agentnova 0.2.3__tar.gz → 0.2.5__tar.gz

{agentnova-0.2.3 → agentnova-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentnova
-Version: 0.2.3
+Version: 0.2.5
 Summary: A minimal, hackable agentic framework for Ollama and BitNet - local-first AI agent toolkit
 Author-email: VTSTech <veritas@vts-tech.org>
 Maintainer-email: VTSTech <veritas@vts-tech.org>
@@ -34,7 +34,7 @@ Requires-Dist: black>=23.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
 Dynamic: license-file
 
-# ⚛️ AgentNova R02.3
+# ⚛️ AgentNova R02.5
 
 A minimal, hackable agentic framework engineered to run **entirely locally** with [Ollama](https://ollama.com) or [BitNet](https://github.com/microsoft/BitNet).
 
@@ -44,7 +44,9 @@ Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first o
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/VTSTech/AgentNova/blob/main/AgentNova.ipynb)
 [![GitHub commits](https://badgen.net/github/commits/VTSTech/AgentNova)](https://GitHub.com/VTSTech/AgentNova/commit/) [![GitHub latest commit](https://badgen.net/github/last-commit/VTSTech/AgentNova)](https://GitHub.com/VTSTech/AgentNova/commit/)
-[![pip - agentnova](https://img.shields.io/badge/pip-agentnova-2ea44f?logo=PyPi)](https://pypi.org/project/agentnova/)
+
+[![pip - agentnova](https://img.shields.io/badge/pip-agentnova-2ea44f?logo=PyPi)](https://pypi.org/project/agentnova/) [![PyPI version fury.io](https://badge.fury.io/py/agentnova.svg)](https://pypi.python.org/pypi/agentnova/) [![PyPI download month](https://img.shields.io/pypi/dm/agentnova.svg)](https://pypi.org/project/agentnova/) [![PyPI download day](https://img.shields.io/pypi/dd/agentnova.svg)](https://pypi.python.org/pypi/agentnova/)
+
 [![License](https://img.shields.io/badge/License-MIT-blue)](#license) [![Go to Python website](https://img.shields.io/badge/dynamic/toml?url=https%3A%2F%2Fraw.githubusercontent.com%2FVTSTech%2FAgentNova%2Frefs%2Fheads%2Fmain%2Fpyproject.toml&query=project.requires-python&label=python&logo=python&logoColor=white)](https://python.org)
 
 ---
@@ -199,7 +201,7 @@ agentnova models --tool_support
 
 ### Performance by Tool Support
 
-R02.3 benchmark results (15-test suite):
+R02.5 benchmark results (15-test suite):
 
 | Model | Params | Tool Support | Score | Time |
 |-------|--------|--------------|-------|------|
@@ -211,19 +213,19 @@ R02.3 benchmark results (15-test suite):
 
 **Quick Diagnostic (Test 15 - 5 questions, ~30s/model):**
 
-| Model | Score | Tool Support |
-|-------|-------|--------------|
-| **`qwen3.5:0.8b`** | **100%** | native |
-| **`qwen2.5:0.5b`** | **100%** | react |
-| `functiongemma:270m` | 80% | native |
-| `granite4:350m` | 80% | native |
-| `qwen3:0.6b` | 60% | react |
+| Model | Score | Time | Tool Support |
+|-------|-------|------|--------------|
+| **`dolphin3.0-llama3:1b`** | **100%** | 48.7s | native |
+| **`granite4:350m`** | **100%** | 75.2s | native |
+| **`qwen2.5-coder:0.5b`** | **100%** | 76.0s | react |
+| **`qwen3:0.6b`** | **100%** | 151.0s | react |
+| `functiongemma:270m` | 80% | 28.5s | native |
+| `dolphin3.0-qwen2.5:0.5b` | 80% | 38.4s | none |
 
-**Key improvements in R02.3**:
-- **+13%** for granite3.1-moe:1b (80% → 93%) from few-shot fix
-- **+20%** for llama3.2:1b (67% → 87%) from observation role fix
-- **qwen3:0.6b restored** from 0% (broken) with `think=False` API fix
-- **qwen3.5:0.8b** new sub-1B champion with 100% on quick diagnostic
+**Key improvements in R02.5**:
+- **4 models achieve 100%** on quick diagnostic (dolphin3.0-llama3:1b fastest at 48.7s)
+- **Module refactoring** - agent.py split into 6 focused modules (~1550 lines from ~2770)
+- **All tests passing** after module separation, backward compatibility maintained
 
 ---
 
@@ -274,7 +276,7 @@ Output shows:
 - **Tool Support** - `✓ native`, `ReAct`, `○ none`, or `untested`
 
 ```
-⚛️ AgentNova R02.3 Models
+⚛️ AgentNova R02.5 Models
   Model                                      Family       Context    Tool Support
   ──────────────────────────────────────────────────────────────────────────────
   gemma3:270m                                gemma3       32K        ○ none

{agentnova-0.2.3 → agentnova-0.2.5}/README.md

@@ -1,4 +1,4 @@
-# ⚛️ AgentNova R02.3
+# ⚛️ AgentNova R02.5
 
 A minimal, hackable agentic framework engineered to run **entirely locally** with [Ollama](https://ollama.com) or [BitNet](https://github.com/microsoft/BitNet).
 
@@ -8,7 +8,9 @@ Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first o
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/VTSTech/AgentNova/blob/main/AgentNova.ipynb)
 [![GitHub commits](https://badgen.net/github/commits/VTSTech/AgentNova)](https://GitHub.com/VTSTech/AgentNova/commit/) [![GitHub latest commit](https://badgen.net/github/last-commit/VTSTech/AgentNova)](https://GitHub.com/VTSTech/AgentNova/commit/)
-[![pip - agentnova](https://img.shields.io/badge/pip-agentnova-2ea44f?logo=PyPi)](https://pypi.org/project/agentnova/)
+
+[![pip - agentnova](https://img.shields.io/badge/pip-agentnova-2ea44f?logo=PyPi)](https://pypi.org/project/agentnova/) [![PyPI version fury.io](https://badge.fury.io/py/agentnova.svg)](https://pypi.python.org/pypi/agentnova/) [![PyPI download month](https://img.shields.io/pypi/dm/agentnova.svg)](https://pypi.org/project/agentnova/) [![PyPI download day](https://img.shields.io/pypi/dd/agentnova.svg)](https://pypi.python.org/pypi/agentnova/)
+
 [![License](https://img.shields.io/badge/License-MIT-blue)](#license) [![Go to Python website](https://img.shields.io/badge/dynamic/toml?url=https%3A%2F%2Fraw.githubusercontent.com%2FVTSTech%2FAgentNova%2Frefs%2Fheads%2Fmain%2Fpyproject.toml&query=project.requires-python&label=python&logo=python&logoColor=white)](https://python.org)
 
 ---
@@ -163,7 +165,7 @@ agentnova models --tool_support
 
 ### Performance by Tool Support
 
-R02.3 benchmark results (15-test suite):
+R02.5 benchmark results (15-test suite):
 
 | Model | Params | Tool Support | Score | Time |
 |-------|--------|--------------|-------|------|
@@ -175,19 +177,19 @@ R02.3 benchmark results (15-test suite):
 
 **Quick Diagnostic (Test 15 - 5 questions, ~30s/model):**
 
-| Model | Score | Tool Support |
-|-------|-------|--------------|
-| **`qwen3.5:0.8b`** | **100%** | native |
-| **`qwen2.5:0.5b`** | **100%** | react |
-| `functiongemma:270m` | 80% | native |
-| `granite4:350m` | 80% | native |
-| `qwen3:0.6b` | 60% | react |
+| Model | Score | Time | Tool Support |
+|-------|-------|------|--------------|
+| **`dolphin3.0-llama3:1b`** | **100%** | 48.7s | native |
+| **`granite4:350m`** | **100%** | 75.2s | native |
+| **`qwen2.5-coder:0.5b`** | **100%** | 76.0s | react |
+| **`qwen3:0.6b`** | **100%** | 151.0s | react |
+| `functiongemma:270m` | 80% | 28.5s | native |
+| `dolphin3.0-qwen2.5:0.5b` | 80% | 38.4s | none |
 
-**Key improvements in R02.3**:
-- **+13%** for granite3.1-moe:1b (80% → 93%) from few-shot fix
-- **+20%** for llama3.2:1b (67% → 87%) from observation role fix
-- **qwen3:0.6b restored** from 0% (broken) with `think=False` API fix
-- **qwen3.5:0.8b** new sub-1B champion with 100% on quick diagnostic
+**Key improvements in R02.5**:
+- **4 models achieve 100%** on quick diagnostic (dolphin3.0-llama3:1b fastest at 48.7s)
+- **Module refactoring** - agent.py split into 6 focused modules (~1550 lines from ~2770)
+- **All tests passing** after module separation, backward compatibility maintained
 
 ---
 
@@ -238,7 +240,7 @@ Output shows:
 - **Tool Support** - `✓ native`, `ReAct`, `○ none`, or `untested`
 
 ```
-⚛️ AgentNova R02.3 Models
+⚛️ AgentNova R02.5 Models
   Model                                      Family       Context    Tool Support
   ──────────────────────────────────────────────────────────────────────────────
   gemma3:270m                                gemma3       32K        ○ none

{agentnova-0.2.3 → agentnova-0.2.5}/agentnova/__init__.py

@@ -1,211 +1,212 @@
-"""
-⚛️ AgentNova R02.3 - A minimal, hackable agentic framework for Ollama and BitNet
-
-Written by VTSTech
-https://www.vts-tech.org
-https://github.com/VTSTech/AgentNova
-"""
-
-import os
-
-from .core.agent import Agent, AgentRun, StepResult
-from .core.memory import Memory
-from .core.tools import Tool, ToolRegistry, ToolParam
-from .core.ollama_client import OllamaClient
-from .core.orchestrator import Orchestrator, AgentCard
-from .skills import SkillLoader, Skill, SkillRegistry
-from .acp_plugin import ACPPlugin, create_acp_agent
-from .core.model_family_config import (
-    ModelFamilyConfig, FAMILY_CONFIGS,
-    get_family_config, get_stop_tokens, supports_tools,
-    get_tool_format, get_preferred_temperature, should_use_few_shot,
-    get_few_shot_style, has_known_issues, get_react_system_suffix,
-    get_native_tool_hints,
-)
-
-# Config exports
-from .config import (
-    OLLAMA_BASE_URL,
-    BITNET_BASE_URL,
-    ACP_BASE_URL,
-    ACP_USER,
-    ACP_PASS,
-    DEFAULT_MODEL,
-    AGENTNOVA_BACKEND,
-)
-
-# R00: BitNet backend support
-try:
-    from .bitnet_client import BitnetClient, KNOWN_MODELS
-    _BITNET_AVAILABLE = True
-except ImportError:
-    _BITNET_AVAILABLE = False
-    BitnetClient = None
-    KNOWN_MODELS = []
-
-
-def get_default_client():
-    """
-    Get the default client based on AGENTNOVA_BACKEND setting.
-    
-    Returns
-    -------
-    OllamaClient or BitnetClient
-        The appropriate client for the configured backend.
-    
-    Examples
-    --------
-    >>> # With AGENTNOVA_BACKEND=ollama (default)
-    >>> client = get_default_client()  # Returns OllamaClient
-    
-    >>> # With AGENTNOVA_BACKEND=bitnet
-    >>> client = get_default_client()  # Returns BitnetClient
-    """
-    if AGENTNOVA_BACKEND == "bitnet":
-        if not _BITNET_AVAILABLE:
-            raise ImportError("BitNet backend requested but bitnet_client not available")
-        return BitnetClient()
-    else:
-        return OllamaClient()
-
-
-def get_available_models(client=None):
-    """
-    Get list of available models from the configured backend.
-    
-    Parameters
-    ----------
-    client : OllamaClient or BitnetClient, optional
-        Client to use. Creates one via get_default_client() if not provided.
-    
-    Returns
-    -------
-    list[str]
-        List of model names available on the backend.
-    """
-    if client is None:
-        client = get_default_client()
-    
-    if not client.is_running():
-        return []
-    
-    return client.list_models() or []
-
-
-def get_system_prompt(model: str, client=None, default_prompt: str = None):
-    """
-    Get the system prompt based on AGENTNOVA_USE_MF_SYS environment variable.
-    
-    If AGENTNOVA_USE_MF_SYS=1, returns the Modelfile's system prompt for the model.
-    Otherwise returns the provided default_prompt.
-    
-    Parameters
-    ----------
-    model : str
-        Model name to get system prompt for.
-    client : OllamaClient or BitnetClient, optional
-        Client to use. Creates one via get_default_client() if not provided.
-    default_prompt : str, optional
-        Default system prompt to use if AGENTNOVA_USE_MF_SYS is not set.
-        If None and AGENTNOVA_USE_MF_SYS=1 but no Modelfile system prompt,
-        returns None (agent will use its own default).
-    
-    Returns
-    -------
-    str or None
-        The system prompt to use, or None.
-    
-    Examples
-    --------
-    >>> # Without AGENTNOVA_USE_MF_SYS set
-    >>> sys_prompt = get_system_prompt("llama3.2", default_prompt="You are helpful.")
-    >>> print(sys_prompt)  # "You are helpful."
-    
-    >>> # With AGENTNOVA_USE_MF_SYS=1
-    >>> sys_prompt = get_system_prompt("qwen2.5-coder", default_prompt="You are helpful.")
-    >>> print(sys_prompt)  # Modelfile's system prompt, e.g., "You are Qwen..."
-    """
-    use_mf_sys = os.environ.get("AGENTNOVA_USE_MF_SYS", "0") == "1"
-    
-    if use_mf_sys:
-        if client is None:
-            client = get_default_client()
-        
-        # Only OllamaClient has get_modelfile_system_prompt
-        if hasattr(client, "get_modelfile_system_prompt"):
-            mf_sys = client.get_modelfile_system_prompt(model)
-            if mf_sys:
-                print(f"  📜 Using Modelfile system prompt ({len(mf_sys)} chars)")
-                return mf_sys
-            else:
-                print(f"  ⚠ No SYSTEM prompt in Modelfile for '{model}', using default")
-                return default_prompt
-    
-    return default_prompt
-
-# R00 Enhancements
-from .core.orchestrator_enhanced import Orchestrator as EnhancedOrchestrator, AgentCard as EnhancedAgentCard
-
-# Tool support detection
-from .cli import get_tool_support
-
-# Shared args for test scripts
-from .shared_args import add_shared_args, parse_shared_args, SharedConfig
-
-# R00: Agent Mode
-from .agent_mode import (
-    AgentMode, AgentState, TaskPlan, Step, Action,
-    create_file_write_action, create_file_delete_action,
-    create_mkdir_action, create_shell_action,
-    format_status, format_progress,
-)
-
-__all__ = [
-    # Core
-    "Agent", "AgentRun", "StepResult",
-    "Memory", "Tool", "ToolRegistry", "ToolParam",
-    "OllamaClient", "Orchestrator", "AgentCard",
-    # Skills
-    "SkillLoader", "Skill", "SkillRegistry",
-    # R00 Enhancements
-    "EnhancedOrchestrator", "EnhancedAgentCard",
-    "ACPPlugin",
-    # R00: Backend-agnostic helpers
-    "get_default_client",
-    "get_available_models",
-    "get_system_prompt",
-    "get_tool_support",  # Tool support detection
-    "model_discovery",
-    "add_shared_args",   # Shared CLI args for test scripts
-    "parse_shared_args",
-    "SharedConfig",
-    # R00: Agent Mode
-    "AgentMode", "AgentState", "TaskPlan", "Step", "Action",
-    "create_file_write_action", "create_file_delete_action",
-    "create_mkdir_action", "create_shell_action",
-    "format_status", "format_progress",
-    # R02.3: Model Family Configuration
-    "ModelFamilyConfig", "FAMILY_CONFIGS",
-    "get_family_config", "get_stop_tokens", "supports_tools",
-    "get_tool_format", "get_preferred_temperature", "should_use_few_shot",
-    "get_few_shot_style", "has_known_issues", "get_react_system_suffix",
-    "get_native_tool_hints",
-    # Config exports
-    "OLLAMA_BASE_URL",
-    "BITNET_BASE_URL", 
-    "ACP_BASE_URL",
-    "ACP_USER",
-    "ACP_PASS",
-    "DEFAULT_MODEL",
-    "AGENTNOVA_BACKEND",
-]
-
-# Conditionally export BitNet
-if _BITNET_AVAILABLE:
-    __all__.extend(["BitnetClient", "KNOWN_MODELS"])
-
-__version__ = "0.2.2"
-__author__ = "VTSTech"
-__author_email__ = "contact@vts-tech.org"
-__url__ = "https://github.com/VTSTech/AgentNova"
-__website__ = "https://www.vts-tech.org"
+"""
+⚛️ AgentNova R02.5 - A minimal, hackable agentic framework for Ollama and BitNet
+
+Written by VTSTech
+https://www.vts-tech.org
+https://github.com/VTSTech/AgentNova
+"""
+
+import os
+
+from .core.agent import Agent
+from .core.models import AgentRun, StepResult
+from .core.memory import Memory
+from .core.tools import Tool, ToolRegistry, ToolParam
+from .core.ollama_client import OllamaClient
+from .core.orchestrator import Orchestrator, AgentCard
+from .skills import SkillLoader, Skill, SkillRegistry
+from .acp_plugin import ACPPlugin, create_acp_agent
+from .core.model_family_config import (
+    ModelFamilyConfig, FAMILY_CONFIGS,
+    get_family_config, get_stop_tokens, supports_tools,
+    get_tool_format, get_preferred_temperature, should_use_few_shot,
+    get_few_shot_style, has_known_issues, get_react_system_suffix,
+    get_native_tool_hints,
+)
+
+# Config exports
+from .config import (
+    OLLAMA_BASE_URL,
+    BITNET_BASE_URL,
+    ACP_BASE_URL,
+    ACP_USER,
+    ACP_PASS,
+    DEFAULT_MODEL,
+    AGENTNOVA_BACKEND,
+)
+
+# R02: BitNet backend support
+try:
+    from .bitnet_client import BitnetClient, KNOWN_MODELS
+    _BITNET_AVAILABLE = True
+except ImportError:
+    _BITNET_AVAILABLE = False
+    BitnetClient = None
+    KNOWN_MODELS = []
+
+
+def get_default_client():
+    """
+    Get the default client based on AGENTNOVA_BACKEND setting.
+    
+    Returns
+    -------
+    OllamaClient or BitnetClient
+        The appropriate client for the configured backend.
+    
+    Examples
+    --------
+    >>> # With AGENTNOVA_BACKEND=ollama (default)
+    >>> client = get_default_client()  # Returns OllamaClient
+    
+    >>> # With AGENTNOVA_BACKEND=bitnet
+    >>> client = get_default_client()  # Returns BitnetClient
+    """
+    if AGENTNOVA_BACKEND == "bitnet":
+        if not _BITNET_AVAILABLE:
+            raise ImportError("BitNet backend requested but bitnet_client not available")
+        return BitnetClient()
+    else:
+        return OllamaClient()
+
+
+def get_available_models(client=None):
+    """
+    Get list of available models from the configured backend.
+    
+    Parameters
+    ----------
+    client : OllamaClient or BitnetClient, optional
+        Client to use. Creates one via get_default_client() if not provided.
+    
+    Returns
+    -------
+    list[str]
+        List of model names available on the backend.
+    """
+    if client is None:
+        client = get_default_client()
+    
+    if not client.is_running():
+        return []
+    
+    return client.list_models() or []
+
+
+def get_system_prompt(model: str, client=None, default_prompt: str = None):
+    """
+    Get the system prompt based on AGENTNOVA_USE_MF_SYS environment variable.
+    
+    If AGENTNOVA_USE_MF_SYS=1, returns the Modelfile's system prompt for the model.
+    Otherwise returns the provided default_prompt.
+    
+    Parameters
+    ----------
+    model : str
+        Model name to get system prompt for.
+    client : OllamaClient or BitnetClient, optional
+        Client to use. Creates one via get_default_client() if not provided.
+    default_prompt : str, optional
+        Default system prompt to use if AGENTNOVA_USE_MF_SYS is not set.
+        If None and AGENTNOVA_USE_MF_SYS=1 but no Modelfile system prompt,
+        returns None (agent will use its own default).
+    
+    Returns
+    -------
+    str or None
+        The system prompt to use, or None.
+    
+    Examples
+    --------
+    >>> # Without AGENTNOVA_USE_MF_SYS set
+    >>> sys_prompt = get_system_prompt("llama3.2", default_prompt="You are helpful.")
+    >>> print(sys_prompt)  # "You are helpful."
+    
+    >>> # With AGENTNOVA_USE_MF_SYS=1
+    >>> sys_prompt = get_system_prompt("qwen2.5-coder", default_prompt="You are helpful.")
+    >>> print(sys_prompt)  # Modelfile's system prompt, e.g., "You are Qwen..."
+    """
+    use_mf_sys = os.environ.get("AGENTNOVA_USE_MF_SYS", "0") == "1"
+    
+    if use_mf_sys:
+        if client is None:
+            client = get_default_client()
+        
+        # Only OllamaClient has get_modelfile_system_prompt
+        if hasattr(client, "get_modelfile_system_prompt"):
+            mf_sys = client.get_modelfile_system_prompt(model)
+            if mf_sys:
+                print(f"  📜 Using Modelfile system prompt ({len(mf_sys)} chars)")
+                return mf_sys
+            else:
+                print(f"  ⚠ No SYSTEM prompt in Modelfile for '{model}', using default")
+                return default_prompt
+    
+    return default_prompt
+
+# R02 Enhancements
+from .core.orchestrator_enhanced import Orchestrator as EnhancedOrchestrator, AgentCard as EnhancedAgentCard
+
+# Tool support detection
+from .cli import get_tool_support
+
+# Shared args for test scripts
+from .shared_args import add_shared_args, parse_shared_args, SharedConfig
+
+# R02: Agent Mode
+from .agent_mode import (
+    AgentMode, AgentState, TaskPlan, Step, Action,
+    create_file_write_action, create_file_delete_action,
+    create_mkdir_action, create_shell_action,
+    format_status, format_progress,
+)
+
+__all__ = [
+    # Core
+    "Agent", "AgentRun", "StepResult",
+    "Memory", "Tool", "ToolRegistry", "ToolParam",
+    "OllamaClient", "Orchestrator", "AgentCard",
+    # Skills
+    "SkillLoader", "Skill", "SkillRegistry",
+    # R02 Enhancements
+    "EnhancedOrchestrator", "EnhancedAgentCard",
+    "ACPPlugin",
+    # R02: Backend-agnostic helpers
+    "get_default_client",
+    "get_available_models",
+    "get_system_prompt",
+    "get_tool_support",  # Tool support detection
+    "model_discovery",
+    "add_shared_args",   # Shared CLI args for test scripts
+    "parse_shared_args",
+    "SharedConfig",
+    # R02: Agent Mode
+    "AgentMode", "AgentState", "TaskPlan", "Step", "Action",
+    "create_file_write_action", "create_file_delete_action",
+    "create_mkdir_action", "create_shell_action",
+    "format_status", "format_progress",
+    # R02.5: Model Family Configuration
+    "ModelFamilyConfig", "FAMILY_CONFIGS",
+    "get_family_config", "get_stop_tokens", "supports_tools",
+    "get_tool_format", "get_preferred_temperature", "should_use_few_shot",
+    "get_few_shot_style", "has_known_issues", "get_react_system_suffix",
+    "get_native_tool_hints",
+    # Config exports
+    "OLLAMA_BASE_URL",
+    "BITNET_BASE_URL", 
+    "ACP_BASE_URL",
+    "ACP_USER",
+    "ACP_PASS",
+    "DEFAULT_MODEL",
+    "AGENTNOVA_BACKEND",
+]
+
+# Conditionally export BitNet
+if _BITNET_AVAILABLE:
+    __all__.extend(["BitnetClient", "KNOWN_MODELS"])
+
+__version__ = "0.2.5"
+__author__ = "VTSTech"
+__author_email__ = "veritas@vts-tech.org"
+__url__ = "https://github.com/VTSTech/AgentNova"
+__website__ = "https://www.vts-tech.org"

{agentnova-0.2.3 → agentnova-0.2.5}/agentnova/__main__.py

@@ -1,27 +1,27 @@
-#!/usr/bin/env python3
-"""
-⚛️ AgentNova R00 — Command Line Interface
-
-Entry point for: python -m agentnova [command] [options]
-
-Commands:
-  run     Run the agent on a single prompt and exit
-  chat    Interactive multi-turn conversation with memory
-  models  List models available in Ollama
-  tools   List available built-in tools
-  skills  List available Agent Skills
-
-Examples:
-  python -m agentnova run "What is the capital of France?"
-  python -m agentnova chat --model llama3.1:8b --tools calculator,shell
-  python -m agentnova models
-  python -m agentnova tools
-  python -m agentnova skills
-
-Written by VTSTech · https://www.vts-tech.org · https://github.com/VTSTech/AgentNova
-"""
-
-from agentnova.cli import main
-
-if __name__ == "__main__":
-    main()
+#!/usr/bin/env python3
+"""
+⚛️ AgentNova R02 — Command Line Interface
+
+Entry point for: python -m agentnova [command] [options]
+
+Commands:
+  run     Run the agent on a single prompt and exit
+  chat    Interactive multi-turn conversation with memory
+  models  List models available in Ollama
+  tools   List available built-in tools
+  skills  List available Agent Skills
+
+Examples:
+  python -m agentnova run "What is the capital of France?"
+  python -m agentnova chat --model llama3.1:8b --tools calculator,shell
+  python -m agentnova models
+  python -m agentnova tools
+  python -m agentnova skills
+
+Written by VTSTech · https://www.vts-tech.org · https://github.com/VTSTech/AgentNova
+"""
+
+from agentnova.cli import main
+
+if __name__ == "__main__":
+    main()