ci: add the delta-gate workflow for the capped functional lane

workflow_dispatch, runs-on gate-functional — a host-mode, Bun-only lane
with no Node.js runtime, so every step is plain git + bun in shell
rather than a JS-based action. Clones candidate and control, runs the
full vitest suite on each, enforces a >=3,000-collected guard per side,
and diffs the two fail lists for genuinely new reds. The lane's own
tripwire marker (host pressure — never our own red or green) is checked
before the verdict is printed, and the job cleans up its own checkouts
so repeat runs don't feed the lane's disk-budget trip.
This commit is contained in:
David Snelling 2026-09-02 09:09:33 -07:00
parent 2633e8d5e1
commit 9922631d1f

View file

@ -0,0 +1,127 @@
name: Delta Gate
# On-demand candidate-vs-control gate on the capped functional CI lane
# (label: gate-functional). That lane is Bun-only host-mode — there is no
# Node.js runtime available to it, so this workflow deliberately avoids every
# JS-based action (checkout/setup-node/setup-bun/upload-artifact all require
# one) and does everything with plain git + bun in shell steps instead.
#
# Verdict lines a caller should grep for in the run log:
# COLLECTED patch=<n> control=<n> — collection-truncation guard inputs
# NEW-RED-COUNT:<n> — failures on candidate absent from control
# DELTA-GATE: CLEAN | NEW REDS | INVALID | STOPPED-BY-REGISTRY-TRIPWIRE
#
# The lane's own housekeeping stops the runner and drops a marker file when
# host pressure (I/O, registry latency, disk budget) trips — never ours to
# interpret as a red or a green. The final step checks for that marker before
# it says anything about pass/fail.
on:
workflow_dispatch:
inputs:
candidate:
description: 'Candidate ref (branch or sha) to gate'
required: true
type: string
control:
description: 'Control sha to diff against'
required: true
type: string
concurrency:
group: delta-gate
cancel-in-progress: false
jobs:
delta-gate:
name: Delta gate — candidate vs control
runs-on: gate-functional
timeout-minutes: 120
steps:
- name: Clean any residue from a prior run
run: rm -rf "ob-cand-${{ github.run_id }}" "ob-ctrl-${{ github.run_id }}" "/tmp/ob-${{ github.run_id }}-"*
- name: Clone + test — candidate
id: patch
run: |
set -o pipefail
git clone --quiet "https://source.soulcraft.com/soulcraftlabs/open-brainy.git" "ob-cand-${{ github.run_id }}"
cd "ob-cand-${{ github.run_id }}"
git checkout --quiet "${{ github.event.inputs.candidate }}"
git log --oneline -1
bun install
rc=0
bun x vitest run > "/tmp/ob-${{ github.run_id }}-patch.log" 2>&1 || rc=$?
echo "PATCH-RC:$rc"
grep -aE "Tests .*(passed|failed)" "/tmp/ob-${{ github.run_id }}-patch.log" | tail -1
grep -aE "^ FAIL |^\s+×" "/tmp/ob-${{ github.run_id }}-patch.log" | sed -E "s/ [0-9]+ms$//" | sed -E "s/^\s+//" | sort -u > "/tmp/ob-${{ github.run_id }}-patch.fail"
echo "PATCH-FAILING:$(wc -l < "/tmp/ob-${{ github.run_id }}-patch.fail")"
- name: Clone + test — control
id: control
run: |
set -o pipefail
git clone --quiet "https://source.soulcraft.com/soulcraftlabs/open-brainy.git" "ob-ctrl-${{ github.run_id }}"
cd "ob-ctrl-${{ github.run_id }}"
git checkout --quiet "${{ github.event.inputs.control }}"
git log --oneline -1
bun install
rc=0
bun x vitest run > "/tmp/ob-${{ github.run_id }}-control.log" 2>&1 || rc=$?
echo "CONTROL-RC:$rc"
grep -aE "Tests .*(passed|failed)" "/tmp/ob-${{ github.run_id }}-control.log" | tail -1
grep -aE "^ FAIL |^\s+×" "/tmp/ob-${{ github.run_id }}-control.log" | sed -E "s/ [0-9]+ms$//" | sed -E "s/^\s+//" | sort -u > "/tmp/ob-${{ github.run_id }}-control.fail"
echo "CONTROL-FAILING:$(wc -l < "/tmp/ob-${{ github.run_id }}-control.fail")"
- name: Delta gate verdict
if: always()
run: |
set -o pipefail
# The lane's own tripwire wins over anything we would otherwise say:
# a bare failure/timeout above with this marker present is host
# pressure, never a real red and never a real green.
if [ -f /srv/gate-lane/TRIPWIRE-STOPPED ]; then
echo "DELTA-GATE: STOPPED-BY-REGISTRY-TRIPWIRE"
head -1 /srv/gate-lane/TRIPWIRE-STOPPED
exit 3
fi
patch_log="/tmp/ob-${{ github.run_id }}-patch.log"
control_log="/tmp/ob-${{ github.run_id }}-control.log"
patch_fail="/tmp/ob-${{ github.run_id }}-patch.fail"
control_fail="/tmp/ob-${{ github.run_id }}-control.fail"
if [ ! -s "$patch_log" ] || [ ! -s "$control_log" ]; then
echo "DELTA-GATE: INVALID — a leg produced no log (see the two steps above for the real cause)"
exit 2
fi
pt=$(grep -aoE "\(([0-9]+)\)$" "$patch_log" | tail -1 | tr -d "()")
ct=$(grep -aoE "\(([0-9]+)\)$" "$control_log" | tail -1 | tr -d "()")
echo "COLLECTED patch=${pt:-0} control=${ct:-0}"
if [ "${pt:-0}" -lt 3000 ] || [ "${ct:-0}" -lt 3000 ]; then
echo "DELTA-GATE: INVALID — truncated collection"
exit 2
fi
echo "=== NEW REDS ==="
comm -23 "$patch_fail" "$control_fail"
new=$(comm -23 "$patch_fail" "$control_fail" | wc -l)
echo "NEW-RED-COUNT:$new"
echo "=== full candidate fail list ==="
cat "$patch_fail"
echo "=== full control fail list ==="
cat "$control_fail"
if [ "$new" -eq 0 ]; then
echo "DELTA-GATE: CLEAN"
else
echo "DELTA-GATE: NEW REDS"
exit 1
fi
- name: Clean up (mind the lane's disk budget)
if: always()
run: rm -rf "ob-cand-${{ github.run_id }}" "ob-ctrl-${{ github.run_id }}" "/tmp/ob-${{ github.run_id }}-"*