Initial Commit

app/owuitools/vm_preflight.py

@@ -0,0 +1,88 @@
+"""The one question vm_agent stops to ask, and how it decides to ask it.
+
+WHY THIS IS A SEPARATE MODULE
+
+Two reasons, and the second is the real one.
+
+It is dependency-free, so it can be unit-tested on the host without the
+container - the same arrangement as matlab_lint.py, and for the same
+reason: the interesting half of this rule cannot be tested over HTTP. A
+task that is let through starts a real VM session, which is minutes long
+by design, and the smoke suite's per-case timeout is 90 seconds.
+
+And it puts the rule somewhere findable. It is the only pre-flight
+refusal in the suite that is about the CALLER's judgement rather than
+about a malformed argument, so it will be argued with, and the argument
+should happen against a file that explains itself.
+
+WHY THE RULE EXISTS
+
+A Python script runs on both machines. A `.sh` runs only on Ubuntu; a
+`.ps1` or `.bat` only on Windows. The model has to choose, and it has no
+way to know unless the user said - but the machine is destroyed at the
+end of the session, so guessing wrong does not cost a retry, it costs the
+whole session.
+
+The system prompt asks the model to check first. That is not enough on
+its own: this file's oldest and most-repeated finding is that the model
+treats tool output as fact and system-prompt text as advice, and a prompt
+rule loses to an explicit user demand. So the tool refuses, in its own
+output, and hands back the exact question to relay.
+
+WHY IT HAS TO BE NARROW
+
+Firing when the caller has already said which machine would be worse than
+not firing at all. It would teach the model that the way past this tool
+is to add a magic word, rather than to ask - and a model that has learned
+to appease a check has stopped reading it.
+"""
+
+from __future__ import annotations
+
+import re
+
+# Things that run on both machines. Word-bounded throughout: `\bgo\b`
+# rather than `go`, or every mention of "gopher" and "going" trips it.
+CROSS_PLATFORM = re.compile(
+    r"\bpython3?\b|\bpy\b|\.py\b|\bpip3?\b|\bnode\b|\bnpm\b|\.js\b"
+    r"|\bjava\b|\bgo\b|\bgolang\b|\brust\b|\bcargo\b|\bdotnet\b|\bruby\b|\bperl\b",
+    re.IGNORECASE,
+)
+
+# Deliberately generous. The point is to catch a silent guess, not to
+# interrogate a caller who has already been clear - so a mention of the
+# shell, the file extension or the package manager counts as having said.
+_SAYS_UBUNTU = (
+    "ubuntu", "linux", "debian", "bash", "sh script", ".sh", "shell script",
+    "apt ", "apt-get", "apt install", "/usr/", "/etc/", "/home/", "systemd",
+)
+_SAYS_WINDOWS = (
+    "windows", "powershell", "pwsh", ".ps1", "batch", ".bat", ".cmd",
+    "cmd.exe", "winget", "c:\\", "registry", ".exe",
+)
+
+
+def names_its_machine(task: str, os_name: str) -> bool:
+    """Has the caller already said which machine, in the task itself?"""
+    lowered = (task or "").lower()
+    words = _SAYS_WINDOWS if os_name == "windows" else _SAYS_UBUNTU
+    return any(word in lowered for word in words)
+
+
+def should_ask(task: str, os_name: str) -> bool:
+    """True when the tool should stop and have the user asked."""
+    return bool(CROSS_PLATFORM.search(task or "")) and not names_its_machine(task, os_name)
+
+
+def question(os_name: str) -> str:
+    """The refusal, written for the model to relay rather than to obey."""
+    other = "Windows" if os_name == "ubuntu" else "Ubuntu"
+    return (
+        f"CANNOT DO THAT YET: this task mentions something that runs on both machines, "
+        f"and you chose {os_name}. Ask the user which they want - {other} is just as "
+        "likely and there is nothing in the task text to tell you.\n\n"
+        "Put it to them in one round, then call again with their answer. If they do not "
+        f"mind, say which you picked and call again with the task naming {os_name} "
+        "explicitly. Guessing costs the whole session: the machine is destroyed at the "
+        "end of it, so there is nothing to correct afterwards."
+    )