feat: add tool server health check and show error details in CLI

- Add _wait_for_tool_server_health() to verify tool server is responding after init
- Show error details in CLI mode when penetration test fails
- Simplify error message (remove technical URL details)

strix/interface/cli.py

@@ -167,8 +167,11 @@ async def run_cli(args: Any) -> None:  # noqa: PLR0915
 
                 if isinstance(result, dict) and not result.get("success", True):
                     error_msg = result.get("error", "Unknown error")
+                    error_details = result.get("details")
                     console.print()
                     console.print(f"[bold red]❌ Penetration test failed:[/] {error_msg}")
+                    if error_details:
+                        console.print(f"[dim]{error_details}[/]")
                     console.print()
                     sys.exit(1)
             finally:

strix/runtime/docker_runtime.py

@@ -1,4 +1,3 @@
-import asyncio
 import contextlib
 import logging
 import os
@@ -305,22 +304,20 @@ class DockerRuntime(AbstractRuntime):
 
         time.sleep(2)
 
-        self._wait_for_tool_server_health(tool_server_port)
+        host = self._resolve_docker_host()
+        health_url = f"http://{host}:{tool_server_port}/health"
+        self._wait_for_tool_server_health(health_url)
 
     def _wait_for_tool_server_health(
         self,
-        port: int,
+        health_url: str,
         max_retries: int = TOOL_SERVER_HEALTH_RETRIES,
         timeout: int = TOOL_SERVER_HEALTH_TIMEOUT,
     ) -> None:
         import httpx
 
-        host = self._resolve_docker_host()
-        health_url = f"http://{host}:{port}/health"
-
         logger.info(f"Waiting for tool server health at {health_url}")
 
-        last_error: Exception | None = None
         for attempt in range(max_retries):
             try:
                 with httpx.Client(trust_env=False, timeout=timeout / max_retries) as client:
@@ -336,32 +333,25 @@ class DockerRuntime(AbstractRuntime):
 
                     logger.warning(f"Tool server returned unexpected status: {health_data}")
 
-            except httpx.ConnectError as e:
-                last_error = e
+            except httpx.ConnectError:
                 logger.debug(
                     f"Tool server not ready (attempt {attempt + 1}/{max_retries}): "
                     f"Connection refused"
                 )
-            except httpx.TimeoutException as e:
-                last_error = e
+            except httpx.TimeoutException:
                 logger.debug(
                     f"Tool server not ready (attempt {attempt + 1}/{max_retries}): "
                     f"Request timed out"
                 )
             except (httpx.RequestError, httpx.HTTPStatusError) as e:
-                last_error = e
                 logger.debug(f"Tool server not ready (attempt {attempt + 1}/{max_retries}): {e}")
 
             sleep_time = min(2**attempt * 0.5, 5)
             time.sleep(sleep_time)
 
-        error_detail = str(last_error) if last_error else "Unknown error"
         raise SandboxInitializationError(
             "Tool server failed to start",
-            f"Could not connect to tool server at {health_url} after {max_retries} attempts. "
-            f"Last error: {error_detail}. "
-            "Please ensure Docker Desktop is installed and running, "
-            "and try running strix again.",
+            "Please ensure Docker Desktop is installed and running, and try running strix again.",
         )
 
     def _copy_local_directory_to_container(
@@ -439,7 +429,6 @@ class DockerRuntime(AbstractRuntime):
 
         api_url = await self.get_sandbox_url(container_id, self._tool_server_port)
 
-        await self._verify_tool_server_health(api_url)
         await self._register_agent_with_tool_server(api_url, agent_id, token)
 
         return {
@@ -450,60 +439,6 @@ class DockerRuntime(AbstractRuntime):
             "agent_id": agent_id,
         }
 
-    async def _verify_tool_server_health(
-        self,
-        api_url: str,
-        max_retries: int = 3,
-        timeout: int = 10,
-    ) -> None:
-        import httpx
-
-        health_url = f"{api_url}/health"
-        last_error: Exception | None = None
-
-        for attempt in range(max_retries):
-            try:
-                async with httpx.AsyncClient(trust_env=False, timeout=timeout) as client:
-                    response = await client.get(health_url)
-                    response.raise_for_status()
-                    health_data = response.json()
-
-                    if health_data.get("status") == "healthy":
-                        logger.debug(f"Tool server health verified: {health_data}")
-                        return
-
-                    logger.warning(f"Tool server returned unexpected status: {health_data}")
-
-            except httpx.ConnectError as e:
-                last_error = e
-                logger.debug(
-                    f"Tool server health check failed (attempt {attempt + 1}/{max_retries}): "
-                    f"Connection refused"
-                )
-            except httpx.TimeoutException as e:
-                last_error = e
-                logger.debug(
-                    f"Tool server health check failed (attempt {attempt + 1}/{max_retries}): "
-                    f"Request timed out"
-                )
-            except (httpx.RequestError, httpx.HTTPStatusError) as e:
-                last_error = e
-                logger.debug(
-                    f"Tool server health check failed (attempt {attempt + 1}/{max_retries}): {e}"
-                )
-
-            if attempt < max_retries - 1:
-                await asyncio.sleep(min(2**attempt, 4))
-
-        error_detail = str(last_error) if last_error else "Unknown error"
-        raise SandboxInitializationError(
-            "Tool server is not responding",
-            f"Could not connect to tool server at {health_url}. "
-            f"Last error: {error_detail}. "
-            "Please ensure Docker Desktop is installed and running, "
-            "and try running strix again.",
-        )
-
     async def _register_agent_with_tool_server(
         self, api_url: str, agent_id: str, token: str
     ) -> None: