Both found by reading the output of a real page through a real pod, which is
the only place either was visible.

WHICH CONFIGURATION. A pod answers with the engine it ran, because the
configuration ids in ocr.engine_configs are an orchestrator-side naming layer
it has never heard of. So `engine=surya-layout` came back `engine: surya`, same
as plain surya -- and telling two configurations of one engine apart in the
answer is most of the point of having two ids. The local path already reported
the id; now both do, and a plain engine name still reports itself.

A CONFIDENCE NOBODY MEASURED. surya's table recogniser does not score cells in
the mode we call it in, so every cell carried `conf: 0.0` -- a placeholder
wearing a measurement's clothes, which is the confusion `confidence_measured`
already exists to prevent for pages. The key is now present only when surya
reported a number, and the table says `confidence_measured` so a caller gating
on cell confidence can tell whether there is anything to gate on. Presence
decides it rather than truthiness, because a real 0.0 IS a measurement.

Table markup likewise: `html` is absent rather than empty, so "this engine
returns no HTML" (surya, which returns cells) is distinguishable from "this
table's HTML is empty".

Two of the tests written for this asserted against a fixed byte window after a
`def`, and failed on the correct edit that grew the function -- the same
brittleness fixed in test_image_edit_uses_an_image_pipeline an hour earlier.
They read the function by AST now.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S8LAP3ueNzQJtwzhgVbq66