agentnova 0.3.3__tar.gz → 0.3.4__tar.gz

{agentnova-0.3.3 → agentnova-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentnova
-Version: 0.3.3
+Version: 0.3.4
 Summary: ⚛️ AgentNova - A minimal, hackable agentic framework for local LLM inference
 Author-email: VTSTech <veritas@vts-tech.org>
 Maintainer-email: VTSTech <veritas@vts-tech.org>
@@ -49,7 +49,7 @@ Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first o
 
 [![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)
 
-<img width="1102" height="960" alt="image" src="https://github.com/user-attachments/assets/2a5fe9b4-93df-46a0-9383-9e01e0c0105d" />
+<img width="1400" height="1001" alt="image" src="https://github.com/user-attachments/assets/1bc8fb7a-415b-4750-9ce2-1e721bbf9149" />
 
 ## 📚 Documentation
 

{agentnova-0.3.3 → agentnova-0.3.4}/README.md

@@ -1,321 +1,321 @@
-# ⚛️ AgentNova R03.3
-
-**Status: Alpha**
-
-A minimal, hackable agentic framework engineered to run **entirely locally** with [Ollama](https://ollama.com) or [BitNet](https://github.com/microsoft/BitNet).
-
-Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first operation.
-
-**Written by [VTSTech](https://www.vts-tech.org)** · [GitHub](https://github.com/VTSTech/AgentNova)
-
-[![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/) [![PyPI version fury.io](https://badge.fury.io/py/agentnova.svg)](https://pypi.org/project/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.org/project/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)
-
-<img width="1102" height="960" alt="image" src="https://github.com/user-attachments/assets/2a5fe9b4-93df-46a0-9383-9e01e0c0105d" />
-
-## 📚 Documentation
-
-| Document | Description |
-|----------|-------------|
-| [Architecture.md](https://github.com/VTSTech/AgentNova/blob/main/Architecture.md) | Technical documentation for developers (directory structure, core design, orchestrator modes) |
-| [CHANGELOG.md](https://github.com/VTSTech/AgentNova/blob/main/CHANGELOG.md) | Version history and release notes (includes LocalClaw history) |
-| [TESTS.md](https://github.com/VTSTech/AgentNova/blob/main/TESTS.md) | Benchmark results, model recommendations, and testing guide |
-
-## Features
-
-- **Zero dependencies** — Uses Python stdlib only (urllib for HTTP)
-- **Ollama + BitNet backends** — Switch with `--backend` flag
-- **Dual API support** — OpenResponses (`--api resp`) and Chat-Completions (`--api comp`)
-- **Three-tier tool support** — Native, ReAct, or none (auto-detected)
-- **Small model optimized** — Fuzzy matching, argument normalization
-- **Built-in security** — Path validation, command blocklist, SSRF protection
-- **Multi-agent orchestration** — Router, pipeline, and parallel modes
-- **Soul Spec v0.5** — Persona packages with progressive disclosure
-- **ACP v1.0.5 integration** — Agent Control Panel for monitoring and control
-- **AgentSkills spec** — Skill loading with SPDX license validation
-
-## Installation
-
-```bash
-# From source
-git clone https://github.com/VTSTech/AgentNova.git
-cd AgentNova
-pip install -e .
-
-# Or from PyPI (when published)
-pip install agentnova
-```
-
-## Quick Start
-
-### CLI Usage
-
-```bash
-# Run a single prompt
-agentnova run "What is 15 * 8?" --tools calculator
-
-# Interactive chat
-agentnova chat -m qwen2.5:0.5b --tools calculator,shell
-
-# Autonomous agent mode
-agentnova agent -m qwen2.5:7b --tools calculator,shell,write_file
-
-# Use Chat-Completions API (OpenAI-compatible)
-agentnova chat -m qwen2.5:0.5b --api comp
-
-# List available models
-agentnova models
-
-# List available tools
-agentnova tools
-```
-
-### Python API
-
-```python
-from agentnova import Agent
-from agentnova.tools import make_builtin_registry
-
-# Create tools
-tools = make_builtin_registry().subset(["calculator", "shell"])
-
-# Create agent
-agent = Agent(
-    model="qwen2.5:0.5b",
-    tools=tools,
-    backend="ollama",
-)
-
-# Run
-result = agent.run("What is 15 * 8?")
-print(result.final_answer)
-print(f"Completed in {result.total_ms:.0f}ms")
-```
-
-### Chat-Completions Streaming
-
-```python
-from agentnova.backends import get_backend
-from agentnova.core.types import ApiMode
-
-# Use Chat-Completions mode with streaming
-backend = get_backend("ollama", api_mode=ApiMode.COMPLETIONS)
-
-for chunk in backend.generate_completions_stream(
-    model="qwen2.5:0.5b",
-    messages=[{"role": "user", "content": "Hello!"}],
-    response_format={"type": "json_object"}
-):
-    print(chunk["delta"], end="", flush=True)
-```
-
-### Skill License Validation
-
-```python
-from agentnova.skills import validate_spdx_license, parse_compatibility
-
-# Validate SPDX license identifier
-valid, msg = validate_spdx_license("MIT")  # (True, "Valid SPDX identifier: MIT")
-valid, msg = validate_spdx_license("Custom")  # (False, "Unknown license...")
-
-# Parse compatibility requirements
-compat = parse_compatibility("python>=3.8, ollama")
-# Returns: {"python": ">=3.8", "runtimes": ["ollama"], "frameworks": []}
-```
-
-### Multi-Agent Orchestration
-
-```python
-from agentnova import Agent, Orchestrator, AgentCard
-
-orchestrator = Orchestrator(mode="router")
-
-# Register specialized agents
-orchestrator.register(AgentCard(
-    name="math_agent",
-    description="Handles mathematical calculations",
-    capabilities=["calculate", "math", "compute"],
-    tools=["calculator"],
-))
-
-orchestrator.register(AgentCard(
-    name="file_agent",
-    description="Handles file operations",
-    capabilities=["read", "write", "file"],
-    tools=["read_file", "write_file"],
-))
-
-# Route tasks to appropriate agent
-result = orchestrator.run("Calculate 15 * 8 and save to file")
-```
-
-## Tool Support Levels
-
-AgentNova supports three levels of tool use:
-
-1. **Native** — Models with built-in function calling (qwen2.5, llama3.1+, mistral, granite, functiongemma)
-2. **ReAct** — Text-based tool use via reasoning prompts (qwen2.5-coder, qwen3)
-3. **None** — Pure reasoning without tools
-
-Tool support is auto-detected by running `agentnova models --tool-support`. Results are cached in `~/.cache/agentnova/tool_support.json`.
-
-```bash
-# Test and cache tool support for all models
-agentnova models --tool-support
-
-# Re-test (ignore cache)
-agentnova models --tool-support --no-cache
-```
-
-You can also force ReAct mode:
-
-```python
-agent = Agent(model="qwen2.5:0.5b", force_react=True)
-```
-
-## Model Families
-
-Configured model families with optimized prompts:
-
-- **qwen2.5** — Native tool support, excellent performance
-- **llama3.1/3.2/3.3** — Native tool support
-- **mistral/mixtral** — Native tool support
-- **gemma2/gemma3** — ReAct mode, special prompting
-- **granite/granitemoe** — Native tool support
-- **phi3** — Native tool support
-- **deepseek** — Native with `<think/>` tag handling
-
-## Security Features
-
-Built-in security for safe operation:
-
-- **Command blocklist** — Blocks dangerous shell commands (rm, sudo, etc.)
-- **Path validation** — Prevents access to sensitive directories
-- **SSRF protection** — Blocks requests to local/internal URLs
-- **Injection detection** — Detects shell injection patterns
-
-## Configuration
-
-Environment variables:
-
-```bash
-# Backend URLs
-OLLAMA_BASE_URL=https://your-ollama-server.com    # Default: http://localhost:11434
-BITNET_BASE_URL=http://localhost:8765              # BitNet server URL
-BITNET_TUNNEL=https://your-tunnel.com              # Alternative BitNet URL
-ACP_BASE_URL=http://localhost:8766                 # ACP server URL
-
-# Agent settings
-AGENTNOVA_BACKEND=ollama      # Default backend: ollama or bitnet
-AGENTNOVA_MODEL=qwen2.5:0.5b  # Default model
-AGENTNOVA_MAX_STEPS=10        # Maximum reasoning steps
-AGENTNOVA_DEBUG=false         # Enable debug output
-```
-
-Check current configuration:
-```bash
-agentnova config
-agentnova config --urls  # Show only URLs
-```
-
-### CLI Options (run, chat, agent)
-
-| Option | Description |
-|--------|-------------|
-| `--api resp\|comp` | API mode: OpenResponses (default) or Chat-Completions |
-| `--response-format text\|json` | Response format (Chat-Completions mode) |
-| `--truncation auto\|disabled` | Truncation behavior for long responses |
-| `--soul <path>` | Load Soul Spec persona package |
-| `--soul-level 1-3` | Progressive disclosure level |
-| `--num-ctx <tokens>` | Context window size (default: 4096) |
-| `--timeout <seconds>` | Request timeout (default: 120) |
-| `--acp` | Enable ACP (Agent Control Panel) logging |
-| `--acp-url <url>` | ACP server URL |
-
-## LocalClaw Redirect
-
-The `localclaw` command is provided for backward compatibility:
-
-```bash
-# Both work identically
-localclaw run "What is 2+2?"
-agentnova run "What is 2+2?"
-```
-
-## Tests & Examples
-
-AgentNova includes a suite of tests for validating agent capabilities:
-
-```bash
-# Basic agent test (no tools)
-python -m agentnova.examples.00_basic_agent
-
-# Quick 5-question diagnostic
-python -m agentnova.examples.01_quick_diagnostic
-
-# Tool usage tests (calculator, shell, datetime)
-python -m agentnova.examples.02_tool_test
-
-# Logic and reasoning tests (BBH-style)
-python -m agentnova.examples.03_reasoning_test
-
-# GSM8K math benchmark (50 questions)
-python -m agentnova.examples.04_gsm8k_benchmark
-```
-
-### Test Categories
-
-| Test | Questions | Focus |
-|------|-----------|-------|
-| Quick Diagnostic | 5 | Calculator tool, multi-step reasoning |
-| Tool Test | 10 | Calculator, shell, datetime tools |
-| Reasoning Test | 13 | Logic, deduction, patterns, spatial |
-| GSM8K Benchmark | 50 | Math word problems |
-
-### Benchmark Results (Quick Diagnostic)
-
-| Model | Score | Time | Tool Support |
-|-------|-------|------|-------------|
-| functiongemma:270m | 5/5 (100%) | ~20s | native |
-| granite4:350m | 5/5 (100%) | ~50s | native |
-| qwen2.5:0.5b | 5/5 (100%) | 38s | native |
-| qwen2.5-coder:0.5b | 5/5 (100%) | 93s | react |
-| qwen3:0.6b | 5/5 (100%) | 70s | react |
-
-All tested models achieve 100% on the Quick Diagnostic. Native models are ~2x faster than ReAct models due to direct API tool calling.
-
-## Development
-
-```bash
-# Install dev dependencies
-pip install -e ".[dev]"
-
-# Run unit tests
-pytest
-
-# Format code
-black agentnova
-ruff check agentnova
-```
-
-## License
-
-MIT License - See LICENSE file for details.
-
-## Author
-
-**VTSTech** — [https://www.vts-tech.org](https://www.vts-tech.org)
-
-## Contributing
-
-Contributions welcome! Please read the contributing guidelines first.
-
-## Acknowledgments
-
-- Built for local inference with [Ollama](https://ollama.ai)
-- Optimized for small, efficient models
-- Inspired by ReAct and other agentic frameworks
+# ⚛️ AgentNova R03.3
+
+**Status: Alpha**
+
+A minimal, hackable agentic framework engineered to run **entirely locally** with [Ollama](https://ollama.com) or [BitNet](https://github.com/microsoft/BitNet).
+
+Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first operation.
+
+**Written by [VTSTech](https://www.vts-tech.org)** · [GitHub](https://github.com/VTSTech/AgentNova)
+
+[![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/) [![PyPI version fury.io](https://badge.fury.io/py/agentnova.svg)](https://pypi.org/project/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.org/project/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)
+
+<img width="1400" height="1001" alt="image" src="https://github.com/user-attachments/assets/1bc8fb7a-415b-4750-9ce2-1e721bbf9149" />
+
+## 📚 Documentation
+
+| Document | Description |
+|----------|-------------|
+| [Architecture.md](https://github.com/VTSTech/AgentNova/blob/main/Architecture.md) | Technical documentation for developers (directory structure, core design, orchestrator modes) |
+| [CHANGELOG.md](https://github.com/VTSTech/AgentNova/blob/main/CHANGELOG.md) | Version history and release notes (includes LocalClaw history) |
+| [TESTS.md](https://github.com/VTSTech/AgentNova/blob/main/TESTS.md) | Benchmark results, model recommendations, and testing guide |
+
+## Features
+
+- **Zero dependencies** — Uses Python stdlib only (urllib for HTTP)
+- **Ollama + BitNet backends** — Switch with `--backend` flag
+- **Dual API support** — OpenResponses (`--api resp`) and Chat-Completions (`--api comp`)
+- **Three-tier tool support** — Native, ReAct, or none (auto-detected)
+- **Small model optimized** — Fuzzy matching, argument normalization
+- **Built-in security** — Path validation, command blocklist, SSRF protection
+- **Multi-agent orchestration** — Router, pipeline, and parallel modes
+- **Soul Spec v0.5** — Persona packages with progressive disclosure
+- **ACP v1.0.5 integration** — Agent Control Panel for monitoring and control
+- **AgentSkills spec** — Skill loading with SPDX license validation
+
+## Installation
+
+```bash
+# From source
+git clone https://github.com/VTSTech/AgentNova.git
+cd AgentNova
+pip install -e .
+
+# Or from PyPI (when published)
+pip install agentnova
+```
+
+## Quick Start
+
+### CLI Usage
+
+```bash
+# Run a single prompt
+agentnova run "What is 15 * 8?" --tools calculator
+
+# Interactive chat
+agentnova chat -m qwen2.5:0.5b --tools calculator,shell
+
+# Autonomous agent mode
+agentnova agent -m qwen2.5:7b --tools calculator,shell,write_file
+
+# Use Chat-Completions API (OpenAI-compatible)
+agentnova chat -m qwen2.5:0.5b --api comp
+
+# List available models
+agentnova models
+
+# List available tools
+agentnova tools
+```
+
+### Python API
+
+```python
+from agentnova import Agent
+from agentnova.tools import make_builtin_registry
+
+# Create tools
+tools = make_builtin_registry().subset(["calculator", "shell"])
+
+# Create agent
+agent = Agent(
+    model="qwen2.5:0.5b",
+    tools=tools,
+    backend="ollama",
+)
+
+# Run
+result = agent.run("What is 15 * 8?")
+print(result.final_answer)
+print(f"Completed in {result.total_ms:.0f}ms")
+```
+
+### Chat-Completions Streaming
+
+```python
+from agentnova.backends import get_backend
+from agentnova.core.types import ApiMode
+
+# Use Chat-Completions mode with streaming
+backend = get_backend("ollama", api_mode=ApiMode.COMPLETIONS)
+
+for chunk in backend.generate_completions_stream(
+    model="qwen2.5:0.5b",
+    messages=[{"role": "user", "content": "Hello!"}],
+    response_format={"type": "json_object"}
+):
+    print(chunk["delta"], end="", flush=True)
+```
+
+### Skill License Validation
+
+```python
+from agentnova.skills import validate_spdx_license, parse_compatibility
+
+# Validate SPDX license identifier
+valid, msg = validate_spdx_license("MIT")  # (True, "Valid SPDX identifier: MIT")
+valid, msg = validate_spdx_license("Custom")  # (False, "Unknown license...")
+
+# Parse compatibility requirements
+compat = parse_compatibility("python>=3.8, ollama")
+# Returns: {"python": ">=3.8", "runtimes": ["ollama"], "frameworks": []}
+```
+
+### Multi-Agent Orchestration
+
+```python
+from agentnova import Agent, Orchestrator, AgentCard
+
+orchestrator = Orchestrator(mode="router")
+
+# Register specialized agents
+orchestrator.register(AgentCard(
+    name="math_agent",
+    description="Handles mathematical calculations",
+    capabilities=["calculate", "math", "compute"],
+    tools=["calculator"],
+))
+
+orchestrator.register(AgentCard(
+    name="file_agent",
+    description="Handles file operations",
+    capabilities=["read", "write", "file"],
+    tools=["read_file", "write_file"],
+))
+
+# Route tasks to appropriate agent
+result = orchestrator.run("Calculate 15 * 8 and save to file")
+```
+
+## Tool Support Levels
+
+AgentNova supports three levels of tool use:
+
+1. **Native** — Models with built-in function calling (qwen2.5, llama3.1+, mistral, granite, functiongemma)
+2. **ReAct** — Text-based tool use via reasoning prompts (qwen2.5-coder, qwen3)
+3. **None** — Pure reasoning without tools
+
+Tool support is auto-detected by running `agentnova models --tool-support`. Results are cached in `~/.cache/agentnova/tool_support.json`.
+
+```bash
+# Test and cache tool support for all models
+agentnova models --tool-support
+
+# Re-test (ignore cache)
+agentnova models --tool-support --no-cache
+```
+
+You can also force ReAct mode:
+
+```python
+agent = Agent(model="qwen2.5:0.5b", force_react=True)
+```
+
+## Model Families
+
+Configured model families with optimized prompts:
+
+- **qwen2.5** — Native tool support, excellent performance
+- **llama3.1/3.2/3.3** — Native tool support
+- **mistral/mixtral** — Native tool support
+- **gemma2/gemma3** — ReAct mode, special prompting
+- **granite/granitemoe** — Native tool support
+- **phi3** — Native tool support
+- **deepseek** — Native with `<think/>` tag handling
+
+## Security Features
+
+Built-in security for safe operation:
+
+- **Command blocklist** — Blocks dangerous shell commands (rm, sudo, etc.)
+- **Path validation** — Prevents access to sensitive directories
+- **SSRF protection** — Blocks requests to local/internal URLs
+- **Injection detection** — Detects shell injection patterns
+
+## Configuration
+
+Environment variables:
+
+```bash
+# Backend URLs
+OLLAMA_BASE_URL=https://your-ollama-server.com    # Default: http://localhost:11434
+BITNET_BASE_URL=http://localhost:8765              # BitNet server URL
+BITNET_TUNNEL=https://your-tunnel.com              # Alternative BitNet URL
+ACP_BASE_URL=http://localhost:8766                 # ACP server URL
+
+# Agent settings
+AGENTNOVA_BACKEND=ollama      # Default backend: ollama or bitnet
+AGENTNOVA_MODEL=qwen2.5:0.5b  # Default model
+AGENTNOVA_MAX_STEPS=10        # Maximum reasoning steps
+AGENTNOVA_DEBUG=false         # Enable debug output
+```
+
+Check current configuration:
+```bash
+agentnova config
+agentnova config --urls  # Show only URLs
+```
+
+### CLI Options (run, chat, agent)
+
+| Option | Description |
+|--------|-------------|
+| `--api resp\|comp` | API mode: OpenResponses (default) or Chat-Completions |
+| `--response-format text\|json` | Response format (Chat-Completions mode) |
+| `--truncation auto\|disabled` | Truncation behavior for long responses |
+| `--soul <path>` | Load Soul Spec persona package |
+| `--soul-level 1-3` | Progressive disclosure level |
+| `--num-ctx <tokens>` | Context window size (default: 4096) |
+| `--timeout <seconds>` | Request timeout (default: 120) |
+| `--acp` | Enable ACP (Agent Control Panel) logging |
+| `--acp-url <url>` | ACP server URL |
+
+## LocalClaw Redirect
+
+The `localclaw` command is provided for backward compatibility:
+
+```bash
+# Both work identically
+localclaw run "What is 2+2?"
+agentnova run "What is 2+2?"
+```
+
+## Tests & Examples
+
+AgentNova includes a suite of tests for validating agent capabilities:
+
+```bash
+# Basic agent test (no tools)
+python -m agentnova.examples.00_basic_agent
+
+# Quick 5-question diagnostic
+python -m agentnova.examples.01_quick_diagnostic
+
+# Tool usage tests (calculator, shell, datetime)
+python -m agentnova.examples.02_tool_test
+
+# Logic and reasoning tests (BBH-style)
+python -m agentnova.examples.03_reasoning_test
+
+# GSM8K math benchmark (50 questions)
+python -m agentnova.examples.04_gsm8k_benchmark
+```
+
+### Test Categories
+
+| Test | Questions | Focus |
+|------|-----------|-------|
+| Quick Diagnostic | 5 | Calculator tool, multi-step reasoning |
+| Tool Test | 10 | Calculator, shell, datetime tools |
+| Reasoning Test | 13 | Logic, deduction, patterns, spatial |
+| GSM8K Benchmark | 50 | Math word problems |
+
+### Benchmark Results (Quick Diagnostic)
+
+| Model | Score | Time | Tool Support |
+|-------|-------|------|-------------|
+| functiongemma:270m | 5/5 (100%) | ~20s | native |
+| granite4:350m | 5/5 (100%) | ~50s | native |
+| qwen2.5:0.5b | 5/5 (100%) | 38s | native |
+| qwen2.5-coder:0.5b | 5/5 (100%) | 93s | react |
+| qwen3:0.6b | 5/5 (100%) | 70s | react |
+
+All tested models achieve 100% on the Quick Diagnostic. Native models are ~2x faster than ReAct models due to direct API tool calling.
+
+## Development
+
+```bash
+# Install dev dependencies
+pip install -e ".[dev]"
+
+# Run unit tests
+pytest
+
+# Format code
+black agentnova
+ruff check agentnova
+```
+
+## License
+
+MIT License - See LICENSE file for details.
+
+## Author
+
+**VTSTech** — [https://www.vts-tech.org](https://www.vts-tech.org)
+
+## Contributing
+
+Contributions welcome! Please read the contributing guidelines first.
+
+## Acknowledgments
+
+- Built for local inference with [Ollama](https://ollama.ai)
+- Optimized for small, efficient models
+- Inspired by ReAct and other agentic frameworks

{agentnova-0.3.3 → agentnova-0.3.4}/agentnova/__init__.py

@@ -28,7 +28,7 @@ Example Usage:
     agent = Agent(model="qwen2.5:0.5b", soul="/path/to/soul/package")
 """
 
-__version__ = "0.3.3"
+__version__ = "0.3.4"
 __author__ = "VTSTech"
 __status__ = "Alpha"
 

{agentnova-0.3.3 → agentnova-0.3.4}/agentnova/agent.py

@@ -900,7 +900,15 @@ Final Answer: <the answer>
                 role = msg.get('role', '?')
                 content = msg.get('content', '')
                 tc = msg.get('tool_calls', [])
-                content_preview = content[:2048] if content else '(empty)'
+                tool_call_id = msg.get('tool_call_id', '')
+                # Show just length for system prompts, content for others
+                if role == 'system':
+                    content_preview = f"<{len(content)} chars>"
+                elif role == 'tool':
+                    # Show tool message with tool_call_id
+                    content_preview = f"{content[:100] if content else '(empty)'} (tool_call_id={tool_call_id})"
+                else:
+                    content_preview = content[:200] if content else '(empty)'
                 print(f"  [MSG {i}] role={role}, content={content_preview!r}{' as tool_calls]' if tc else ']'}")
             print(f"  [DEBUG] Tools: {[t.name for t in self.tools.all()] if self.tools else None}")
 

{agentnova-0.3.3 → agentnova-0.3.4}/agentnova/backends/ollama.py

@@ -73,6 +73,48 @@ class OllamaBackend(BaseBackend):
             value = ApiMode(value.lower())
         self._api_mode = value
 
+    def _convert_messages_to_ollama_format(self, messages: list[dict]) -> list[dict]:
+        """
+        Convert messages to Ollama native format.
+        
+        Key difference from OpenAI format:
+        - OpenAI: tool_calls[].function.arguments is a JSON STRING
+        - Ollama: tool_calls[].function.arguments should be an OBJECT
+        
+        This method parses the JSON string arguments back to objects for
+        Ollama's native /api/chat endpoint.
+        """
+        converted = []
+        for msg in messages:
+            converted_msg = dict(msg)  # Copy the message
+            
+            # Convert tool_calls if present
+            if "tool_calls" in msg and msg["tool_calls"]:
+                ollama_tool_calls = []
+                for tc in msg["tool_calls"]:
+                    ollama_tc = dict(tc)
+                    if "function" in tc:
+                        func = tc["function"]
+                        args = func.get("arguments", "{}")
+                        
+                        # Parse JSON string to object for Ollama
+                        if isinstance(args, str):
+                            try:
+                                args = json.loads(args)
+                            except json.JSONDecodeError:
+                                args = {}
+                        
+                        ollama_tc["function"] = {
+                            "name": func.get("name", ""),
+                            "arguments": args
+                        }
+                    ollama_tool_calls.append(ollama_tc)
+                converted_msg["tool_calls"] = ollama_tool_calls
+            
+            converted.append(converted_msg)
+        
+        return converted
+
     def generate(
         self,
         model: str,
@@ -114,10 +156,14 @@ class OllamaBackend(BaseBackend):
 
         url = f"{self.base_url}/api/chat"
 
+        # Convert messages to Ollama native format
+        # Key difference: Ollama expects tool_call arguments as OBJECT, not JSON string
+        ollama_messages = self._convert_messages_to_ollama_format(messages)
+
         # Build request body
         body = {
             "model": model,
-            "messages": messages,
+            "messages": ollama_messages,
             "stream": False,
             "keep_alive": "1m",  # Keep model loaded briefly but clear KV cache between requests
             "options": {
@@ -144,6 +190,18 @@ class OllamaBackend(BaseBackend):
         # Debug output for request
         if os.environ.get("AGENTNOVA_DEBUG"):
             print(f"  [Ollama] Request: tools={len(tools) if tools else 0}, think={think}")
+            # Show messages being sent (truncated for readability)
+            for i, msg in enumerate(body.get("messages", [])):
+                role = msg.get("role", "?")
+                if role == "system":
+                    print(f"  [Ollama.Body] msg[{i}]: role={role}, content=<{len(msg.get('content', ''))} chars>")
+                elif role == "tool":
+                    print(f"  [Ollama.Body] msg[{i}]: role={role}, tool_call_id={msg.get('tool_call_id', 'MISSING')!r}, content={msg.get('content', '')[:50]!r}")
+                elif "tool_calls" in msg:
+                    tc = msg.get("tool_calls", [])
+                    print(f"  [Ollama.Body] msg[{i}]: role={role}, tool_calls={tc}")
+                else:
+                    print(f"  [Ollama.Body] msg[{i}]: role={role}, content={msg.get('content', '')[:100]!r}")
 
         # Make request
         start_time = time.time()

{agentnova-0.3.3 → agentnova-0.3.4}/agentnova.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentnova
-Version: 0.3.3
+Version: 0.3.4
 Summary: ⚛️ AgentNova - A minimal, hackable agentic framework for local LLM inference
 Author-email: VTSTech <veritas@vts-tech.org>
 Maintainer-email: VTSTech <veritas@vts-tech.org>
@@ -49,7 +49,7 @@ Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first o
 
 [![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)
 
-<img width="1102" height="960" alt="image" src="https://github.com/user-attachments/assets/2a5fe9b4-93df-46a0-9383-9e01e0c0105d" />
+<img width="1400" height="1001" alt="image" src="https://github.com/user-attachments/assets/1bc8fb7a-415b-4750-9ce2-1e721bbf9149" />
 
 ## 📚 Documentation
 

{agentnova-0.3.3 → agentnova-0.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agentnova"
-version = "0.3.3"
+version = "0.3.4"
 description = "⚛️ AgentNova - A minimal, hackable agentic framework for local LLM inference"
 readme = "README.md"
 license = {text = "MIT"}