fix: persist workspace Python environments

agent_platform/gateway/provider.py

@@ -122,13 +122,21 @@ class DockerExecutionProvider:
         ref = workspace_ref(user_id)
 
         def ensure():
+            try:
+                desired_image = self.client.images.get(self.settings.workspace_image)
+            except ImageNotFound as exc:
+                raise RuntimeError(f"Workspace image {self.settings.workspace_image!r} is not installed") from exc
             try:
                 container = self.client.containers.get(ref.container_name)
+                container.reload()
+                configured_image = str(container.attrs.get("Config", {}).get("Image", ""))
+                running_image_id = str(container.attrs.get("Image", ""))
+                if configured_image != self.settings.workspace_image or running_image_id != desired_image.id:
+                    container.remove(force=True)
+                    container = None
             except NotFound:
-                try:
-                    self.client.images.get(self.settings.workspace_image)
-                except ImageNotFound as exc:
-                    raise RuntimeError(f"Workspace image {self.settings.workspace_image!r} is not installed") from exc
+                container = None
+            if container is None:
                 if self.settings.workspace_network_enabled:
                     try:
                         self.client.networks.get(ref.network_name)
@@ -153,6 +161,7 @@ class DockerExecutionProvider:
                     labels={
                         "app.k1412.component": "user-workspace",
                         "app.k1412.workspace-id": ref.workspace_id,
+                        "app.k1412.workspace-image": self.settings.workspace_image,
                     },
                     detach=True,
                     read_only=True,
@@ -222,8 +231,20 @@ class DockerExecutionProvider:
     async def exec(self, user_id: str, command: str, cwd: str, timeout_seconds: int) -> ToolResult:
         normalize_workspace_path(cwd)
         bounded_timeout = max(1, min(timeout_seconds, 1800))
-        shell = f"timeout --signal=TERM {bounded_timeout}s sh -lc {shlex.quote(command)}"
-        return await self._exec_argv(user_id, ["sh", "-lc", shell], cwd=cwd)
+        return await self._exec_argv(
+            user_id,
+            [
+                "timeout",
+                "--signal=TERM",
+                f"{bounded_timeout}s",
+                "bash",
+                "-o",
+                "pipefail",
+                "-c",
+                command,
+            ],
+            cwd=cwd,
+        )
 
     async def list_files(self, user_id: str, path: str, max_depth: int, limit: int) -> ToolResult:
         absolute = absolute_workspace_path(path)
@@ -233,7 +254,7 @@ class DockerExecutionProvider:
             "base_depth=root.rstrip('/').count('/')\n"
             "for current, dirs, files in os.walk(root):\n"
             " depth=current.rstrip('/').count('/')-base_depth\n"
-            " dirs[:]=sorted(d for d in dirs if d not in {'.git','node_modules','.venv','__pycache__'})\n"
+            " dirs[:]=sorted(d for d in dirs if d not in {'.agent','.git','node_modules','.venv','__pycache__'})\n"
             " if depth>=max_depth: dirs[:]=[]\n"
             " rel=os.path.relpath(current,'/workspace')\n"
             " for name in sorted(dirs): out.append((os.path.join(rel,name) if rel!='.' else name)+'/')\n"
@@ -408,19 +429,19 @@ class DockerExecutionProvider:
         process_id = uuid.uuid4().hex
         process_dir = absolute_workspace_path(f".agent/processes/{process_id}")
         worker = (
-            f"sh -lc {shlex.quote(command)}; "
+            f"bash -o pipefail -c {shlex.quote(command)}; "
             "code=$?; "
             f'echo "$code" > {shlex.quote(process_dir + "/exit_code")}; '
             'exit "$code"'
         )
         wrapped = (
             f"mkdir -p {shlex.quote(process_dir)}; "
-            f"setsid sh -lc {shlex.quote(worker)} "
+            f"setsid bash -c {shlex.quote(worker)} "
             f"> {shlex.quote(process_dir + '/output.log')} 2>&1 & "
             f'pid=$!; echo "$pid" > {shlex.quote(process_dir + "/pid")}; '
             f"echo {shlex.quote(json.dumps({'process_id': process_id}))}"
         )
-        result = await self._exec_argv(user_id, ["sh", "-lc", wrapped], cwd=cwd)
+        result = await self._exec_argv(user_id, ["bash", "-o", "pipefail", "-c", wrapped], cwd=cwd)
         result.metadata = {"process_id": process_id}
         return result
 

agent_platform/gateway/schemas.py

@@ -33,7 +33,7 @@ class SearchFilesRequest(BaseModel):
 class ExecRequest(BaseModel):
     command: str = Field(min_length=1, max_length=32_000)
     cwd: str = Field(default=".", max_length=4096, description="Working directory relative to /workspace.")
-    timeout_seconds: int = Field(default=120, ge=1, le=1800)
+    timeout_seconds: int = Field(default=900, ge=1, le=1800)
 
 
 class ApplyPatchRequest(BaseModel):