letify 2.6.3__tar.gz → 2.6.4__tar.gz

{letify-2.6.3 → letify-2.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: letify
-Version: 2.6.3
+Version: 2.6.4
 Summary: Declarations that become infrastructure.
 Project-URL: Homepage, https://github.com/DarkPyonix/letify
 Project-URL: Documentation, https://github.com/DarkPyonix/letify/tree/main/docs

{letify-2.6.3 → letify-2.6.4}/docs/SPEC.md

@@ -807,7 +807,11 @@ A `read_until` blocks until the sandbox prints a line, and the adapter answers o
 - `Modal.stop` calls `abort()` when the adapter is out of step or its lock is still held after 5 s. The call timeout watchdog calls it through `SandboxChannel._kill`, so a call past its `timeout` ends its sandbox too.
 - The adapter's `terminate` for an id it did not create finds the sandbox with `modal.Sandbox.from_id` and terminates it. A sandbox that is already gone is not an error.
 
-Modal also bounds a sandbox that nothing terminates. `create` passes `timeout`, the entry option `timeout`, 3600 s by default, as the sandbox's maximum lifetime. It passes `idle_timeout`, the entry option `idle_timeout`, 600 s by default, after which Modal terminates a sandbox that is idle.
+Modal also bounds a sandbox that nothing terminates. `create` passes `idle_timeout`, the entry option `idle_timeout`, 600 s by default, after which Modal terminates a sandbox that is idle. That is the bound that stops an abandoned sandbox billing, because an abandoned one is idle by definition once its worker has no one to answer.
+
+It passes `timeout`, the entry option `timeout`, as the sandbox's maximum lifetime, and the default is the longest Modal accepts, 86400 s, measured as accepted. It is not a shorter number letify picked, for the reason The declaration gives for `timeout` having no default: a deadline letify invented would end a two hour training run at whatever hour it guessed. The default was 3600 s, exactly one hour, and it ended two Modal sessions of a real training run at one hour each with nothing saying why, which is that sentence happening. An account that wants a hard cap sets `timeout` itself.
+
+A sandbox that reaches that lifetime takes its worker with it, so the channel sees a worker that stopped without replying. Where the session's age is within a minute of the lifetime letify asked for, the failure says so instead of listing causes: `the Modal sandbox reached the <seconds> s lifetime letify asked for; raise timeout on the account to run longer`.
 
 ### Modal data channel <!-- id: modal-data-channel -->
 

{letify-2.6.3 → letify-2.6.4}/letify/__init__.py

@@ -66,7 +66,7 @@ distributed: Final = Host.distributed
 # The enum class stays importable from letify.declare.instance for letify's own use.
 del Host
 
-__version__ = "2.6.3"
+__version__ = "2.6.4"
 
 
 def fetch(tensor):  # type: ignore[no-untyped-def]

{letify-2.6.3 → letify-2.6.4}/letify/providers/modal.py

@@ -102,6 +102,26 @@ STOP_WAIT = 5.0
 #: ``idle_timeout``.
 IDLE_TIMEOUT = 600
 
+#: The sandbox's maximum lifetime, the longest Modal accepts, measured as accepted.
+#: Spec "Modal": not a shorter number letify picked, for the reason The declaration gives
+#: for ``timeout`` having no default. The previous 3600 s ended two sessions of a real
+#: training run at one hour each with nothing saying why.
+SANDBOX_TIMEOUT = 86400
+
+
+def lifetime_detail(*, age_s: float, lifetime_s: int) -> str | None:
+    """What to say when a sandbox died at the lifetime letify asked for, or None.
+
+    Spec "Modal": the channel otherwise reports a worker that stopped without replying and
+    lists causes, none of which is the deadline letify set itself.
+    """
+    if lifetime_s <= 0 or age_s < lifetime_s - 60.0:
+        return None
+    return (
+        f"the Modal sandbox reached the {lifetime_s} s lifetime letify asked for; "
+        f"raise timeout on the account to run longer"
+    )
+
 
 class VolumePathMissing(RuntimeFailure):
     """The adapter answered that a volume path does not exist."""
@@ -377,6 +397,18 @@ class Modal(Provider):
         self._sandboxes: dict[str, str] = {}
         self._adapter: Adapter | None = None
 
+    @property
+    def sandbox_timeout_s(self) -> int:
+        """The sandbox's maximum lifetime, from the account or the longest Modal accepts."""
+        value = self.config.option("timeout", SANDBOX_TIMEOUT)
+        return max(1, int(value))
+
+    @property
+    def sandbox_idle_timeout_s(self) -> int:
+        """Seconds a sandbox may be idle before Modal terminates it. Spec "Modal"."""
+        value = self.config.option("idle_timeout", IDLE_TIMEOUT)
+        return max(1, int(value))
+
     def adapter(self) -> Adapter:
         """The adapter acting as this account, started on its first request."""
         if self._adapter is None or self._adapter.closed:
@@ -440,14 +472,15 @@ class Modal(Provider):
             args=["python3", "-u", "-c", BOOTSTRAP],
             packages=list(WORKER_PACKAGES),
             gpu=self.wire_name(runtime.instance) or None,
-            timeout=int(self.config.option("timeout", 3600)),
-            idle_timeout=int(self.config.option("idle_timeout", IDLE_TIMEOUT)),
+            timeout=self.sandbox_timeout_s,
+            idle_timeout=self.sandbox_idle_timeout_s,
             ports=[] if data_port is None else [data_port],
         )
         sandbox = str(created["sandbox"])
         self._sandboxes[runtime.name] = sandbox
         return SandboxChannel(
-            adapter, sandbox, name=runtime.name, data_port=data_port, streams=streams
+            adapter, sandbox, name=runtime.name, data_port=data_port, streams=streams,
+            lifetime_s=self.sandbox_timeout_s,
         )
 
     def stop(self, runtime: Runtime) -> None:
@@ -598,11 +631,15 @@ class SandboxChannel(FramedChannel):
         name: str,
         data_port: int | None = None,
         streams: int = 1,
+        lifetime_s: int = 0,
     ):
         self.adapter = adapter
         self.sandbox = sandbox
         self.name = name
         self.data_port = data_port
+        #: The sandbox's maximum lifetime, so a death at it is named rather than guessed.
+        self.lifetime_s = lifetime_s
+        self.opened_at = time.monotonic()
         #: TCP connections the data channel carries its frames over.
         self.streams = streams
         self._sockets: list[socket.socket] = []
@@ -628,7 +665,13 @@ class SandboxChannel(FramedChannel):
         self._await_ready()
 
     def _raw_text(self) -> str:
-        return bytes(self._raw[-2000:]).decode("utf-8", "replace")
+        text = bytes(self._raw[-2000:]).decode("utf-8", "replace")
+        # Spec "Modal": a sandbox that reached the lifetime letify asked for takes its
+        # worker with it, and the channel otherwise lists causes, none of them this one.
+        said = lifetime_detail(
+            age_s=time.monotonic() - self.opened_at, lifetime_s=self.lifetime_s
+        )
+        return f"{said}\n{text}" if said else text
 
     def _send_worker(self) -> None:
         # After a reexec the data connection is gone, so the source goes back over stdio.

{letify-2.6.3 → letify-2.6.4}/letify-core/Cargo.lock

@@ -138,7 +138,7 @@ dependencies = [
 
 [[package]]
 name = "letify-agent"
-version = "2.6.3"
+version = "2.6.4"
 dependencies = [
  "letify-wire",
  "libloading",
@@ -146,7 +146,7 @@ dependencies = [
 
 [[package]]
 name = "letify-driver"
-version = "2.6.3"
+version = "2.6.4"
 dependencies = [
  "letify-wire",
 ]
@@ -164,7 +164,7 @@ dependencies = [
 
 [[package]]
 name = "letify-wire"
-version = "2.6.3"
+version = "2.6.4"
 
 [[package]]
 name = "libc"

{letify-2.6.3 → letify-2.6.4}/letify-core/Cargo.toml

@@ -8,7 +8,7 @@ resolver = "3"
 members = ["letify-wire", "letify-driver", "letify-agent", "letify-quic"]
 
 [workspace.package]
-version = "2.6.3"
+version = "2.6.4"
 edition = "2024"
 license = "MIT"
 repository = "https://github.com/DarkPyonix/letify"

{letify-2.6.3 → letify-2.6.4}/letify-ext/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "letify-status",
-  "version": "2.6.3",
+  "version": "2.6.4",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "letify-status",
-      "version": "2.6.3",
+      "version": "2.6.4",
       "license": "SEE LICENSE IN LICENSE",
       "devDependencies": {
         "@types/node": "^18.19.0",

{letify-2.6.3 → letify-2.6.4}/letify-ext/package.json

@@ -2,7 +2,7 @@
   "name": "letify-status",
   "displayName": "letify Status",
   "description": "letify quota and GPU activity in the status bar, read from the letify CLI.",
-  "version": "2.6.3",
+  "version": "2.6.4",
   "publisher": "darkpyonix",
   "license": "SEE LICENSE IN LICENSE",
   "repository": {

{letify-2.6.3 → letify-2.6.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "letify"
-version = "2.6.3"
+version = "2.6.4"
 description = "Declarations that become infrastructure."
 readme = "README.md"
 requires-python = ">=3.11"

{letify-2.6.3 → letify-2.6.4}/tests/test_providers.py

@@ -2218,7 +2218,9 @@ def test_a_modal_sandbox_is_created_with_a_lifetime_and_an_idle_limit(
     provider.open_channel(runtime)
     try:
         [created] = fake_modal.requests("create")
-        assert created["timeout"] == 3600
+        # Spec "Modal": the lifetime is the longest Modal accepts, not an hour letify
+        # picked, because a deadline letify invented ends the user's work at its guess.
+        assert created["timeout"] == 86400
         assert created["idle_timeout"] == 600
     finally:
         provider.stop(runtime)
@@ -2910,3 +2912,32 @@ def test_colab_punch_rendezvous_completes_during_tailcat_installation(
         release.set()
         installing.join(2)
     assert endpoints == [("fake", 22)]
+
+
+def test_a_modal_sandbox_is_not_given_an_hour_long_deadline(config_file) -> None:
+    """Spec "Modal": a deadline letify invented would end a two hour run at its guess.
+
+    The default was 3600 s, exactly one hour, and it ended two Modal sessions of a real
+    training run at one hour each with nothing saying why. The declaration's own `timeout`
+    has no default for this reason, and the sandbox's lifetime is the same question.
+    """
+    from conftest import provider_of
+
+    from letify.providers import Modal
+
+    provider = provider_of(Modal, "lab")
+    assert provider.sandbox_timeout_s == 86400, "letify picked a deadline again"
+    # An idle sandbox is what has to be bounded, and that bound is unchanged.
+    assert provider.sandbox_idle_timeout_s == 600
+    # An account that wants a cap still sets one.
+    assert provider_of(Modal, "lab", timeout=7200).sandbox_timeout_s == 7200
+
+
+def test_a_sandbox_that_reached_its_lifetime_says_so(config_file) -> None:
+    """Spec "Modal": the channel otherwise lists causes, none of them this one."""
+    from letify.providers.modal import lifetime_detail
+
+    assert lifetime_detail(age_s=3599.5, lifetime_s=3600) is not None
+    assert "3600" in lifetime_detail(age_s=3599.5, lifetime_s=3600)
+    assert "raise timeout" in lifetime_detail(age_s=3601.0, lifetime_s=3600)
+    assert lifetime_detail(age_s=120.0, lifetime_s=3600) is None