From 7df49656d18f0ae7519b25e57fb78a9ab4233db8 Mon Sep 17 00:00:00 2001
From: ClumsyLucid <xianjunbao03@gmail.com>
Date: Mon, 13 Jul 2026 00:23:10 +0800
Subject: [PATCH] fix(skillopt-sleep): surface Claude CLI spawn failures
 instead of silent zero scores (#126)

* fix(skillopt-sleep): surface Claude CLI spawn failures instead of silent zero scores

In _call and attempt_with_tools, the bare 'except Exception: return ""'
swallows FileNotFoundError (e.g. bare 'claude' on Windows with npm .cmd
shim) and any other spawn failure, returning an empty string that the
trainer treats as a legitimate model response that scores 0.0 everywhere.

Now the exception is caught explicitly: last_call_error is set, a
warning is logged, and the empty-string return is preserved for
backward compatibility of the control flow. This mirrors the pattern
from #92 (codex backend) which fixed the same class of 'dead CLI
masquerades as nothing to learn' bug.

Issue: #121

* test(skillopt-sleep): add tests verifying Claude CLI spawn failures are surfaced

Add two tests to TestClaudeCliBackendBare:
- test_spawn_failure_sets_last_call_error: _call sets last_call_error
  and returns '' when subprocess.run raises FileNotFoundError.
- test_attempt_tools_spawn_failure_sets_last_call_error: same for
  attempt_with_tools.

These prove the fix from the parent commit (surface spawn failures
instead of silently scoring 0) and guard against regressions.
---
 skillopt_sleep/backend.py  | 14 ++++++++++++--
 tests/test_sleep_engine.py | 30 ++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/skillopt_sleep/backend.py b/skillopt_sleep/backend.py
index 94b44e0..ef56343 100644
--- a/skillopt_sleep/backend.py
+++ b/skillopt_sleep/backend.py
@@ -634,7 +634,12 @@ class ClaudeCliBackend(CliBackend):
                 cmd, capture_output=True, creationflags=_NO_WINDOW, text=True, timeout=self.timeout, cwd=clean_cwd,
                 input=prompt,
             )
-        except Exception:
+        except Exception as exc:
+            import logging
+            self.last_call_error = f"Claude CLI spawn failed: {exc}"
+            logging.getLogger("skillopt_sleep").warning(
+                "Claude CLI could not be executed: %s", exc,
+            )
             return ""
         finally:
             try:
@@ -698,7 +703,12 @@ class ClaudeCliBackend(CliBackend):
                 )
                 resp = (proc.stdout or "").strip()
                 self._detect_cli_error(resp, proc.stderr or "")
-            except Exception:
+            except Exception as exc:
+                import logging
+                self.last_call_error = f"Claude CLI spawn failed: {exc}"
+                logging.getLogger("skillopt_sleep").warning(
+                    "Claude CLI could not be executed: %s", exc,
+                )
                 resp = ""
             self._tokens += len(prompt) // 4 + len(resp) // 4
             called: List[str] = []
diff --git a/tests/test_sleep_engine.py b/tests/test_sleep_engine.py
index e9e39a0..c421729 100644
--- a/tests/test_sleep_engine.py
+++ b/tests/test_sleep_engine.py
@@ -1118,6 +1118,36 @@ class TestClaudeCliBackendBare(unittest.TestCase):
         # But it's also recorded for detection
         self.assertIn("Not logged in", getattr(be, "last_call_error", ""))
 
+    def test_spawn_failure_sets_last_call_error(self):
+        """When subprocess.run raises FileNotFoundError, _call must set
+        last_call_error and log a warning instead of silently returning ''."""
+        from skillopt_sleep.backend import ClaudeCliBackend
+        be = ClaudeCliBackend(
+            claude_path="/nonexistent/claude-binary",
+            timeout=3,
+        )
+        result = be._call("test prompt")
+        self.assertEqual(result, "")
+        self.assertIn("Claude CLI spawn failed", be.last_call_error)
+
+    def test_attempt_tools_spawn_failure_sets_last_call_error(self):
+        """When subprocess.run raises in attempt_with_tools, last_call_error
+        must be set and a warning logged."""
+        from skillopt_sleep.backend import ClaudeCliBackend
+        from skillopt_sleep.types import TaskRecord
+        be = ClaudeCliBackend(
+            claude_path="/nonexistent/claude-binary",
+            timeout=3,
+        )
+        task = TaskRecord(
+            id="t1", project="/p", intent="test",
+            reference="ref", reference_kind="exact",
+            tags=[], split="train",
+        )
+        resp, called = be.attempt_with_tools(task, "", "", tools=["search"])
+        self.assertEqual(resp, "")
+        self.assertIn("Claude CLI spawn failed", be.last_call_error)
+