attune-ai 2.0.2__py3-none-any.whl → 2.1.0__py3-none-any.whl

attune/workflows/perf_audit.py

@@ -77,14 +77,11 @@ PERF_PATTERNS = {
         "description": "Wildcard import may slow startup",
         "impact": "low",
     },
-    "large_list_copy": {
-        "patterns": [
-            r"list\(\w+\)",
-            r"\w+\[:\]",
-        ],
-        "description": "Full list copy (may be inefficient for large lists)",
-        "impact": "low",
-    },
+    # REMOVED: large_list_copy - too many false positives
+    # - list(x) is often intentional defensive copying or type conversion
+    # - dirs[:] is REQUIRED for os.walk directory filtering (see os-walk-dirs-pattern.md)
+    # - Low impact even when not intentional
+    # See: .claude/rules/attune/list-copy-guidelines.md
     "repeated_regex": {
         "patterns": [
             r're\.(search|match|findall)\s*\(["\'][^"\']+["\']',
@@ -110,10 +107,13 @@ PERF_PATTERNS = {
 #   - Now correctly excludes: generator expressions inside any(), all(), etc.
 #   - Sequential string building (code += "line1"; code += "line2") correctly ignored
 #
-# FALSE POSITIVE: large_list_copy
+# REMOVED: large_list_copy (v2.1.0)
 #   - list(x) or x[:] used for defensive copying or type conversion
+#   - dirs[:] is REQUIRED for os.walk directory filtering
 #   - Often intentional to avoid mutating original data
-#   - Verdict: OK - usually intentional, low impact
+#   - Verdict: REMOVED - too many false positives, low impact even when real
+#   - See: .claude/rules/attune/list-copy-guidelines.md
+#   - See: .claude/rules/attune/os-walk-dirs-pattern.md
 #
 # FALSE POSITIVE: repeated_regex (edge cases)
 #   - Single-use regex in rarely-called functions
@@ -591,11 +591,7 @@ Provide detailed optimization strategies."""
                 "description": "Create the list once before the loop",
                 "estimated_impact": "medium",
             },
-            "large_list_copy": {
-                "action": "Use iterators",
-                "description": "Consider using iterators instead of copying entire lists",
-                "estimated_impact": "low",
-            },
+            # large_list_copy removed - too many false positives
             "global_import": {
                 "action": "Use specific imports",
                 "description": "Import only needed names to reduce memory and startup time",

{attune_ai-2.0.2.dist-info → attune_ai-2.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: attune-ai
-Version: 2.0.2
+Version: 2.1.0
 Summary: AI collaboration framework with real LLM agent execution, AskUserQuestion tool integration, Socratic agent generation, progressive tier escalation (70-85% cost savings), meta-orchestration, dynamic agent composition (10 patterns including Anthropic-inspired), intelligent caching (85% hit rate), semantic workflow discovery, visual workflow editor, MCP integration for Claude Code, and multi-agent orchestration.
 Author-email: Patrick Roebuck <admin@smartaimemory.com>
 Maintainer-email: Smart-AI-Memory <admin@smartaimemory.com>
@@ -421,14 +421,14 @@ Requires-Dist: aiohttp<4.0.0,>=3.10.0; extra == "all"
 Requires-Dist: filelock<4.0.0,>=3.16.0; extra == "all"
 Dynamic: license-file
 
-# Attune AI
+# Empathy Framework
 
 **AI-powered developer workflows with cost optimization and pattern learning.**
 
 Run code review, debugging, testing, and release workflows from your terminal or Claude Code. Smart tier routing saves 34-86% on LLM costs.
 
 [![PyPI](https://img.shields.io/pypi/v/attune-ai?color=blue)](https://pypi.org/project/attune-ai/)
-[![Tests](https://img.shields.io/badge/tests-13%2C489%20collected-brightgreen)](https://github.com/Smart-AI-Memory/attune-ai/actions)
+[![Tests](https://img.shields.io/badge/tests-7%2C168%20passing%20(99.9%25)-brightgreen)](https://github.com/Smart-AI-Memory/attune-ai/actions)
 [![Python](https://img.shields.io/badge/python-3.10+-blue)](https://www.python.org)
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE)
 [![Performance](https://img.shields.io/badge/performance-18x%20faster-success)](https://github.com/Smart-AI-Memory/attune-ai/blob/main/CHANGELOG.md)
@@ -439,64 +439,188 @@ pip install attune-ai[developer]
 
 ---
 
-## What's New in v2.0.0
+## 🎯 Transitioning to Claude-Native Architecture
 
-**🎉 Introducing Attune AI** - A fresh start with a new name and renewed focus:
+**Empathy Framework is evolving to focus exclusively on Anthropic/Claude** to unlock features impossible with multi-provider abstraction:
 
-**Package Rebrand**: `empathy-framework` is now `attune-ai`
+- **📦 Prompt Caching:** 90% cost reduction on repeated prompts
+- **📖 Flexible Context:** 200K via subscription for most tasks, up to 1M via API for large codebases
+- **🧠 Extended Thinking:** See Claude's internal reasoning process
+- **🔧 Advanced Tool Use:** Optimized for agentic workflows
 
-- New package name, same powerful features
-- All capabilities from v5.x preserved
-- Starting fresh at v2.0.0 to mark the new brand
+**Timeline:**
 
-**🤖 Multi-Agent Orchestration** - Build and coordinate specialized AI agents:
+- ✅ **v4.8.0 (Jan 2026):** Deprecation warnings for OpenAI/Google/Ollama providers
+- ✅ **v5.0.0 (Jan 26, 2026):** Non-Anthropic providers removed (BREAKING - COMPLETE)
+- ✅ **v5.0.2 (Jan 28, 2026):** Cost optimization suite with batch processing and caching monitoring
 
-- **Agent Coordination Dashboard** - Real-time monitoring with 6 coordination patterns
-- **Custom Agents** - Create specialized agents for your workflow needs
-- **LLM Agents** - Leverage Claude's advanced capabilities
-- Dashboard at `http://localhost:8000` with `python examples/dashboard_demo.py` (requires Redis)
+**Migration Guide:** [docs/CLAUDE_NATIVE.md](docs/CLAUDE_NATIVE.md)
 
-**💰 Intelligent Cost Optimization**:
+---
+
+## What's New in v5.3.0
+
+**🎨 Dashboard Enhancements** - Improved usability and clarity:
+
+- **Agent Display Names** - Human-readable labels for agents in dashboard (e.g., "Code Analyzer" instead of UUID)
+- **Comprehensive Help Panel** - 5-section accordion explaining dashboard features, use cases, and Redis setup
+- **UX Improvements** - "Source Agent:" label clarity, "Redis Requires Enabling" status message
+- **Browser Cache Busting** - Date-based versioning ensures updates appear immediately
 
-- **Authentication Strategy** - Smart routing between Claude subscription (free) and Anthropic API
-- **Batch API** - 50% cost savings for non-urgent tasks
-- **Smart Tier Routing** - Automatic model selection saves 34-86% on costs
-- **Precise Token Counting** - >98% accurate cost tracking
+**📚 Documentation Improvements**:
 
-**⚡ Performance & Scale**:
+- Clarified flexible context strategy (200K subscription + 1M API routing)
+- Added Redis requirement documentation for dashboard
+- Root directory cleanup (8 archived files)
 
-- **18x Faster** - Redis caching, parallel scanning, incremental updates
-- **99.9% Memory Reduction** - Generator expressions across 27 optimizations
-- **Natural Language** - Use plain English for workflow commands
-- **13,489 Tests** - Comprehensive test coverage (99.9% passing)
+**🧪 Test Infrastructure**:
+
+- Sequential test execution to fix import timing issues
+- All agent tracking tests passing (19/19)
+
+[See Full Changelog](CHANGELOG.md#530---2026-01-31)
+
+---
 
-**🔐 Security & Quality**:
+## What's New in v5.1.0
 
-- **Automated Security Scanning** - 82% accuracy, blocks critical issues
-- **Path Traversal Protection** - All file operations validated
-- **HIPAA/GDPR Compliance** - Enterprise-ready security options
+**🤖 Multi-Agent Orchestration** - Full support for custom agents and Anthropic LLM agents:
 
-**🧭 Developer Experience**:
+- **Agent Coordination Dashboard** - Real-time monitoring with 6 coordination patterns:
+  - Agent heartbeats and status tracking
+  - Inter-agent coordination signals
+  - Event streaming across agent workflows
+  - Approval gates for human-in-the-loop
+  - Quality feedback and performance metrics
+  - Demo mode with test data generation
 
-- **MCP Integration** - 10 tools auto-discovered by Claude Code
-- **Hub-Based Commands** - Organized workflows (`/dev`, `/testing`, `/release`, etc.)
-- **Socratic Workflows** - Interactive discovery through guided questions
-- **$0 Workflows** - Run via Claude Code with no API costs, unless a 1 million API context is required.
+- **Custom Agents** - Build specialized agents for your workflow needs
+- **LLM Agents from Anthropic** - Leverage Claude's advanced capabilities
+- Dashboard accessible at `http://localhost:8000` with `python examples/dashboard_demo.py` **(Requires Redis)**
 
-**Migration from Empathy Framework**:
+**🔐 Authentication Strategy System** - Intelligent routing between Claude subscriptions and Anthropic API:
 
 ```bash
-# Old package
-pip uninstall empathy-framework
+# Interactive setup
+python -m attune.models.auth_cli setup
 
-# New package
-pip install attune-ai[developer]
+# View current configuration
+python -m attune.models.auth_cli status
+
+# Get recommendation for a file
+python -m attune.models.auth_cli recommend src/module.py
+```
+
+**💰 Automatic Cost Optimization** - Workflows choose the best auth method:
+
+- Small/medium modules (<2000 LOC) → Claude subscription (free)
+- Large modules (>2000 LOC) → Anthropic API (pay for what you need)
+- 7 workflows integrated: document-gen, test-gen, code-review, bug-predict, security-audit, perf-audit, release-prep
+- Auth mode tracking in all workflow outputs for telemetry
+
+**🧪 Comprehensive Testing** - 7 new integration tests for auth strategy:
+
+- All workflows tested with auth enabled/disabled
+- API and subscription mode verification
+- Cost tracking validation
+
+**📖 Documentation** - 950+ lines across 3 guides:
+
+- [AUTH_STRATEGY_GUIDE.md](docs/AUTH_STRATEGY_GUIDE.md) - User guide for configuration
+- [AUTH_CLI_IMPLEMENTATION.md](docs/AUTH_CLI_IMPLEMENTATION.md) - CLI command reference
+- [AUTH_WORKFLOW_INTEGRATIONS.md](docs/AUTH_WORKFLOW_INTEGRATIONS.md) - Integration patterns
+
+[See Full Changelog](CHANGELOG.md#510---2026-01-29)
+
+---
+
+## What's New in v5.0.2
+
+**💰 50% Cost Savings with Batch API** - Process non-urgent tasks asynchronously:
+
+```bash
+empathy batch submit batch_requests.json  # Submit batch job
+empathy batch status msgbatch_abc123      # Check progress
+empathy batch results msgbatch_abc123 output.json  # Download results
+```
+
+Perfect for: log analysis, report generation, bulk classification, test generation
+
+**📊 Precise Token Counting** - >98% accurate cost tracking:
+
+- Integrated Anthropic's `count_tokens()` API for billing-accurate measurements
+- 3-tier fallback: API → tiktoken (local) → heuristic
+- Cache-aware cost calculation (25% write markup, 90% read discount)
+
+**📈 Cache Performance Monitoring** - Track your 20-30% caching savings:
+
+```bash
+empathy cache stats           # Show hit rates and cost savings
+empathy cache stats --verbose # Detailed token metrics
+empathy cache stats --format json  # Machine-readable output
+```
+
+**🧭 Adaptive Routing Analytics** - Intelligent tier recommendations:
+
+```bash
+empathy routing stats <workflow>    # Performance metrics
+empathy routing check --all         # Tier upgrade recommendations
+empathy routing models --provider anthropic  # Compare models
+```
+
+**🔧 Dashboard Fixes** - All 6 agent coordination patterns now operational:
+- Agent heartbeats displaying correctly
+- Event streaming functional
+- Coordination signals working
+- Approval gates operational
+
+[See Full Changelog](CHANGELOG.md#502---2026-01-28) | [Batch API Guide](docs/BATCH_API_GUIDE.md) | [User API Docs](docs/USER_API_DOCUMENTATION.md)
 
-# Update imports in your code
-# from empathy_os → from attune
+---
+
+## What's New in v4.9.0
+
+**⚡ 18x Faster Performance** - Massive performance gains through Phase 2 optimizations:
+
+- **Redis Two-Tier Caching:** 2x faster memory operations (37,000x for cached keys)
+- **Generator Expressions:** 99.9% memory reduction across 27 optimizations
+- **Parallel Scanning:** Multi-core processing enabled by default (2-4x faster)
+- **Incremental Scanning:** Git diff-based updates (10x faster)
+
+**🧭 Natural Language Workflows** - Use plain English instead of workflow names:
+
+```bash
+/workflows "find security vulnerabilities"  # → security-audit
+/workflows "check code performance"         # → perf-audit
+/workflows "predict bugs"                   # → bug-predict
+/plan "review my code"                      # → code-review
 ```
 
-[See Full Changelog](CHANGELOG.md) | [Migration Guide](docs/MIGRATION_GUIDE.md)
+**📊 Real-World Performance:**
+
+- Combined workflow: 3.59s → 0.2s (**18x faster**)
+- Full scan: 3,472 files in 0.98s (was 3.59s)
+- Redis cached operations: 37ms → 0.001ms
+
+**🎯 Improved Navigation:**
+
+- Split `/workflow` into `/workflows` (automated analysis) and `/plan` (planning/review)
+- Clearer hub organization with better categorization
+- Natural language routing matches intent to workflow
+
+[See CHANGELOG.md](CHANGELOG.md) | [Performance Docs](docs/REDIS_OPTIMIZATION_SUMMARY.md)
+
+---
+
+## What's New in v4.7.0
+
+**$0 Workflows via Skills** - Multi-agent workflows run through Claude Code's Task tool instead of API calls. No additional cost with your Claude subscription.
+
+**Socratic Workflows** - Interactive discovery through guided questions. Workflows ask what you need rather than requiring upfront configuration.
+
+**Security Hardened** - Fixed critical vulnerabilities (path traversal, JWT, SSRF).
+
+**Hub-Based Commands** - Organized workflows into intuitive command hubs.
 
 ---
 
@@ -535,7 +659,7 @@ python -m attune.models.cli provider --set anthropic
 /plan "review my code"
 
 # Direct tool access via MCP (v5.1.1+):
-# Claude Code automatically discovers Attune AI tools through the MCP server
+# Claude Code automatically discovers Empathy tools through the MCP server
 # Just describe what you need in natural language:
 "Run a security audit on src/"          → Invokes security_audit tool
 "Generate tests for config.py"          → Invokes test_generation tool
@@ -545,7 +669,7 @@ python -m attune.models.cli provider --set anthropic
 
 **MCP Server Integration (v5.1.1+):**
 
-Attune AI now includes a Model Context Protocol (MCP) server that exposes all workflows as native Claude Code tools:
+Empathy Framework now includes a Model Context Protocol (MCP) server that exposes all workflows as native Claude Code tools:
 
 - **10 Tools Available:** security_audit, bug_predict, code_review, test_generation, performance_audit, release_prep, auth_status, auth_recommend, telemetry_stats, dashboard_status
 - **Automatic Discovery:** No manual configuration needed - Claude Code finds tools via `.claude/mcp.json`
@@ -567,9 +691,9 @@ See [.claude/MCP_TEST_RESULTS.md](.claude/MCP_TEST_RESULTS.md) for full integrat
 **CLI:**
 
 ```bash
-attune workflow run security-audit --path ./src
-attune workflow run test-coverage --target 90
-attune telemetry show  # View cost savings
+empathy workflow run security-audit --path ./src
+empathy workflow run test-coverage --target 90
+empathy telemetry show  # View cost savings
 ```
 
 **Python:**
@@ -577,8 +701,8 @@ attune telemetry show  # View cost savings
 ```python
 from attune import EmpathyOS
 
-async with EmpathyOS() as attune:
-    result = await attune.level_2_guided(
+async with EmpathyOS() as empathy:
+    result = await empathy.level_2_guided(
         "Review this code for security issues"
     )
     print(result["response"])
@@ -688,7 +812,7 @@ For programmatic use, smart tier routing saves 34-86%:
 
 ```bash
 # Track API usage and savings
-attune telemetry savings --days 30
+empathy telemetry savings --days 30
 ```
 
 ---
@@ -699,10 +823,10 @@ attune telemetry savings --days 30
 
 ```bash
 # 4 parallel agents check release readiness
-attune orchestrate release-prep
+empathy orchestrate release-prep
 
 # Sequential coverage improvement
-attune orchestrate test-coverage --target 90
+empathy orchestrate test-coverage --target 90
 ```
 
 ### Response Caching
@@ -750,21 +874,21 @@ python -m attune.models.cli provider
 python -m attune.models.cli provider --set hybrid
 
 # Workflows
-attune workflow list
-attune workflow run <workflow-name>
+empathy workflow list
+empathy workflow run <workflow-name>
 
 # Cost tracking
-attune telemetry show
-attune telemetry savings --days 30
-attune telemetry export --format csv
+empathy telemetry show
+empathy telemetry savings --days 30
+empathy telemetry export --format csv
 
 # Orchestration
-attune orchestrate release-prep
-attune orchestrate test-coverage --target 90
+empathy orchestrate release-prep
+empathy orchestrate test-coverage --target 90
 
 # Meta-workflows
-attune meta-workflow list
-attune meta-workflow run release-prep --real
+empathy meta-workflow list
+empathy meta-workflow run release-prep --real
 ```
 
 ---
@@ -810,7 +934,7 @@ export REDIS_URL="redis://localhost:6379"
 
 ## VSCode Extension
 
-Install the Attune AI VSCode extension for:
+Install the Empathy VSCode extension for:
 
 - **Dashboard** - Health score, costs, patterns
 - **One-Click Workflows** - Run from command palette
@@ -845,10 +969,10 @@ See [SECURITY.md](SECURITY.md) for vulnerability reporting.
 
 ```bash
 # Run security audit locally
-attune workflow run security-audit
+empathy workflow run security-audit
 
 # Scan specific directory
-attune workflow run security-audit --input '{"path":"./src"}'
+empathy workflow run security-audit --input '{"path":"./src"}'
 ```
 
 **Documentation:**

{attune_ai-2.0.2.dist-info → attune_ai-2.1.0.dist-info}/RECORD

@@ -291,7 +291,7 @@ attune/workflows/new_sample_workflow1_README.md,sha256=1pd--DASCiZlqMmcaq-FI_zIa
 attune/workflows/orchestrated_health_check.py,sha256=d4R8iOvw4kQ_EfRdvNYDNrjjR6hzPow55fWSuLHkhPs,30486
 attune/workflows/orchestrated_release_prep.py,sha256=Erp2rw-EBNOfIwyT0nJhGqpYPg2v-YL_h06aMtaALlA,20224
 attune/workflows/output.py,sha256=BJHDdaYB7ptemZy8KHbuLkSmrEAiFCArjOfvQfRMnCU,12829
-attune/workflows/perf_audit.py,sha256=KVSPJBgZJGlrTQtLQ71enUBHp7yr_Trgnf9yGlNZPQE,32064
+attune/workflows/perf_audit.py,sha256=Xjom8vg4W9vQ4DKQTVTnhNzsccOD0RyIcAN2YwPocdI,32203
 attune/workflows/pr_review.py,sha256=lR7TxvGjBj1fIMxYgBtgxuSvWFTGqQHTsVpL5zKLUB8,26796
 attune/workflows/progress.py,sha256=z_0UV2uH4Xu9fG85VYtcqJwJWQhTfa7WvFqrtIe-ISE,26588
 attune/workflows/progress_server.py,sha256=3UmIW8j-Hxayod4kV9BoWPvJO8lNX38YVCq6UDEnYlQ,10229
@@ -330,7 +330,6 @@ attune/workflows/keyboard_shortcuts/parsers.py,sha256=aws4HSjqBOrl-DQEOV9WeJX6dy
 attune/workflows/keyboard_shortcuts/prompts.py,sha256=gcV2F2bAMjZUrbB13lOI4ixXzXm2TNWEZ4VbPhC7ITw,9164
 attune/workflows/keyboard_shortcuts/schema.py,sha256=MwvM63J9WTO6nqtwes5A04HH1dTa9XhJlD0SbFhsS5E,5806
 attune/workflows/keyboard_shortcuts/workflow.py,sha256=EGEyZ3azXnmyu24ycTDgHDulwXPU7FaIWn2GDpixsG0,17674
-attune/workflows/progressive/README 2.md,sha256=zZNzVWK56hQdzFNePArefG0n_mL3v_LEGv3jfltVrmQ,13745
 attune/workflows/progressive/README.md,sha256=zZNzVWK56hQdzFNePArefG0n_mL3v_LEGv3jfltVrmQ,13745
 attune/workflows/progressive/__init__.py,sha256=e1lacdjDlc58evGbrpWK83Nl7_-PW1zwsiaYbdxaPug,2155
 attune/workflows/progressive/cli.py,sha256=2XAEqh9O8_8iT69cykx6OhnZ-YbnLIXrU1ySil3Wt5g,6113
@@ -347,8 +346,8 @@ attune/workflows/test_gen/data_models.py,sha256=wXfef60ptiG6AvygayTxWqlL5FVOss19
 attune/workflows/test_gen/report_formatter.py,sha256=RaxbDp6-9iQRfJmVwrrIReVkOkrnb668NgHrNaS-SPY,10705
 attune/workflows/test_gen/test_templates.py,sha256=4ywqGYYaSoZxOU6Y1_E-27KEgMI5-v2a1ndia406E9c,13180
 attune/workflows/test_gen/workflow.py,sha256=U0dhAcCKmlltPIvCSXUeFzt_Q4TodQI4tXtR6cz19MQ,25729
-attune_ai-2.0.2.dist-info/licenses/LICENSE,sha256=kqe3EeGatNB79lUTHxjLnxDe7VJr0iYetThOr4_Fx7A,11348
-attune_ai-2.0.2.dist-info/licenses/LICENSE_CHANGE_ANNOUNCEMENT.md,sha256=JH9yAQGv_lQej5YlztI_kawbVQ2H8uVLhPGlrWnR_34,3844
+attune_ai-2.1.0.dist-info/licenses/LICENSE,sha256=kqe3EeGatNB79lUTHxjLnxDe7VJr0iYetThOr4_Fx7A,11348
+attune_ai-2.1.0.dist-info/licenses/LICENSE_CHANGE_ANNOUNCEMENT.md,sha256=JH9yAQGv_lQej5YlztI_kawbVQ2H8uVLhPGlrWnR_34,3844
 attune_healthcare/__init__.py,sha256=4NioL1_86UXzkd-QNkQZUSZ8rKTQGSP0TC9VXP32kQs,295
 attune_healthcare/monitors/__init__.py,sha256=Udp8qfZR504QAq5_eQjvtIaE7v06Yguc7nuF40KllQc,196
 attune_healthcare/monitors/clinical_protocol_monitor.py,sha256=MWE5t8tW9HWZn_SNo-inx8-0nhdTNGhbcB8ZeDWyXa0,11648
@@ -450,8 +449,8 @@ workflow_scaffolding/__init__.py,sha256=UpX5vjjjPjIaAKyIV1D4GxJzLUZy5DzdzgSkePYM
 workflow_scaffolding/__main__.py,sha256=0qspuNoadTDqyskXTlT8Sahqau-XIxN35NHTSGVW6z4,236
 workflow_scaffolding/cli.py,sha256=RUVqU9SeAgm7YkM0YNd-quh8u6BNzmX8xM2y9K_p68Y,6759
 workflow_scaffolding/generator.py,sha256=2WC02A10lzF2NQgOn66ksV17Oe72kKlU2qCQs39LIlw,8861
-attune_ai-2.0.2.dist-info/METADATA,sha256=kAyR6yCwivlRaPgLaKV_Uv6kiSIEwuJM5MJz44qtIyY,40096
-attune_ai-2.0.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-attune_ai-2.0.2.dist-info/entry_points.txt,sha256=GVlb04zFlpkaPtaL7X3JCZI8R0AEOZRsZjJ-wIDQvdo,1458
-attune_ai-2.0.2.dist-info/top_level.txt,sha256=iLyjKpuOzWtwmIOZqzeBh8_SVztY2vFvhHcyo1WPtTY,73
-attune_ai-2.0.2.dist-info/RECORD,,
+attune_ai-2.1.0.dist-info/METADATA,sha256=86GO_8mUvQMAl6W1vd4BKqnN8jzx2zJcgj8aNkr5BCM,45033
+attune_ai-2.1.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+attune_ai-2.1.0.dist-info/entry_points.txt,sha256=GVlb04zFlpkaPtaL7X3JCZI8R0AEOZRsZjJ-wIDQvdo,1458
+attune_ai-2.1.0.dist-info/top_level.txt,sha256=iLyjKpuOzWtwmIOZqzeBh8_SVztY2vFvhHcyo1WPtTY,73
+attune_ai-2.1.0.dist-info/RECORD,,

attune/workflows/progressive/README 2.md

@@ -1,454 +0,0 @@
-# Progressive Tier Escalation System
-
-**Version:** 4.1.0
-**Status:** Production Ready
-**Test Coverage:** 86.58% (123 tests)
-
-## Overview
-
-The Progressive Tier Escalation System is an intelligent cost optimization framework that automatically routes tasks through multiple AI model tiers (cheap → capable → premium) based on quality metrics, providing 70-85% cost savings compared to using premium models for all tasks.
-
-## Key Features
-
-- ✅ **Multi-tier execution**: Automatic progression from cheap to premium models
-- ✅ **Composite Quality Score (CQS)**: Multi-signal failure detection
-- ✅ **Smart escalation**: Only failed items escalate, successful ones stay at current tier
-- ✅ **Cost management**: Budget controls with approval prompts
-- ✅ **Privacy-preserving telemetry**: Local tracking with hashed user IDs
-- ✅ **Comprehensive analytics**: Historical cost savings analysis
-- ✅ **CLI tools**: Manage and analyze workflow results
-
-## Quick Start
-
-```python
-from attune.workflows.progressive import (
-    ProgressiveTestGenWorkflow,
-    EscalationConfig,
-    Tier
-)
-
-# Configure escalation
-config = EscalationConfig(
-    enabled=True,
-    tiers=[Tier.CHEAP, Tier.CAPABLE, Tier.PREMIUM],
-    max_cost=10.00,
-    auto_approve_under=1.00,
-    abort_on_budget_exceeded=True
-)
-
-# Create workflow
-workflow = ProgressiveTestGenWorkflow(config)
-
-# Execute with automatic tier progression
-result = workflow.execute(target_file="src/myapp/calculator.py")
-
-# View results
-print(result.generate_report())
-print(f"Cost: ${result.total_cost:.2f}")
-print(f"Savings: ${result.cost_savings:.2f} ({result.cost_savings_percent:.0f}%)")
-
-# Save results for analytics
-result.save_to_disk()
-```
-
-## Architecture
-
-### Tier Progression
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│                     PROGRESSIVE ESCALATION                  │
-└─────────────────────────────────────────────────────────────┘
-                              │
-                              ▼
-                    ┌─────────────────┐
-                    │   CHEAP TIER    │
-                    │  (gpt-4o-mini)  │
-                    │   $0.003/item   │
-                    │   1 agent       │
-                    └────────┬────────┘
-                             │
-                    CQS < 75? ───No──> SUCCESS
-                             │
-                            Yes
-                             │
-                             ▼
-                    ┌─────────────────┐
-                    │  CAPABLE TIER   │
-                    │ (claude-3-5-s)  │
-                    │   $0.015/item   │
-                    │   2 agents      │
-                    └────────┬────────┘
-                             │
-                    CQS < 85? ───No──> SUCCESS
-                             │
-                            Yes
-                             │
-                             ▼
-                    ┌─────────────────┐
-                    │  PREMIUM TIER   │
-                    │ (claude-opus-4) │
-                    │   $0.05/item    │
-                    │   3 agents      │
-                    └────────┬────────┘
-                             │
-                             ▼
-                         FINAL RESULT
-```
-
-### Composite Quality Score (CQS)
-
-Quality is measured using a weighted multi-signal metric:
-
-```
-CQS = (0.40 × test_pass_rate +
-       0.25 × code_coverage +
-       0.20 × assertion_quality +
-       0.15 × llm_confidence) × syntax_penalty
-```
-
-**Thresholds:**
-- **CHEAP tier**: CQS ≥ 75 (pass), < 75 (escalate)
-- **CAPABLE tier**: CQS ≥ 85 (pass), < 85 (escalate)
-- **PREMIUM tier**: CQS ≥ 90 (target), no escalation
-
-**Syntax Penalty:** 50% reduction if syntax errors detected
-
-## Core Components
-
-### 1. EscalationConfig
-
-Configuration for tier escalation behavior:
-
-```python
-config = EscalationConfig(
-    enabled=True,                    # Enable progressive escalation
-    tiers=[Tier.CHEAP, Tier.CAPABLE, Tier.PREMIUM],
-    cheap_min_attempts=2,            # Try cheap tier 2× before escalating
-    capable_min_attempts=1,          # Try capable tier 1× before escalating
-    max_cost=10.00,                  # Abort if cost exceeds $10
-    auto_approve_under=1.00,         # Auto-approve costs < $1
-    abort_on_budget_exceeded=True,   # Abort vs warn on budget exceeded
-    warn_on_budget_exceeded=False,
-    stagnation_threshold=0.05,       # 5% improvement threshold
-    stagnation_window=2,             # Over 2 consecutive runs
-)
-```
-
-### 2. Meta-Orchestration
-
-Dynamic agent team creation based on tier:
-
-| Tier     | Agents | Strategy                              |
-|----------|--------|---------------------------------------|
-| CHEAP    | 1      | Single agent, fast iteration          |
-| CAPABLE  | 2      | Planner + executor, collaborative     |
-| PREMIUM  | 3      | Architect + executor + reviewer, deep |
-
-### 3. Telemetry
-
-Privacy-preserving usage tracking:
-
-```python
-from attune.workflows.progressive import ProgressiveTelemetry
-
-# Initialize telemetry
-telemetry = ProgressiveTelemetry(
-    workflow_name="test-gen",
-    user_id="user@example.com"  # SHA256 hashed for privacy
-)
-
-# Track tier execution
-telemetry.track_tier_execution(tier_result, attempt=1, escalated=False)
-
-# Track escalation
-telemetry.track_escalation(
-    from_tier=Tier.CHEAP,
-    to_tier=Tier.CAPABLE,
-    reason="Low CQS (65)",
-    item_count=10,
-    current_cost=0.30
-)
-
-# Track workflow completion
-telemetry.track_workflow_completion(result)
-```
-
-**Data Stored:**
-- Workflow name, tier, model, cost, tokens
-- Quality metrics (CQS, test pass rate, coverage)
-- Escalation reasons and patterns
-- Timestamps and durations
-
-**Privacy:**
-- User IDs are SHA256 hashed
-- No prompts, responses, or PII stored
-- Local-only storage (~/.empathy/telemetry/)
-
-### 4. CLI Tools
-
-Manage and analyze saved results:
-
-```bash
-# List all workflow results
-empathy progressive list
-
-# Show detailed report for specific run
-empathy progressive show test-gen-20260117-120000
-
-# Show JSON output
-empathy progressive show test-gen-20260117-120000 --json
-
-# Generate cost analytics
-empathy progressive analytics
-
-# Cleanup old results (30 day retention)
-empathy progressive cleanup --retention-days 30
-
-# Dry run cleanup (preview)
-empathy progressive cleanup --retention-days 30 --dry-run
-
-# Custom storage path
-empathy progressive list --storage-path ./my-results
-```
-
-## Usage Examples
-
-### Example 1: Test Generation with Escalation
-
-```python
-from attune.workflows.progressive import ProgressiveTestGenWorkflow
-
-workflow = ProgressiveTestGenWorkflow()
-result = workflow.execute(target_file="src/auth.py")
-
-# View tier progression
-for tier_result in result.tier_results:
-    print(f"{tier_result.tier.value}: CQS={tier_result.failure_analysis.calculate_quality_score():.1f}")
-    if tier_result.escalated:
-        print(f"  → Escalated: {tier_result.escalation_reason}")
-
-# Output:
-# cheap: CQS=68.5
-#   → Escalated: Low CQS (68.5)
-# capable: CQS=92.0
-```
-
-### Example 2: Cost Analysis
-
-```python
-from attune.workflows.progressive.reports import generate_cost_analytics
-
-analytics = generate_cost_analytics()
-
-print(f"Total runs: {analytics['total_runs']}")
-print(f"Total cost: ${analytics['total_cost']:.2f}")
-print(f"Total savings: ${analytics['total_savings']:.2f}")
-print(f"Avg savings: {analytics['avg_savings_percent']:.1f}%")
-print(f"Escalation rate: {analytics['escalation_rate']:.1%}")
-print(f"Success rate: {analytics['success_rate']:.1%}")
-
-# Per-workflow breakdown
-for workflow, stats in analytics['workflow_stats'].items():
-    print(f"\n{workflow}:")
-    print(f"  Runs: {stats['runs']}")
-    print(f"  Avg cost: ${stats['avg_cost']:.2f}")
-    print(f"  Success rate: {stats['success_rate']:.1%}")
-```
-
-### Example 3: Custom Escalation Logic
-
-```python
-from attune.workflows.progressive import ProgressiveWorkflow, Tier
-
-class CustomWorkflow(ProgressiveWorkflow):
-    def _should_escalate_custom(self, tier_result):
-        """Custom escalation logic."""
-        # Example: Escalate if any syntax errors
-        if tier_result.failure_analysis.syntax_errors:
-            return True, "Syntax errors detected"
-
-        # Example: Escalate if test pass rate < 90%
-        if tier_result.failure_analysis.test_pass_rate < 0.90:
-            return True, f"Low test pass rate ({tier_result.failure_analysis.test_pass_rate:.1%})"
-
-        return False, None
-
-    def _execute_tier_impl(self, tier, items, context):
-        """Implement tier execution logic."""
-        # Your custom implementation
-        pass
-
-workflow = CustomWorkflow()
-result = workflow.execute(items=my_items)
-```
-
-## Performance Characteristics
-
-### Cost Savings
-
-Based on production usage:
-
-| Scenario              | Cheap % | Capable % | Premium % | Savings |
-|-----------------------|---------|-----------|-----------|---------|
-| Simple tasks          | 80%     | 15%       | 5%        | 85%     |
-| Medium complexity     | 60%     | 30%       | 10%       | 72%     |
-| High complexity       | 40%     | 40%       | 20%       | 60%     |
-| **Average**           | **60%** | **28%**   | **12%**   | **72%** |
-
-### Execution Time
-
-Progressive execution adds minimal latency:
-
-- **Cheap tier**: ~5-10s per item (baseline)
-- **Capable tier**: ~10-20s per item (+5-10s overhead)
-- **Premium tier**: ~20-40s per item (+10-20s overhead)
-
-**Parallel escalation**: Failed items escalate in parallel, reducing total time.
-
-## Troubleshooting
-
-### Issue: Excessive Escalation
-
-**Symptoms:** Most items escalate to premium tier
-
-**Causes:**
-- CQS thresholds too strict
-- Input items too complex for cheap/capable tiers
-- Stagnation detection too sensitive
-
-**Solutions:**
-```python
-# Lower CQS thresholds
-config = EscalationConfig(
-    cheap_cqs_threshold=70,  # Down from 75
-    capable_cqs_threshold=80  # Down from 85
-)
-
-# Increase stagnation threshold
-config = EscalationConfig(
-    stagnation_threshold=0.10,  # 10% improvement required
-    stagnation_window=3  # Over 3 runs
-)
-
-# Increase min attempts
-config = EscalationConfig(
-    cheap_min_attempts=3,  # Try 3× before escalating
-    capable_min_attempts=2
-)
-```
-
-### Issue: Budget Exceeded Errors
-
-**Symptoms:** `BudgetExceededError` raised frequently
-
-**Solutions:**
-```python
-# Increase budget
-config = EscalationConfig(max_cost=20.00)
-
-# Warn instead of abort
-config = EscalationConfig(
-    abort_on_budget_exceeded=False,
-    warn_on_budget_exceeded=True
-)
-
-# Increase auto-approve threshold
-config = EscalationConfig(auto_approve_under=5.00)
-```
-
-### Issue: Poor Quality Results
-
-**Symptoms:** Final CQS < 85
-
-**Causes:**
-- Insufficient premium tier attempts
-- Input quality issues
-- Test assertion depth too low
-
-**Solutions:**
-```python
-# Force premium tier for critical tasks
-config = EscalationConfig(
-    tiers=[Tier.PREMIUM],  # Skip cheap/capable
-    enabled=False  # Disable escalation
-)
-
-# Increase premium min attempts
-config = EscalationConfig(
-    premium_min_attempts=2
-)
-```
-
-## API Reference
-
-### Core Classes
-
-- `Tier`: Enum defining tier levels (CHEAP, CAPABLE, PREMIUM)
-- `EscalationConfig`: Configuration for tier escalation
-- `FailureAnalysis`: Quality metrics and failure signals
-- `TierResult`: Results from a single tier execution
-- `ProgressiveWorkflowResult`: Complete multi-tier execution results
-
-### Base Classes
-
-- `ProgressiveWorkflow`: Abstract base for progressive workflows
-- `MetaOrchestrator`: Tier escalation decision logic
-
-### Workflows
-
-- `ProgressiveTestGenWorkflow`: Test generation with progressive escalation
-
-### Utilities
-
-- `ProgressiveTelemetry`: Usage tracking and analytics
-- `generate_cost_analytics()`: Analyze historical cost savings
-- `cleanup_old_results()`: Retention policy enforcement
-
-## Testing
-
-Run progressive workflow tests:
-
-```bash
-# All progressive tests
-pytest tests/unit/workflows/progressive/ -v
-
-# Specific test modules
-pytest tests/unit/workflows/progressive/test_core.py -v
-pytest tests/unit/workflows/progressive/test_orchestrator.py -v
-pytest tests/unit/workflows/progressive/test_cost_telemetry.py -v
-pytest tests/unit/workflows/progressive/test_reports_analytics.py -v
-pytest tests/unit/workflows/progressive/test_test_gen.py -v
-
-# With coverage
-pytest tests/unit/workflows/progressive/ --cov=src/attune/workflows/progressive --cov-report=term-missing
-```
-
-**Test Coverage:** 86.58% (123 tests)
-
-## Contributing
-
-When adding new progressive workflows:
-
-1. **Inherit from `ProgressiveWorkflow`**
-2. **Implement `_execute_tier_impl()`** for tier-specific execution logic
-3. **Define quality metrics** in `_analyze_quality()`
-4. **Add comprehensive tests** (aim for 85%+ coverage)
-5. **Document usage** with examples
-
-See `ProgressiveTestGenWorkflow` for a complete implementation example.
-
-## License
-
-Fair Source License 0.9
-
-## Version History
-
-- **4.1.0** (2026-01-17): Initial release with test generation workflow
-- **4.1.0-alpha**: Development version
-
-## Support
-
-- **Documentation**: [Empathy Framework Docs](https://attune-ai.readthedocs.io)
-- **Issues**: [GitHub Issues](https://github.com/Smart-AI-Memory/attune-ai/issues)
-- **Discussions**: [GitHub Discussions](https://github.com/Smart-AI-Memory/attune-ai/discussions)