Add hallucination-probe scoring across chat + tabular review

↗ view on GitHub · Matilda · 2026-05-06 · e7549126

Wire Mike to a Modal-hosted, OpenAI-compatible probe service. After
each Claude/Gemini response, send the completion as a prefilled
assistant turn to the probe and stream per-token scores onto the
existing SSE channel. Persist scores on `chat_messages.probe_scores`
and `tabular_cells.probe_scores`. UI fades a heat-strip + risk badge
under cells/messages as scores arrive.

Also: local mock probe at /mock-probe for development without the
Modal service, and a "Think" toggle on the chat input so users can
opt into adaptive thinking per turn (off by default - Sonnet 4.6 was
rejecting the unconditional flag).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Repository mglynnhenley/mikehasprobes
Author Matilda <matilda@Matildas-MacBook-Pro.local>
Authored
Parents d9690965
Stats 25 files changed , +609 , -16
Part of Hallucination-probe scoring across chat and tabular review

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-e7549126.md from inside the repo you want the change in.

⬇ Download capture-commit-e7549126.md