viktor/payslip-ingest
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

extractor: bump claude poll timeout to 600s

Browse source 
Real UK payslip PDFs are 100-200KB base64'd, which means ~300-500KB of prompt
tokens. Claude (even Haiku) takes 1-5 minutes to process and emit structured JSON.
The original 120s ceiling timed out before extraction could finish.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Viktor Barzin 2026-04-18 22:32:34 +00:00
parent 11a8256e6a
commit 7a32885d26
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
payslip_ingest/extractor.py
View file

@ -39,12 +39,12 @@ EXTRACTION_PROMPT = (
"- All money in GBP unless the payslip is denominated otherwise.\n"
'- If a field\'s value is ambiguous, pick the value from the "this period" column, not YTD.')
POLL_INTERVAL_SECONDS = 2
MAX_POLL_SECONDS = 120
POLL_INTERVAL_SECONDS = 3
MAX_POLL_SECONDS = 600
BUSY_RETRY_DELAY_SECONDS = 5
MAX_BUSY_RETRIES = 10
DEFAULT_MAX_BUDGET_USD = 1.0
DEFAULT_TIMEOUT_SECONDS = 300
DEFAULT_TIMEOUT_SECONDS = 600
TERMINAL_STATUSES = {"completed", "failed", "timeout", "error"}