whd (looaeedr) errors

8 recurring problems engineers report in whd (looaeedr), ranked by impact.

#59 by errors trackedMCAD

Recurring whd (looaeedr) errors, by impact

  1. 1The manufacturing adapter silently swallowed profile readback and workspace source failures, letting incomplete snapshot or default inputs enter Engine manufacturing resolution. In the companion GUI fix, default width, height, depth and thickness were substituted when physical control reads failed and then saved.MCAD · Agent failure · 1 report74
  2. 2Follow-up to last hour's whd findings. "The main GUI still independently calculated marking-hole X/count/pitch/Y while the Engine's real IndicatorBox MARKING scene generated the same pattern." Other PRs remove a GUI copy of part-identity logic and stop the engine from replacing corrupt inputs with a default group "or fabricating 1mm physical Door/BasePlate sizes for invalid geometry." Agent-written PRs, each starting with a SOURCE_READ_EVIDENCE block listing what was read first, which is its own interesting habit.MCAD · Agent failure · 1 report66
  3. 3Follow-up to last hour's whd findings. "The main GUI still independently calculated marking-hole X/count/pitch/Y while the Engine's real IndicatorBox MARKING scene generated the same pattern." Other PRs remove a GUI copy of part-identity logic and stop the engine from replacing corrupt inputs with a default group "or fabricating 1mm physical Door/BasePlate sizes for invalid geometry." Agent-written PRs, each starting with a SOURCE_READ_EVIDENCE block listing what was read first, which is its own interesting habit.MCAD · Agent failure · 1 report66
  4. 4Follow-up to last hour's whd findings. "The main GUI still independently calculated marking-hole X/count/pitch/Y while the Engine's real IndicatorBox MARKING scene generated the same pattern." Other PRs remove a GUI copy of part-identity logic and stop the engine from replacing corrupt inputs with a default group "or fabricating 1mm physical Door/BasePlate sizes for invalid geometry." Agent-written PRs, each starting with a SOURCE_READ_EVIDENCE block listing what was read first, which is its own interesting habit.MCAD · Agent failure · 1 report66
  5. 5Follow-up to last hour's whd findings. "The main GUI still independently calculated marking-hole X/count/pitch/Y while the Engine's real IndicatorBox MARKING scene generated the same pattern." Other PRs remove a GUI copy of part-identity logic and stop the engine from replacing corrupt inputs with a default group "or fabricating 1mm physical Door/BasePlate sizes for invalid geometry." Agent-written PRs, each starting with a SOURCE_READ_EVIDENCE block listing what was read first, which is its own interesting habit.MCAD · Agent failure · 1 report66
  6. 6Saved false text turned on real inner doors in manufacturing output: sheet-metal cabinet code used bool on the multi_door_enabled field and pre-coerced Door Layout rows with float, so saved legacy false enabled real physical inner doors and True in an unselected grid cell became a valid-looking 1-mm physical cell. Python truthiness reached CUTTING, BEND and DXF output.MCAD · Agent failure · 1 report66
  7. 7The engine strictly validates door-cell indicator data, but the Fold Designer snapshot first ran a GUI repair that silently swapped invalid lamp counts and offsets for defaults. That could make bad saved manufacturing source look like valid holes in the DXF output. The fix rejects it before the snapshot.MCAD · Agent failure · 1 report66
  8. 8The legacy single-door export swallowed malformed indicator input or an engine rejection and still wrote the door DXF, minus the holes. Preview and engine already refused that input, so the GUI path and the manufacturing path disagreed. Same repo as the default-dimension findings earlier today.MCAD · Agent failure · 1 report66

How it fails

  1. Agent failure8

Sourced from public community reports. Costs and delays on individual entries are modeled estimates, not measurements.