chore: release api v0.3.4

webber-api/src/domains/agents/router.py

@@ -10,6 +10,7 @@ from src.domains.agents.base import get_agent, list_agents
 # Import agents to ensure they're registered
 import src.domains.agents.explore  # noqa: F401
 import src.domains.agents.plan  # noqa: F401
+import src.domains.agents.task  # noqa: F401
 from src.domains.agents.schemas import (
     AgentRunRequest,
     AgentRunResponse,

webber-api/src/domains/agents/task/__init__.py

@@ -0,0 +1,33 @@
+"""
+Task Agent - Full orchestrator for autonomous task execution.
+
+The Task agent can:
+- Execute multi-step tasks autonomously
+- Use all tools (read + write + bash)
+- Spawn sub-agents (Explore, Plan) for focused work
+- Return consolidated task summaries
+
+Usage:
+    from src.domains.agents.task import task_agent, task
+
+    # Direct agent access
+    result = await task_agent.run("Create a new user model with tests")
+
+    # Convenience function
+    result = await task("Create a new user model with tests")
+"""
+from src.domains.agents.task.agent import (
+    TaskAgentImpl,
+    TaskContext,
+    task_agent,
+    task,
+    task_stream,
+)
+
+__all__ = [
+    "TaskAgentImpl",
+    "TaskContext",
+    "task_agent",
+    "task",
+    "task_stream",
+]

webber-api/src/domains/agents/task/agent.py

@@ -0,0 +1,174 @@
+"""
+Task Agent implementation using PydanticAI.
+
+Full orchestrator agent that can:
+- Execute multi-step tasks autonomously
+- Use all tools (read + write)
+- Spawn sub-agents (Explore, Plan) for focused work
+"""
+import os
+from collections.abc import AsyncIterator
+from dataclasses import dataclass
+from typing import Any
+
+from pydantic_ai import Agent
+from pydantic_ai.models.openai import OpenAIModel
+
+from src.domains.agents.base import BaseAgent, AgentContext, register_agent
+from src.domains.agents.task.prompts import TASK_SYSTEM_PROMPT
+from src.ollama.provider import get_ollama_provider
+from src.shared.config import get_settings
+from src.shared.logging import logged, get_logger, trace_span
+
+logger = get_logger(__name__)
+
+
+@dataclass
+class TaskContext(AgentContext):
+    """
+    Context for task agent tools.
+
+    Passed to all tool functions via RunContext.
+    Uses the same fields as base AgentContext.
+    """
+    pass
+
+
+class TaskAgentImpl(BaseAgent):
+    """
+    Full orchestrator agent for autonomous task execution.
+
+    Has access to ALL tools:
+    - Read-only: read_file, glob_files, grep_content, bash_readonly
+    - Write: edit_file, write_file, bash
+    - External: web_search
+    - Orchestration: spawn_agent (launch sub-agents)
+
+    Can spawn Explore and Plan agents to offload focused tasks,
+    keeping context efficient across complex multi-step work.
+    """
+
+    name = "task"
+    description = "Autonomous multi-step task execution with sub-agent orchestration"
+
+    def __init__(self):
+        """Initialize the task agent."""
+        self._agent: Agent[TaskContext, str] | None = None
+        self._settings = get_settings()
+
+    def _create_agent(self) -> Agent[TaskContext, str]:
+        """Create the PydanticAI agent with Ollama backend."""
+        # Use sanitized Ollama provider to fix content: null issues
+        model = OpenAIModel(
+            model_name=self._settings.ollama_agent_model,
+            provider=get_ollama_provider(),
+        )
+
+        agent: Agent[TaskContext, str] = Agent(
+            model=model,
+            system_prompt=TASK_SYSTEM_PROMPT,
+            deps_type=TaskContext,
+            output_type=str,
+            # Mistral Nemo settings:
+            # - temperature 0.3 (Nemo needs slightly higher than 0.0)
+            # - tool_choice "required" forces tool use
+            model_settings={
+                "temperature": 0.3,
+                "extra_body": {"tool_choice": "required"},
+            },
+        )
+
+        # Register all tools including orchestration
+        self._register_tools(agent)
+
+        return agent
+
+    def _register_tools(self, agent: Agent[TaskContext, str]) -> None:
+        """Register all tools with the agent."""
+        from src.domains.agents.task.tools import register_task_tools
+        register_task_tools(agent)
+
+    @logged()
+    async def run(
+        self,
+        prompt: str,
+        working_dir: str | None = None,
+        allowed_paths: list[str] | None = None,
+        **kwargs: Any
+    ) -> str:
+        """
+        Run the task agent to execute a multi-step task.
+
+        Args:
+            prompt: Description of the task to execute
+            working_dir: Working directory for the agent
+            allowed_paths: Restrict tool access to these paths
+
+        Returns:
+            Consolidated task summary with results
+        """
+        ctx = TaskContext(
+            working_dir=working_dir or os.getcwd(),
+            allowed_paths=allowed_paths or self._settings.effective_allowed_paths,
+            timeout_seconds=self._settings.tool_timeout_seconds,
+        )
+
+        async with trace_span("task_agent_run"):
+            try:
+                # Use run() not run_stream() - Ollama has bugs with streaming + tools
+                result = await self.agent.run(prompt, deps=ctx)
+                return result.output
+            except Exception as e:
+                logger.exception(f"Task agent error: {e}")
+                raise
+
+    async def run_stream(
+        self,
+        prompt: str,
+        working_dir: str | None = None,
+        allowed_paths: list[str] | None = None,
+        **kwargs: Any
+    ) -> AsyncIterator[str]:
+        """
+        Run the task agent with streaming output.
+
+        Yields text chunks as they become available.
+        """
+        ctx = TaskContext(
+            working_dir=working_dir or os.getcwd(),
+            allowed_paths=allowed_paths or self._settings.effective_allowed_paths,
+            timeout_seconds=self._settings.tool_timeout_seconds,
+        )
+
+        async with trace_span("task_agent_stream"):
+            try:
+                async with self.agent.run_stream(prompt, deps=ctx) as result:
+                    async for chunk in result.stream_text():
+                        yield chunk
+            except Exception as e:
+                logger.exception(f"Task agent stream error: {e}")
+                raise
+
+
+# Create and register the singleton instance
+task_agent = TaskAgentImpl()
+register_agent(task_agent)
+
+
+async def task(
+    prompt: str,
+    working_dir: str | None = None,
+    **kwargs: Any
+) -> str:
+    """Run task execution."""
+    return await task_agent.run(prompt, working_dir=working_dir, **kwargs)
+
+
+async def task_stream(
+    prompt: str,
+    working_dir: str | None = None,
+    **kwargs: Any
+) -> AsyncIterator[str]:
+    """Run task execution with streaming."""
+    async for chunk in task_agent.run_stream(prompt, working_dir=working_dir, **kwargs):
+        yield chunk

webber-api/src/domains/agents/task/prompts.py

@@ -0,0 +1,83 @@
+"""
+System prompts for the Task agent.
+
+The Task agent is a full orchestrator that can:
+- Execute multi-step tasks autonomously
+- Use all tools (read + write)
+- Spawn sub-agents (Explore, Plan) for focused work
+"""
+
+TASK_SYSTEM_PROMPT = """You are an autonomous task execution agent.
+
+You have access to ALL tools including file editing, writing, and bash execution.
+You can also spawn sub-agents to help with complex tasks.
+
+AVAILABLE TOOLS:
+
+File Operations:
+- read_file: Read file contents with line numbers
+- glob_files: Find files by pattern
+- grep_content: Search file contents with regex
+- edit_file: Make targeted edits via find-and-replace
+- write_file: Create or overwrite files
+
+Shell:
+- bash_readonly: Read-only commands (ls, git status, git log, etc.)
+- bash: Full bash execution (git commit, pytest, mkdir, etc.)
+
+External:
+- web_search: Search the web for current information
+
+Orchestration:
+- spawn_agent: Launch sub-agents for focused tasks
+
+WORKFLOW:
+1. Understand the task requirements
+2. Break down into sub-tasks if complex
+3. Use spawn_agent for research (explore) or planning (plan)
+4. Execute implementation steps using write tools
+5. Validate changes (run tests if applicable)
+6. Return consolidated summary
+
+TOOL CALL EXAMPLES:
+
+To spawn an Explore agent for research:
+  Call spawn_agent with agent_type="explore" and prompt="find all config files"
+
+To spawn a Plan agent for design:
+  Call spawn_agent with agent_type="plan" and prompt="design user auth feature"
+
+To edit a file:
+  Call edit_file with file_path="/path/to/file.py" and old_string="old" and new_string="new"
+
+To run tests:
+  Call bash with command="pytest tests/ -v"
+
+SPAWN_AGENT USAGE:
+- Use spawn_agent to offload focused tasks to specialized agents
+- Explore agent: Fast codebase searches and analysis
+- Plan agent: Design implementation strategies
+- Keep each agent's context focused and efficient
+
+GIT DISCIPLINE:
+- Create feature branches for changes
+- Use conventional commit format (feat:, fix:, docs:, etc.)
+- Never commit directly to main
+- Run tests before committing
+
+RULES:
+- ALWAYS use tools first, then analyze results
+- Never guess file contents - read them first
+- Prefer edit_file over write_file for existing files
+- Use spawn_agent to keep context focused
+- Validate changes by running tests when applicable
+
+OUTPUT FORMAT:
+End your response with a summary:
+
+### Task Summary
+- **Accomplished:** What was done
+- **Files modified:** List of changed files
+- **Commands run:** Key commands executed
+- **Issues:** Any problems encountered
+"""

webber-api/src/domains/agents/task/tools.py

@@ -0,0 +1,350 @@
+"""
+Tool registrations for the Task agent.
+
+The Task agent has access to ALL tools:
+- Read-only tools (same as Explore/Plan)
+- Write tools (edit, write, bash full)
+- External tools (web search)
+- Orchestration (spawn sub-agents)
+"""
+from pydantic_ai import Agent, RunContext
+
+from src.domains.agents.base import AgentContext
+from src.domains.tools.file.read import ReadFileTool
+from src.domains.tools.file.glob import GlobFilesTool
+from src.domains.tools.file.edit import EditFileTool
+from src.domains.tools.file.write import WriteFileTool
+from src.domains.tools.search.grep import GrepContentTool
+from src.domains.tools.search.web import WebSearchTool
+from src.domains.tools.shell.bash import BashReadOnlyTool
+from src.domains.tools.shell.bash_full import BashTool
+
+
+def register_task_tools(agent: Agent[AgentContext, str]) -> None:
+    """
+    Register all tools with the Task agent.
+
+    Includes:
+    - Read-only tools: read_file, glob_files, grep_content, bash_readonly
+    - Write tools: edit_file, write_file, bash
+    - External: web_search
+    - Orchestration: spawn_agent
+    """
+
+    # === Read-only tools ===
+
+    @agent.tool
+    async def read_file(
+        ctx: RunContext[AgentContext],
+        file_path: str,
+        offset: int = 0,
+        limit: int = 2000
+    ) -> str:
+        """Read contents of a file with line numbers.
+
+        Args:
+            file_path: Absolute path to the file to read
+            offset: Line number to start from (0-based, default: 0)
+            limit: Maximum number of lines to read (default: 2000)
+
+        Returns:
+            File contents with line numbers, or error message.
+
+        IMPORTANT: Always use absolute paths. Read files before editing them.
+        """
+        tool = ReadFileTool(allowed_paths=ctx.deps.allowed_paths)
+        result = await tool.execute(
+            file_path=file_path,
+            offset=offset,
+            limit=limit
+        )
+        return result.to_string()
+
+    @agent.tool
+    async def glob_files(
+        ctx: RunContext[AgentContext],
+        pattern: str,
+        path: str | None = None,
+        limit: int = 100
+    ) -> str:
+        """Find files matching a glob pattern.
+
+        Args:
+            pattern: Glob pattern (e.g., "**/*.py", "src/**/*.ts", "*.md")
+            path: Directory to search in (default: working directory)
+            limit: Maximum number of files to return (default: 100)
+
+        Returns:
+            List of absolute file paths, sorted by modification time (newest first).
+
+        Examples:
+            - "**/*.py" finds all Python files
+            - "src/**/*.ts" finds TypeScript files in src/
+            - "**/test_*.py" finds all test files
+        """
+        tool = GlobFilesTool(allowed_paths=ctx.deps.allowed_paths)
+        search_path = path or ctx.deps.working_dir
+        result = await tool.execute(
+            pattern=pattern,
+            path=search_path,
+            limit=limit
+        )
+        return result.to_string()
+
+    @agent.tool
+    async def grep_content(
+        ctx: RunContext[AgentContext],
+        pattern: str,
+        path: str | None = None,
+        file_glob: str | None = None,
+        context_lines: int = 0,
+        case_sensitive: bool = True
+    ) -> str:
+        """Search file contents using regex pattern.
+
+        Args:
+            pattern: Regex pattern to search for (Python re syntax)
+            path: Directory or file to search (default: working directory)
+            file_glob: Filter files by glob (e.g., "*.py", "*.ts")
+            context_lines: Lines of context before/after matches (default: 0)
+            case_sensitive: Case-sensitive search (default: True)
+
+        Returns:
+            Matching lines with file paths and line numbers.
+            Format: "filepath:line_num: content"
+        """
+        tool = GrepContentTool(allowed_paths=ctx.deps.allowed_paths)
+        search_path = path or ctx.deps.working_dir
+        result = await tool.execute(
+            pattern=pattern,
+            path=search_path,
+            file_glob=file_glob,
+            context_lines=context_lines,
+            case_sensitive=case_sensitive
+        )
+        return result.to_string()
+
+    @agent.tool
+    async def bash_readonly(
+        ctx: RunContext[AgentContext],
+        command: str,
+        cwd: str | None = None,
+        timeout: int = 30
+    ) -> str:
+        """Execute a read-only bash command.
+
+        ALLOWED commands:
+        - File inspection: ls, find, cat, head, tail, wc, file, stat, tree, du
+        - Git (read-only): git status, git log, git diff, git show, git branch
+        - Text processing: grep, awk, sed (read-only), sort, uniq
+        - System info: pwd, whoami, hostname, which
+
+        FORBIDDEN:
+        - File modification (rm, mv, cp, mkdir, touch)
+        - Redirects (>, >>)
+        - Command chaining (&&, ||, ;)
+        - Network (curl, wget)
+
+        Args:
+            command: The bash command to execute
+            cwd: Working directory (default: agent working directory)
+            timeout: Timeout in seconds (default: 30)
+        """
+        tool = BashReadOnlyTool(allowed_paths=ctx.deps.allowed_paths)
+        working_dir = cwd or ctx.deps.working_dir
+        result = await tool.execute(
+            command=command,
+            cwd=working_dir,
+            timeout=min(timeout, ctx.deps.timeout_seconds)
+        )
+        return result.to_string()
+
+    # === Write tools ===
+
+    @agent.tool
+    async def edit_file(
+        ctx: RunContext[AgentContext],
+        file_path: str,
+        old_string: str,
+        new_string: str,
+        replace_all: bool = False
+    ) -> str:
+        """Make targeted edits to a file using find-and-replace.
+
+        Args:
+            file_path: Absolute path to the file to edit
+            old_string: The exact text to find and replace (must exist in file)
+            new_string: The replacement text
+            replace_all: If True, replace all occurrences. If False (default),
+                         old_string must be unique (appear exactly once).
+
+        Returns:
+            Success message with diff preview, or error.
+
+        IMPORTANT:
+        - old_string must exactly match file content (including whitespace)
+        - By default, old_string must appear exactly once (for safety)
+        - Always read the file first to verify exact content before editing
+        """
+        tool = EditFileTool(allowed_paths=ctx.deps.allowed_paths)
+        result = await tool.execute(
+            file_path=file_path,
+            old_string=old_string,
+            new_string=new_string,
+            replace_all=replace_all
+        )
+        return result.to_string()
+
+    @agent.tool
+    async def write_file(
+        ctx: RunContext[AgentContext],
+        file_path: str,
+        content: str
+    ) -> str:
+        """Create a new file or overwrite an existing file.
+
+        Args:
+            file_path: Absolute path to the file to create/write
+            content: The content to write to the file
+
+        Returns:
+            Success message with file path and size.
+
+        IMPORTANT:
+        - Parent directory must exist (use bash mkdir first if needed)
+        - For editing existing files, prefer edit_file instead
+        - Will overwrite existing files without confirmation
+        """
+        tool = WriteFileTool(allowed_paths=ctx.deps.allowed_paths)
+        result = await tool.execute(
+            file_path=file_path,
+            content=content
+        )
+        return result.to_string()
+
+    @agent.tool
+    async def bash(
+        ctx: RunContext[AgentContext],
+        command: str,
+        cwd: str | None = None,
+        timeout: int = 60
+    ) -> str:
+        """Execute a bash command with write capabilities.
+
+        ALLOWED:
+        - File operations: ls, find, mkdir, touch, cp, mv, rm (single files)
+        - Git (full): git add, git commit, git checkout, git merge, git pull
+        - Python: python, pip install, pytest, mypy, ruff
+        - Text processing: grep, awk, sed, sort
+        - Command chaining: && and || are allowed
+
+        FORBIDDEN:
+        - sudo, su (privilege escalation)
+        - Network: curl, wget, ssh, scp, rsync
+        - Dangerous: rm -rf, chmod 777, dd, mkfs
+
+        Args:
+            command: The bash command to execute
+            cwd: Working directory (default: agent working directory)
+            timeout: Timeout in seconds (default: 60)
+
+        Examples:
+            - "mkdir -p src/utils" creates directory
+            - "git add . && git commit -m 'fix: bug'" commits changes
+            - "pytest tests/ -v" runs tests
+        """
+        tool = BashTool(allowed_paths=ctx.deps.allowed_paths)
+        working_dir = cwd or ctx.deps.working_dir
+        result = await tool.execute(
+            command=command,
+            cwd=working_dir,
+            timeout=min(timeout, ctx.deps.timeout_seconds)
+        )
+        return result.to_string()
+
+    # === External tools ===
+
+    @agent.tool
+    async def web_search(
+        ctx: RunContext[AgentContext],
+        query: str,
+        num_results: int = 5,
+        categories: str | None = None
+    ) -> str:
+        """Search the web for current information.
+
+        Args:
+            query: Search query (e.g., "Python 3.12 new features")
+            num_results: Number of results to return (1-10, default: 5)
+            categories: Optional category filter ("general", "it", "news", "science")
+
+        Returns:
+            Search results with titles, URLs, and snippets.
+
+        Use this for:
+        - Current events or recent information
+        - Documentation updates
+        - Technical references with URLs
+        """
+        tool = WebSearchTool()
+        result = await tool.execute(
+            query=query,
+            num_results=num_results,
+            categories=categories
+        )
+        return result.to_string()
+
+    # === Orchestration tools ===
+
+    @agent.tool
+    async def spawn_agent(
+        ctx: RunContext[AgentContext],
+        agent_type: str,
+        prompt: str,
+        working_dir: str | None = None
+    ) -> str:
+        """Spawn a sub-agent to handle a focused task.
+
+        Use this to offload work to specialized agents:
+        - "explore": Fast codebase searches and analysis (read-only)
+        - "plan": Design implementation strategies (read-only)
+
+        Args:
+            agent_type: Type of agent to spawn ("explore" or "plan")
+            prompt: Task description for the sub-agent
+            working_dir: Working directory for the sub-agent (default: current)
+
+        Returns:
+            Sub-agent's consolidated response.
+
+        Examples:
+            - spawn_agent(agent_type="explore", prompt="find all test files")
+            - spawn_agent(agent_type="plan", prompt="design user auth feature")
+
+        IMPORTANT:
+        - Use sub-agents to keep context focused and efficient
+        - Explore agent for research, Plan agent for design
+        - Cannot spawn nested Task agents (recursion risk)
+        """
+        from src.domains.agents.base import get_agent
+
+        # Validate agent type
+        allowed_types = ["explore", "plan"]
+        if agent_type not in allowed_types:
+            if agent_type == "task":
+                return "Error: Cannot spawn nested Task agents (recursion risk)"
+            return f"Error: Unknown agent type '{agent_type}'. Allowed: {allowed_types}"
+
+        sub_agent = get_agent(agent_type)
+        if not sub_agent:
+            return f"Error: Agent '{agent_type}' not found in registry"
+
+        try:
+            result = await sub_agent.run(
+                prompt=prompt,
+                working_dir=working_dir or ctx.deps.working_dir,
+                allowed_paths=ctx.deps.allowed_paths,
+            )
+            return result
+        except Exception as e:
+            return f"Sub-agent error: {e}"