agentnova 0.3.2__tar.gz → 0.3.4__tar.gz

{agentnova-0.3.2 → agentnova-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentnova
-Version: 0.3.2
+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>
@@ -32,7 +32,7 @@ Requires-Dist: black>=23.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
 Dynamic: license-file
 
-# ⚛️ AgentNova R03.2
+# ⚛️ AgentNova R03.3
 
 **Status: Alpha**
 
@@ -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
 
@@ -63,10 +63,14 @@ Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first o
 
 - **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
 
@@ -94,6 +98,9 @@ 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
 
@@ -123,6 +130,37 @@ 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
@@ -218,6 +256,20 @@ 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:

{agentnova-0.3.2 → agentnova-0.3.4}/README.md

@@ -1,4 +1,4 @@
-# ⚛️ AgentNova R03.2
+# ⚛️ AgentNova R03.3
 
 **Status: Alpha**
 
@@ -15,7 +15,7 @@ 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
 
@@ -29,10 +29,14 @@ Inspired by the architecture of OpenClaw, rebuilt from scratch for local-first o
 
 - **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
 
@@ -60,6 +64,9 @@ 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
 
@@ -89,6 +96,37 @@ 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
@@ -184,6 +222,20 @@ 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:

{agentnova-0.3.2 → 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__ = "0.3.1"
+__version__ = "0.3.4"
 __author__ = "VTSTech"
 __status__ = "Alpha"
 

{agentnova-0.3.2 → agentnova-0.3.4}/agentnova/acp_plugin.py

@@ -2059,3 +2059,152 @@ class ACPPlugin:
 
         self._log(f"A2A: Broadcast {action} to {len(results)} agent(s)")
         return results
+
+    # ------------------------------------------------------------------ #
+    #  Batch Context Manager (v1.0.6)                                     #
+    # ------------------------------------------------------------------ #
+
+    def batch_context(
+        self,
+        description: str = "Batch operation",
+        auto_complete: bool = True,
+    ):
+        """
+        Context manager for batch operations.
+
+        This provides a convenient way to group multiple activities
+        into a single batch with automatic completion.
+
+        Parameters
+        ----------
+        description : str
+            Description for the batch operation
+        auto_complete : bool
+            Whether to automatically complete all activities on exit (default: True)
+
+        Yields
+        ------
+        BatchHelper
+            A helper object for adding activities to the batch
+
+        Example
+        -------
+        >>> with acp.batch_context("Read multiple config files") as batch:
+        ...     batch.add_read("/etc/config1.yaml")
+        ...     batch.add_read("/etc/config2.yaml")
+        ...     batch.add_read("/etc/config3.yaml")
+        >>> # All activities are automatically started and completed
+        """
+        return _BatchContext(self, description, auto_complete)
+
+
+class _BatchContext:
+    """
+    Internal batch context manager for grouping activities.
+
+    Collects activities and submits them as a batch when the context exits.
+    """
+
+    def __init__(self, acp: "ACPPlugin", description: str, auto_complete: bool):
+        self._acp = acp
+        self._description = description
+        self._auto_complete = auto_complete
+        self._activities: list[dict] = []
+        self._results: list[dict] = []
+        self._activity_ids: list[str] = []
+
+    def add(self, action: str, target: str, details: str = "", **kwargs) -> None:
+        """
+        Add an activity to the batch.
+
+        Parameters
+        ----------
+        action : str
+            Action type (READ, WRITE, EDIT, BASH, etc.)
+        target : str
+            Target for the action (file path, command, etc.)
+        details : str
+            Optional details about the activity
+        **kwargs
+            Additional fields (content_size, priority, etc.)
+        """
+        self._activities.append({
+            "action": action,
+            "target": target,
+            "details": details,
+            **kwargs
+        })
+
+    def add_read(self, path: str, content_size: int = 0) -> None:
+        """Add a READ activity for a file."""
+        self.add("READ", path, f"Read file: {path}", content_size=content_size)
+
+    def add_write(self, path: str, content_size: int = 0) -> None:
+        """Add a WRITE activity for a file."""
+        self.add("WRITE", path, f"Write file: {path}", content_size=content_size)
+
+    def add_edit(self, path: str, content_size: int = 0) -> None:
+        """Add an EDIT activity for a file."""
+        self.add("EDIT", path, f"Edit file: {path}", content_size=content_size)
+
+    def add_bash(self, command: str) -> None:
+        """Add a BASH activity for a command."""
+        self.add("BASH", command[:100], f"Execute: {command[:200]}")
+
+    def add_search(self, query: str) -> None:
+        """Add a SEARCH activity for a web search."""
+        self.add("SEARCH", query[:100], f"Search: {query[:200]}")
+
+    def add_api(self, url: str, method: str = "GET") -> None:
+        """Add an API activity for an HTTP request."""
+        self.add("API", url[:100], f"{method} {url[:200]}")
+
+    @property
+    def activity_ids(self) -> list[str]:
+        """Get the list of activity IDs (available after entering context)."""
+        return self._activity_ids
+
+    @property
+    def results(self) -> list[dict]:
+        """Get the batch results (available after exiting context)."""
+        return self._results
+
+    def __enter__(self):
+        """Start all activities in the batch."""
+        if not self._acp.enabled or not self._activities:
+            return self
+
+        # Start all activities in batch
+        result = self._acp.batch_start(self._activities)
+        self._results = result.get("results", [])
+        self._activity_ids = [
+            r.get("activity_id") for r in self._results if r.get("activity_id")
+        ]
+
+        # Track activities
+        for aid in self._activity_ids:
+            if aid:
+                self._acp._activity_stack.append(aid)
+
+        self._acp._log(f"Batch started: {len(self._activity_ids)} activities for '{self._description}'")
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """Complete all activities in the batch."""
+        if not self._acp.enabled or not self._activity_ids:
+            return False
+
+        if self._auto_complete:
+            # Complete all activities
+            completions = []
+            for aid in self._activity_ids:
+                result = "Completed" if exc_type is None else f"Error: {exc_val}"
+                completions.append({
+                    "activity_id": aid,
+                    "result": result,
+                })
+
+            self._acp.batch_complete(completions)
+            self._acp._log(f"Batch completed: {len(self._activity_ids)} activities")
+
+        return False  # Don't suppress exceptions