- book_chapter.yml PASS 0: Reader Knows Rule box, outline truncated at chapter_number_next,
character state priority chain (RAG first, then prev-chapter traits, not final-book state)
- drafting.yml PASS 0: same rule applied, voice-only character profiles
- chapter_pass0_bible.yml (included by scifi/ya/romance/cozy genre templates): same fix
All three reference {chapter_number_prev}, {chapter_number_next}, {chapter_ref_prev}
which are now injected by OutlineSyncService.CreateChapterTaskAsync
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Tasks fail at step 7:package when character_profiles is not in context_vars because the
spawn context check incorrectly reports {character_profiles} as an unresolved placeholder.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When writing ch-07, PASS 3 was reading character-state-ch-08 deliverables and
carrying 'Known secrets' from future chapters into the current state. Added
explicit FUTURE-CHAPTER CONTAMINATION GUARD: only use secrets from state files
whose chapter number is EARLIER than the current chapter being written.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The MANDATORY CHECK was rigidly applying DECEASED status from previous
character-state deliverables even when author_intent explicitly retconned
the character as alive. Similarly, the DEATH-FORWARD RULE had no exception
for author-directed resurrection/retcon.
Fixes:
- MANDATORY CHECK: add STEP 2 resurrection check -- if AUTHOR'S INTENT
explicitly states character is ALIVE, skip DECEASED format entirely
- DEATH-FORWARD RULE: add EXCEPTION clause -- author_intent overrides
previous state DECEASED status; prose is authoritative source of truth
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Root cause: PASS 0 loads all project deliverables including Ch1-13 drafts.
Ch 3 'adjoining quarters' scene appeared LAST in deliverables just before
the Write Chapter 8 instruction. PASS 3 was using that as 'the chapter I
just wrote' instead of the actual PASS 1 narrative.
Fix: PASS 3 hint now explicitly identifies the conversation turn structure,
anchors to Turn 2 (PASS 1 response), and adds an ANCHOR TEST that rejects
any Location from a [Chapter_N_draft.md] deliverable file.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Previous rule was hint-only and ignored by LLM deep in long context.
Now uses system: override (added to system prompt) plus hyper-explicit
step-by-step self-check targeting Kaelen by name. Dead = no Location,
no Physical, no Emotional, no Arc. Final self-check before submit.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Added DECEASED CHARACTER RULE block at top of PASS 3 hint. Dead characters
get a two-line entry (Established + Legacy), NO Location/Physical/Emotional/Arc.
Prevents the LLM from inventing living Kaelen presence in Ch 6-12 state files.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add source_step: 4 so rag_write explicitly targets PASS 3 output instead of
relying on last_text() which could fall back to the chapter document text.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Changed 'STRUCTURAL VALIDATION ONLY' → 'STRUCTURAL VALIDATION AND WORD-COUNT EXPANSION'
- Word floor check now EXPANDS (not just flags) when draft is >10% below chapter_target_words
- Added expansion rules: interiority, sensory grounding, dialogue beats, scene transitions
- Added max_tokens: 32000 and model: power to self-check step for capacity headroom
- Removed 'Expand any description or add sensory detail' from NOT ALLOWED (only applies to existing prose)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- drafting.yml: add {character_profiles} in PASS 0, PASS 3 character state
extraction, rag_write for character-state asset (enables butterfly effect
in draft mode), document for character-state file, conditional_skills
- character_sheet.yml: add rag_write step writing voice-sig-{slug} asset
so auto-import can pick up completed character sheets from RagMemory
- book_chapter.yml: package hint now detects new characters from PASS 3
Character State (spawns character_sheet tasks) and detects Permanent:YES
changes (spawns character_update tasks)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Chapter_N_draft doc step was placed after PASS 3 think, so last_text()
returned char state (3151 chars) instead of the actual chapter from SELF-CHECK.
Moved doc step to immediately after step 2 (SELF-CHECK).
New step order: 0-think, 1-think, 2-think(selfcheck), 3-doc(draft),
4-think(charstate), 5-rag_write, 6-doc(charstate), 7-package, 8-close
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- book_chapter: Remove PASS 2+3 (internal polish cycle); replace with narrow
SELF-CHECK step (structural validation only — names/POV/hook/format/word-floor).
Add anti-overpolish drafting discipline rules to PASS 1.
Add genre-aware guide-use note (apply only the guide matching {genre_name}).
Update adjudication prose_quality description to match draft-quality standard.
- chapter_polish: Convert from broad 'Rewrite the chapter' pass to bounded
editorial control pass. Explicitly forbids expansion, sensory addition,
global voice upgrades, new content. Instructs verbatim preservation of
unaffected paragraphs. Adjudication rewritten around correction fidelity
rather than 'more polished is better'. Threshold lowered from 90 to 80.
- chapter_review: Add explicit output categories — STRENGTHS TO PRESERVE,
MUST-FIX CONTINUITY, MUST-FIX CLARITY, OPTIONAL, FORBIDDEN, VERDICT.
Remove 'REWRITE' verdict option (roundtable resolves that). Remove all three
writing-craft guides (editorial tasks do not need genre writing guidance).
- chapter_roundtable: Update CONSENSUS REACHED block to MUST APPLY / OPTIONAL /
PRESERVE / VERDICT categories. Require disagreements to be resolved before
calling consensus. Remove REWRITE verdict option. Remove all writing-craft
guides. Remove 'skills' from sections. Add package hint to populate key_changes
from the full structured consensus. Update adjudication to score structured output.
- book_outline: Strengthen Voice & Tone Guide as hard operating constraints
(not aspirations); include anti-overpolish rules, rhythm rules, and voice
don'ts. Expand per-chapter outline format to include Opens-at location,
Character state, and Dominant tension. Enrich chapter task description
packets with that state data so book_chapter has richer upstream context.
- skills/skills.md: Document writing-vs-editorial guide split established in
Sprint 56. Update Used-by column. Add boundary rules section.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This change reorganizes the repository structure to keep the root directory
clean. All 15 project folders are now nested under projects/, alongside
infrastructure directories (agents/, templates/, deliverables/, rag/, skills/).
This allows the repository to grow without polluting the core service directories.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Skills guides wired (all were dead code — no templates declared skills:):
- book_chapter.yml: YAFictionGuide + RomanceFictionGuide + SciFiFictionGuide
- chapter_review.yml: same (Devon, Lane, Cora reviewers now have genre context)
- chapter_roundtable.yml: same (debate participants use genre craft knowledge)
- chapter_polish.yml: same (Iris polishes with full genre guide in context)
- short_story.yml: same
- blog_write.yml: BlogWritingGuide
- recipe_develop.yml: RecipeWritingGuide
All templates updated to include 'skills' in sections list so guides
are injected as SKILLS & GUIDES block in the prompt.
Iris RAG deduplication:
- agents/iris/rag/agent.rag.md: 15 near-identical entries -> 2 canonical
Entry 1: Bible & Continuity Check requirement
Entry 2: Editorial assignments (Devon/Lane/Cora with their roles)
13 duplicates removed
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
chapter_roundtable.yml:
- Reduce max_iterations 9 → 5 (3 rounds of 3 editors is enough; 9 was
burning credits in a retry loop after credit exhaustion)
- Add explicit 'Once any participant outputs CONSENSUS REACHED, the
debate is over' — prevents continuation into wasted rounds
planning.yml:
- Add ANTI-HALLUCINATION RULE FOR AGENTS block: explicitly names the
known ghost agents (Worldbuilder, Prose Engine, Plot Architect, etc.)
and forbids their use; maps task types to canonical CLP agents so
planning LLM has unambiguous fallback assignments
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- chapter_polish: remove sections:deliverables — chapter text already in
{chapter_text}; this caused 150KB+ prompts for late chapters (40MB logs)
- chapter_roundtable: require structured CONSENSUS REACHED block so
key_changes is always formatted as an extractable string; change
key_changes schema from list to string to match
- book_chapter: remove sections:history to reduce context; restructure
Pass 0 to plan-only (no prose output) so the chapter is only written
once in Pass 1 instead of twice; add explicit instruction in package
hint to copy full chapter_text into spawn context
- short_story: remove sections:history and sections:deliverables (standalone
task, needs neither); restructure Pass 0 to plan-only, Pass 1 to write;
add note to handle literal {genre_name} placeholders gracefully
- recipe_develop, ai_article_write, blog_write: remove sections:history
(these standalone tasks do not need full project conversation history;
deliverables kept so they can read the research/plan file)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- pass_threshold: 65→60 (reviews scoring 58-64 are high quality but barely
missing the bar; editorial reviews are inherently subjective)
- deliverable_type: coordination→editorial_review (correct semantic type)
- Improved criteria descriptions to clearly signal this is an editorial
feedback document, not a task completion report
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
With 3 agents and max_iterations=3, effective_max=max(3,3)=3, meaning
each agent speaks exactly once per roundtable — no back-and-forth.
Adjudicator correctly rejected these as incomplete (score=0-58 on
completeness/consensus_clarity/actionability).
9 iterations = 3 full rounds for 3 agents, allowing genuine debate:
Round 1: Initial assessments | Round 2: Responses | Round 3: Consensus
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Replace agent_name: Devon with agents: [Devon, Lane, Cora] so the
chapter_roundtable task has all three editors rotating in the debate.
Addresses user feedback that roundtable should not be a specific
agent - everyone in the editorial team should be drafted.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
