Merge master updates into the UAC1 host branch

Bring the audio work onto the current host core and build files before applying the remaining review fixes.

Signed-off-by: HiFiPHile <[email protected]>

1 files changed, 338 insertions, 32 deletions

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index c8c597e50..8f6014f48 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -41,27 +41,100 @@ jobs:
               - '.github/actions/**'
               - '.github/workflows/build.yml'
               - '.github/workflows/build_util.yml'
-              - '.github/workflows/ci_set_matrix.py'
+              - '.github/scripts/**'
 
   set-matrix:
     runs-on: ubuntu-latest
     outputs:
       json: ${{ steps.set-matrix-json.outputs.matrix }}
       hil_json: ${{ steps.set-matrix-json.outputs.hil_matrix }}
+      # one pair per rig job: hil-tinyusb (tinyusb.json minus esptool boards),
+      # hil-tinyusb-esp (esptool boards only), hil-tinyusb (hfp.json)
+      hil_args_tinyusb: ${{ steps.hil-select.outputs.args_tinyusb }}
+      hil_run_tinyusb: ${{ steps.hil-select.outputs.run_tinyusb }}
+      hil_args_tinyusb_esp: ${{ steps.hil-select.outputs.args_tinyusb_esp }}
+      hil_run_tinyusb_esp: ${{ steps.hil-select.outputs.run_tinyusb_esp }}
+      hil_args_hfp: ${{ steps.hil-select.outputs.args_hfp }}
+      hil_run_hfp: ${{ steps.hil-select.outputs.run_hfp }}
     steps:
       - name: Checkout TinyUSB
         uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: HIL selection (PR only)
+        id: hil-select
+        if: github.event_name == 'pull_request'
+        env:
+          BASE_REF: ${{ github.base_ref }}
+        run: |
+          # Best-effort by design: set-matrix gates cmake, hil-build and every rig job,
+          # so a missing origin/<base>, a shallow-clone hiccup or a selector traceback
+          # must fall back to the FULL matrix (no --select, run=true, no args) instead
+          # of failing the job. Same fail-open shape as pr_comment.yml's `|| true`.
+          #
+          # The selector's own unit suite gates it (stdlib-only, seconds): a selector
+          # whose tests fail can still exit 0 with valid-but-WRONG JSON -- fail-open alone
+          # never catches that class, and the pre-commit hil-test hook is a separate,
+          # advisory workflow that nothing here can `needs:`. Test-failing selector =>
+          # full matrix, same as a crashing one.
+          SELECT_JSON=''
+          if ! python3 test/hil/test/test_hil_select.py; then
+            echo "::warning::hil_select unit suite failed - falling back to the full HIL matrix"
+          elif ! SELECT_JSON=$(python3 test/hil/helper/hil_select.py --base "origin/$BASE_REF" test/hil/tinyusb.json test/hil/hfp.json); then
+            echo "::warning::hil_select failed - falling back to the full HIL matrix"
+            SELECT_JSON=''
+          fi
+
+          # One args/run pair per rig job, split by flasher: a job whose own subset is
+          # empty skips explicitly instead of running a board filter that matches zero
+          # boards ("No tests were run." exits 0 and would read as a green HIL run).
+          OUT=''
+          if [ -n "$SELECT_JSON" ]; then
+            OUT=$(SELECT_JSON="$SELECT_JSON" python3 -c '
+          import json, os
+          s = json.loads(os.environ["SELECT_JSON"])
+          tin = s.get("args_flasher", {}).get("tinyusb.json", {})
+          legs = (("tinyusb", " ".join(a for f, a in sorted(tin.items()) if f != "esptool" and a)),
+                  ("tinyusb_esp", tin.get("esptool", "")),
+                  ("hfp", s.get("args", {}).get("hfp.json", "")))
+          for key, a in legs:
+              print("args_" + key + "=" + a)
+              print("run_" + key + "=" + ("true" if (s.get("full") or a) else "false"))
+          ') || OUT=''
+            if [ -z "$OUT" ]; then
+              echo "::warning::hil_select output unusable - falling back to the full HIL matrix"
+              SELECT_JSON=''
+            fi
+          fi
+          if [ -z "$OUT" ]; then
+            OUT=$(for k in tinyusb tinyusb_esp hfp; do printf 'args_%s=\nrun_%s=true\n' "$k" "$k"; done)
+          fi
+          echo "$OUT"
+          { echo "select=$SELECT_JSON"; echo "$OUT"; } >> $GITHUB_OUTPUT
 
       - name: Generate matrix json
         id: set-matrix-json
+        env:
+          SELECT: ${{ steps.hil-select.outputs.select }}
         run: |
           # build matrix
-          MATRIX_JSON=$(python .github/workflows/ci_set_matrix.py)
+          MATRIX_JSON=$(python .github/scripts/ci_set_matrix.py)
           echo "matrix=$MATRIX_JSON"
           echo "matrix=$MATRIX_JSON" >> $GITHUB_OUTPUT
 
-          # HIL matrix (merged from tinyusb + hifiphile configs)
-          HIL_MATRIX_JSON=$(python test/hil/hil_ci_set_matrix.py test/hil/tinyusb.json test/hil/hfp.json)
+          # HIL matrix (merged from tinyusb + hifiphile configs), scoped on PRs.
+          # Scoping is best-effort too: fall back to the unscoped (full) matrix.
+          HIL_MATRIX_JSON=''
+          if [ -n "$SELECT" ]; then
+            HIL_MATRIX_JSON=$(python .github/scripts/hil_ci_set_matrix.py --select "$SELECT" test/hil/tinyusb.json test/hil/hfp.json) || HIL_MATRIX_JSON=''
+            if [ -z "$HIL_MATRIX_JSON" ]; then
+              echo "::warning::scoped HIL matrix failed - falling back to the full HIL matrix"
+            fi
+          fi
+          if [ -z "$HIL_MATRIX_JSON" ]; then
+            HIL_MATRIX_JSON=$(python .github/scripts/hil_ci_set_matrix.py test/hil/tinyusb.json test/hil/hfp.json)
+          fi
           echo "hil_matrix=$HIL_MATRIX_JSON"
           echo "hil_matrix=$HIL_MATRIX_JSON" >> $GITHUB_OUTPUT
 
@@ -271,23 +344,55 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
+        # These names are the bucket keys of .github/scripts/hil_ci_set_matrix.py: every
+        # non-esptool roster board must land in one of them (esptool boards go to
+        # 'esp-idf', built by hil-build-esp below). hil_ci_set_matrix.py rejects a
+        # board whose "toolchain" is not a bucket, so a new bucket must be added in
+        # both places.
+        #
+        # INVARIANT the PR-scoped skip cascade rests on: hil_run_tinyusb / hil_run_hfp
+        # true => hil-build has at least one non-empty leg. It holds because those
+        # flags count only non-esptool boards and every such board builds here. It
+        # would break if an esptool board were added to hfp.json, because
+        # hil_args_hfp is NOT flasher-split: the hfp leg of hil-tinyusb would want to
+        # run while hil-build (and therefore that leg) skipped.
         toolchain:
           - 'arm-gcc'
           - 'riscv-gcc'
-          - 'esp-idf'
     with:
       build-system: 'cmake'
       toolchain: ${{ matrix.toolchain }}
       build-args: ${{ toJSON(fromJSON(needs.set-matrix.outputs.hil_json)[matrix.toolchain]) }}
       upload-artifacts: true
 
+  # esp-idf builds are by far the slowest; keep them out of hil-build so the main
+  # hil-tinyusb run starts as soon as the fast toolchains finish (esp boards get
+  # their own hil-tinyusb-esp run gated only on this job)
+  hil-build-esp:
+    needs: [ check-paths, set-matrix ]
+    if: needs.check-paths.outputs.code_changed == 'true' && github.repository_owner == 'hathach'
+    uses: ./.github/workflows/build_util.yml
+    with:
+      build-system: 'cmake'
+      toolchain: 'esp-idf'
+      build-args: ${{ toJSON(fromJSON(needs.set-matrix.outputs.hil_json)['esp-idf']) }}
+      upload-artifacts: true
+
   # ---------------------------------------
   # Hardware in the loop (HIL)
   # self-hosted on local VM, for attached hardware checkout HIL_JSON
   # ---------------------------------------
   hil-tinyusb:
-    needs: hil-build
+    needs: [ hil-build, set-matrix ]
     name: hil-tinyusb (${{ matrix.display }})
+    # Above hil_test.py's pool guard (HIL_POOL_TIMEOUT, 60 min) so the guard fires first
+    # and still gets to write its report. The 30 min on top is what the job pays OUTSIDE
+    # the guard clock: workspace cleanup, checkout, the multi-board artifact merge and
+    # the D-state note before it; kill_worker_children, shutdown_pool's 30 s grace, the
+    # report write and the upload after it. On a multi-stray convoy that tail alone is
+    # minutes, and a ceiling below guard+tail cancels the job before hil_report.md exists
+    # -- the inversion this branch removes. Both legs share the script and the guard.
+    timeout-minutes: 90
     strategy:
       fail-fast: false
       matrix:
@@ -295,26 +400,39 @@ jobs:
           - display: tinyusb.json
             runner: [ self-hosted, X64, hathach, hardware-in-the-loop ]
             hil_json: test/hil/tinyusb.json
+            # esptool-flashed (espressif) boards run in hil-tinyusb-esp,
+            # gated on the slow esp-idf build
+            test_args: '--exclude-flasher esptool'
           - display: hfp.json
             runner: [ self-hosted, Linux, X64, hifiphile ]
             hil_json: test/hil/hfp.json
+            test_args: ''
     runs-on: ${{ matrix.runner }}
     env:
+      # HIL_POOL_TIMEOUT deliberately unset: hil_test.py's 60 min default is below every
+      # ceiling here, so ceiling > guard holds by construction. Pin it to SHORTEN a run
+      # only -- pinning it above a ceiling re-inverts the two.
       HIL_JSON: ${{ matrix.hil_json }}
     steps:
-      - name: Set HIL report dir (sibling of workspace; persists across run attempts)
-        run: echo "HIL_REPORT_DIR=$(dirname "$GITHUB_WORKSPACE")/hil-report" >> "$GITHUB_ENV"
+      - name: Set HIL report dir (per run+job; persists across run attempts)
+        run: |
+          # one report dir per (run id, job): re-run attempts find their own report/spec,
+          # and interleaved runs of other PRs/jobs on the same runner cannot clobber them
+          BASE="$(dirname "$GITHUB_WORKSPACE")/hil-report"
+          # prune per-run dirs older than 2 weeks
+          find "$BASE" -mindepth 1 -maxdepth 1 -type d -mtime +14 -exec rm -rf {} + 2>/dev/null || true
+          echo "HIL_REPORT_DIR=$BASE/${GITHUB_RUN_ID}-$(basename "${{ matrix.display }}" .json)" >> "$GITHUB_ENV"
 
-      - name: Get Skip Boards from previous run
+      - name: Get re-run spec from previous attempt
         if: github.run_attempt != '1'
         run: |
-          if [ -f "${{ env.HIL_JSON }}.skip" ]; then
-            SKIP_BOARDS=$(cat "${{ env.HIL_JSON }}.skip")
-          else
-            SKIP_BOARDS=""
-          fi
-          echo "SKIP_BOARDS=$SKIP_BOARDS"
-          echo "SKIP_BOARDS=$SKIP_BOARDS" >> $GITHUB_ENV
+          # the report dir is keyed by run id, so a spec here can only have been
+          # written by an earlier attempt of THIS run
+          SPEC="$HIL_REPORT_DIR/$(basename "${{ env.HIL_JSON }}").failed"
+          RERUN_ARGS=""
+          [ -f "$SPEC" ] && RERUN_ARGS=$(cat "$SPEC")
+          echo "RERUN_ARGS=$RERUN_ARGS"
+          echo "RERUN_ARGS=$RERUN_ARGS" >> $GITHUB_ENV
 
       - name: Clean workspace
         run: |
@@ -333,15 +451,33 @@ jobs:
           merge-multiple: true
 
       - name: Test on actual hardware
+        # Single attempt per test (--retry 1), no in-run second pass: a broken fixture
+        # fails fast instead of holding the runner (and other PRs' HIL jobs) for hours.
+        env:
+          # tinyusb.json minus the esptool boards (they run in hil-tinyusb-esp): each
+          # job gates on its own flasher subset, never on a rig-wide flag
+          SEL_ARGS_TINYUSB: ${{ needs.set-matrix.outputs.hil_args_tinyusb }}
+          SEL_RUN_TINYUSB: ${{ needs.set-matrix.outputs.hil_run_tinyusb }}
+          SEL_ARGS_HFP: ${{ needs.set-matrix.outputs.hil_args_hfp }}
+          SEL_RUN_HFP: ${{ needs.set-matrix.outputs.hil_run_hfp }}
         run: |
-          python3 test/hil/hil_test.py ${{ env.HIL_JSON }} $SKIP_BOARDS || \
-          (if [ -f "${{ env.HIL_JSON }}.skip" ]; then
-            SKIP_BOARDS=$(cat "${{ env.HIL_JSON }}.skip")
-            echo "Re-running with SKIP_BOARDS=$SKIP_BOARDS"
-            python3 test/hil/hil_test.py ${{ env.HIL_JSON }} $SKIP_BOARDS
-          else
-            exit 1
-          fi)
+          case "$HIL_JSON" in
+            *tinyusb.json) SEL_ARGS="$SEL_ARGS_TINYUSB"; SEL_RUN="$SEL_RUN_TINYUSB" ;;
+            *hfp.json)     SEL_ARGS="$SEL_ARGS_HFP";     SEL_RUN="$SEL_RUN_HFP" ;;
+          esac
+          if [ "$SEL_RUN" = "false" ]; then
+            echo "HIL skipped by PR selection (no affected boards on this rig)"
+            # leave a marker so the combined PR comment says so instead of dropping the
+            # section (and leaving a stale table from an earlier push in its place)
+            mkdir -p "$HIL_REPORT_DIR"
+            echo "_Skipped by PR selection: no affected boards on this rig._" > "$HIL_REPORT_DIR/hil_report.md"
+            exit 0
+          fi
+          # a re-run spec is already a subset of the selection (only the boards/tests
+          # that failed); -b/-bt accumulate, so keeping SEL_ARGS here would re-run the
+          # entire original selection instead of just what failed
+          if [ -n "$RERUN_ARGS" ]; then SEL_ARGS=''; fi
+          python3 test/hil/hil_test.py --retry 1 ${{ matrix.test_args }} $SEL_ARGS ${{ env.HIL_JSON }} $RERUN_ARGS
 
       - name: Upload HIL report
         if: always() && github.event_name == 'pull_request'
@@ -353,6 +489,92 @@ jobs:
           overwrite: true
 
   # ---------------------------------------
+  # Hardware in the loop (HIL) - espressif boards only
+  # Same rig as hil-tinyusb (tinyusb.json) but gated only on the slow esp-idf build,
+  # so the main run does not wait for it. Per-board flocks arbitrate the shared rig;
+  # the runner has a single job slot, so the two HIL jobs never overlap - adding a
+  # second slot would double the per-controller flash/usbtest budgets.
+  # ---------------------------------------
+  hil-tinyusb-esp:
+    needs: [ hil-build-esp, set-matrix ]
+    name: hil-tinyusb (tinyusb-esp.json)
+    runs-on: [ self-hosted, X64, hathach, hardware-in-the-loop ]
+    # above hil_test.py's pool guard (60 min) with room for the pre-pool checkout
+    # and the post-guard sweep + report upload, so its own guard still writes a report;
+    # only a job wedged past that (unkillable D-state worker) hits this ceiling, which
+    # must exist because the runner has one job slot and holds every queued job hostage
+    timeout-minutes: 90
+    env:
+      HIL_JSON: test/hil/tinyusb.json
+      TEST_ARGS: '--flasher esptool'
+    steps:
+      - name: Set HIL report dir (per run+job; persists across run attempts)
+        run: |
+          # one report dir per (run id, job): re-run attempts find their own report/spec,
+          # and interleaved runs of other PRs/jobs on the same runner cannot clobber them
+          BASE="$(dirname "$GITHUB_WORKSPACE")/hil-report"
+          # prune per-run dirs older than 2 weeks
+          find "$BASE" -mindepth 1 -maxdepth 1 -type d -mtime +14 -exec rm -rf {} + 2>/dev/null || true
+          echo "HIL_REPORT_DIR=$BASE/${GITHUB_RUN_ID}-tinyusb-esp" >> "$GITHUB_ENV"
+
+      - name: Get re-run spec from previous attempt
+        if: github.run_attempt != '1'
+        run: |
+          # the report dir is keyed by run id, so a spec here can only have been
+          # written by an earlier attempt of THIS run
+          SPEC="$HIL_REPORT_DIR/$(basename "${{ env.HIL_JSON }}").failed"
+          RERUN_ARGS=""
+          [ -f "$SPEC" ] && RERUN_ARGS=$(cat "$SPEC")
+          echo "RERUN_ARGS=$RERUN_ARGS"
+          echo "RERUN_ARGS=$RERUN_ARGS" >> $GITHUB_ENV
+
+      - name: Clean workspace
+        run: |
+          echo "Cleaning up for the first run"
+          rm -rf "${{ github.workspace }}"
+          mkdir -p "${{ github.workspace }}"
+
+      - name: Checkout TinyUSB
+        uses: actions/checkout@v6
+
+      - name: Download Artifacts
+        uses: actions/download-artifact@v5
+        with:
+          pattern: binaries-esp-idf-*
+          path: cmake-build
+          merge-multiple: true
+
+      - name: Test on actual hardware
+        env:
+          # esptool subset of tinyusb.json: this job must gate on its own boards, not
+          # on the rig-wide flag (which would run a filter matching zero boards)
+          SEL_ARGS: ${{ needs.set-matrix.outputs.hil_args_tinyusb_esp }}
+          SEL_RUN: ${{ needs.set-matrix.outputs.hil_run_tinyusb_esp }}
+        run: |
+          if [ "$SEL_RUN" = "false" ]; then
+            echo "HIL skipped by PR selection (no affected esptool boards)"
+            # leave a marker so the combined PR comment says so instead of dropping the
+            # section (and leaving a stale table from an earlier push in its place)
+            mkdir -p "$HIL_REPORT_DIR"
+            echo "_Skipped by PR selection: no affected esptool boards._" > "$HIL_REPORT_DIR/hil_report.md"
+            exit 0
+          fi
+          # a re-run spec is already a subset of the selection (only the boards/tests
+          # that failed); -b/-bt accumulate, so keeping SEL_ARGS here would re-run the
+          # entire original selection instead of just what failed
+          if [ -n "$RERUN_ARGS" ]; then SEL_ARGS=''; fi
+          python3 test/hil/hil_test.py --retry 1 $TEST_ARGS $SEL_ARGS ${{ env.HIL_JSON }} $RERUN_ARGS
+
+      - name: Upload HIL report
+        if: always() && github.event_name == 'pull_request'
+        uses: actions/upload-artifact@v7
+        with:
+          name: hil-report-tinyusb-esp.json
+          path: ${{ env.HIL_REPORT_DIR }}/hil_report.md
+          if-no-files-found: ignore
+          overwrite: true
+
+  # ---------------------------------------
   # Hardware in the loop (HIL)
   # self-hosted by HFP, build with IAR toolchain, for attached hardware checkout test/hil/hfp.json
   # Since IAR Token secret is not passed to forked PR, only build non-forked PR
@@ -364,7 +586,13 @@ jobs:
       github.repository_owner == 'hathach' &&
       !(github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true)
     runs-on: [ self-hosted, Linux, X64, hifiphile ]
-    timeout-minutes: 30
+    # Unlike the hil-tinyusb jobs, this one BUILDS with IAR in the same job before running
+    # hil_test.py -- hfp.json's 3 boards, 4 variant entries, "up to 30 minutes" (see the
+    # comment above the selection step). The ceiling has to cover build + the 60 min pool
+    # guard + overhead, or GitHub cancels before the guard can write its report -- the
+    # inversion this branch removes. 30 + 60 = 90; the remaining 30 is the full-history
+    # checkout, get_deps, the post-guard sweep and the report upload.
+    timeout-minutes: 120
     env:
       IAR_LMS_BEARER_TOKEN: ${{ secrets.IAR_LMS_BEARER_TOKEN }}
       PYTHONUNBUFFERED: '1'
@@ -381,23 +609,87 @@ jobs:
 
       - name: Checkout TinyUSB
         uses: actions/checkout@v6
+        with:
+          # full history: the "HIL selection" step below needs
+          # merge-base(HEAD, origin/<base_ref>) for PR-scoped selection
+          fetch-depth: 0
+
+      # Computed BEFORE the build: the IAR build is four boards and up to 30 minutes on
+      # a runner that hil-tinyusb (hfp.json) also needs, so an unaffected PR must release
+      # it immediately instead of building everything and then skipping. The selection
+      # also narrows what gets built.
+      # This job has no needs: on set-matrix (it must run even if that unrelated job
+      # fails), so it computes its own selection instead of reading set-matrix's outputs.
+      - name: HIL selection (PR only)
+        if: github.event_name == 'pull_request'
+        env:
+          BASE_REF: ${{ github.base_ref }}
+        run: |
+          # Best-effort: this job is deliberately decoupled from set-matrix so unrelated
+          # failures cannot kill hfp coverage - a selector failure here must likewise
+          # fall back to the full hfp matrix (no hil_select.json, no SEL_* vars), never
+          # fail the job.
+          if ! python3 test/hil/test/test_hil_select.py; then
+            echo "::warning::hil_select unit suite failed - running the full hfp matrix"
+            rm -f hil_select.json
+            exit 0
+          fi
+          if ! python3 test/hil/helper/hil_select.py --base "origin/$BASE_REF" test/hil/hfp.json > hil_select.json; then
+            echo "::warning::hil_select failed - running the full hfp matrix"
+            rm -f hil_select.json
+            exit 0
+          fi
+          # hil_select.json is passed to hil_ci_set_matrix.py --select below to scope the
+          # build; it already honours full=true by ignoring the board list.
+          # The hil_test.py args go to a file, never to $GITHUB_ENV: they are derived
+          # from roster board names, which a PR can edit. Only SEL_RUN (a literal
+          # true/false computed here, needed by the step-level `if:`) goes to the env.
+          if ! SEL_RUN=$(python3 -c '
+          import json
+          s = json.load(open("hil_select.json"))
+          a = s["args"]["hfp.json"]
+          open("hil_sel_args.txt", "w").write(a)
+          print("true" if (s["full"] or a) else "false")
+          '); then
+            echo "::warning::hil_select output unusable - running the full hfp matrix"
+            rm -f hil_select.json hil_sel_args.txt
+            exit 0
+          fi
+          echo "SEL_RUN=$SEL_RUN"
+          echo "SEL_RUN=$SEL_RUN" >> $GITHUB_ENV
 
       - name: Get build boards
+        if: env.SEL_RUN != 'false'
         run: |
-          MATRIX_JSON=$(python test/hil/hil_ci_set_matrix.py test/hil/hfp.json)
-          BUILD_ARGS=$(echo $MATRIX_JSON | jq -r '.["arm-gcc"] | join(" ")')
+          if [ -f hil_select.json ]; then
+            MATRIX_JSON=$(python .github/scripts/hil_ci_set_matrix.py --select "$(cat hil_select.json)" test/hil/hfp.json)
+          else
+            MATRIX_JSON=$(python .github/scripts/hil_ci_set_matrix.py test/hil/hfp.json)
+          fi
+          # Each variant carries its own --build-name/--cflag, which are global to a
+          # single build.py invocation — so keep one matrix entry per line and build
+          # them one at a time (joining would leak a variant's flags onto every board).
+          echo "$MATRIX_JSON" | jq -r '.["arm-gcc"][]' > hil_build_entries.txt
+          cat hil_build_entries.txt
+          BUILD_ARGS=$(echo "$MATRIX_JSON" | jq -r '.["arm-gcc"] | join(" ")')
           echo "BUILD_ARGS=$BUILD_ARGS"
           echo "BUILD_ARGS=$BUILD_ARGS" >> $GITHUB_ENV
 
       - name: Get Dependencies
+        if: env.SEL_RUN != 'false'
         run: python3 tools/get_deps.py $BUILD_ARGS
 
       - name: Build
+        if: env.SEL_RUN != 'false'
+        # Bounded SEPARATELY from the job. This is the only HIL job that builds inline
+        # (hil-tinyusb downloads artifacts), and the job ceiling went 30 -> 120 to give the
+        # HIL step room -- which would hand a stalled IAR build the whole two hours on the
+        # shared self-hosted runner, never reaching hil_test.py or the report upload. That
+        # is the stranded-runner-with-no-report failure this branch exists to prevent.
+        # Typical full build here is a few minutes; 30 leaves generous headroom.
+        timeout-minutes: 30
         run: |
-          # Each variant carries its own --build-name/--cflag, which are global to a
-          # single build.py invocation — so build one matrix entry at a time rather
-          # than joining them (joining would leak a variant's flags onto every board).
-          readarray -t ENTRIES < <(python test/hil/hil_ci_set_matrix.py test/hil/hfp.json | jq -r '.["arm-gcc"][]')
+          readarray -t ENTRIES < hil_build_entries.txt
           for entry in "${ENTRIES[@]}"; do
             echo "+ tools/build.py --toolchain iar $entry"
             python3 tools/build.py --toolchain iar $entry
@@ -405,7 +697,21 @@ jobs:
 
       - name: Test on actual hardware (hardware in the loop)
         run: |
-          python3 test/hil/hil_test.py hfp.json
+          if [ "$SEL_RUN" = "false" ]; then
+            echo "HIL skipped by PR selection (no affected boards on this rig)"
+            # leave a marker so the combined PR comment says so instead of dropping
+            # the section (and leaving a stale table from an earlier push)
+            echo "_Skipped by PR selection: no affected boards on this rig._" > hil_report.md
+            exit 0
+          fi
+          # empty/absent on a non-PR event or a selector fallback -> full hfp matrix
+          SEL_ARGS=$(cat hil_sel_args.txt 2>/dev/null || true)
+          # --retry 1, like the other two HIL legs. The pool guard is a FLAT 3600s and
+          # does NOT scale with max_retry, so argparse's default of 3 would multiply the
+          # serialized usbtest tail (hfp.json runs four batteries) by three against an
+          # unchanged guard -- on a runner with a single job slot that queues every other
+          # job behind it.
+          python3 test/hil/hil_test.py --retry 1 $SEL_ARGS hfp.json
 
       - name: Upload HIL report
         if: always() && github.event_name == 'pull_request'