agentmesh_lightning 3.0.2__tar.gz

agentmesh_lightning-3.0.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) Microsoft Corporation.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

agentmesh_lightning-3.0.2/PKG-INFO

@@ -0,0 +1,204 @@
+Metadata-Version: 2.1
+Name: agentmesh_lightning
+Version: 3.0.2
+Summary: Public Preview — Agent-Lightning RL integration for the Agent Governance Toolkit: governed training with policy enforcement
+Author-email: Microsoft Corporation <agentgovtoolkit@microsoft.com>
+Maintainer-email: Agent Governance Toolkit Team <agentgovtoolkit@microsoft.com>
+License: MIT
+Project-URL: Homepage, https://github.com/microsoft/agent-governance-toolkit
+Project-URL: Repository, https://github.com/microsoft/agent-governance-toolkit
+Project-URL: Bug Tracker, https://github.com/microsoft/agent-governance-toolkit/issues
+Keywords: ai-agents,governance,reinforcement-learning,agentmesh-lightning,agent-os,enterprise-ai
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: agent-os
+Requires-Dist: agent-os-kernel<2.0,>=1.0.0; extra == "agent-os"
+Provides-Extra: dev
+Requires-Dist: pytest<8.0,>=7.0; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+
+# Agent Lightning — RL Training Governance
+
+> [!IMPORTANT]
+> **Public Preview** — The `agentmesh-lightning` package on PyPI is a Microsoft-signed
+> public preview release. APIs may change before GA.
+
+Train AI agents with RL while maintaining **0% policy violations**.
+
+*Part of the [Agent Governance Toolkit](https://github.com/microsoft/agent-governance-toolkit)*
+
+[![CI](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml)
+[![License](https://img.shields.io/badge/license-MIT-blue.svg)](../../LICENSE)
+[![Python](https://img.shields.io/badge/python-3.9+-blue.svg)](https://python.org)
+[![PyPI](https://img.shields.io/pypi/v/agentmesh-lightning)](https://pypi.org/project/agentmesh-lightning/)
+
+## 🎯 Overview
+
+This package provides governed RL training integration:
+- **Agent-Lightning** = Training/Optimization (the "brains")
+- **Agent-OS** = Governance/Safety (the "guardrails")
+
+**Result**: Agents learn to be smart AND safe from the start.
+
+> **Note:** This package was extracted from `agent_os.integrations.agent_lightning`.
+> The old import path still works via a backward-compatibility shim but new code
+> should import from `agent_lightning_gov` directly.
+
+## 🚀 Quick Start
+
+```bash
+pip install agentmesh-lightning
+# Optional: pip install agent-os-kernel  # for kernel integration
+```
+
+```python
+from agent_lightning_gov import GovernedRunner, PolicyReward
+from agent_os import KernelSpace
+from agent_os.policies import SQLPolicy, CostControlPolicy
+
+# 1. Create governed kernel
+kernel = KernelSpace(policy=[
+    SQLPolicy(deny=["DROP", "DELETE"]),
+    CostControlPolicy(max_cost_usd=100)
+])
+
+# 2. Create governed runner
+runner = GovernedRunner(kernel)
+
+# 3. Create policy-aware reward function
+def base_accuracy(rollout):
+    return rollout.task_output.accuracy if rollout.success else 0.0
+
+reward_fn = PolicyReward(kernel, base_reward_fn=base_accuracy)
+
+# 4. Train with Agent-Lightning
+from agentlightning import Trainer
+trainer = Trainer(
+    runner=runner,
+    reward_fn=reward_fn,
+    algorithm="GRPO"
+)
+
+trainer.train(num_epochs=100)
+```
+
+## 📊 Key Benefits
+
+| Metric | Without Agent-OS | With Agent-OS |
+|--------|------------------|---------------|
+| Policy Violations | 12.3% | **0.0%** |
+| Task Accuracy | 76.4% | **79.2%** |
+| Training Stability | Variable | Consistent |
+
+## 🔧 Components
+
+### GovernedRunner
+
+Agent-Lightning runner that enforces policies during execution:
+
+```python
+from agent_lightning_gov import GovernedRunner
+
+runner = GovernedRunner(
+    kernel,
+    fail_on_violation=False,   # Continue but penalize
+    log_violations=True,        # Log all violations
+)
+
+# Execute a task
+rollout = await runner.step(task_input)
+print(f"Violations: {len(rollout.violations)}")
+print(f"Total penalty: {rollout.total_penalty}")
+```
+
+### PolicyReward
+
+Converts policy violations to RL penalties:
+
+```python
+from agent_lightning_gov import PolicyReward, RewardConfig
+
+config = RewardConfig(
+    critical_penalty=-100.0,  # Harsh penalty for critical violations
+    high_penalty=-50.0,
+    medium_penalty=-10.0,
+    low_penalty=-1.0,
+    clean_bonus=5.0,          # Bonus for no violations
+)
+
+reward_fn = PolicyReward(kernel, config=config)
+
+# Calculate reward
+reward = reward_fn(rollout)  # Base reward + policy penalties
+```
+
+### GovernedEnvironment
+
+Gym-compatible training environment:
+
+```python
+from agent_lightning_gov import GovernedEnvironment
+
+env = GovernedEnvironment(
+    kernel,
+    config=EnvironmentConfig(
+        max_steps=100,
+        terminate_on_critical=True,
+    )
+)
+
+# Standard Gym interface
+state, info = env.reset()
+while not env.terminated:
+    action = agent.get_action(state)
+    state, reward, terminated, truncated, info = env.step(action)
+```
+
+### FlightRecorderEmitter
+
+Export audit logs to LightningStore:
+
+```python
+from agent_os import FlightRecorder
+from agent_lightning_gov import FlightRecorderEmitter
+
+recorder = FlightRecorder()
+emitter = FlightRecorderEmitter(recorder)
+
+# Export to LightningStore
+emitter.emit_to_store(lightning_store)
+
+# Or export to file for analysis
+emitter.export_to_file("training_audit.json")
+
+# Get violation summary
+summary = emitter.get_violation_summary()
+print(f"Violation rate: {summary['violation_rate']:.1%}")
+```
+
+## Ecosystem
+
+Agent Lightning is one of 7 packages in the Agent Governance Toolkit:
+
+| Package | Role |
+|---------|------|
+| **Agent OS** | Policy engine — deterministic action evaluation |
+| **AgentMesh** | Trust infrastructure — identity, credentials, protocol bridges |
+| **Agent Runtime** | Execution supervisor — rings, sessions, sagas |
+| **Agent SRE** | Reliability — SLOs, circuit breakers, chaos testing |
+| **Agent Compliance** | Regulatory compliance — GDPR, HIPAA, SOX frameworks |
+| **Agent Marketplace** | Plugin lifecycle — discover, install, verify, sign |
+| **Agent Lightning** | RL training governance — governed runners, policy rewards *(this package)* |
+
+## 📋 License
+
+MIT — see [LICENSE](../../LICENSE).

agentmesh_lightning-3.0.2/README.md

@@ -0,0 +1,176 @@
+# Agent Lightning — RL Training Governance
+
+> [!IMPORTANT]
+> **Public Preview** — The `agentmesh-lightning` package on PyPI is a Microsoft-signed
+> public preview release. APIs may change before GA.
+
+Train AI agents with RL while maintaining **0% policy violations**.
+
+*Part of the [Agent Governance Toolkit](https://github.com/microsoft/agent-governance-toolkit)*
+
+[![CI](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/microsoft/agent-governance-toolkit/actions/workflows/ci.yml)
+[![License](https://img.shields.io/badge/license-MIT-blue.svg)](../../LICENSE)
+[![Python](https://img.shields.io/badge/python-3.9+-blue.svg)](https://python.org)
+[![PyPI](https://img.shields.io/pypi/v/agentmesh-lightning)](https://pypi.org/project/agentmesh-lightning/)
+
+## 🎯 Overview
+
+This package provides governed RL training integration:
+- **Agent-Lightning** = Training/Optimization (the "brains")
+- **Agent-OS** = Governance/Safety (the "guardrails")
+
+**Result**: Agents learn to be smart AND safe from the start.
+
+> **Note:** This package was extracted from `agent_os.integrations.agent_lightning`.
+> The old import path still works via a backward-compatibility shim but new code
+> should import from `agent_lightning_gov` directly.
+
+## 🚀 Quick Start
+
+```bash
+pip install agentmesh-lightning
+# Optional: pip install agent-os-kernel  # for kernel integration
+```
+
+```python
+from agent_lightning_gov import GovernedRunner, PolicyReward
+from agent_os import KernelSpace
+from agent_os.policies import SQLPolicy, CostControlPolicy
+
+# 1. Create governed kernel
+kernel = KernelSpace(policy=[
+    SQLPolicy(deny=["DROP", "DELETE"]),
+    CostControlPolicy(max_cost_usd=100)
+])
+
+# 2. Create governed runner
+runner = GovernedRunner(kernel)
+
+# 3. Create policy-aware reward function
+def base_accuracy(rollout):
+    return rollout.task_output.accuracy if rollout.success else 0.0
+
+reward_fn = PolicyReward(kernel, base_reward_fn=base_accuracy)
+
+# 4. Train with Agent-Lightning
+from agentlightning import Trainer
+trainer = Trainer(
+    runner=runner,
+    reward_fn=reward_fn,
+    algorithm="GRPO"
+)
+
+trainer.train(num_epochs=100)
+```
+
+## 📊 Key Benefits
+
+| Metric | Without Agent-OS | With Agent-OS |
+|--------|------------------|---------------|
+| Policy Violations | 12.3% | **0.0%** |
+| Task Accuracy | 76.4% | **79.2%** |
+| Training Stability | Variable | Consistent |
+
+## 🔧 Components
+
+### GovernedRunner
+
+Agent-Lightning runner that enforces policies during execution:
+
+```python
+from agent_lightning_gov import GovernedRunner
+
+runner = GovernedRunner(
+    kernel,
+    fail_on_violation=False,   # Continue but penalize
+    log_violations=True,        # Log all violations
+)
+
+# Execute a task
+rollout = await runner.step(task_input)
+print(f"Violations: {len(rollout.violations)}")
+print(f"Total penalty: {rollout.total_penalty}")
+```
+
+### PolicyReward
+
+Converts policy violations to RL penalties:
+
+```python
+from agent_lightning_gov import PolicyReward, RewardConfig
+
+config = RewardConfig(
+    critical_penalty=-100.0,  # Harsh penalty for critical violations
+    high_penalty=-50.0,
+    medium_penalty=-10.0,
+    low_penalty=-1.0,
+    clean_bonus=5.0,          # Bonus for no violations
+)
+
+reward_fn = PolicyReward(kernel, config=config)
+
+# Calculate reward
+reward = reward_fn(rollout)  # Base reward + policy penalties
+```
+
+### GovernedEnvironment
+
+Gym-compatible training environment:
+
+```python
+from agent_lightning_gov import GovernedEnvironment
+
+env = GovernedEnvironment(
+    kernel,
+    config=EnvironmentConfig(
+        max_steps=100,
+        terminate_on_critical=True,
+    )
+)
+
+# Standard Gym interface
+state, info = env.reset()
+while not env.terminated:
+    action = agent.get_action(state)
+    state, reward, terminated, truncated, info = env.step(action)
+```
+
+### FlightRecorderEmitter
+
+Export audit logs to LightningStore:
+
+```python
+from agent_os import FlightRecorder
+from agent_lightning_gov import FlightRecorderEmitter
+
+recorder = FlightRecorder()
+emitter = FlightRecorderEmitter(recorder)
+
+# Export to LightningStore
+emitter.emit_to_store(lightning_store)
+
+# Or export to file for analysis
+emitter.export_to_file("training_audit.json")
+
+# Get violation summary
+summary = emitter.get_violation_summary()
+print(f"Violation rate: {summary['violation_rate']:.1%}")
+```
+
+## Ecosystem
+
+Agent Lightning is one of 7 packages in the Agent Governance Toolkit:
+
+| Package | Role |
+|---------|------|
+| **Agent OS** | Policy engine — deterministic action evaluation |
+| **AgentMesh** | Trust infrastructure — identity, credentials, protocol bridges |
+| **Agent Runtime** | Execution supervisor — rings, sessions, sagas |
+| **Agent SRE** | Reliability — SLOs, circuit breakers, chaos testing |
+| **Agent Compliance** | Regulatory compliance — GDPR, HIPAA, SOX frameworks |
+| **Agent Marketplace** | Plugin lifecycle — discover, install, verify, sign |
+| **Agent Lightning** | RL training governance — governed runners, policy rewards *(this package)* |
+
+## 📋 License
+
+MIT — see [LICENSE](../../LICENSE).

agentmesh_lightning-3.0.2/pyproject.toml

@@ -0,0 +1,44 @@
+[build-system]
+requires = ["setuptools>=68.0,<69.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "agentmesh_lightning"
+version = "3.0.2"
+description = "Public Preview — Agent-Lightning RL integration for the Agent Governance Toolkit: governed training with policy enforcement"
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.9"
+authors = [
+    {name = "Microsoft Corporation", email = "agentgovtoolkit@microsoft.com"},
+]
+maintainers = [
+    {name = "Agent Governance Toolkit Team", email = "agentgovtoolkit@microsoft.com"},
+]
+keywords = [
+    "ai-agents", "governance", "reinforcement-learning",
+    "agentmesh-lightning", "agent-os", "enterprise-ai"
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = []
+
+[project.optional-dependencies]
+agent-os = ["agent-os-kernel>=1.0.0,<2.0"]
+dev = ["pytest>=7.0,<8.0", "pytest-cov"]
+
+[project.urls]
+Homepage = "https://github.com/microsoft/agent-governance-toolkit"
+Repository = "https://github.com/microsoft/agent-governance-toolkit"
+"Bug Tracker" = "https://github.com/microsoft/agent-governance-toolkit/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]

agentmesh_lightning-3.0.2/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

agentmesh_lightning-3.0.2/src/agent_lightning_gov/__init__.py

@@ -0,0 +1,36 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+"""
+Agent-Lightning Governance Integration
+=======================================
+
+Provides kernel-level safety during Agent-Lightning RL training.
+
+Key components:
+- GovernedRunner: Agent-Lightning runner with policy enforcement
+- PolicyReward: Convert policy violations to RL penalties
+- FlightRecorderEmitter: Export audit logs to LightningStore
+- GovernedEnvironment: Training environment with governance constraints
+
+Example:
+    >>> from agent_lightning_gov import GovernedRunner, PolicyReward
+    >>> from agent_os import KernelSpace
+    >>> from agent_os.policies import SQLPolicy
+    >>>
+    >>> kernel = KernelSpace(policy=SQLPolicy())
+    >>> runner = GovernedRunner(kernel)
+    >>> reward_fn = PolicyReward(kernel, base_reward_fn=accuracy)
+"""
+
+from .emitter import FlightRecorderEmitter
+from .environment import GovernedEnvironment
+from .reward import PolicyReward, policy_penalty
+from .runner import GovernedRunner
+
+__all__ = [
+    "GovernedRunner",
+    "PolicyReward",
+    "policy_penalty",
+    "FlightRecorderEmitter",
+    "GovernedEnvironment",
+]