mrhavens
d3bc43daca
feat: Issue #21 - Purpose-Based Critique Criteria
...
Created critique_criteria.py with purpose-specific evaluation:
TUTORIAL:
- Clarity (30%), Completeness (25%), Progressiveness (20%)
- Actionability (15%), Error Prevention (10%)
EXPLAINER:
- Analogy Quality (25%), Examples (25%), Mental Model (20%)
- Depth (15%), Misconceptions (15%)
TRANSFORMATION:
- Emotional Honesty (30%), Relatability (25%), Hope (20%)
- Specificity (15%), Actionability (10%)
DECIDE:
- Evidence Quality (30%), Balance (25%), Credibility (20%)
- Clarity (15%), Completeness (10%)
REFERENCE:
- Accuracy (35%), Completeness (30%), Organization (20%)
- Examples (15%)
INSPIRED:
- Emotional Impact (30%), Vision (25%), Authenticity (25%)
- Story Quality (20%)
Each criterion has:
- Weight
- Description
- Evaluation questions
- Pass threshold
Functions:
- get_critique_criteria(purpose) → CritiqueCriteriaSet
- evaluate_chapter(content, purpose) → scores
- get_evaluation_prompt(content, purpose) → LLM prompt
- list_all_criteria() → overview
2026-03-13 22:30:26 +00:00
mrhavens
8cf833c729
feat: Content-Based Purpose Inference
...
Added content_infer.py - analyzes existing content to infer purpose:
- ContentPurposeInferer class
- Analyzes blog posts, articles, text
- Detects signals: tutorials, explainers, transformation stories, etc.
- Returns purpose, confidence, reasoning
Updated intake.py to weight all signals:
1. Explicit flags (weight: 1.0)
2. Content inference (weight: 0.4) - NEW
3. Keyword classification (weight: 0.3)
4. Conversational (weight: 0.5)
Now if you point at a blog:
- Tutorial posts → LEARN_HANDS_ON
- Explainers → UNDERSTAND
- Transformation stories → TRANSFORM
- Reviews/Comparisons → DECIDE
- Reference docs → REFERENCE
- Journey/Biography → BE_INSPIRED
2026-03-13 20:50:36 +00:00
mrhavens
b46e87ff76
feat: Nonfiction Intake System - All Three Paths
...
This commit completes Issue #18 (Purpose Classifier), adds Intake Agent
and CLI integration:
1. PURPOSE CLASSIFIER (Issue #18 - DONE earlier)
- Keyword-based classification into 6 ReaderPurposes
- LLM-enhanced classification for nuanced cases
2. INTAKE AGENT (NEW - addresses Issue #20 , #23 )
- Created opus_orchestrator/nonfiction/intake.py
- Intelligent agent that combines:
* Explicit flags (--purpose, --category)
* Keyword classification (auto-detect)
* Conversational questions (when ambiguous)
- IntakeAgent class with process() method
- determine_intake() convenience function
- get_questions() for conversational mode
- Source tracking: explicit | classifier | intake | hybrid
3. CLI INTEGRATION (Issue #23 )
- Added --purpose flag: learn, understand, transform, decide, reference, inspire
- Added --category flag: business, leadership, memoir, etc.
- Both passed to orchestrator
Usage:
# Explicit
opus generate --book-type nonfiction --purpose transform --category self_help
# Auto-classify
opus generate --book-type nonfiction --concept "How to build a startup"
# Programmatic
result = await determine_intake(
concept="Leadership for introverts",
purpose="transform", # or None for auto
category="leadership",
mode="auto" # or "conversational"
)
2026-03-13 20:46:06 +00:00
mrhavens
4b4addedf7
feat: Issue #18 - Purpose Classifier for Nonfiction
...
- Created opus_orchestrator/nonfiction/classifier.py
- PurposeClassifier class with keyword-based classification
- LLM-enhanced classification (optional)
- ReaderPurpose enum (6 purposes)
- ClassificationResult dataclass
- Keyword classification covers:
- LEARN_HANDS_ON: how to, learn to, tutorial, skills, etc.
- UNDERSTAND: understand, why, concept, mental model, etc.
- TRANSFORM: change, become, improve, habits, etc.
- DECIDE: decide, choose, compare, vs, analysis
- REFERENCE: manual, handbook, comprehensive, API
- BE_INSPIRED: inspire, story, journey, biography
- Tests pass for all 6 purposes with high confidence
This is the foundation for the entire nonfiction pipeline (Issue #18 ).
2026-03-13 20:15:20 +00:00
mrhavens