How it works / VERSION 6.0

How one chapter
becomes part of the book.

How material flows, how reviews shape what comes next, and how every change is approved and saved. This page walks through each part of COSMO.

01 / Components

Author, AI and tools,
each with a clear role.

The author sets the direction and makes the calls. The AI researches, drafts and revises. Local tools connect preparation, checking and saving into one workflow, and whatever is adopted is written into the book's own files.

How the parts work togetherTools and book files all stay local
Author

Creative intent · Choices · Explicit approval

Co-writing

AI assistant

  • Understands existing material and agreements
  • Researches, drafts, rereads and revises
  • Explains problems and the reasons for changes
⇄

Workflow

Writing system

  • Assembles what each chapter needs
  • Checks candidates against the current files
  • Records and saves approved changes
⇄

The book's record

Book project

  • Creative intent, setting and voice
  • Outline, chapter cards, manuscript and state
  • Setups, feedback and revision history
↳ Adopted work and records become the starting point for the next round

Every formal operation runs through novel.py. The model and the workflow are independent: another AI tool that works with local files can continue from the book's entry files and current state.

02 / Chapter loop

Every finished chapter
is where the next one starts.

Setting up a book starts with the material you already have: story direction, structure and voice are worked out and confirmed before initialization. Writing then runs in batches of three chapters by default, one at a time if you prefer, up to five. Every batch follows the same loop.

From chapter design to the permanent recordEvery round uses the current adopted material
  1. 01

    Chapter design

    Set the focus and the changes from the current outline.

  2. 02

    Reading package

    Bring in setting, voice, character state and related chapters.

  3. 03

    Draft and review

    Two passes, one revision, a full reread, then an independent review.

  4. 04

    Dry run

    List every change and check content against records.

  5. 05

    Approve and save

    Chapters and records become part of the book together.

↳ Updated state + any reviews now due → next chapter design

Candidates: try freely, discard freely

Dry runs happen on a copy of the project. A candidate that fails a check goes back for revision; you can keep adjusting or keep the original.

The book: nothing counts until you approve

Only changes you approve, and that pass the final pre-save check, are written to the book. Explorations and rejected options never count toward the manuscript, progress or character facts.

Voice samples also go through a candidate first: INIT during book setup, REVISE once the book is under way, written only after the sample analysis is complete and you approve. The two passes focus on reader momentum, then continuity and language; each batch also gets an independent review, and the whole arc is reread when it ends.

03 / Stage reviews · 6.0

The outline leads the story.
The story corrects the outline.

Reviews count chapters in finalized reading order. Chapters three, six and nine look back at recent reading experience; chapter twelve reviews the structure of the stage and includes the short review due then.

Short reviews / full reviewsShown across one twelve-chapter cycle
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05
  6. 06
  7. 07
  8. 08
  9. 09
  10. 10
  11. 11
  12. 12

Why would a reader keep going?

Short review

Setup and payoff

Are earlier expectations moving forward, or is the story setting things up again and again without a result?

Variety and pace

With a new setting, object or opponent, does the reader still get the same feeling? Do quiet or repeated moments add something new?

What happens next

Share a stage summary and hear your thoughts on direction and motivation; decide from the reading evidence what to keep or adjust, and check the effect next round.

Name the reading problem before choosing a fix. Never pile on conflict, twists or cliffhangers mechanically.

Can this stage carry a longer story?

Full review

Reread the stage

Read the clean manuscript in batches and note real reactions first, then compare against the main promise, chapter cards and earlier assessments, rather than explaining everything from the plan.

Study comparable books, if useful

Research into ranked books is optional. If you do it, pick two or three works from relevant lists and prefer three legally accessible consecutive chapters or a complete scene.

Keep or adjust

Based on the reading and your feedback, write down why the plan stays or what changes. Borrow general techniques, never specific plots or phrasing.

When research is done, record list sources, dates, works and reading scope; when it is skipped, note the reason. If access is limited, record what was actually read; no follow-up task is added automatically.

The same outline, the same workflow

Book setup uses INIT; books under way use REVISE. Agreed changes go into the original outline and related chapter cards before shaping later writing, and the scope of each chapter candidate stays unchanged.

When the manuscript changes, the review restarts

Each review records the chapter order and manuscript digest it covered. If an earlier chapter is edited or reordered, the system asks for a fresh check. Preparing a task, refreshing material or logging a deferral never counts as a completed review.

The program identifies reviews that are due and records what they covered. Waiting for your reply does not count as a conversation, and an existing reply for this round is picked up directly. Local fixes and stage-level judgments are reported separately; the quality of reading, conversation and research still needs real review.

04 / Approve and save

The version you approve
is the version that gets saved.

The system calculates a content digest for every candidate and records the state of the related files during the dry run. Everything is checked again before saving, so a draft cannot change after you approve it.

Everything matches what you approvedThe check before saving
What you approvedVersion A

The draft and scope of changes you reviewed

Candidate to saveVersion A

Same as when you approved it

Related book filesOriginal state

Same as during the dry run

Ready to save

Once the digest matches and the required checks pass, the chapters and related records are written together.

If the draft becomes version B, rerun the dry run and approve the new digest. If the related book files change, recheck against the current files, then rerun the dry run and approve.

The content digest pins down exactly what you approved. It cannot prove you read every word, and it does not replace reviewing characters, language and cause and effect.

05 / Run feedback

Every problem
leaves a complete record.

Misunderstandings, rework and workflow blockers are written up by the AI from the visible conversation and existing evidence: what happened, how it was judged, how it was handled and how it was verified.

  1. 01 / Source

    Capture concrete evidence

    Record conversation excerpts, tool output or the AI's observations, with their source and visible scope.

  2. 02 / Diagnosis

    Name the kind of problem

    Separate creative choices, execution slips, template limits and software bugs, and keep explanations that still need testing.

  3. 03 / Response

    State the fix and its reach

    Record the correction and the steps it affects; if the system is left unchanged, record why.

  4. 04 / Verification

    Keep the conclusion open to review

    Open issues carry into the next round and are checked against real revisions and reader feedback; a recurrence keeps the same number and its full history.

↳ Book issue log → General lessons → Proposed system changes → Verified in later use

Archived and backed up

Run records live in the book's append-only log and are included in backups. They never alter creative commit records and are never pasted wholesale into chapter reading packages.

Clear evidence scope; the book stays the book's

The system never scrapes all your chats or other tasks; the AI records only evidence it actually saw. When the system is updated, only reusable methods and rules are extracted.

06 / Isolation and updates

The system keeps improving.
Your book stays exactly as it is.

The downloaded folder is ready to hold one book. Keep a blank copy before you start and duplicate it for each new book, or download a fresh copy. Existing books keep their folders; before any tool update, the system checks the installation record and local changes.

Where the system ends and the book beginsShared updates go to the tools; creative material stays with the book

Clean template

Reusable methods and tools

Shared rules, blank templates, checks and programs.

Agent protocolPython toolsGenre plugins

One project per book

The book's content and history

This book's setting, manuscript, research, feedback and customizations.

Story materialChaptersBook customizations
Every sync starts by comparing against the installation record. Unknown differences or local edits stop it by default; recognized book customizations are preserved by rule, and any remaining decisions are yours to review.
What if a save is interrupted?

Before the full write is verified

The system keeps the unfinished state and blocks further writes. Only after you review the affected files and explicitly approve recovery does it roll back to the state before the save.

Verified, stopped during wrap-up

It completes the commit record and history from the point of interruption and keeps the verified content. Checking the status never triggers recovery.

When a write error can be caught, the system attempts to roll it back automatically; recovery after a forced interruption must be run explicitly, after checking the related records.

Retained candidates: the commit scene, preserved

After a chapter commit succeeds, the candidate is moved whole into a retained-candidate directory and its location is reported. Anything saved during the commit can be checked there; it never becomes the manuscript automatically and is not part of the next approved candidate.

Regular backups: the current adopted content

Candidates, retained candidates, reading packages and transaction history are excluded, so save any unused material you want to keep separately. Snapshots taken during an interrupted save are labeled separately, are not guaranteed to be consistent, and do not replace the original project's recovery records.

6.0 keeps schema 2 and the existing INIT / REVISE workflows. New books default to General mode, built around reader expectations and stage development; Progression and Conflict mode adds requirements for opponents and escalation. Cards from earlier versions keep their original meaning, and older books that never enabled the feature do not need to fill anything in. Upgrading never reopens an existing book or adopts a new story plan on its own.

07 / Limits

A workflow can be checked.
A good story still has to be read.

Technical safeguards make files, versions and records more reliable. Whether a book comes alive is still decided by real passages and the experience of reading them.

What the program checks

  • Required material, file structure and records are complete
  • The candidate digest matches what was approved
  • Related files, transactions and review coverage have not changed
  • A sync does not touch local edits

What authors, AI and readers judge

  • Whether motives and cause and effect are believable
  • Whether voice, scene and narration fit
  • Whether pace and expectation create momentum
  • Whether research and revision truly improve the book

Passing software checks means only that the corresponding workflow checks passed. Literary quality and long-term benefits to your writing need real review, reader feedback and continued use.