docs: morning list — substrate section filled (make check = AMBER expected, plain meaning), judgment log opened (prompt_sync finding, spine call, honest baseline count)

MORNING-TEST-2026-10-16.md

@@ -19,13 +19,21 @@ This list gets filled in further as overnight work lands.
 - If still silent: tell Rune — the next fix (umu runtime rollback) is
   already planned and takes minutes.
 
-## 3. The one-command whole-system check (substrate — lands overnight)
+## 3. The one-command whole-system check (LANDED overnight)
 
-- Run:
-  `python scripts/unified_check.py`
-- Expect: one verdict line, green, with a short report of every test
-  world (Rust, Python, Go when it exists, boundary conversation tests).
-- This is the command that every future landing must pass.
+- Run, from the repo root:
+  `make check`
+  (same thing, spelled out: `python scripts/unified_check.py`)
+- Takes several minutes — it sweeps everything: all 103 Rust crates, the
+  whole Python suite, the Go side, the boundary conversation tests, the
+  code-generation gate, and the no-binaries gate.
+- Expect the final verdict **AMBER**. Plain meaning of AMBER: "only the
+  old, known failures remain — nothing new." That is the correct, honest
+  green for this repo right now. RED means something new broke.
+- The known-old list it tolerates: ~120 old Python failures (recorded
+  baseline, being paid down over time) + one known-sick Rust crate
+  (prompt_sync — found by this very runner on its first ever sweep;
+  repair already queued overnight).
 
 ## 4. The TUI first breath (foundation — lands overnight)
 
@@ -51,3 +59,18 @@ test list above is only for things that need human eyes or ears.
 
 (Filled in as they happen — each one gets a line here so you can
 overrule anything in the morning.)
+
+1. **Substrate's first sweep found a sick Rust crate** (`prompt_sync` —
+   an arithmetic overflow that crashes three of its tests; pre-existing,
+   never swept before, NOT caused by tonight's work). Left unfixed by
+   the substrate worker (correctly — separate concern), repair queued
+   overnight.
+2. **The repo's "spine" snapshot was stale** relative to yesterday's
+   landed fixes. The suite refreshes it when it runs; I left the
+   refreshed version in place because restoring the stale one would arm
+   a false alarm. Flagged for your call if you want spine handling
+   changed.
+3. **The old failure count is 120, not 116** (the research's number was
+   approximate). The runner records the honest baseline and compares
+   against it by content, not by count — the edges of the old set flicker
+   by one or two between runs, so exact counts lie.