Intermediate commit

This commit is contained in:
Justin Visser 2026-02-26 16:09:57 +01:00
parent 0e9e49df16
commit 3d4cfeff1a
65 changed files with 5507 additions and 333 deletions

View file

@ -79,12 +79,15 @@ LOG_REDACT_FIELDS=
SCHEDULER_ENABLED=1
SCHEDULER_TICK_SECONDS=60
SCHEDULER_QUEUE_BATCH_SIZE=10
SCHEDULER_PDF_QUEUE_BATCH_SIZE=15
INGESTION_AUTOMATION_ALLOWED=1
INGESTION_MANUAL_RUN_ALLOWED=1
INGESTION_MIN_RUN_INTERVAL_MINUTES=15
INGESTION_MIN_REQUEST_DELAY_SECONDS=2
INGESTION_NETWORK_ERROR_RETRIES=1
INGESTION_RETRY_BACKOFF_SECONDS=1.0
INGESTION_RATE_LIMIT_RETRIES=3
INGESTION_RATE_LIMIT_BACKOFF_SECONDS=30.0
INGESTION_MAX_PAGES_PER_SCHOLAR=30
INGESTION_PAGE_SIZE=100
INGESTION_ALERT_BLOCKED_FAILURE_THRESHOLD=1
@ -125,6 +128,14 @@ UNPAYWALL_RETRY_COOLDOWN_SECONDS=1800
UNPAYWALL_PDF_DISCOVERY_ENABLED=1
UNPAYWALL_PDF_DISCOVERY_MAX_CANDIDATES=5
UNPAYWALL_PDF_DISCOVERY_MAX_HTML_BYTES=500000
ARXIV_ENABLED=1
ARXIV_TIMEOUT_SECONDS=3.0
ARXIV_MIN_INTERVAL_SECONDS=4.0
ARXIV_RATE_LIMIT_COOLDOWN_SECONDS=60.0
ARXIV_DEFAULT_MAX_RESULTS=3
ARXIV_CACHE_TTL_SECONDS=900
ARXIV_CACHE_MAX_ENTRIES=512
ARXIV_MAILTO=
PDF_AUTO_RETRY_INTERVAL_SECONDS=86400
PDF_AUTO_RETRY_FIRST_INTERVAL_SECONDS=3600
PDF_AUTO_RETRY_MAX_ATTEMPTS=3
@ -133,6 +144,9 @@ CROSSREF_MAX_ROWS=10
CROSSREF_TIMEOUT_SECONDS=8.0
CROSSREF_MIN_INTERVAL_SECONDS=0.6
CROSSREF_MAX_LOOKUPS_PER_REQUEST=8
OPENALEX_API_KEY=
CROSSREF_API_TOKEN=
CROSSREF_API_MAILTO=
# ------------------------------
# Startup Bootstrap + DB Wait