Knowledge Graph: figures with pictures, the review queue marked, where each value was found

Knowledge Graph page: the whole database as one graph, kept current

Process type and process conditions on every property row (prompt 2.1)

Cost notes: gemini-3.5-flash output is 6x input; run #543 re-priced (~$7.50, not $2.02)

README: 30 Sep cost note (real prices, model knobs, near-duplicate gate)

Budget hold: no downloads while Gemini refuses for budget reasons, one probe per cycle, automatic resume; adoption capped; target default

Cost: bounded Gemini thinking on every call (default low), figure mining off by default; one-shot config migration

Never store a credential: redact at every DB write and at boot; keep PDFs when Gemini refuses for budget reasons

Candidate queue: a bulk discovery pass fills agent_candidates, cycles drain it; UDSpace + CORE lanes

README: fold the 17 Sep operations notes into the 22/28 Sep ones; describe the lanes and parallel ingestion

Merge the 17 Sep "more papers" lanes onto the hotfix line; parallel ingestion; throughput knobs

Rotate the query frontier on dry cycles; adopt and re-queue never-ingested downloads

README: operations notes for the 22 Sep update (stall detector, budgeted sources, cost column, figure linking)

More papers: budget-aware sources, frontier rotation, schema gate, topic walk, S2 bulk, datasheets, query grid

Keep the agent running: cycle watchdog, Retry-After cap, boot at container start, self keep-alive

Figure & graph mining in the autonomous cycle: figures.py + Postgres port, crops stored in DB, review UI

ui: README pages table reflects the restyled UI (front-matter unchanged)

Initial deploy: autonomous ingestion agent (plan→discover→dedupe→download→ingest→report)

initial commit