m2-harness 0.6.0__tar.gz

m2_harness-0.6.0/LICENSE

@@ -0,0 +1,17 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   Copyright 2024 Hamza
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

m2_harness-0.6.0/PKG-INFO

@@ -0,0 +1,227 @@
+Metadata-Version: 2.4
+Name: m2-harness
+Version: 0.6.0
+Summary: Cost-Aware Hierarchical Coding Agent & Context Firewall — Universal MCP Server, CLI, and Python SDK
+Author-email: Hamza <ameerhamzakhan1305@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/HamzaDevv/hierarchical-coding-agent
+Project-URL: Repository, https://github.com/HamzaDevv/hierarchical-coding-agent
+Project-URL: Documentation, https://github.com/HamzaDevv/hierarchical-coding-agent/tree/main/docs
+Project-URL: Bug Tracker, https://github.com/HamzaDevv/hierarchical-coding-agent/issues
+Keywords: ai-agent,mcp,coding-agent,context-firewall,deepseek,hierarchical-agent,model-context-protocol,llm
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=1.0.0
+Requires-Dist: mcp<2.0.0,>=1.2.0
+Requires-Dist: litellm>=1.30.0
+Requires-Dist: diskcache>=5.6.0
+Requires-Dist: tree-sitter>=0.24.0
+Requires-Dist: tree-sitter-python
+Requires-Dist: tree-sitter-javascript
+Requires-Dist: tree-sitter-typescript
+Requires-Dist: tree-sitter-go
+Requires-Dist: tree-sitter-rust
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.24.0; extra == "dev"
+Requires-Dist: build>=1.0.0; extra == "dev"
+Requires-Dist: wheel>=0.40.0; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Provides-Extra: providers
+Requires-Dist: anthropic>=0.18.0; extra == "providers"
+Requires-Dist: google-genai>=0.1.0; extra == "providers"
+Dynamic: license-file
+
+# M2 Harness 🚀 — Cost-Aware Hierarchical Coding Agent & Context Firewall
+
+[![Python Version](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue.svg)](https://www.python.org/)
+[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
+[![Tests](https://img.shields.io/badge/tests-221%20passed-brightgreen.svg)](tests/)
+[![MCP Ready](https://img.shields.io/badge/MCP-FastMCP%20Ready-purple.svg)](https://modelcontextprotocol.io/)
+
+**M2 Harness** is a high-throughput, cost-aware Autonomous Worker and Context Firewall framework. It enables **Frontier Reasoners (M1)** (such as Claude 3.7 Sonnet, Gemini 2.0 Pro, Cursor, or Google Antigravity) to delegate noisy, token-heavy tool loops (searches, test iterations, multi-file refactoring) to a **Cheap Worker (M2)** (DeepSeek V4-Flash, OpenCode Zen, or local models), filtering raw context by **80%–98% (CCR)** before returning verified structured evidence to M1.
+
+---
+
+## 🏛️ Architecture Overview
+
+```mermaid
+flowchart TD
+    User([User Prompt / M1 Frontier]) --> Router{M1 Orchestrator Router}
+    
+    subgraph Path_A ["Path A: Delegated Worker (85%+ of Tasks)"]
+        Router -->|Heavy Search / Multi-file / Test Loop| M2Runtime[M2 Worker Engine]
+        M2Runtime --> L0[Zero-Token L0 Layer: AST & Git]
+        M2Runtime --> SandboxedTools[Execution Sandbox & Symlink Jail]
+        M2Runtime --> ContextFirewall[Context Firewall: 80-98% CCR]
+        ContextFirewall --> ResultContract[Structured ResultContract JSON]
+    end
+
+    subgraph Path_B ["Path B: Direct Precision Fallback"]
+        Router -->|Subtle Race / Exact Bytecode / Review| DirectInspection[Direct Inspection & Precision Edits]
+    end
+
+    subgraph Path_C ["Path C: Autonomous Diagnostic Loop"]
+        Router -->|Investigate Bug / TDD Repro| DiagnosticLoop[M2 Diagnostic Hypothesis Loop]
+        DiagnosticLoop --> TestOracles[Independent Test & AST Oracles]
+    end
+
+    ResultContract --> Synthesis[M1 Final Synthesis & User Response]
+    DirectInspection --> Synthesis
+```
+
+---
+
+## 🌟 Key Features
+
+1. **Context Firewall & Active Working Memory**: Filters thousands of characters of verbose logs, greps, and test traces down to high-signal structured evidence ($CCR \ge 80\%–98\%$).
+2. **Zero-Token L0 Deterministic Layer**: Instant Python AST outlines, symbol definitions, and git diff summaries consuming **0 LLM tokens**.
+3. **Tri-Modal Execution**:
+   * **Path A (Delegated)**: Offloads heavy tool loops to cheap workers.
+   * **Path B (Direct)**: Precision fallback for subtle race conditions or exact reviews.
+   * **Path C (Diagnostic)**: Autonomous TDD failure reproduction and repair loops.
+4. **Deterministic Tri-Level Replay**: 100% offline, zero-network regression testing across Provider, Runtime, and Semantic ($Hash_A = Hash_B = Hash_C$) layers.
+5. **M2-Bench & Independent Oracles**: Multi-oracle evaluation (`TestOracle`, `ASTOracle`, `FileOracle`, `IntegrityOracle` anti-tampering) with mathematically rigorous metrics (VSR, FSR, Verification Gap, FTAR, ROI).
+6. **Release-Grade Diagnostics (`m2 doctor`)**: Deep environment inspection across Python, Git, Tree-sitter parsers, sandbox jails, and providers.
+
+---
+
+## 📦 Installation
+
+```bash
+pip install m2-harness
+```
+
+Or install from source:
+```bash
+git clone https://github.com/HamzaDevv/hierarchical-coding-agent.git
+cd hierarchical-coding-agent
+pip install -e .
+```
+
+---
+
+## 🩺 Environment Diagnostics (`m2 doctor`)
+
+Verify your environment and workspace health in one command:
+
+```bash
+m2 doctor
+```
+
+```text
+=========================================================================
+   🩺 M2 WORKER DIAGNOSTIC HEALTH REPORT (m2 doctor)                    
+=========================================================================
+  [✓ PASS] Python Environment     : Python 3.13.3 with all dependencies ready
+  [✓ PASS] Git & Workspace        : Workspace writable and valid Git repository
+  [✓ PASS] L0 AST Engine          : L0 zero-token AST parser operational
+  [✓ PASS] Security Sandbox       : Execution sandbox path jail and env sanitization active
+  [✓ PASS] LLM Providers          : Providers ready (Replay, Zen, DeepSeek, Gemini)
+  [✓ PASS] Deterministic Replay   : Deterministic replay fixtures and schema v2.0 verified
+-------------------------------------------------------------------------
+  Summary: 6 Passed | 0 Warnings | 0 Failures
+  Overall Status: ✅ READY FOR PRODUCTION
+=========================================================================
+```
+
+Use `--strict` in CI/CD pipelines to fail on any warning:
+```bash
+m2 doctor --strict --json
+```
+
+---
+
+## 🚀 Quick Start (CLI)
+
+```bash
+# Execute one-shot task
+m2 "Find all references to ResultContract and outline their symbols"
+
+# Launch instant zero-token AST code outline (0 LLM tokens)
+m2 outline
+
+# Launch instant zero-token git diff summary (0 LLM tokens)
+m2 diff
+
+# Scaffold cognitive rule files (AGENTS.md, .cursorrules) into project
+m2 init
+
+# Launch local Webview HUD live dashboard
+m2 hud --port 4040
+
+# Replay an execution trace offline
+m2 replay tests/replay/golden_task --mode semantic
+
+# Run benchmark suite
+m2 bench run --suite dev --baselines C
+```
+
+---
+
+## 🔌 Model Context Protocol (FastMCP) Integration
+
+M2 exposes a high-performance FastMCP server for IDEs (Cursor, Windsurf, Claude Desktop, Antigravity):
+
+```json
+{
+  "mcpServers": {
+    "m2-worker-agent": {
+      "command": "m2-mcp-server",
+      "env": {
+        "DEEPSEEK_API_KEY": "sk-...",
+        "WORKSPACE_ROOT": "/path/to/your/project"
+      }
+    }
+  }
+}
+```
+
+---
+
+## 🐍 Python SDK Usage
+
+```python
+from m1_m2_agent import M1OrchestratorAgent, TaskContract
+
+# Initialize M1/M2 Hierarchical Agent
+agent = M1OrchestratorAgent(workspace_root=".")
+
+# Route and execute task through Context Firewall
+result = agent.route_and_execute(
+    objective="Analyze contracts/models.py and verify ResultContract fields"
+)
+
+print(f"Status: {result['contract']['status']}")
+print(f"Evidence: {result['contract']['evidence']}")
+print(f"Context Compression: {agent.get_telemetry_report()['context_compression_ratio']}%")
+```
+
+---
+
+## 📊 Documentation Index
+
+* 📐 [Architecture Guide](docs/architecture.md)
+* ⚙️ [Runtime & Event Subsystem](docs/runtime.md)
+* 🛡️ [Context Firewall & Memory](docs/context-firewall.md)
+* ⚡ [Deterministic Replay](docs/replay.md)
+* 🧪 [M2-Bench & Multi-Oracle Evaluation](docs/benchmarking.md)
+* 🌐 [Model Providers](docs/providers.md)
+
+---
+
+## 📄 License
+
+Licensed under the [Apache License, Version 2.0](LICENSE).

m2_harness-0.6.0/README.md

@@ -0,0 +1,181 @@
+# M2 Harness 🚀 — Cost-Aware Hierarchical Coding Agent & Context Firewall
+
+[![Python Version](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue.svg)](https://www.python.org/)
+[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
+[![Tests](https://img.shields.io/badge/tests-221%20passed-brightgreen.svg)](tests/)
+[![MCP Ready](https://img.shields.io/badge/MCP-FastMCP%20Ready-purple.svg)](https://modelcontextprotocol.io/)
+
+**M2 Harness** is a high-throughput, cost-aware Autonomous Worker and Context Firewall framework. It enables **Frontier Reasoners (M1)** (such as Claude 3.7 Sonnet, Gemini 2.0 Pro, Cursor, or Google Antigravity) to delegate noisy, token-heavy tool loops (searches, test iterations, multi-file refactoring) to a **Cheap Worker (M2)** (DeepSeek V4-Flash, OpenCode Zen, or local models), filtering raw context by **80%–98% (CCR)** before returning verified structured evidence to M1.
+
+---
+
+## 🏛️ Architecture Overview
+
+```mermaid
+flowchart TD
+    User([User Prompt / M1 Frontier]) --> Router{M1 Orchestrator Router}
+    
+    subgraph Path_A ["Path A: Delegated Worker (85%+ of Tasks)"]
+        Router -->|Heavy Search / Multi-file / Test Loop| M2Runtime[M2 Worker Engine]
+        M2Runtime --> L0[Zero-Token L0 Layer: AST & Git]
+        M2Runtime --> SandboxedTools[Execution Sandbox & Symlink Jail]
+        M2Runtime --> ContextFirewall[Context Firewall: 80-98% CCR]
+        ContextFirewall --> ResultContract[Structured ResultContract JSON]
+    end
+
+    subgraph Path_B ["Path B: Direct Precision Fallback"]
+        Router -->|Subtle Race / Exact Bytecode / Review| DirectInspection[Direct Inspection & Precision Edits]
+    end
+
+    subgraph Path_C ["Path C: Autonomous Diagnostic Loop"]
+        Router -->|Investigate Bug / TDD Repro| DiagnosticLoop[M2 Diagnostic Hypothesis Loop]
+        DiagnosticLoop --> TestOracles[Independent Test & AST Oracles]
+    end
+
+    ResultContract --> Synthesis[M1 Final Synthesis & User Response]
+    DirectInspection --> Synthesis
+```
+
+---
+
+## 🌟 Key Features
+
+1. **Context Firewall & Active Working Memory**: Filters thousands of characters of verbose logs, greps, and test traces down to high-signal structured evidence ($CCR \ge 80\%–98\%$).
+2. **Zero-Token L0 Deterministic Layer**: Instant Python AST outlines, symbol definitions, and git diff summaries consuming **0 LLM tokens**.
+3. **Tri-Modal Execution**:
+   * **Path A (Delegated)**: Offloads heavy tool loops to cheap workers.
+   * **Path B (Direct)**: Precision fallback for subtle race conditions or exact reviews.
+   * **Path C (Diagnostic)**: Autonomous TDD failure reproduction and repair loops.
+4. **Deterministic Tri-Level Replay**: 100% offline, zero-network regression testing across Provider, Runtime, and Semantic ($Hash_A = Hash_B = Hash_C$) layers.
+5. **M2-Bench & Independent Oracles**: Multi-oracle evaluation (`TestOracle`, `ASTOracle`, `FileOracle`, `IntegrityOracle` anti-tampering) with mathematically rigorous metrics (VSR, FSR, Verification Gap, FTAR, ROI).
+6. **Release-Grade Diagnostics (`m2 doctor`)**: Deep environment inspection across Python, Git, Tree-sitter parsers, sandbox jails, and providers.
+
+---
+
+## 📦 Installation
+
+```bash
+pip install m2-harness
+```
+
+Or install from source:
+```bash
+git clone https://github.com/HamzaDevv/hierarchical-coding-agent.git
+cd hierarchical-coding-agent
+pip install -e .
+```
+
+---
+
+## 🩺 Environment Diagnostics (`m2 doctor`)
+
+Verify your environment and workspace health in one command:
+
+```bash
+m2 doctor
+```
+
+```text
+=========================================================================
+   🩺 M2 WORKER DIAGNOSTIC HEALTH REPORT (m2 doctor)                    
+=========================================================================
+  [✓ PASS] Python Environment     : Python 3.13.3 with all dependencies ready
+  [✓ PASS] Git & Workspace        : Workspace writable and valid Git repository
+  [✓ PASS] L0 AST Engine          : L0 zero-token AST parser operational
+  [✓ PASS] Security Sandbox       : Execution sandbox path jail and env sanitization active
+  [✓ PASS] LLM Providers          : Providers ready (Replay, Zen, DeepSeek, Gemini)
+  [✓ PASS] Deterministic Replay   : Deterministic replay fixtures and schema v2.0 verified
+-------------------------------------------------------------------------
+  Summary: 6 Passed | 0 Warnings | 0 Failures
+  Overall Status: ✅ READY FOR PRODUCTION
+=========================================================================
+```
+
+Use `--strict` in CI/CD pipelines to fail on any warning:
+```bash
+m2 doctor --strict --json
+```
+
+---
+
+## 🚀 Quick Start (CLI)
+
+```bash
+# Execute one-shot task
+m2 "Find all references to ResultContract and outline their symbols"
+
+# Launch instant zero-token AST code outline (0 LLM tokens)
+m2 outline
+
+# Launch instant zero-token git diff summary (0 LLM tokens)
+m2 diff
+
+# Scaffold cognitive rule files (AGENTS.md, .cursorrules) into project
+m2 init
+
+# Launch local Webview HUD live dashboard
+m2 hud --port 4040
+
+# Replay an execution trace offline
+m2 replay tests/replay/golden_task --mode semantic
+
+# Run benchmark suite
+m2 bench run --suite dev --baselines C
+```
+
+---
+
+## 🔌 Model Context Protocol (FastMCP) Integration
+
+M2 exposes a high-performance FastMCP server for IDEs (Cursor, Windsurf, Claude Desktop, Antigravity):
+
+```json
+{
+  "mcpServers": {
+    "m2-worker-agent": {
+      "command": "m2-mcp-server",
+      "env": {
+        "DEEPSEEK_API_KEY": "sk-...",
+        "WORKSPACE_ROOT": "/path/to/your/project"
+      }
+    }
+  }
+}
+```
+
+---
+
+## 🐍 Python SDK Usage
+
+```python
+from m1_m2_agent import M1OrchestratorAgent, TaskContract
+
+# Initialize M1/M2 Hierarchical Agent
+agent = M1OrchestratorAgent(workspace_root=".")
+
+# Route and execute task through Context Firewall
+result = agent.route_and_execute(
+    objective="Analyze contracts/models.py and verify ResultContract fields"
+)
+
+print(f"Status: {result['contract']['status']}")
+print(f"Evidence: {result['contract']['evidence']}")
+print(f"Context Compression: {agent.get_telemetry_report()['context_compression_ratio']}%")
+```
+
+---
+
+## 📊 Documentation Index
+
+* 📐 [Architecture Guide](docs/architecture.md)
+* ⚙️ [Runtime & Event Subsystem](docs/runtime.md)
+* 🛡️ [Context Firewall & Memory](docs/context-firewall.md)
+* ⚡ [Deterministic Replay](docs/replay.md)
+* 🧪 [M2-Bench & Multi-Oracle Evaluation](docs/benchmarking.md)
+* 🌐 [Model Providers](docs/providers.md)
+
+---
+
+## 📄 License
+
+Licensed under the [Apache License, Version 2.0](LICENSE).

m2_harness-0.6.0/pyproject.toml

@@ -0,0 +1,85 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "m2-harness"
+version = "0.6.0"
+description = "Cost-Aware Hierarchical Coding Agent & Context Firewall — Universal MCP Server, CLI, and Python SDK"
+readme = "README.md"
+license = {text = "Apache-2.0"}
+requires-python = ">=3.10"
+authors = [
+    {name = "Hamza", email = "ameerhamzakhan1305@gmail.com"}
+]
+keywords = [
+    "ai-agent",
+    "mcp",
+    "coding-agent",
+    "context-firewall",
+    "deepseek",
+    "hierarchical-agent",
+    "model-context-protocol",
+    "llm"
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "openai>=1.0.0",
+    "mcp>=1.2.0,<2.0.0",
+    "litellm>=1.30.0",
+    "diskcache>=5.6.0",
+    "tree-sitter>=0.24.0",
+    "tree-sitter-python",
+    "tree-sitter-javascript",
+    "tree-sitter-typescript",
+    "tree-sitter-go",
+    "tree-sitter-rust",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0.0",
+    "pytest-asyncio>=0.24.0",
+    "build>=1.0.0",
+    "wheel>=0.40.0",
+    "twine>=4.0.0",
+]
+providers = [
+    "anthropic>=0.18.0",
+    "google-genai>=0.1.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/HamzaDevv/hierarchical-coding-agent"
+Repository = "https://github.com/HamzaDevv/hierarchical-coding-agent"
+Documentation = "https://github.com/HamzaDevv/hierarchical-coding-agent/tree/main/docs"
+"Bug Tracker" = "https://github.com/HamzaDevv/hierarchical-coding-agent/issues"
+
+[project.scripts]
+m2 = "m1_m2_agent.standalone.cli:main"
+m1-m2-cli = "m1_m2_agent.standalone.cli:main"
+m2-mcp-server = "m1_m2_agent.mcp.server:main"
+m2-hud = "m1_m2_agent.standalone.cli:hud_main"
+m2-init = "m1_m2_agent.scaffold:main"
+m2-config = "m1_m2_agent.standalone.config_wizard:config_main"
+m2-doctor = "m1_m2_agent.standalone.cli:doctor_main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["m1_m2_agent*"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src", "."]
+asyncio_default_fixture_loop_scope = "function"

m2_harness-0.6.0/setup.cfg

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

m2_harness-0.6.0/src/m1_m2_agent/__init__.py

@@ -0,0 +1,159 @@
+"""
+M2 Harness — Hierarchical Coding Agent Architecture
+"""
+
+__version__ = "0.6.0"
+
+# Clean top-level exports
+from m1_m2_agent.runtime.runtime import M2Runtime
+from m1_m2_agent.engine.client import M2WorkerEngine
+from m1_m2_agent.engine.config import M2Config
+from m1_m2_agent.tools.dispatcher import ToolDispatcher
+from m1_m2_agent.harness.agent_runner import M1OrchestratorAgent
+from m1_m2_agent.contracts.models import (
+    TaskContract,
+    ResultContract,
+    TaskStatus,
+    BudgetSpec,
+    VerificationSpec,
+    SecuritySpec
+)
+from m1_m2_agent.runtime.state_machine import StateMachine, RuntimeState
+
+# GATE 2: Evidence module
+from m1_m2_agent.evidence.models import EvidenceBundle, EvidenceItem, CitationRef
+from m1_m2_agent.evidence.collector import EvidenceCollector
+from m1_m2_agent.evidence.scorer import ConfidenceScorer
+from m1_m2_agent.kernel.budget import BudgetTracker, ContextBudget
+
+# GATE 3: Context Firewall V3 & Security
+from m1_m2_agent.engine.working_state import WorkingState, Fact, Hypothesis, Action
+from m1_m2_agent.engine.context_budget import ContextBudgetManager, ContextBudgetSnapshot
+from m1_m2_agent.tools.spec import ToolSpec, ToolCapability, ToolRisk, DEFAULT_TOOL_SPECS
+from m1_m2_agent.security.sandbox import ExecutionSandbox
+from m1_m2_agent.security.policy_engine import PolicyEngine, PolicyDecision, PolicyEvaluationResult
+
+# GATE 4: Model-Agnostic Providers & Escalation V2
+from m1_m2_agent.providers.base import ModelProvider, ProviderCapabilities
+from m1_m2_agent.providers.litellm_provider import LiteLLMProvider
+from m1_m2_agent.providers.zen_provider import ZenProvider
+from m1_m2_agent.providers.replay_provider import ReplayProvider
+from m1_m2_agent.providers.registry import ProviderRegistry
+from m1_m2_agent.engine.retry import RetryPolicy
+from m1_m2_agent.escalation.manager import EscalationReason, EscalationManager, EscalationPacket
+
+# GATE 5: Deterministic Replay & M2-Bench Suite
+from m1_m2_agent.replay.schema import DeterminismContract, ReplayMode, TraceManifest, ReplayResultReport
+from m1_m2_agent.replay.recorder import TraceRecorder
+from m1_m2_agent.replay.loader import TraceLoader
+from m1_m2_agent.replay.replayer import DeterministicReplayer
+from m1_m2_agent.replay.hashing import compute_canonical_semantic_hash
+from m1_m2_agent.benchmark.models import (
+    BenchmarkTask,
+    BenchmarkTaskResult,
+    BenchmarkOutcome,
+    TaskCategory,
+    DifficultyTier,
+    FailureType,
+)
+from m1_m2_agent.benchmark.evaluator import IndependentBenchmarkEvaluator
+from m1_m2_agent.benchmark.metrics import BenchmarkMetrics, MetricsCalculator
+from m1_m2_agent.benchmark.runner import BenchmarkRunner, BenchmarkSuiteLoader
+
+# GATE 6: Production Polish, EventBus V2, Pricing & Diagnostics
+from m1_m2_agent.events.types import RuntimeEventType
+from m1_m2_agent.events.models import EventRecord, RuntimeEvent, redact_secrets
+from m1_m2_agent.events.bus import EventBus, global_event_bus
+from m1_m2_agent.pricing.models import ModelPricing
+from m1_m2_agent.pricing.registry import PricingRegistry
+from m1_m2_agent.doctor.checks import DiagnosticCheckResult
+from m1_m2_agent.doctor.runner import DoctorRunner
+
+# Convenient aliases
+M2 = M2WorkerEngine
+Task = TaskContract
+Result = ResultContract
+
+__all__ = [
+    "M2",
+    "M2Runtime",
+    "M2WorkerEngine",
+    "M1OrchestratorAgent",
+    "ToolDispatcher",
+    "TaskContract",
+    "ResultContract",
+    "TaskStatus",
+    "BudgetSpec",
+    "VerificationSpec",
+    "SecuritySpec",
+    "StateMachine",
+    "RuntimeState",
+    "Task",
+    "Result",
+    "M2Config",
+    # GATE 2
+    "EvidenceBundle",
+    "EvidenceItem",
+    "CitationRef",
+    "EvidenceCollector",
+    "ConfidenceScorer",
+    "BudgetTracker",
+    "ContextBudget",
+    # GATE 3
+    "WorkingState",
+    "Fact",
+    "Hypothesis",
+    "Action",
+    "ContextBudgetManager",
+    "ContextBudgetSnapshot",
+    "ToolSpec",
+    "ToolCapability",
+    "ToolRisk",
+    "DEFAULT_TOOL_SPECS",
+    "ExecutionSandbox",
+    "PolicyEngine",
+    "PolicyDecision",
+    "PolicyEvaluationResult",
+    # GATE 4
+    "ModelProvider",
+    "ProviderCapabilities",
+    "LiteLLMProvider",
+    "ZenProvider",
+    "ReplayProvider",
+    "ProviderRegistry",
+    "RetryPolicy",
+    "EscalationReason",
+    "EscalationManager",
+    "EscalationPacket",
+    # GATE 5
+    "DeterminismContract",
+    "ReplayMode",
+    "TraceManifest",
+    "ReplayResultReport",
+    "TraceRecorder",
+    "TraceLoader",
+    "DeterministicReplayer",
+    "compute_canonical_semantic_hash",
+    "BenchmarkTask",
+    "BenchmarkTaskResult",
+    "BenchmarkOutcome",
+    "TaskCategory",
+    "DifficultyTier",
+    "FailureType",
+    "IndependentBenchmarkEvaluator",
+    "BenchmarkMetrics",
+    "MetricsCalculator",
+    "BenchmarkRunner",
+    "BenchmarkSuiteLoader",
+    # GATE 6
+    "RuntimeEventType",
+    "EventRecord",
+    "RuntimeEvent",
+    "redact_secrets",
+    "EventBus",
+    "global_event_bus",
+    "ModelPricing",
+    "PricingRegistry",
+    "DiagnosticCheckResult",
+    "DoctorRunner",
+]