mrhavens
0b8bf3123a
feat: Issue #19 - Taxonomy Integration in Orchestrator
...
- Added imports for nonfiction taxonomy (PurposeClassifier, ReaderPurpose, etc.)
- Modified OpusOrchestrator.__init__ to accept purpose and category params
- Added _classify_purpose_from_intent() - classifies purpose from intent
- Added _select_nonfiction_framework() - selects framework based on purpose
- Added get_framework_context() - returns framework info for agents
- Added generate_stage_outline() - generates outlines from framework stages
New params:
- purpose: Optional reader purpose (learn, understand, transform, decide, reference, inspire)
- category: Optional nonfiction category (business, self_help, memoir, etc.)
The orchestrator now:
1. Classifies purpose from book intent using keyword classifier
2. Selects appropriate framework from taxonomy based on purpose
3. Generates stage scaffolding from framework definition
4. Provides framework context to agents
This is the core integration (Issue #19 ).
2026-03-13 20:32:48 +00:00
mrhavens
8e92e99205
Fix: Remove hardcoded paths - now fully standalone
...
- Changed all load_dotenv() calls to use relative path (just load_dotenv())
- No OpenClaw dependencies
- Works anywhere after pip install
2026-03-13 04:34:22 +00:00
mrhavens
607719b3b2
Fix: Add ingest_from_github method to OpusOrchestrator
...
- Wire GitHubIngestor into the orchestrator
- Test: successfully ingested 251k chars from The-Last-Love-Story repo
- Also verified: run_opus generates 1k+ word stories with AutoGen critique
2026-03-13 02:42:00 +00:00
mrhavens
9eee1ac1e7
Add GitHub ingestion - pull content from repos as source material
...
- GitHubIngestor class to fetch repo contents
- Support for .md, .txt, .notes, .draft files
- Method to ingest from GitHub directly into orchestrator
- Export GitHubIngestor in __init__.py
Usage:
orch = OpusOrchestrator(book_type='fiction', genre='memoir')
content = await orch.ingest_from_github('mrhavens/my-notes')
await orch.run()
2026-03-13 00:40:47 +00:00
mrhavens
265b8934a0
Add multiple story frameworks
...
- Snowflake Method (already had)
- Three-Act Structure
- Save the Cat (Blake Snyder)
- Hero's Journey (Joseph Campbell)
- Story Circle (Dan Harmon)
- The 7-Point Plot (The Pantone)
- Fichtean Curve
Pass framework='hero-journey' or 'save-the-cat' etc. to use.
2026-03-12 19:52:47 +00:00
mrhavens
fe1e001878
Implement full Snowflake Method pipeline
...
- Stage 1: One sentence summary
- Stage 2: One paragraph outline
- Stage 3: Character sheets
- Stage 4: Four-page outline
- Stage 5: Detailed character charts
- Stage 6: Scene list
- Stage 7: Scene descriptions
- Then: Style guide → Write chapters → Critique → Compile
Full pre-writing workflow now wired up.
2026-03-12 19:36:25 +00:00
mrhavens
dec5aae09a
Wire up all agents with LLM calls
...
- Worldsmith, Character Lead, Voice, Editor agents now call LLM
- All nonfiction agents wired (Researcher, Analyst, Writer, FactChecker, Editor)
- Orchestrator fully wired with agent pipeline
- Add python-dotenv dependency
2026-03-12 18:42:15 +00:00
mrhavens
40378ad65e
Initial commit: Opus Orchestrator AI - Full-flow book generation
...
- LangGraph workflow orchestration
- CrewAI agent crews (Fiction Fortress & Nonfiction Fortress)
- PydanticAI schema validation
- Fiction agents: Architect, Worldsmith, Character Lead, Voice, Editor
- Nonfiction agents: Researcher, Analyst, Writer, Fact-Checker, Editor
- Complete schema definitions for books, chapters, critiques
- Configuration management
- Basic test suite
2026-03-12 17:45:05 +00:00
mrhavens