agentic-dev-loop 1.0.0a49__tar.gz → 1.0.0a50__tar.gz

{agentic_dev_loop-1.0.0a49/src/agentic_dev_loop.egg-info → agentic_dev_loop-1.0.0a50}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-dev-loop
-Version: 1.0.0a49
+Version: 1.0.0a50
 Summary: Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.
 Author: Luke Wilson
 License-Expression: Apache-2.0
@@ -169,7 +169,10 @@ engine-owned object to its owning run and a `live`, `orphaned`,
 registry-owned orphans whose owner pid is dead (never unregistered names).
 A SIGTERM to a running pipeline still closes the sandbox (the graph's
 `finally` runs); SIGKILL is unhandleable, so its containers are reclaimed by
-the startup reaper on the next run or by `containers --reap`. Pass
+the startup reaper on the next run or by `containers --reap`. The reaper
+and `--reap` prune a registry entry only after the daemon confirms the
+object is gone; a surviving object (a failed removal) keeps its entry so
+the next startup retries it. Pass
 `--state-dir` to point at a custom `isolation.state_dir`.
 
 **What a run looks like** (the shipped self-loop example):

{agentic_dev_loop-1.0.0a49 → agentic_dev_loop-1.0.0a50}/README.md

@@ -125,7 +125,10 @@ engine-owned object to its owning run and a `live`, `orphaned`,
 registry-owned orphans whose owner pid is dead (never unregistered names).
 A SIGTERM to a running pipeline still closes the sandbox (the graph's
 `finally` runs); SIGKILL is unhandleable, so its containers are reclaimed by
-the startup reaper on the next run or by `containers --reap`. Pass
+the startup reaper on the next run or by `containers --reap`. The reaper
+and `--reap` prune a registry entry only after the daemon confirms the
+object is gone; a surviving object (a failed removal) keeps its entry so
+the next startup retries it. Pass
 `--state-dir` to point at a custom `isolation.state_dir`.
 
 **What a run looks like** (the shipped self-loop example):

{agentic_dev_loop-1.0.0a49 → agentic_dev_loop-1.0.0a50}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agentic-dev-loop"
-version = "1.0.0a49"
+version = "1.0.0a50"
 description = "Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase."
 readme = "README.md"
 requires-python = ">=3.12"

{agentic_dev_loop-1.0.0a49 → agentic_dev_loop-1.0.0a50}/src/agentic_dev_loop/engine/isolation.py

@@ -1632,23 +1632,12 @@ class DockerBackend(Sandbox):
         _write_registry(self._iso_state_dir, remaining)
 
     def _container_gone(self, name: str) -> bool:
-        """True only when the daemon confirms the container no longer exists.
-        A nonzero daemon exit keeps the entry."""
-        res = self._runner.run(
-            ["docker", "ps", "-a", "--filter", f"name={name}",
-             "--format", "{{.Names}}"], timeout=30)
-        if res.exit_code != 0:
-            return False
-        return name not in res.stdout.splitlines()
+        """Thin delegation to the module-level confirm helper (050 D2)."""
+        return _container_gone(self._runner, name)
 
     def _network_gone(self, name: str) -> bool:
-        """True only when the daemon reports the network is missing. Any
-        other inspect failure (daemon unreachable) keeps the entry."""
-        res = self._runner.run(
-            ["docker", "network", "inspect", name], timeout=30)
-        if res.exit_code == 0:
-            return False
-        return "No such network" in f"{res.stderr} {res.stdout}"
+        """Thin delegation to the module-level confirm helper (050 D2)."""
+        return _network_gone(self._runner, name)
 
     # -- internal -----------------------------------------------------------
 
@@ -1882,6 +1871,28 @@ def _pid_alive_matches(pid: int, recorded_start: str | None) -> bool:
     return current == recorded_start
 
 
+def _container_gone(runner: CommandRunner, name: str) -> bool:
+    """True only when the daemon confirms the container no longer exists.
+    A nonzero daemon exit keeps the entry."""
+    res = runner.run(
+        ["docker", "ps", "-a", "--filter", f"name={name}",
+         "--format", "{{.Names}}"], timeout=30)
+    if res.exit_code != 0:
+        return False
+    return name not in res.stdout.splitlines()
+
+
+def _network_gone(runner: CommandRunner, name: str) -> bool:
+    """True only when the daemon reports the network is missing. Any
+    other inspect failure (daemon unreachable) keeps the entry."""
+    res = runner.run(
+        ["docker", "network", "inspect", name], timeout=30)
+    if res.exit_code == 0:
+        return False
+    return "No such network" in f"{res.stderr} {res.stdout}"
+
+
+
 def reap_orphaned_containers(state_dir: str | Path,
                              runner: CommandRunner | None = None,
                              *, announce: bool = True) -> list[str]:
@@ -1889,7 +1900,9 @@ def reap_orphaned_containers(state_dir: str | Path,
     and the per-run internal network whose owning CLI process is gone (crashed
     before close()). Exact by construction - only engine registry names are
     touched, and a live owner (pid alive with the same start time) is left
-    alone. Best-effort: never raises."""
+    alone. A surviving object (rm failure) keeps its entry so the next
+    startup reaper retries; only a daemon-confirmed absence prunes it (050
+    D1). Best-effort: never raises."""
     runner = runner or _default_runner
     entries = _read_registry(Path(state_dir))
     if not entries:
@@ -1909,6 +1922,9 @@ def reap_orphaned_containers(state_dir: str | Path,
                 remaining.append(entry)
                 continue
             runner.run(["docker", "network", "rm", name], timeout=60)
+            if not _network_gone(runner, name):
+                remaining.append(entry)
+                continue
             if announce:
                 _announce(f"reaped orphaned sandbox network {name}")
             reaped.append(name)
@@ -1924,6 +1940,9 @@ def reap_orphaned_containers(state_dir: str | Path,
             remaining.append(entry)
             continue
         runner.run(["docker", "rm", "-f", name], timeout=60)
+        if not _container_gone(runner, name):
+            remaining.append(entry)
+            continue
         if announce:
             _announce(f"reaped orphaned sandbox container {name}")
         reaped.append(name)

{agentic_dev_loop-1.0.0a49 → agentic_dev_loop-1.0.0a50/src/agentic_dev_loop.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentic-dev-loop
-Version: 1.0.0a49
+Version: 1.0.0a50
 Summary: Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.
 Author: Luke Wilson
 License-Expression: Apache-2.0
@@ -169,7 +169,10 @@ engine-owned object to its owning run and a `live`, `orphaned`,
 registry-owned orphans whose owner pid is dead (never unregistered names).
 A SIGTERM to a running pipeline still closes the sandbox (the graph's
 `finally` runs); SIGKILL is unhandleable, so its containers are reclaimed by
-the startup reaper on the next run or by `containers --reap`. Pass
+the startup reaper on the next run or by `containers --reap`. The reaper
+and `--reap` prune a registry entry only after the daemon confirms the
+object is gone; a surviving object (a failed removal) keeps its entry so
+the next startup retries it. Pass
 `--state-dir` to point at a custom `isolation.state_dir`.
 
 **What a run looks like** (the shipped self-loop example):

{agentic_dev_loop-1.0.0a49 → agentic_dev_loop-1.0.0a50}/tests/test_containers.py

@@ -123,7 +123,11 @@ class TestReapReturnValue:
         _write(tmp_path / "state", [_entry(name, proc.pid, None)])
         runner = FakeRunner(ok(""))
         assert reap_orphaned_containers(tmp_path / "state", runner) == [name]
-        assert runner.calls == [["docker", "rm", "-f", name]]
+        assert runner.calls == [
+            ["docker", "rm", "-f", name],
+            ["docker", "ps", "-a", "--filter", f"name={name}",
+             "--format", "{{.Names}}"],
+        ]
 
     def test_reap_live_owner_returns_empty(self, tmp_path):
         name = f"{'b' * 32}-exec"

{agentic_dev_loop-1.0.0a49 → agentic_dev_loop-1.0.0a50}/tests/test_isolation.py

@@ -2251,7 +2251,11 @@ class TestReaper:
         runner = FakeRunner()
         reaped = reap_orphaned_containers(tmp_path / "state", runner)
         assert reaped == [name]
-        assert runner.calls == [["docker", "rm", "-f", name]]
+        assert runner.calls == [
+            ["docker", "rm", "-f", name],
+            ["docker", "ps", "-a", "--filter", f"name={name}",
+             "--format", "{{.Names}}"],
+        ]
         assert self._read(tmp_path / "state") == []
 
     def test_live_pid_left_alone(self, tmp_path):
@@ -2282,9 +2286,13 @@ class TestReaper:
             "run_id": "r", "name": name, "kind": "network",
             "pid": proc.pid, "process_start": None, "created_at": "now",
         }])
-        runner = FakeRunner()
-        reap_orphaned_containers(tmp_path / "state", runner)
-        assert runner.calls == [["docker", "network", "rm", name]]
+        runner = FakeRunner(ok(""), fail(1, "No such network"))
+        reaped = reap_orphaned_containers(tmp_path / "state", runner)
+        assert reaped == [name]
+        assert runner.calls == [
+            ["docker", "network", "rm", name],
+            ["docker", "network", "inspect", name],
+        ]
         assert self._read(tmp_path / "state") == []
 
     def test_malformed_name_skipped(self, tmp_path):
@@ -2300,11 +2308,65 @@ class TestReaper:
         proc.wait()
         name = f"{'e' * 32}-exec"
         self._write(tmp_path / "state", [self._entry(name, proc.pid)])
-        runner = FakeRunner(fail(1, "No such container"))
-        reap_orphaned_containers(tmp_path / "state", runner)
-        assert runner.calls == [["docker", "rm", "-f", name]]
+        runner = FakeRunner(fail(1, "No such container"), ok(""))
+        reaped = reap_orphaned_containers(tmp_path / "state", runner)
+        assert reaped == [name]
+        assert runner.calls == [
+            ["docker", "rm", "-f", name],
+            ["docker", "ps", "-a", "--filter", f"name={name}",
+             "--format", "{{.Names}}"],
+        ]
         assert self._read(tmp_path / "state") == []
 
+    def test_rm_failure_container_survives_retained(self, tmp_path):
+        proc = subprocess.Popen([sys.executable, "-c", "pass"])
+        proc.wait()
+        name = f"{'a' * 32}-exec"
+        entry = self._entry(name, proc.pid)
+        self._write(tmp_path / "state", [entry])
+        runner = FakeRunner(fail(1, "daemon busy"), ok(name + "\n"))
+        reaped = reap_orphaned_containers(tmp_path / "state", runner)
+        assert reaped == []
+        assert self._read(tmp_path / "state") == [entry]
+        assert runner.calls == [
+            ["docker", "rm", "-f", name],
+            ["docker", "ps", "-a", "--filter", f"name={name}",
+             "--format", "{{.Names}}"],
+        ]
+
+    def test_rm_failure_network_survives_retained(self, tmp_path):
+        proc = subprocess.Popen([sys.executable, "-c", "pass"])
+        proc.wait()
+        name = f"{'a' * 32}-net"
+        entry = {"run_id": "r", "name": name, "kind": "network",
+                 "pid": proc.pid, "process_start": None, "created_at": "now"}
+        self._write(tmp_path / "state", [entry])
+        runner = FakeRunner(fail(1, "daemon busy"), ok(name))
+        reaped = reap_orphaned_containers(tmp_path / "state", runner)
+        assert reaped == []
+        assert self._read(tmp_path / "state") == [entry]
+        assert runner.calls == [
+            ["docker", "network", "rm", name],
+            ["docker", "network", "inspect", name],
+        ]
+
+    def test_missing_network_tolerated(self, tmp_path):
+        proc = subprocess.Popen([sys.executable, "-c", "pass"])
+        proc.wait()
+        name = f"{'a' * 32}-net"
+        entry = {"run_id": "r", "name": name, "kind": "network",
+                 "pid": proc.pid, "process_start": None, "created_at": "now"}
+        self._write(tmp_path / "state", [entry])
+        runner = FakeRunner(fail(1, "No such network"),
+                            fail(1, "No such network"))
+        reaped = reap_orphaned_containers(tmp_path / "state", runner)
+        assert reaped == [name]
+        assert self._read(tmp_path / "state") == []
+        assert runner.calls == [
+            ["docker", "network", "rm", name],
+            ["docker", "network", "inspect", name],
+        ]
+
     def test_no_registry_is_a_noop(self, tmp_path):
         runner = FakeRunner()
         reap_orphaned_containers(tmp_path / "state", runner)