[WIP] Update chapter generation defaults for scene strategy and emotion polish

[Copilot]

Thanks for asking me to work on this. I will get started on it and keep this PR's description up to date as I form a plan and make progress.

Original prompt

Update chapter generation defaults to use scene-chunked strategy with randomized scene count per chapter and a polish pass that enhances emotion.

Repo: crazyrob425/KDP-E-Book-Generator (ref main)

Requirements:

1. Default chapter generation strategy = chunked scenes.
2. Scene count per chapter should be randomized between 11 and 14 (inclusive) to avoid cookie-cutter structure while remaining controllable/reproducible.
   • Add a deterministic seeded RNG option so reruns with same seed produce same scene count.
   • If seed not provided, derive from projectId/chapter number/time as appropriate.
3. Scene plan step should produce JSON with scene fields and include per-scene word/token budgets.
4. Scene drafting should use rolling micro-summaries to keep context small and continuity strong.
5. Add final polish step that enhances emotion (<= 5–8% expansion cap), improves flow, and removes repetition without changing plot facts.
6. Add UI setting(s):
   • Toggle: Chunked vs single-pass (default chunked)
   • Slider/select: scene count range min/max (default 11–14)
   • Toggle: emotional polish (default ON)
7. Add token telemetry updates to reflect chunked generation (per scene + polish), and track cache hits.
8. Ensure these defaults are persisted in project state (IndexedDB) and migrated safely for existing saved projects.

Acceptance:

• New projects default to chunked + 11–14 randomized scenes + emotional polish.
• Existing projects load without errors; if settings missing, defaults apply.
• Generation uses scene planner + per-scene writer + polish pass with cap.

The following is the prior conversation context from the user's chat exploration (may be truncated):

User: analyze the codes line by line and create a detailed blueprint and todo

Assistant: Below is a codebase analysis + blueprint + TODO plan for crazyrob425/KDP-E-Book-Generator based on the files I could pull from the repo (root, services/, server/, electron/, hooks/, plus directory listings under components/). Where I say “line-by-line”, I’m going file-by-file and section-by-section (the repo has a very large App.tsx, so I’m describing it in contiguous “blocks” of lines / responsibilities rather than literally enumerating 45k lines one by one).

---

0) High-level: what this repo currently is

Current architecture (as implemented):

• React + Vite + TypeScript frontend (mostly driven by a single massive App.tsx orchestrator).
• AI generation via Google Gemini (client-side calls through @google/genai) in services/geminiService.ts.
• Local persistence:
  • “V5 DB” using IndexedDB wrapper in services/storageService.ts.
  • Extra “AutoSave” feature saving a JSON file via Electron IPC if running as desktop (hooks/useAutoSave.ts).
• Electron wrapper:
  • electron/main.ts sets up a frameless window + IPC handlers.
  • Bridges to “bot automation” and “market research workers”.
• Optional Node server:
  • server/server.ts provides WebSocket-based automation sessions.
  • server/automation-worker.ts Playwright automation for KDP upload flow (with CAPTCHA yield/continue).
  • server/market-research-worker.ts fetches Google Trends + scrapes Amazon results + Amazon suggest.

Big gaps (blocking “Binary Books E‑Crafter” spec):

• EPUB generation is currently stubbed/disabled (services/epubGenerator.ts returns a plain text Blob).
• The “multi-agent swarm”, lore engine, continuity, long-form pipeline, and robust formatting checks are not implemented yet (only single-pass prompts exist).
• Scraping/automation will be fragile and has compliance/risk concerns (Amazon ToS, bot detection, CAPTCHA handling, account lock risk).

---

1) Repository map (what’s here)

Root

• App.tsx (very large): main UI, state machine, orchestration of steps, saving, generation triggers.
• index.tsx, index.html: Vite/React entry.
• types.ts: shared types (MarketReport, BookOutline, Chapter, KDP marketing, Electron API, etc.), includes expansion types for “Universe/Lore”.
• README.md: describes product as “FraudRob’s AI Book Factory”.

services/

• geminiService.ts: main AI calls (genres, topics, market report, outline, chapter content, rewrite, image prompts, image generation, cover generation, example cover).
• realMarketService.ts: (listed; not pulled content in the same batch) likely calls into Electron/Server for “real” market data.
• storageService.ts: IndexedDB wrapper for saving/loading state + persistent storage/quota helpers.
• epubGenerator.ts: markdown→HTML helper + EPUB generation stub (disabled).
• audioService.ts: (listed) audiobook/tts related.
• thirdPartyServices.ts: (listed) small integration config.
• kdpAutomationService.ts: (listed) tiny placeholder file (52 bytes).

electron/

• main.ts: creates BrowserWindow; IPC: window controls, automation start/stop/captcha, market research calls, save/load file dialogs.
• preload.ts: (liste...

This pull request was created from Copilot chat.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.