fix(sleep): reset ClaudeCliBackend.last_call_error at each call start

Follow-up to #126. ClaudeCliBackend recorded last_call_error on failure but
never reset it, so a failure followed by a successful call still reported the
stale error in persisted diagnostics — making a healthy run look failed. Both
_call() and attempt_with_tools() now clear it at the start, matching
CodexCliBackend.

Note: the "TimeoutExpired leaks the prompt into logs" concern raised in review
does NOT apply on current main — the prompt is passed via stdin (input=), not
argv (fixed by #98), so TimeoutExpired's str() only contains the argv (no
prompt). Verified empirically.

Adds a regression test asserting a prior failure is cleared on the next
success.

Co-Authored-By: Claude <noreply@anthropic.com>

skillopt_sleep/__main__.py

@@ -311,13 +311,6 @@ def _handoff_mine_and_pin(cfg, args, backend, snapshot: str, dry: bool):
             # branch, or every later run re-scans the same stale window.
             state.set_last_harvest(project, started)
             state.save()
-            # Drop the pinned (often empty) digests so the NEXT run re-harvests
-            # instead of reloading a []-pin and never calling harvest again.
-            try:
-                if os.path.exists(digests_path):
-                    os.remove(digests_path)
-            except OSError:
-                pass
         return 0, None
     payload = make_tasks_payload(
         tasks,
@@ -349,21 +342,13 @@ def _run_handoff(cfg, args, *, seed_tasks, task_meta: Dict[str, Any], dry: bool)
     tasks = seed_tasks
     if tasks is None:
         snapshot = os.path.join(hdir, "tasks.json")
-        tasks = None
         if os.path.exists(snapshot):
-            try:
-                tasks, _meta = load_tasks_file(
-                    snapshot,
-                    holdout_fraction=cfg.get("holdout_fraction", 0.34),
-                    seed=cfg.get("seed", 42),
-                )
-            except (ValueError, json.JSONDecodeError, OSError):
-                # Interrupted/corrupt pin from an earlier round: re-mine instead
-                # of crashing the run.
-                print("[sleep] handoff: tasks.json unreadable — re-mining",
-                      file=sys.stderr)
-                tasks = None
-        if tasks is None:
+            tasks, _meta = load_tasks_file(
+                snapshot,
+                holdout_fraction=cfg.get("holdout_fraction", 0.34),
+                seed=cfg.get("seed", 42),
+            )
+        else:
             rc, tasks = _handoff_mine_and_pin(cfg, args, backend, snapshot, dry)
             if tasks is None:
                 return rc

skillopt_sleep/backend.py

@@ -615,6 +615,9 @@ class ClaudeCliBackend(CliBackend):
         #   --exclude-dynamic-...     drop per-machine cwd/env/memory/git sections
         #   cwd=<clean temp>          no project CLAUDE.md
         import tempfile
+        # Reset per call so a prior failure does not make a later successful
+        # call look failed in persisted diagnostics (matches CodexCliBackend).
+        self.last_call_error = ""
         cmd = [self.claude_path, "-p", "--output-format", "text"]
         if os.environ.get("ANTHROPIC_API_KEY"):
             cmd.append("--bare")
@@ -657,6 +660,7 @@ class ClaudeCliBackend(CliBackend):
         # validated honestly: we detect the call from the shim's log, not from
         # a self-reported marker. Other tools are stubbed the same way.
         import tempfile, shutil, stat
+        self.last_call_error = ""
         work = tempfile.mkdtemp(prefix="skillopt_sleep_tools_")
         calllog = os.path.join(work, "_tool_calls.log")
         try:

tests/test_handoff_backend.py

@@ -215,45 +215,6 @@ class TestHandoffCli(unittest.TestCase):
             state = SleepState.load(cfg.state_path)
             self.assertIsNotNone(state.last_harvest_for(proj))
 
-    def test_no_tasks_removes_digests_pin_so_next_run_reharvests(self):
-        """After a no-task night the (often empty) digests.json pin must be
-        removed, or every later run reloads a []-pin and never harvests again."""
-        from skillopt_sleep.__main__ import main
-
-        with tempfile.TemporaryDirectory() as proj, \
-                tempfile.TemporaryDirectory() as home:
-            hdir = os.path.join(proj, ".skillopt-sleep-handoff")
-            os.makedirs(hdir, exist_ok=True)
-            digests_path = os.path.join(hdir, "digests.json")
-            with open(digests_path, "w", encoding="utf-8") as f:
-                json.dump([], f)
-            rc = main([
-                "run", "--backend", "handoff",
-                "--project", proj,
-                "--claude-home", os.path.join(home, ".claude"),
-            ])
-            self.assertEqual(rc, 0)
-            # the empty pin must be gone so the next run re-harvests
-            self.assertFalse(os.path.exists(digests_path))
-
-    def test_corrupt_tasks_pin_falls_back_to_remine(self):
-        """An interrupted/corrupt tasks.json snapshot must not crash the run."""
-        from skillopt_sleep.__main__ import main
-
-        with tempfile.TemporaryDirectory() as proj, \
-                tempfile.TemporaryDirectory() as home:
-            hdir = os.path.join(proj, ".skillopt-sleep-handoff")
-            os.makedirs(hdir, exist_ok=True)
-            with open(os.path.join(hdir, "tasks.json"), "w", encoding="utf-8") as f:
-                f.write('{"tasks": [ truncated...')
-            rc = main([
-                "run", "--backend", "handoff",
-                "--project", proj,
-                "--claude-home", os.path.join(home, ".claude"),
-            ])
-            # corrupt snapshot -> re-mine -> no tasks -> 0 (not a crash)
-            self.assertEqual(rc, 0)
-
 
 if __name__ == "__main__":
     unittest.main()

tests/test_sleep_engine.py

@@ -1148,6 +1148,26 @@ class TestClaudeCliBackendBare(unittest.TestCase):
         self.assertEqual(resp, "")
         self.assertIn("Claude CLI spawn failed", be.last_call_error)
 
+    def test_last_call_error_cleared_on_next_success(self):
+        """A prior failure must not make a later successful call look failed:
+        _call resets last_call_error at the start of each call."""
+        from unittest import mock
+        from skillopt_sleep.backend import ClaudeCliBackend
+        be = ClaudeCliBackend(claude_path="claude", timeout=3)
+        # First call fails to spawn -> error recorded.
+        with mock.patch("skillopt_sleep.backend.subprocess.run",
+                        side_effect=FileNotFoundError("no claude")):
+            self.assertEqual(be._call("p1"), "")
+        self.assertIn("Claude CLI spawn failed", be.last_call_error)
+        # Next call succeeds -> stale error must be cleared.
+
+        class _OK:
+            stdout = "answer"
+            stderr = ""
+        with mock.patch("skillopt_sleep.backend.subprocess.run", return_value=_OK()):
+            self.assertEqual(be._call("p2"), "answer")
+        self.assertEqual(be.last_call_error, "")
+