hud-python 0.4.11__py3-none-any.whl → 0.4.13__py3-none-any.whl

hud/__main__.py

@@ -0,0 +1,8 @@
+"""Allow running CLI with python -m hud."""
+
+from __future__ import annotations
+
+from hud.cli import main
+
+if __name__ == "__main__":
+    main()

hud/agents/base.py

@@ -306,7 +306,7 @@ class MCPAgent(ABC):
                         if decision == "STOP":
                             # Try to submit response through lifecycle tool
                             await self._maybe_submit_response(response, messages)
-                            
+
                             logger.info("Stopping execution")
                             final_response = response
                             break
@@ -487,7 +487,7 @@ class MCPAgent(ABC):
             self._available_tools.append(tool)
             # Simplified mapping - just tool name to tool
             self._tool_map[tool.name] = tool
-            
+
             # Auto-detect response tool as a lifecycle tool
             if tool.name == "response" and "response" not in self.lifecycle_tools:
                 logger.debug("Auto-detected 'response' tool as a lifecycle tool")
@@ -495,7 +495,7 @@ class MCPAgent(ABC):
 
     async def _maybe_submit_response(self, response: AgentResponse, messages: list[Any]) -> None:
         """Submit response through lifecycle tool if available.
-        
+
         Args:
             response: The agent's response
             messages: The current message history (will be modified in-place)
@@ -506,17 +506,16 @@ class MCPAgent(ABC):
             try:
                 # Call the response tool with the agent's response
                 response_tool_call = MCPToolCall(
-                    name="response",
-                    arguments={"response": response.content, "messages": messages}
+                    name="response", arguments={"response": response.content, "messages": messages}
                 )
                 response_results = await self.call_tools(response_tool_call)
-                
+
                 # Format and add the response tool results to messages
                 response_messages = await self.format_tool_results(
                     [response_tool_call], response_results
                 )
                 messages.extend(response_messages)
-                
+
                 # Mark the task as done
                 logger.info("Response lifecycle tool executed, marking task as done")
             except Exception as e:
@@ -579,7 +578,7 @@ class MCPAgent(ABC):
                 logger.warning("Failed to close auto-created trace: %s", e)
             finally:
                 self._auto_trace_cm = None
-        
+
         # Clean up auto-created client
         if self._auto_created_client and self.mcp_client:
             try:

hud/agents/langchain.py

@@ -15,10 +15,10 @@ import hud
 if TYPE_CHECKING:
     from langchain.schema.language_model import BaseLanguageModel
     from langchain_core.tools import BaseTool
-    from mcp_use.adapters.langchain_adapter import LangChainAdapter
+    from mcp_use.adapters.langchain_adapter import LangChainAdapter  # type: ignore[attr-defined]
 
 try:
-    from mcp_use.adapters.langchain_adapter import LangChainAdapter
+    from mcp_use.adapters.langchain_adapter import LangChainAdapter  # type: ignore[attr-defined]
 except ImportError:
     LangChainAdapter = None  # type: ignore[misc, assignment]
 

hud/agents/tests/test_openai.py

@@ -17,7 +17,9 @@ class TestOperatorAgent:
     @pytest.fixture
     def mock_mcp_client(self):
         """Create a mock MCP client."""
-        mcp_client = MagicMock()
+        mcp_client = AsyncMock()
+        # Set up the mcp_config attribute as a regular dict, not a coroutine
+        mcp_client.mcp_config = {"test_server": {"url": "http://test"}}
         return mcp_client
 
     @pytest.fixture

hud/cli/__init__.py

@@ -4,15 +4,15 @@ from __future__ import annotations
 
 import asyncio
 import json
-import os
 import sys
-from pathlib import Path  # noqa: TC003
+from pathlib import Path
 
 import typer
 from rich.console import Console
 from rich.panel import Panel
 from rich.table import Table
 
+from . import list_func as list_module
 from .analyze import (
     analyze_environment,
     analyze_environment_from_config,
@@ -20,15 +20,14 @@ from .analyze import (
 )
 from .build import build_command
 from .clone import clone_repository, get_clone_message, print_error, print_tutorial
-from .cursor import get_cursor_config_path, list_cursor_servers, parse_cursor_config
 from .debug import debug_mcp_stdio
+from .dev import run_mcp_dev_server
 from .init import create_environment
-from . import list_func as list_module
-from .mcp_server import run_mcp_dev_server
 from .pull import pull_command
 from .push import push_command
 from .remove import remove_command
-from .utils import CaptureLogger
+from .utils.cursor import get_cursor_config_path, list_cursor_servers, parse_cursor_config
+from .utils.logging import CaptureLogger
 
 # Create the main Typer app
 app = typer.Typer(
@@ -113,7 +112,7 @@ def analyze(
             asyncio.run(analyze_environment(docker_cmd, output_format, verbose))
         else:
             # Fast mode - analyze from metadata
-            from .analyze_metadata import analyze_from_metadata
+            from .utils.metadata import analyze_from_metadata
 
             asyncio.run(analyze_from_metadata(image, output_format, verbose))
     else:
@@ -175,11 +174,17 @@ def debug(
         hud debug . --max-phase 3               # Stop after phase 3
     """
     # Import here to avoid circular imports
-    from .env_utils import get_image_name, is_environment_directory, build_environment, image_exists
     from hud.utils.design import HUDDesign
-    
+
+    from .utils.environment import (
+        build_environment,
+        get_image_name,
+        image_exists,
+        is_environment_directory,
+    )
+
     design = HUDDesign()
-    
+
     # Determine the command to run
     command = None
     docker_args = []
@@ -202,18 +207,18 @@ def debug(
     elif params:
         first_param = params[0]
         docker_args = params[1:] if len(params) > 1 else []
-        
+
         # Check if it's a directory
         if Path(first_param).exists() and is_environment_directory(first_param):
             # Directory mode - like hud dev
             directory = first_param
-            
+
             # Get or generate image name
             image_name, source = get_image_name(directory)
-            
+
             if source == "auto":
                 design.info(f"Auto-generated image name: {image_name}")
-            
+
             # Build if requested or if image doesn't exist
             if build or not image_exists(image_name):
                 if not build and not image_exists(image_name):
@@ -221,11 +226,10 @@ def debug(
                         build = True
                     else:
                         raise typer.Exit(1)
-                
-                if build:
-                    if not build_environment(directory, image_name):
-                        raise typer.Exit(1)
-            
+
+                if build and not build_environment(directory, image_name):
+                    raise typer.Exit(1)
+
             # Build Docker command
             command = ["docker", "run", "--rm", "-i", *docker_args, image_name]
         else:
@@ -233,7 +237,9 @@ def debug(
             image = first_param
             command = ["docker", "run", "--rm", "-i", *docker_args, image]
     else:
-        console.print("[red]Error: Must specify a directory, Docker image, --config, or --cursor[/red]")
+        console.print(
+            "[red]Error: Must specify a directory, Docker image, --config, or --cursor[/red]"
+        )
         console.print("\nExamples:")
         console.print("  hud debug .                      # Debug current directory")
         console.print("  hud debug environments/browser   # Debug specific directory")
@@ -342,6 +348,11 @@ def dev(
     ),
     port: int = typer.Option(8765, "--port", "-p", help="HTTP server port (ignored for stdio)"),
     no_reload: bool = typer.Option(False, "--no-reload", help="Disable hot-reload"),
+    full_reload: bool = typer.Option(
+        False,
+        "--full-reload",
+        help="Restart entire container on file changes (instead of just server process)",
+    ),
     verbose: bool = typer.Option(False, "--verbose", "-v", help="Show server logs"),
     inspector: bool = typer.Option(
         False, "--inspector", help="Launch MCP Inspector (HTTP mode only)"
@@ -369,12 +380,13 @@ def dev(
         hud dev . --inspector        # Launch MCP Inspector (HTTP mode only)
         hud dev . --interactive      # Launch interactive testing mode (HTTP mode only)
         hud dev . --no-logs          # Disable Docker log streaming
+        hud dev . --full-reload      # Restart entire container on file changes (instead of just server)
 
         # With Docker arguments (after all options):
         hud dev . -e BROWSER_PROVIDER=anchorbrowser -e ANCHOR_API_KEY=xxx
         hud dev . -e API_KEY=secret -v /tmp/data:/data --network host
         hud dev . --build -e DEBUG=true --memory 2g
-    """
+    """  # noqa: E501
     # Parse directory and Docker arguments
     if params:
         directory = params[0]
@@ -391,6 +403,7 @@ def dev(
         transport,
         port,
         no_reload,
+        full_reload,
         verbose,
         inspector,
         no_logs,
@@ -448,6 +461,11 @@ def run(
         "-v",
         help="Show detailed output",
     ),
+    interactive: bool = typer.Option(
+        False,
+        "--interactive",
+        help="Launch interactive testing mode (HTTP transport only)",
+    ),
 ) -> None:
     """🚀 Run MCP server locally or remotely.
 
@@ -462,6 +480,10 @@ def run(
         hud run --local hud-text-2048:latest
         hud run --local my-server:v1 -e API_KEY=xxx
         hud run --local my-server:v1 --transport http
+
+    Interactive Testing (local only):
+        hud run --local --interactive --transport http hud-text-2048:latest
+        hud run --local --interactive --transport http --port 9000 my-server:v1
     """
     if not params:
         typer.echo("❌ Docker image is required")
@@ -479,18 +501,28 @@ def run(
     # Default to remote if not explicitly local
     is_local = local and not remote
 
+    # Check for interactive mode restrictions
+    if interactive:
+        if transport != "http":
+            typer.echo("❌ Interactive mode requires HTTP transport (use --transport http)")
+            raise typer.Exit(1)
+        if not is_local:
+            typer.echo("❌ Interactive mode is only available for local execution (use --local)")
+            raise typer.Exit(1)
+
     if is_local:
         # Local Docker execution
-        from .runner import run_mcp_server
+        from .utils.runner import run_mcp_server
 
-        run_mcp_server(image, docker_args, transport, port, verbose)
+        run_mcp_server(image, docker_args, transport, port, verbose, interactive)
     else:
         # Remote execution via proxy
-        from .remote_runner import run_remote_server
+        from .utils.remote_runner import run_remote_server
 
         # Get URL from options or environment
         if not url:
             from hud.settings import settings
+
             url = settings.hud_mcp_url
 
         run_remote_server(image, docker_args, transport, port, url, api_key, run_id, verbose)
@@ -534,9 +566,12 @@ def clone(
         raise typer.Exit(1)
 
 
-@app.command()
+@app.command(context_settings={"allow_extra_args": True, "ignore_unknown_options": True})
 def build(
-    directory: str = typer.Argument(".", help="Environment directory to build"),
+    params: list[str] = typer.Argument(  # type: ignore[arg-type]  # noqa: B008
+        None,
+        help="Environment directory followed by optional arguments (e.g., '. -e API_KEY=secret')",
+    ),
     tag: str | None = typer.Option(
         None, "--tag", "-t", help="Docker image tag (default: from pyproject.toml)"
     ),
@@ -552,11 +587,47 @@ def build(
 
     Examples:
         hud build                    # Build current directory
-        hud build environments/text_2048
-        hud build . --tag my-env:v1.0
+        hud build environments/text_2048 -e API_KEY=secret
+        hud build . --tag my-env:v1.0 -e VAR1=value1 -e VAR2=value2
         hud build . --no-cache       # Force rebuild
     """
-    build_command(directory, tag, no_cache, verbose)
+    # Parse directory and extra arguments
+    if params:
+        directory = params[0]
+        extra_args = params[1:] if len(params) > 1 else []
+    else:
+        directory = "."
+        extra_args = []
+
+    # Parse environment variables from extra args
+    env_vars = {}
+    i = 0
+    while i < len(extra_args):
+        if extra_args[i] == "-e" and i + 1 < len(extra_args):
+            # Parse -e KEY=VALUE format
+            env_arg = extra_args[i + 1]
+            if "=" in env_arg:
+                key, value = env_arg.split("=", 1)
+                env_vars[key] = value
+            i += 2
+        elif extra_args[i].startswith("--env="):
+            # Parse --env=KEY=VALUE format
+            env_arg = extra_args[i][6:]  # Remove --env=
+            if "=" in env_arg:
+                key, value = env_arg.split("=", 1)
+                env_vars[key] = value
+            i += 1
+        elif extra_args[i] == "--env" and i + 1 < len(extra_args):
+            # Parse --env KEY=VALUE format
+            env_arg = extra_args[i + 1]
+            if "=" in env_arg:
+                key, value = env_arg.split("=", 1)
+                env_vars[key] = value
+            i += 2
+        else:
+            i += 1
+
+    build_command(directory, tag, no_cache, verbose, env_vars)
 
 
 @app.command()
@@ -615,20 +686,14 @@ def list_environments(
     filter_name: str | None = typer.Option(
         None, "--filter", "-f", help="Filter environments by name (case-insensitive)"
     ),
-    json_output: bool = typer.Option(
-        False, "--json", help="Output as JSON"
-    ),
-    show_all: bool = typer.Option(
-        False, "--all", "-a", help="Show all columns including digest"
-    ),
-    verbose: bool = typer.Option(
-        False, "--verbose", "-v", help="Show detailed output"
-    ),
+    json_output: bool = typer.Option(False, "--json", help="Output as JSON"),
+    show_all: bool = typer.Option(False, "--all", "-a", help="Show all columns including digest"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Show detailed output"),
 ) -> None:
     """📋 List all HUD environments in local registry.
-    
+
     Shows environments pulled with 'hud pull' stored in ~/.hud/envs/
-    
+
     Examples:
         hud list                    # List all environments
         hud list --filter text      # Filter by name
@@ -642,21 +707,16 @@ def list_environments(
 @app.command()
 def remove(
     target: str | None = typer.Argument(
-        None, 
-        help="Environment to remove (digest, name, or 'all' for all environments)"
-    ),
-    yes: bool = typer.Option(
-        False, "--yes", "-y", help="Skip confirmation prompt"
-    ),
-    verbose: bool = typer.Option(
-        False, "--verbose", "-v", help="Show detailed output"
+        None, help="Environment to remove (digest, name, or 'all' for all environments)"
     ),
+    yes: bool = typer.Option(False, "--yes", "-y", help="Skip confirmation prompt"),
+    verbose: bool = typer.Option(False, "--verbose", "-v", help="Show detailed output"),
 ) -> None:
     """🗑️ Remove HUD environments from local registry.
-    
+
     Removes environment metadata from ~/.hud/envs/
     Note: This does not remove the Docker images.
-    
+
     Examples:
         hud remove abc123              # Remove by digest
         hud remove text_2048           # Remove by name
@@ -740,22 +800,24 @@ def eval(
     valid_agents = ["claude", "openai"]
     if agent not in valid_agents:
         from hud.utils.design import HUDDesign
+
         design = HUDDesign()
         design.error(f"Invalid agent: {agent}. Must be one of: {', '.join(valid_agents)}")
         raise typer.Exit(1)
-    
+
     # Import eval_command lazily to avoid importing agent dependencies
     try:
         from .eval import eval_command
     except ImportError as e:
         from hud.utils.design import HUDDesign
+
         design = HUDDesign()
         design.error(
             "Evaluation dependencies are not installed. "
             "Please install with: pip install 'hud-python[agent]'"
         )
         raise typer.Exit(1) from e
-    
+
     # Run the command
     eval_command(
         source=source,