empathy-framework 3.7.0__py3-none-any.whl → 3.8.0__py3-none-any.whl

coach_wizards/code_reviewer_README.md

@@ -0,0 +1,60 @@
+# Code Reviewer Wizard
+
+**Domain:** software
+**Type:** Wizard
+**Generated:** Pattern-Compose Methodology
+
+## Overview
+
+Auto-generated wizard using proven patterns from the Empathy Framework.
+
+## Patterns Used
+
+- **Empathy Level**: 0-4 empathy level configuration
+- **User Guidance**: Help text, examples, and prompts
+- **Code Analysis Input**: Standard code analysis input (code, file_path, language)
+- **Risk Assessment**: Level 4 Anticipatory risk analysis
+- **Prediction**: Level 4 Anticipatory prediction of future issues
+- **Config Validation**: Validate wizard configuration on initialization
+
+## Usage
+
+```python
+from coach_wizards.code_reviewer_wizard import CodeReviewerWizard
+
+wizard = CodeReviewerWizard()
+result = await wizard.process(user_input="...")
+```
+
+## API Endpoints
+
+```bash
+# Process with wizard
+POST /api/wizard/code_reviewer/process
+{
+  "input": "your input here",
+  "context": {}
+}
+```
+
+## Testing
+
+```bash
+# Run unit tests
+pytest tests/unit/wizards/test_code_reviewer_wizard.py
+
+# Run with coverage
+pytest tests/unit/wizards/test_code_reviewer_wizard.py --cov
+```
+
+## Next Steps
+
+1. Customize wizard logic as needed
+2. Add domain-specific validation
+3. Extend with additional features
+4. Update tests for custom logic
+
+---
+
+**Generated by:** Empathy Framework - Wizard Factory
+**Methodology:** Pattern-Compose

coach_wizards/code_reviewer_wizard.py

@@ -0,0 +1,180 @@
+"""Code reviewer Coach Wizard.
+
+Auto-generated by Empathy Framework Scaffolding
+Methodology: pattern-compose
+Domain: software
+Patterns: empathy_level, user_guidance, code_analysis_input, risk_assessment, prediction, config_validation
+Generated: 2026-01-05T20:15:45.111917
+"""
+
+import logging
+from typing import Any
+
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel, Field
+
+from patterns import get_pattern_registry
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/code_reviewer", tags=["code_reviewer"])
+
+# Pattern registry for recommendations
+registry = get_pattern_registry()
+
+
+# Request/Response Models
+class AnalysisRequest(BaseModel):
+    """Request to analyze code."""
+
+    code: str = Field(..., description="Code to analyze")
+    context: dict[str, Any] = Field(default_factory=dict, description="Additional context")
+    include_risk_assessment: bool = Field(default=True, description="Include risk analysis")
+
+
+class AnalysisResult(BaseModel):
+    """Analysis result."""
+
+    wizard_id: str
+    analysis: dict[str, Any]
+    risk_assessment: dict[str, Any] | None = None
+    predictions: list[dict[str, Any]] = Field(default_factory=list)
+
+
+# In-memory session storage (replace with Redis in production)
+sessions: dict[str, dict[str, Any]] = {}
+
+
+@router.post("/analyze", response_model=AnalysisResult)
+async def analyze_code(request: AnalysisRequest) -> AnalysisResult:
+    """Analyze code and provide recommendations.
+
+    Args:
+        request: Analysis request with code and context
+
+    Returns:
+        Analysis results with recommendations
+
+    Raises:
+        HTTPException: If analysis fails
+    """
+    try:
+        # Create session
+        wizard_id = f"code_reviewer_{len(sessions) + 1}"
+
+        # Perform code analysis
+        analysis = await _analyze_code(request.code, request.context)
+
+        result = AnalysisResult(
+            wizard_id=wizard_id,
+            analysis=analysis,
+        )
+
+        # Perform risk assessment
+        if request.include_risk_assessment:
+            risk_assessment = await _assess_risk(analysis)
+            result.risk_assessment = risk_assessment
+
+        # Generate predictions
+        predictions = await _generate_predictions(analysis)
+        result.predictions = predictions
+
+        # Store session
+        sessions[wizard_id] = {
+            "wizard_id": wizard_id,
+            "code": request.code,
+            "analysis": analysis,
+            "result": result.model_dump(),
+        }
+
+        logger.info(f"Analysis complete for {wizard_id}")
+        return result
+
+    except Exception as e:
+        logger.exception(f"Analysis failed: {e}")
+        raise HTTPException(status_code=500, detail=f"Analysis failed: {str(e)}")
+
+
+@router.get("/{wizard_id}/report", response_model=dict[str, Any])
+async def get_report(wizard_id: str) -> dict[str, Any]:
+    """Get analysis report.
+
+    Args:
+        wizard_id: Wizard session ID
+
+    Returns:
+        Complete analysis report
+
+    Raises:
+        HTTPException: If session not found
+    """
+    if wizard_id not in sessions:
+        raise HTTPException(status_code=404, detail="Session not found")
+
+    session = sessions[wizard_id]
+    return {
+        "wizard_id": wizard_id,
+        "analysis": session["analysis"],
+        "result": session["result"],
+    }
+
+
+# Helper functions
+async def _analyze_code(code: str, context: dict[str, Any]) -> dict[str, Any]:
+    """Analyze code (placeholder - implement actual analysis).
+
+    Args:
+        code: Code to analyze
+        context: Additional context
+
+    Returns:
+        Analysis results
+    """
+    # TODO: Implement actual code analysis
+    return {
+        "lines_of_code": len(code.split("\n")),
+        "complexity": "medium",
+        "issues_found": 0,
+        "context": context,
+    }
+
+
+async def _assess_risk(analysis: dict[str, Any]) -> dict[str, Any]:
+    """Assess risk based on analysis.
+
+    Args:
+        analysis: Code analysis results
+
+    Returns:
+        Risk assessment
+    """
+    # TODO: Implement actual risk assessment
+    return {
+        "alert_level": "LOW",
+        "risk_score": 0.2,
+        "by_risk_level": {
+            "critical": 0,
+            "high": 0,
+            "medium": 0,
+            "low": 0,
+        },
+    }
+
+
+async def _generate_predictions(analysis: dict[str, Any]) -> list[dict[str, Any]]:
+    """Generate predictions about future issues.
+
+    Args:
+        analysis: Code analysis results
+
+    Returns:
+        List of predictions
+    """
+    # TODO: Implement actual predictions
+    return [
+        {
+            "type": "performance",
+            "confidence": 0.8,
+            "description": "May experience performance issues with large datasets",
+        }
+    ]

{empathy_framework-3.7.0.dist-info → empathy_framework-3.8.0.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: empathy-framework
-Version: 3.7.0
-Summary: AI collaboration framework with persistent memory, anticipatory intelligence, code inspection, and multi-agent orchestration
+Version: 3.8.0
+Summary: AI collaboration framework with intelligent caching (up to 57% cache hit rate), tier routing (34-86% cost savings depending on task complexity), XML-enhanced prompts, persistent memory, CrewAI integration, and multi-agent orchestration. Includes HIPAA-compliant healthcare wizards.
 Author-email: Patrick Roebuck <admin@smartaimemory.com>
 Maintainer-email: Smart-AI-Memory <admin@smartaimemory.com>
 License: # Fair Source License, version 0.9
@@ -174,6 +174,11 @@ Requires-Dist: structlog<25.0.0,>=23.0.0
 Requires-Dist: defusedxml<1.0.0,>=0.7.0
 Requires-Dist: rich<14.0.0,>=13.0.0
 Requires-Dist: typer<1.0.0,>=0.9.0
+Requires-Dist: pyyaml<7.0,>=6.0
+Requires-Dist: anthropic<1.0.0,>=0.25.0
+Requires-Dist: crewai<1.0.0,>=0.1.0
+Requires-Dist: langchain<1.0.0,>=0.1.0
+Requires-Dist: langchain-core<1.0.0,>=0.1.0
 Provides-Extra: anthropic
 Requires-Dist: anthropic<1.0.0,>=0.25.0; extra == "anthropic"
 Provides-Extra: openai
@@ -195,6 +200,10 @@ Requires-Dist: langgraph-checkpoint<4.0.0,>=3.0.0; extra == "agents"
 Requires-Dist: marshmallow<5.0.0,>=4.1.2; extra == "agents"
 Provides-Extra: crewai
 Requires-Dist: crewai<1.0.0,>=0.1.0; extra == "crewai"
+Provides-Extra: cache
+Requires-Dist: sentence-transformers<4.0.0,>=2.0.0; extra == "cache"
+Requires-Dist: torch<3.0.0,>=2.0.0; extra == "cache"
+Requires-Dist: numpy<3.0.0,>=1.24.0; extra == "cache"
 Provides-Extra: healthcare
 Requires-Dist: anthropic<1.0.0,>=0.25.0; extra == "healthcare"
 Requires-Dist: openai<2.0.0,>=1.12.0; extra == "healthcare"
@@ -213,6 +222,9 @@ Requires-Dist: uvicorn<1.0.0,>=0.20.0; extra == "healthcare"
 Requires-Dist: starlette<1.0.0,>=0.40.0; extra == "healthcare"
 Requires-Dist: bcrypt<5.0.0,>=4.0.0; extra == "healthcare"
 Requires-Dist: PyJWT[crypto]>=2.8.0; extra == "healthcare"
+Requires-Dist: opentelemetry-api<2.0.0,>=1.20.0; extra == "healthcare"
+Requires-Dist: opentelemetry-sdk<2.0.0,>=1.20.0; extra == "healthcare"
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc<2.0.0,>=1.20.0; extra == "healthcare"
 Requires-Dist: redis<6.0.0,>=5.0.0; extra == "healthcare"
 Provides-Extra: software
 Requires-Dist: python-docx<1.0.0,>=0.8.11; extra == "software"
@@ -228,6 +240,10 @@ Requires-Dist: pygls<2.0.0,>=1.0.0; extra == "lsp"
 Requires-Dist: lsprotocol<2024.0.0,>=2023.0.0; extra == "lsp"
 Provides-Extra: windows
 Requires-Dist: colorama<1.0.0,>=0.4.6; extra == "windows"
+Provides-Extra: otel
+Requires-Dist: opentelemetry-api<2.0.0,>=1.20.0; extra == "otel"
+Requires-Dist: opentelemetry-sdk<2.0.0,>=1.20.0; extra == "otel"
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc<2.0.0,>=1.20.0; extra == "otel"
 Provides-Extra: docs
 Requires-Dist: mkdocs<2.0.0,>=1.5.0; extra == "docs"
 Requires-Dist: mkdocs-material<10.0.0,>=9.4.0; extra == "docs"
@@ -277,6 +293,9 @@ Requires-Dist: uvicorn<1.0.0,>=0.20.0; extra == "enterprise"
 Requires-Dist: starlette<1.0.0,>=0.40.0; extra == "enterprise"
 Requires-Dist: bcrypt<5.0.0,>=4.0.0; extra == "enterprise"
 Requires-Dist: PyJWT[crypto]>=2.8.0; extra == "enterprise"
+Requires-Dist: opentelemetry-api<2.0.0,>=1.20.0; extra == "enterprise"
+Requires-Dist: opentelemetry-sdk<2.0.0,>=1.20.0; extra == "enterprise"
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc<2.0.0,>=1.20.0; extra == "enterprise"
 Provides-Extra: full
 Requires-Dist: anthropic<1.0.0,>=0.25.0; extra == "full"
 Requires-Dist: openai<2.0.0,>=1.12.0; extra == "full"
@@ -311,6 +330,9 @@ Requires-Dist: PyJWT[crypto]>=2.8.0; extra == "all"
 Requires-Dist: pygls<2.0.0,>=1.0.0; extra == "all"
 Requires-Dist: lsprotocol<2024.0.0,>=2023.0.0; extra == "all"
 Requires-Dist: colorama<1.0.0,>=0.4.6; extra == "all"
+Requires-Dist: opentelemetry-api<2.0.0,>=1.20.0; extra == "all"
+Requires-Dist: opentelemetry-sdk<2.0.0,>=1.20.0; extra == "all"
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc<2.0.0,>=1.20.0; extra == "all"
 Requires-Dist: mkdocs<2.0.0,>=1.5.0; extra == "all"
 Requires-Dist: mkdocs-material<10.0.0,>=9.4.0; extra == "all"
 Requires-Dist: mkdocstrings[python]<1.0.0,>=0.24.0; extra == "all"
@@ -503,9 +525,11 @@ See ESLintParser, PylintParser, or MyPyParser for examples.
 ### Previous (v3.0.x)
 
 - **Multi-Model Provider System** — Anthropic, OpenAI, Google Gemini, Ollama, or Hybrid mode
-- **80-96% Cost Savings** — Smart tier routing: cheap models detect, best models decide
+- **34-86% Cost Savings** — Smart tier routing varies by role: architects 34%, senior devs 65%, junior devs 86%*
 - **VSCode Dashboard** — 10 integrated workflows with input history persistence
 
+*See [Cost Savings Analysis](docs/cost-analysis/COST_SAVINGS_BY_ROLE_AND_PROVIDER.md) for your specific use case
+
 ---
 
 ## Quick Start (2 Minutes)
@@ -579,12 +603,106 @@ print(result.prevention_steps)    # How to prevent it
 | **Predicts future issues** | 30-90 days ahead | No | No |
 | **Persistent memory** | Redis + patterns | No | No |
 | **Multi-provider support** | Claude, GPT-4, Gemini, Ollama | N/A | GPT only |
-| **Cost optimization** | 80-96% savings | N/A | No |
+| **Cost optimization** | 34-86% savings* | N/A | No |
 | **Your data stays local** | Yes | Cloud | Cloud |
 | **Free for small teams** | ≤5 employees | No | No |
 
 ---
 
+## What's New in v3.8.0
+
+### 🚀 **Intelligent Response Caching: Benchmarked Performance**
+
+**Stop paying full price for repeated LLM calls. Measured results: up to 99.8% faster, 40% cost reduction on test generation, 57% cache hit rate on security audits.**
+
+#### Hybrid Cache: Hash + Semantic Matching
+
+```python
+from empathy_os.workflows import SecurityAuditWorkflow
+
+# That's it - caching auto-configured!
+workflow = SecurityAuditWorkflow(enable_cache=True)
+result = await workflow.execute(target_path="./src")
+
+# Check savings
+print(f"Cost: ${result.cost_report.total_cost:.4f}")
+print(f"Cache hit rate: {result.cost_report.cache_hit_rate:.1f}%")
+print(f"Savings: ${result.cost_report.savings_from_cache:.4f}")
+```
+
+**Real Results** (v3.8.0 benchmark - see [CACHING_BENCHMARK_REPORT.md](CACHING_BENCHMARK_REPORT.md)):
+
+- **Hash-only cache**: 30.3% average hit rate across 12 workflows, up to 99.8% faster (code review: 17.8s → 0.03s)
+- **Hybrid cache**: Up to 57% hit rate on similar prompts (security audit - benchmarked)
+- **Cost reduction**: 40% on test-generation workflow (measured)
+
+#### Two Cache Strategies
+
+**Hash-Only Cache** (Default - Zero Dependencies):
+- Perfect for CI/CD and testing
+- 100% hit rate on identical prompts
+- ~5μs lookup time
+- No ML dependencies needed
+
+**Hybrid Cache** (Semantic Matching):
+
+- Up to 57% hit rate on similar prompts (benchmarked)
+- Understands intent, not just text
+- Install: `pip install empathy-framework[cache]`
+- Best for development and production
+
+#### Automatic Setup
+
+Framework detects your environment and configures optimal caching:
+
+```python
+# First run: Framework checks for sentence-transformers
+# - Found? Uses hybrid cache (semantic matching, up to 57% hit rate)
+# - Missing? Prompts: "Install for semantic matching? (y/n)"
+# - Declined? Falls back to hash-only (100% hit rate on identical prompts)
+# - Any errors? Disables gracefully, workflow continues
+
+# Subsequent runs: Cache just works
+```
+
+#### The Caching Paradox: Adaptive Workflows
+
+**Discovered during v3.8.0 development**: Some workflows (Security Audit, Bug Prediction) cost MORE on Run 2 with cache enabled - and that's a FEATURE.
+
+**Why?** Adaptive workflows use cache to free up time for deeper analysis:
+
+```
+Security Audit without cache:
+Run 1: $0.11, 45 seconds - surface scan finds 3 issues
+
+Security Audit with cache:
+Run 2: $0.13, 15 seconds - cache frees 30s for deep analysis
+       → Uses saved time for PREMIUM tier vulnerability research
+       → Finds 7 issues including critical SQLi we missed
+       → Extra $0.02 cost = prevented security breach
+```
+
+**Result**: Cache makes workflows SMARTER, not just cheaper.
+
+See [Adaptive Workflows Documentation](docs/caching/ADAPTIVE_WORKFLOWS.md) for full explanation.
+
+#### Complete Documentation
+
+- **[Quick Reference](docs/caching/QUICK_REFERENCE.md)** - Common scenarios, 1-page cheat sheet
+- **[Configuration Guide](docs/caching/CONFIGURATION_GUIDE.md)** - All options, when to use each
+- **[Adaptive Workflows](docs/caching/ADAPTIVE_WORKFLOWS.md)** - Why Run 2 can cost more (it's good!)
+
+**Test it yourself**:
+```bash
+# Quick test (2-3 minutes)
+python benchmark_caching_simple.py
+
+# Full benchmark (15-20 minutes, all 12 workflows)
+python benchmark_caching.py
+```
+
+---
+
 ## Become a Power User
 
 ### Level 1: Basic Usage
@@ -597,18 +715,37 @@ pip install empathy-framework[developer]
 - Works out of the box with sensible defaults
 - Auto-detects your API keys
 
-### Level 2: Cost Optimization
+### Level 2: Cost Optimization (Role-Based Savings)
+
+**Tier routing automatically routes tasks to appropriate models, saving 34-86% depending on your work role.**
 
 ```bash
-# Enable hybrid mode for 80-96% cost savings
+# Enable hybrid mode
 python -m empathy_os.models.cli provider --set hybrid
 ```
 
-| Tier | Model | Use Case | Cost |
-|------|-------|----------|------|
-| Cheap | GPT-4o-mini / Haiku | Summarization, simple tasks | $0.15-0.25/M |
-| Capable | GPT-4o / Sonnet | Bug fixing, code review | $2.50-3.00/M |
-| Premium | o1 / Opus | Architecture, complex decisions | $15/M |
+#### Tier Pricing
+
+| Tier | Model | Use Case | Cost per Task* |
+|------|-------|----------|----------------|
+| CHEAP | GPT-4o-mini / Haiku | Summarization, formatting, simple tasks | $0.0045-0.0075 |
+| CAPABLE | GPT-4o / Sonnet | Bug fixing, code review, analysis | $0.0725-0.090 |
+| PREMIUM | o1 / Opus | Architecture, complex decisions, design | $0.435-0.450 |
+
+*Typical task: 5,000 input tokens, 1,000 output tokens
+
+#### Actual Savings by Role
+
+| Your Role | PREMIUM % | CAPABLE % | CHEAP % | Actual Savings | Notes |
+|-----------|-----------|-----------|---------|----------------|-------|
+| **Architect / Designer** | 60% | 30% | 10% | **34%** | Design work requires complex reasoning |
+| **Senior Developer** | 25% | 50% | 25% | **65%** | Mix of architecture and implementation |
+| **Mid-Level Developer** | 15% | 60% | 25% | **73%** | Mostly implementation and bug fixes |
+| **Junior Developer** | 5% | 40% | 55% | **86%** | Simple features, tests, documentation |
+| **QA Engineer** | 10% | 35% | 55% | **80%** | Test generation, reports, automation |
+| **DevOps Engineer** | 20% | 50% | 30% | **69%** | Infrastructure planning + automation |
+
+**See [Complete Cost Analysis](docs/cost-analysis/COST_SAVINGS_BY_ROLE_AND_PROVIDER.md) for provider comparisons (Anthropic vs OpenAI vs Ollama) and detailed calculations.**
 
 ### Level 3: Multi-Model Workflows