core/tools/process: add run_command_batch with pipe_out and mix_stderr

tests/test_tools/test_danger.py

@@ -36,6 +36,28 @@ def test_classify_safe_tools() -> None:
     assert classify_danger("run_command", {"command": ["ls", "-la"]}) is None
 
 
+def test_classify_run_command_batch_risky() -> None:
+    reason = classify_danger(
+        "run_command_batch",
+        {
+            "commands": [
+                {"command": ["echo", "ok"]},
+                {"command": ["bash", "-c", "echo risky"]},
+            ]
+        },
+    )
+    assert reason is not None
+    assert "run_command_batch" in reason
+    assert "risky" in reason or "bash" in reason
+    assert (
+        classify_danger(
+            "run_command_batch",
+            {"commands": [{"command": ["echo", "ok"]}]},
+        )
+        is None
+    )
+
+
 def test_classify_shell_and_dash_c() -> None:
     r = classify_danger("run_command", {"command": ["bash", "-c", "rm -rf /"]})
     assert r is not None

tests/test_tools/test_process.py

@@ -9,6 +9,7 @@ from plyngent.tools.process import (
     open_pty,
     read_pty,
     run_command,
+    run_command_batch,
     write_pty,
     write_pty_keys,
 )
@@ -46,6 +47,85 @@ async def test_run_command_echo(workspace: object) -> None:
     assert "hi" in out
 
 
+async def test_run_command_batch_serial(workspace: object) -> None:
+    del workspace
+    out = await call_async(
+        run_command_batch,
+        [
+            {"command": _py("print('a')")},
+            {"command": _py("print('b')")},
+        ],
+    )
+    assert "steps=2" in out
+    assert "ran=2" in out
+    assert "stopped_early=false" in out
+    assert "--- step 0 ---" in out
+    assert "--- step 1 ---" in out
+    assert "a" in out and "b" in out
+
+
+async def test_run_command_batch_stop_on_error(workspace: object) -> None:
+    del workspace
+    out = await call_async(
+        run_command_batch,
+        [
+            {"command": _py("import sys; sys.exit(2)")},
+            {"command": _py("print('should-not-run')")},
+        ],
+        stop_on_error=True,
+    )
+    assert "ran=1" in out
+    assert "stopped_early=true" in out
+    assert "should-not-run" not in out
+
+
+async def test_run_command_batch_pipe_out(workspace: object) -> None:
+    del workspace
+    out = await call_async(
+        run_command_batch,
+        [
+            {
+                "command": _py("print('piped-payload', end='')"),
+                "pipe_out": True,
+            },
+            {
+                "command": _py("import sys; print(sys.stdin.read())"),
+            },
+        ],
+    )
+    assert "ran=2" in out
+    assert "piped-payload" in out
+    assert "pipe_out=true" in out
+
+
+async def test_run_command_batch_last_pipe_out_error(workspace: object) -> None:
+    del workspace
+    out = await call_async(
+        run_command_batch,
+        [{"command": _py("print(1)"), "pipe_out": True}],
+    )
+    assert "error:" in out
+    assert "pipe_out" in out
+
+
+async def test_run_command_batch_mix_stderr(workspace: object) -> None:
+    del workspace
+    out = await call_async(
+        run_command_batch,
+        [
+            {
+                "command": _py("import sys; sys.stdout.write('out'); sys.stderr.write('err')"),
+                "mix_stderr": True,
+                "pipe_out": True,
+            },
+            {"command": _py("import sys; print(repr(sys.stdin.read()))")},
+        ],
+    )
+    assert "ran=2" in out
+    # Merged capture should include both (order depends on OS scheduling).
+    assert "out" in out and "err" in out
+
+
 async def test_run_command_denied(workspace: object) -> None:
     del workspace
     out = await call_async(run_command, ["rm", "-rf", "."])