Add per-job run logs and separate vision/text model selection.

Capture pipeline stdout into job.log + API/UI so failed runs can be reviewed, and let users pick OpenRouter vision vs text models independently.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/job_log.py

@@ -0,0 +1,93 @@
+"""
+job_log.py - Capture pipeline stdout/stderr into a per-job log.
+
+The pipeline already prints stage progress via print(). For a reviewable
+post-run log we tee those lines into memory + outputs/<job_id>/job.log
+without rewriting every call site.
+"""
+
+import sys
+import time
+from contextlib import contextmanager
+from typing import Callable, Iterator, List, Optional, TextIO
+
+
+class _LineSplitter:
+    """Accumulate write() chunks and emit complete lines."""
+
+    def __init__(self, on_line: Callable[[str], None]):
+        self._buf = ""
+        self._on_line = on_line
+
+    def write(self, s: str) -> None:
+        if not s:
+            return
+        self._buf += s
+        while "\n" in self._buf:
+            line, self._buf = self._buf.split("\n", 1)
+            # Strip trailing CR from Windows-ish streams; keep content intact.
+            self._on_line(line.rstrip("\r"))
+
+    def flush_remainder(self) -> None:
+        if self._buf:
+            self._on_line(self._buf.rstrip("\r"))
+            self._buf = ""
+
+
+class _Tee:
+    """Mirror writes to the original stream and a line callback."""
+
+    def __init__(self, stream: TextIO, on_line: Callable[[str], None]):
+        self._stream = stream
+        self._lines = _LineSplitter(on_line)
+
+    def write(self, s: str) -> int:
+        n = self._stream.write(s)
+        self._stream.flush()
+        self._lines.write(s)
+        return n
+
+    def flush(self) -> None:
+        self._stream.flush()
+
+    def flush_remainder(self) -> None:
+        self._lines.flush_remainder()
+
+    def __getattr__(self, name: str):
+        return getattr(self._stream, name)
+
+
+def stamp_line(line: str, t: Optional[float] = None) -> str:
+    """Prefix a log line with HH:MM:SS."""
+    ts = time.strftime("%H:%M:%S", time.localtime(t if t is not None else time.time()))
+    return f"[{ts}] {line}"
+
+
+@contextmanager
+def capture_stdio(on_line: Callable[[str], None]) -> Iterator[None]:
+    """
+    Tee sys.stdout and sys.stderr into on_line(raw_line) for the duration.
+
+    Safe for the single-job-at-a-time usage of this app; overlapping jobs
+    would interleave (same limitation as the LLM cost counters).
+    """
+    old_out, old_err = sys.stdout, sys.stderr
+    tee_out = _Tee(old_out, on_line)
+    tee_err = _Tee(old_err, on_line)
+    sys.stdout = tee_out  # type: ignore[assignment]
+    sys.stderr = tee_err  # type: ignore[assignment]
+    try:
+        yield
+    finally:
+        tee_out.flush_remainder()
+        tee_err.flush_remainder()
+        sys.stdout = old_out
+        sys.stderr = old_err
+
+
+def read_log_file(path: str) -> List[str]:
+    try:
+        with open(path, encoding="utf-8") as f:
+            return [ln.rstrip("\n") for ln in f]
+    except OSError:
+        return []