teahubxyzandClaude e52e116815 labs/aicharts: show decision confidences, per-request floor, bench user agent (#41) ...

Live: Clef answered both probes right in ~0.5 s but at 0.21-0.25 confidence, so
the 0.5 floor sent them to the LLM. Expose every confidence and the weakest
question; a request may set its own floor (only changes cost); bench.py takes
clef@0 for calibration and sends a user agent Cloudflare accepts.


Claude-Session: https://claude.ai/code/session_01VDkN7ukK1kXkqov8FaZxva

Co-authored-by: Claude <noreply@anthropic.com>

2026-10-13 15:31:05 +00:00

..

ISSUE_TEMPLATE

…

time

labs/aicharts: show decision confidences, per-request floor, bench user agent (#41)

2026-10-13 15:31:05 +00:00

workflows

labs/aicharts: fix model spelling drift, show the model's answer on failure (#37)

2026-10-13 13:47:49 +00:00