[WIP] Update default chapter generation to use scene-chunked strategy

[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

User preference confirmed: default chapter generation should use scene-chunked generation to minimize token waste.

Update the existing PR changes to:

• Set scene-chunked generation as the default strategy for chapter generation.
• Implement chunk planner + rolling micro-summary mechanism.
• Ensure orchestration budgets and telemetry reflect chunked strategy.
• Expose a UI setting to toggle between single-pass and chunked generation, defaulting to chunked.

Repository context: crazyrob425/KDP-E-Book-Generator.

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: (listed; not pulled here) likely exposes window.electronAPI.

server/

• server.ts: Express + HTTP + WebSocket server that runs Playwright automation via async generator.
• automation-worker.ts: Playwright flow for KDP login → new ebook → upload manuscript/cover → publish; yields CAPTCHA events.
• market-research-worker.ts: Google Trends via google-trends-api, Amazon scrape via Playwright, Amazon suggest via public endpoint.
• README.md: server instructions.
• Dockerfile: empty.

hooks/

• useAutoSave.ts: interval-based autosave to a JSON file through Electron.

components/

• Many UI components/steps exist, including steps flow and “ExpansionHub” directories (not pulled contents here).

---

2) “Line-by-line” analysis (by file & functional blocks)

2.1 types.ts (core domain model)

What it defines:

• Market research types
  • GoogleTrendsData: interestOverTime[], relatedQueries[]
  • MarketReport: trendAnalysis, targetAudience{...}, keywords[], suggestedBookTypes[], competitorAnalysis[], optional ...

This pull request was created from Copilot chat.

---

⌨️ Start Copilot coding agent tasks without leaving your editor — available in VS Code, Visual Studio, JetBrains IDEs and Eclipse.