fix(run_tests_batched): keep pytest's full -v output, only filter LogPruner/win errors, colorize per-test status

scripts/run_tests_batched.py

@@ -85,13 +85,50 @@ def _parse_durations_from_pytest_output(stdout: str) -> dict[str, float]:
    continue
  return out
 
+_NOISE_PREFIXES: tuple[str, ...] = (
+ "[LogPruner]",
+ "[startup]",
+ "created: ",
+ "=========",
+)
+
+_NOISE_SUBSTRINGS: tuple[str, ...] = (
+ "[WinError",
+)
+
+def _format_pytest_line(line: str) -> str | None:
+ stripped = line.rstrip()
+ if not stripped:
+  return None
+ for prefix in _NOISE_PREFIXES:
+  if stripped.startswith(prefix):
+   return None
+ for sub in _NOISE_SUBSTRINGS:
+  if sub in stripped:
+   return None
+ if " PASSED " in stripped and "[gw" in stripped:
+  return _c(stripped, _C.GREEN)
+ if " FAILED " in stripped and "[gw" in stripped:
+  return _c(stripped, _C.BOLD_RED)
+ if " ERROR " in stripped and "[gw" in stripped:
+  return _c(stripped, _C.BOLD_RED)
+ if stripped.startswith(("PASSED", "FAILED", "ERROR")) and "::" in stripped:
+  status = stripped.split()[0]
+  rest = stripped[len(status):]
+  if status == "PASSED":
+   return _c(f"{status}{rest}", _C.GREEN)
+  return _c(f"{status}{rest}", _C.BOLD_RED)
+ if stripped.startswith(("passed", "failed", "error")) and " in " in stripped and stripped.endswith("s"):
+  return _c(stripped, _C.BOLD)
+ return stripped
+
 def _run_batch(b: Batch, durations: dict[str, float]) -> tuple[int, float, dict[str, float]]:
  if b.skip_reason:
   return 0, 0.0, {}
  args = list(b.pytest_args)
  if not _HAS_XDIST:
   args = [a for a in args if a not in {"-n", "auto"}]
- cmd = ["uv", "run", "pytest", "-v", "--durations=0"] + args + [str(f) for f in b.files]
+ cmd = ["uv", "run", "pytest", "-v", "--durations=3"] + args + [str(f) for f in b.files]
  print(_c(f"\n>>> Running {b.label} ({len(b.files)} files)", _C.BOLD_CYAN))
  t0 = time.monotonic()
  proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True, bufsize=1)
@@ -99,7 +136,10 @@ def _run_batch(b: Batch, durations: dict[str, float]) -> tuple[int, float, dict[
  assert proc.stdout is not None
  for line in proc.stdout:
   captured.append(line)
-  print(line, end="")
+  formatted = _format_pytest_line(line)
+  if formatted is None:
+   continue
+  print(formatted)
  proc.wait()
  elapsed = time.monotonic() - t0
  new_durs = _parse_durations_from_pytest_output("".join(captured))
@@ -110,20 +150,61 @@ def _run_batch(b: Batch, durations: dict[str, float]) -> tuple[int, float, dict[
  return proc.returncode, elapsed, new_durs
 
 def _print_summary(results: list[tuple[Batch, int, float]]) -> int:
- print("\n" + "=" * 60)
+ print()
- print("SUMMARY")
+ rows: list[tuple[str, str, str, int, float, int]] = []
- print("=" * 60)
  worst = 0
+ total_files = 0
+ total_time = 0.0
+ passed_count = 0
+ failed_count = 0
+ skipped_count = 0
  for b, code, elapsed in results:
-  if b.skip_reason:
-   status = _c("SKIPPED", _C.BOLD_YELLOW)
-  elif code == 0:
-   status = _c("PASS", _C.BOLD_GREEN)
-  else:
-   status = _c("FAIL", _C.BOLD_RED)
-  worst = max(worst, code)
   n = len(b.files)
-  print(f"[{b.tier}] {b.label:40s} {status} {n} files {elapsed:6.1f}s")
+  total_files += n
+  total_time += elapsed
+  if b.skip_reason:
+   status_text = "SKIPPED"
+   skipped_count += 1
+  elif code == 0:
+   status_text = "PASS"
+   passed_count += 1
+  else:
+   status_text = "FAIL"
+   failed_count += 1
+  worst = max(worst, code)
+  rows.append((b.tier, b.label, status_text, n, elapsed, code))
+ tier_w = max(len("TIER"), max(len(r[0]) for r in rows))
+ label_w = max(len("BATCH LABEL"), max(len(r[1]) for r in rows))
+ status_w = max(len("STATUS"), max(len(r[2]) for r in rows))
+ files_w = max(len("FILES"), max(len(str(r[3])) for r in rows))
+ time_w = max(len("TIME"), max(len(f"{r[4]:.1f}s") for r in rows))
+ header = f" {'TIER':{tier_w}s} │ {'BATCH LABEL':{label_w}s} │ {'STATUS':{status_w}s} │ {'FILES':>{files_w}s} │ {'TIME':>{time_w}s} "
+ sep = "─" * len(header)
+ print(_c(sep, _C.DIM))
+ print(_c(header, _C.BOLD))
+ print(_c(sep, _C.DIM))
+ for tier, label, status_text, n, elapsed, _code in rows:
+  if status_text == "PASS":
+   status = _c(status_text, _C.BOLD_GREEN)
+  elif status_text == "FAIL":
+   status = _c(status_text, _C.BOLD_RED)
+  else:
+   status = _c(status_text, _C.BOLD_YELLOW)
+  tier_colored = _c(f" {tier:<{tier_w}s}", _C.CYAN)
+  print(f"{tier_colored} │ {label:<{label_w}s} │ {status} │ {n:>{files_w}d} │ {elapsed:>{time_w - 1}.1f}s")
+ print(_c(sep, _C.DIM))
+ if failed_count:
+  overall_text = f"{failed_count} FAILED"
+  overall = _c(overall_text, _C.BOLD_RED)
+ elif passed_count:
+  overall_text = f"ALL {passed_count} PASS"
+  overall = _c(overall_text, _C.BOLD_GREEN)
+ else:
+  overall_text = "NO BATCHES RUN"
+  overall = _c(overall_text, _C.BOLD_YELLOW)
+ total_label = _c(f" {'TOTAL':<{tier_w}s}", _C.BOLD)
+ print(f"{total_label} │ {'':<{label_w}s} │ {overall} │ {total_files:>{files_w}d} │ {total_time:>{time_w - 1}.1f}s")
+ print(_c(sep, _C.DIM))
  return worst
 
 def main() -> int: