fix: retry + stderr capture + pacing in triage/extractor

Both scripts now:
- Retry up to 3x with 2s/4s exponential backoff on transient
  failures (rate limits, capacity spikes)
- Capture claude CLI stderr in the error message (200 char cap)
  instead of just the exit code — diagnostics actually useful now
- Sleep 0.5s between calls to avoid bursting the backend

Context: last batch run hit 100% failure in triage (every call
exit 1) after 40% failure in extraction. claude CLI worked fine
immediately after, so the failures were capacity/rate-limit
transients. With retry + pacing these batches should complete
cleanly now. 439 candidates are already in the queue waiting
for triage.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-16 16:29:20 -04:00
parent ba36a28453
commit 3011aa77da
2 changed files with 64 additions and 29 deletions

View File

@@ -126,22 +126,34 @@ def extract_one(prompt, response, project, model, timeout_s):
user_message,
]
try:
completed = subprocess.run(
args, capture_output=True, text=True,
timeout=timeout_s, cwd=get_sandbox_cwd(),
encoding="utf-8", errors="replace",
)
except subprocess.TimeoutExpired:
return [], "timeout"
except Exception as exc:
return [], f"subprocess_error: {exc}"
# Retry with exponential backoff on transient failures (rate limits etc)
import time as _time
last_error = ""
for attempt in range(3):
if attempt > 0:
_time.sleep(2 ** attempt) # 2s, 4s
try:
completed = subprocess.run(
args, capture_output=True, text=True,
timeout=timeout_s, cwd=get_sandbox_cwd(),
encoding="utf-8", errors="replace",
)
except subprocess.TimeoutExpired:
last_error = "timeout"
continue
except Exception as exc:
last_error = f"subprocess_error: {exc}"
continue
if completed.returncode != 0:
return [], f"exit_{completed.returncode}"
if completed.returncode == 0:
raw = (completed.stdout or "").strip()
return parse_candidates(raw, project), ""
raw = (completed.stdout or "").strip()
return parse_candidates(raw, project), ""
# Capture stderr for diagnostics (truncate to 200 chars)
stderr = (completed.stderr or "").strip()[:200]
last_error = f"exit_{completed.returncode}: {stderr}" if stderr else f"exit_{completed.returncode}"
return [], last_error
def parse_candidates(raw, interaction_project):
@@ -192,10 +204,14 @@ def main():
total_persisted = 0
errors = 0
for summary in interaction_summaries:
import time as _time
for ix, summary in enumerate(interaction_summaries):
resp_chars = summary.get("response_chars", 0) or 0
if resp_chars < 50:
continue
# Light pacing between calls to avoid bursting the claude CLI
if ix > 0:
_time.sleep(0.5)
iid = summary["id"]
try:
raw = api_get(