Fetch candidate pages sequentially with the full remaining download budget instead of dividing a quick run's 500 KB equally across every URL. This avoids aborting otherwise readable pages at roughly 33 KB before claim extraction can inspect them.
Account for bytes consumed by failed downloads, preserve fetch errors in source responses, and fail runs with no successfully extracted document using an actionable error. Keep attempted sources on failed runs for diagnostics and cover the allocation and no-usable-source paths with regression tests.
Connect source-independence analysis and Stage 8 evidence scoring to the research orchestrator so completed runs retain a transparent score for every extracted claim. Forward those scores into Stage 9's evidence package, allowing synthesis to reason from actual provenance and exposing them through the research API.
Replace the previously technical-only synthesis fallback with the report contract consumed by the UI: a summary, source statistics, methodology, and provenance-preserving uncertain findings. Add regression coverage for score generation, score hand-off to Stage 9, report methodology, and visible fallback findings; record the healthy container deployment in the hand-off.
Protect the research lifecycle with X-API-Key validation backed by persistent user and key records. Store only salted scrypt hashes, support expiry and revocation, and expose a local admin CLI for create/list/revoke workflows.
Initialize only the authentication schema at startup, prevent SQL echo from exposing sensitive bound values, and keep health probes public. Add coverage for valid, missing, invalid, expired, and revoked keys.
Document deployment and key administration, update the local CLI to send NSCT_API_KEY, and record the reset handoff state.
