify the single best search query to find what's TRENDING RIGHT NOW
-      in {genre_name} fiction in 2025–2026.
+      in this fiction genre in 2025–2026.
 
       State your analysis, then on the last line write:
       SEARCH QUERY: [your query here]
@@ -49,7 +52,9 @@ steps:
       You have live search results above (in PRIOR RESULTS).
       If the web search results are empty or unavailable, use your expert training knowledge.
 
-      Synthesize the findings into an actionable publishing brief for a {genre_name} book:
+      Infer the GENRE and AUDIENCE from the PROJECT DESCRIPTION if not explicitly provided above.
+
+      Synthesize the findings into an actionable publishing brief for this book:
 
       1. TOP TRENDING — What sub-genres and themes are hot right now? Rank them.
       2. AUDIENCE INSIGHTS — What does the target reader ({genre_audience}) demand?