.github/workflows/standards-build.yml

@@ -558,6 +558,14 @@ jobs:
       # and macOS. The fabric calibration rows' macOS stamp, and a CPU member
       # priced on this process's own counters against its own energy count
       # (tests/process_calibration.rs), each print their line only there.
+      #
+      # The calibration test meters the GPU counter only once a GPU liveness load has run, and
+      # that load gives up after 500 ms on a GPU too busy to grant it. The test then takes its
+      # refusal branch and passes, but prints no `process calibration:` line, so the grep fails
+      # on host load alone (seen 2026-10-25, the runner's host at load 55). Its own retries
+      # keep that from costing a whole pull request's rerun: up to three runs, 20 s apart, and
+      # the line must still come from a run on live counters. A failing assertion fails the
+      # step at once, as before.
       - name: jouleclaw-loader-gguf (fabric-meter, process calibration)
         shell: bash
         working-directory: jouleclaw/jouleclaw-rs
@@ -565,7 +573,12 @@ jobs:
           set -o pipefail
           log=$(mktemp)
           cargo test -p jouleclaw-loader-gguf --features "rayon fabric-meter" marginal_energy -- --nocapture 2>&1 | tee "$log"
-          cargo test -p jouleclaw-loader-gguf --features "rayon fabric-meter" --test process_calibration -- --nocapture 2>&1 | tee -a "$log"
+          for attempt in 1 2 3; do
+            cargo test -p jouleclaw-loader-gguf --features "rayon fabric-meter" --test process_calibration -- --nocapture 2>&1 | tee -a "$log"
+            grep -q 'process calibration: CPU member' "$log" && break
+            echo "process calibration: attempt $attempt ran without live GPU counters (a busy GPU); trying again in 20 s"
+            sleep 20
+          done
           grep -q 'calibration row stamped on macOS:' "$log"
           grep -q 'process calibration: CPU member' "$log"