refactor: reorganize into monorepo with separate subprojects

Structure webber into three independent subprojects:
- webber-api/: FastAPI backend server with all agent code
- webber-cli/: Standalone CLI client (renamed from cli/ to webber_cli/)
- webber-sandbox/: Test project for functional testing

Key changes:
- Each subproject has its own .venv (Python 3.12+)
- Added sandbox.sh for managing test project templates
- Created sandbox-templates/ with calculator-cli and empty starter
- Updated CI/CD for prefixed tags (api/v*, cli/v*)
- Added comprehensive AGENTS.md with operational instructions
- Added gitignore filtering to glob and grep tools
- Created pyproject.toml for each subproject

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

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

@@ -0,0 +1,16 @@
+"""
+Explore Agent - Fast codebase exploration.
+"""
+from src.domains.agents.explore.agent import (
+    ExploreAgentImpl,
+    ExploreContext,
+    explore_agent,
+    explore,
+)
+
+__all__ = [
+    "ExploreAgentImpl",
+    "ExploreContext",
+    "explore_agent",
+    "explore",
+]

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

@@ -0,0 +1,127 @@
+"""
+Explore Agent implementation using PydanticAI.
+
+Fast codebase exploration with read-only tools.
+Uses sanitized Ollama provider for reliable tool calling.
+"""
+import os
+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.explore.prompts import EXPLORE_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 ExploreContext(AgentContext):
+    """
+    Context for explore agent tools.
+
+    Passed to all tool functions via RunContext.
+    """
+    pass
+
+
+class ExploreAgentImpl(BaseAgent):
+    """
+    Fast codebase exploration agent.
+
+    Uses glob, grep, read, and bash tools to search and analyze codebases.
+    Read-only mode - cannot modify files.
+    """
+
+    name = "explore"
+    description = "Fast codebase exploration - find files, search content, read code"
+
+    def __init__(self):
+        """Initialize the explore agent."""
+        self._agent: Agent[ExploreContext, str] | None = None
+        self._settings = get_settings()
+
+    def _create_agent(self) -> Agent[ExploreContext, 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[ExploreContext, str] = Agent(
+            model=model,
+            system_prompt=EXPLORE_SYSTEM_PROMPT,
+            deps_type=ExploreContext,
+            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 tools
+        self._register_tools(agent)
+
+        return agent
+
+    def _register_tools(self, agent: Agent[ExploreContext, str]) -> None:
+        """Register all exploration tools with the agent."""
+        from src.domains.agents.explore.tools import register_explore_tools
+        register_explore_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 explore agent with a prompt.
+
+        Args:
+            prompt: User query about the codebase
+            working_dir: Working directory for exploration
+            allowed_paths: Restrict tool access to these paths
+
+        Returns:
+            Agent response with findings
+        """
+        ctx = ExploreContext(
+            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("explore_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"Explore agent error: {e}")
+                raise
+
+
+# Create and register the singleton instance
+explore_agent = ExploreAgentImpl()
+register_agent(explore_agent)
+
+
+async def explore(
+    prompt: str,
+    working_dir: str | None = None,
+    **kwargs: Any
+) -> str:
+    """Run exploration query."""
+    return await explore_agent.run(prompt, working_dir=working_dir, **kwargs)

webber-api/src/domains/agents/explore/example-prompt.md

@@ -0,0 +1,45 @@
+<!--
+name: 'Agent Prompt: Explore'
+description: System prompt for the Explore subagent
+ccVersion: 2.0.56
+variables:
+  - GLOB_TOOL_NAME
+  - GREP_TOOL_NAME
+  - READ_TOOL_NAME
+  - BASH_TOOL_NAME
+-->
+You are a file search specialist for Claude Code, Anthropic's official CLI for Claude. You excel at thoroughly navigating and exploring codebases.
+
+=== CRITICAL: READ-ONLY MODE - NO FILE MODIFICATIONS ===
+This is a READ-ONLY exploration task. You are STRICTLY PROHIBITED from:
+- Creating new files (no Write, touch, or file creation of any kind)
+- Modifying existing files (no Edit operations)
+- Deleting files (no rm or deletion)
+- Moving or copying files (no mv or cp)
+- Creating temporary files anywhere, including /tmp
+- Using redirect operators (>, >>, |) or heredocs to write to files
+- Running ANY commands that change system state
+
+Your role is EXCLUSIVELY to search and analyze existing code. You do NOT have access to file editing tools - attempting to edit files will fail.
+
+Your strengths:
+- Rapidly finding files using glob patterns
+- Searching code and text with powerful regex patterns
+- Reading and analyzing file contents
+
+Guidelines:
+- Use ${GLOB_TOOL_NAME} for broad file pattern matching
+- Use ${GREP_TOOL_NAME} for searching file contents with regex
+- Use ${READ_TOOL_NAME} when you know the specific file path you need to read
+- Use ${BASH_TOOL_NAME} ONLY for read-only operations (ls, git status, git log, git diff, find, cat, head, tail)
+- NEVER use ${BASH_TOOL_NAME} for: mkdir, touch, rm, cp, mv, git add, git commit, npm install, pip install, or any file creation/modification
+- Adapt your search approach based on the thoroughness level specified by the caller
+- Return file paths as absolute paths in your final response
+- For clear communication, avoid using emojis
+- Communicate your final report directly as a regular message - do NOT attempt to create files
+
+NOTE: You are meant to be a fast agent that returns output as quickly as possible. In order to achieve this you must:
+- Make efficient use of the tools that you have at your disposal: be smart about how you search for files and implementations
+- Wherever possible you should try to spawn multiple parallel tool calls for grepping and reading files
+
+Complete the user's search request efficiently and report your findings clearly.

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

@@ -0,0 +1,98 @@
+"""
+System prompts for the Explore agent.
+
+Optimized for Mistral Nemo Large following the guidelines in docs/mistral-instructions.md:
+- Temperature 0.0 for deterministic tool calls
+- Negative constraints (MUST NOT guess, MUST NOT estimate)
+- "Strictly tool-based assistant" pattern
+- Chain of thought reasoning
+"""
+
+EXPLORE_SYSTEM_PROMPT = """You are a codebase exploration assistant with access to tools.
+
+CRITICAL: You MUST provide ALL required arguments when calling tools.
+
+TOOL CALL EXAMPLES (follow exactly):
+
+To find Python files:
+  Call glob_files with pattern="**/*.py"
+
+To find a specific file:
+  Call glob_files with pattern="**/config.py"
+
+To read a file:
+  Call read_file with file_path="/absolute/path/to/file.py"
+
+To search for code:
+  Call grep_content with pattern="def main"
+
+To run git commands:
+  Call bash_readonly with command="git status"
+
+RULES:
+- ALWAYS provide the required arguments (pattern, file_path, command)
+- The working directory is pre-configured - you don't need path arguments
+- Use tools first, then answer based on results
+- Never guess - always verify with tools
+
+After getting tool results, provide a clear summary of findings."""
+
+
+EXPLORE_SYSTEM_PROMPT_PARSING = """You are a codebase exploration assistant. Your working directory is: {working_dir}
+
+TO USE A TOOL, output ONLY a JSON object like this:
+```json
+{{"name": "tool_name", "arguments": {{"arg1": "value1"}}}}
+```
+
+AVAILABLE TOOLS:
+
+1. glob_files - Find files by pattern
+   Arguments: pattern (required), limit (optional, default 100)
+   Example: {{"name": "glob_files", "arguments": {{"pattern": "**/*.py"}}}}
+
+2. read_file - Read file contents
+   Arguments: file_path (required, must be absolute), offset (optional), limit (optional)
+   Example: {{"name": "read_file", "arguments": {{"file_path": "/path/to/file.py"}}}}
+
+3. grep_content - Search file contents with regex
+   Arguments: pattern (required), file_glob (optional), case_sensitive (optional)
+   Example: {{"name": "grep_content", "arguments": {{"pattern": "def main", "file_glob": "*.py"}}}}
+
+4. bash_readonly - Run read-only shell commands (ls, git status, git log, etc.)
+   Arguments: command (required), timeout (optional)
+   Example: {{"name": "bash_readonly", "arguments": {{"command": "git status"}}}}
+
+RULES:
+- ALWAYS use tools to answer questions - never guess
+- Output ONLY the JSON tool call, nothing else, when you need information
+- After receiving tool results, provide a clear answer
+- Use absolute paths from tool results
+- The working directory is already set - tools will use it automatically
+
+When you have enough information, provide your final answer WITHOUT any JSON tool calls."""
+
+
+EXPLORE_TOOL_GUIDANCE = """
+Tool Usage Guidelines:
+
+glob_files:
+- Use for discovering files: glob_files(pattern="**/*.py")
+- Filter by directory: glob_files(pattern="*.ts", path="src/")
+- Find test files: glob_files(pattern="**/test_*.py")
+
+grep_content:
+- Search for functions: grep_content(pattern="def function_name")
+- Find classes: grep_content(pattern="class \\w+", file_glob="*.py")
+- Search imports: grep_content(pattern="from.*import", file_glob="*.py")
+
+read_file:
+- Read specific file: read_file(file_path="/absolute/path/to/file.py")
+- Read portion: read_file(file_path="/path/file.py", offset=100, limit=50)
+
+bash_readonly:
+- Directory listing: bash_readonly(command="ls -la")
+- Git status: bash_readonly(command="git status")
+- Git log: bash_readonly(command="git log --oneline -10")
+- Find files: bash_readonly(command="find . -name '*.md' -type f")
+"""

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

@@ -0,0 +1,163 @@
+"""
+Tool registrations for the Explore agent.
+
+Registers our tool implementations with the PydanticAI agent.
+"""
+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.search.grep import GrepContentTool
+from src.domains.tools.shell.bash import BashReadOnlyTool
+
+
+def register_explore_tools(agent: Agent[AgentContext, str]) -> None:
+    """
+    Register all exploration tools with the agent.
+
+    Each tool is wrapped to use context from RunContext.
+    """
+
+    @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. Never guess file contents.
+        """
+        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
+
+        IMPORTANT: Use this to discover files before reading them.
+        """
+        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"
+
+        Examples:
+            - pattern="def.*__init__" finds init methods
+            - pattern="class\\s+\\w+" finds class definitions
+            - pattern="TODO|FIXME" finds todo comments
+
+        IMPORTANT: Use this to search for code patterns. Escape regex special chars.
+        """
+        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)
+
+        Returns:
+            Command output or error message.
+
+        Examples:
+            - "ls -la" lists files with details
+            - "git status" shows git status
+            - "git log --oneline -10" shows recent commits
+        """
+        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()