
Show key i3.conf config for a hub (provider, harvest.type, harvest.endpoint, schedule, email, setlist). Use when user asks for hub config, harvest type/endpoint, who gets emails, schedule months, or OAI setlist details.
Run Community Webs ingest. Use when the user says harvest community-webs, run community-webs ingest, export community webs, or process community webs DB.
Show key i3.conf config for a hub (provider, harvest.type, harvest.endpoint, schedule, email, setlist). Use when user asks for hub config, harvest type/endpoint, who gets emails, schedule months, or OAI setlist details.
Execute a single-hub or manual ingest by following the correct runbook and scripts. Use when the user says run ingest for [hub], harvest [hub], remap [hub], or run the full pipeline for [hub]. Ensures harvest type is identified, correct runbook and scripts are used, and outputs are verified.
Follow the project workflow when adding or modifying shell or Python scripts. Use when the user asks to add a script, create a new script, modify a script, or write a script for a task. Ensures POSIX bash, common.sh, documentation in SCRIPTS.md, and tests are created or updated and run.
Verify ingest outcomes and send failure or status notifications to Slack or [email protected]. Use when the user asks to verify the ingest, check if it succeeded, notify about a failure, or post to tech-alerts.
Show all active and completed ingests in one consolidated view. Use when user asks status of the ingests, ingest status, which hubs are running, show active ingests, or ingest progress.
Debug and fix DPLA hub ingestion failures (harvest/mapping/enrichment/jsonl/s3-sync/anomaly). Use when user asks why a hub failed, to debug an ingest failure, check an escalation report, or retry a failed hub/stage.
Monitor a running IngestRemap (remap.sh / ingest.sh step 2) or orchestrator remap stages. Use when user asks whether mapping/enrichment/jsonl is done yet, to monitor remap progress, or to check which stage is currently running.
Watch an OAI harvest log and report set-by-set progress + ETA (for hubs using harvest.setlist). Use when user asks to watch OAI harvest progress, track sets, estimate completion, or monitor a long OAI harvest.
Run S3 sync and AWS data operations for DPLA ingestion using the correct profile and scripts. Use when the user says sync to S3, check S3 sync, upload to S3, AWS bucket, or check JSONL sync.
Run or monitor the DPLA Python ingest orchestrator. Use when the user says run orchestrator, parallel ingest, ingest status, run hubs, orchestrator dry-run, or retry failed hubs. Covers venv, main entry point, status script, and logs.
Generate/preview/draft/send the monthly pre-scheduling summary email to hub contacts scheduled for a month (from i3.conf schedule.months). Use when user asks to send the scheduling email, monthly scheduling email, notify hubs for a month, or pre-scheduling email.
Report which hubs have new JSONL staged in S3 for a given month, and optionally post the report to Slack. Use when user asks what hubs are staged/ready for indexing, /ingest staged, or what changed this month in S3.
Show key i3.conf config for a hub (provider, harvest.type, harvest.endpoint, schedule, email, setlist). Use when user asks for hub config, harvest type/endpoint, who gets emails, schedule months, or OAI setlist details.
Find the latest harvest/mapping/jsonl exports in S3 for a given hub (under s3://dpla-master-dataset/<hub>/...). Use when user asks latest S3 data for a hub, when a hub was last ingested, check whether mapping/jsonl/harvest exists in S3, or latest jsonl/mapping/harvest for a hub.
Run Community Webs ingest from SQLite DB. Use when the user says harvest community-webs, run community-webs ingest, export community webs, or process community webs DB.
Watch an OAI harvest log and report set-by-set progress + ETA (for hubs using harvest.setlist). Use when user asks to watch OAI harvest progress, track sets, or estimate completion.
Report which hubs have new JSONL staged in S3 for a given month, and optionally post the report to Slack. Use when user asks what hubs are staged/ready for indexing or /ingest staged.
Show all active and completed ingests in one consolidated view. Use when user asks status of the ingests, ingest status, which hubs are running, show active ingests, or ingest progress.
Send an ingest summary email to a hub's configured contacts from i3.conf using the most recent (or specified) mapping output. Use when user asks send/resend a hub ingest summary email.
Monitor a running IngestRemap (remap.sh / ingest.sh step 2) or orchestrator remap stages. Use when user asks whether mapping/enrichment/jsonl is done yet, to monitor remap progress, or to check which stage is currently running.