mirror of
https://github.com/stablyai/orca.git
synced 2026-10-02 08:02:02 +00:00
Free PR CI capacity by avoiding repeated setup and real-time test waits (#24355)
* Reduce repeated PR setup and transcript timing waits; add hosted comparisons * Align parallelism contract with Node-only external rebuild toolchain * Record hosted coverage and launch package, store, and cancellation comparisons * Apply hosted Windows setup savings and remove measured test waits * Keep measured PR package gains and remove completed comparison jobs * Report measured test counts with precise units
This commit is contained in:
Neil
@@ -80,7 +80,9 @@ runs:
|
||||
# PR-local stores compete with reusable build caches for the repository quota.
|
||||
- name: Resolve pnpm download store
|
||||
id: pnpm-store
|
||||
if: github.event_name == 'pull_request'
|
||||
if: >-
|
||||
github.event_name == 'pull_request' &&
|
||||
(runner.os != 'Windows' || runner.arch != 'X64' || !contains(inputs.cache-dependency-path, 'mobile/pnpm-lock.yaml'))
|
||||
shell: bash
|
||||
env:
|
||||
LOCKFILE_HASH: ${{ hashFiles(inputs.cache-dependency-path) }}
|
||||
@@ -92,8 +94,11 @@ runs:
|
||||
printf 'arch=%s\n' "$(node -p 'require("node:os").arch()')" >> "$GITHUB_OUTPUT"
|
||||
|
||||
# Match setup-node's key and path so existing default-branch stores remain reusable.
|
||||
# Hosted Windows x64 mixed installs cost less than restoring their root/mobile store.
|
||||
- name: Restore pnpm download store without saving
|
||||
if: github.event_name == 'pull_request'
|
||||
if: >-
|
||||
github.event_name == 'pull_request' &&
|
||||
(runner.os != 'Windows' || runner.arch != 'X64' || !contains(inputs.cache-dependency-path, 'mobile/pnpm-lock.yaml'))
|
||||
uses: actions/cache/restore@v5
|
||||
with:
|
||||
path: ${{ steps.pnpm-store.outputs.path }}
|
||||
@@ -237,9 +242,9 @@ runs:
|
||||
node_modules/.pnpm/@vscode+windows-process-tre*/node_modules/@vscode/windows-process-tree/build
|
||||
key: native-modules-${{ runner.os }}-${{ steps.native-cache-scope.outputs.scope }}-${{ runner.arch }}-${{ inputs.native-runtime }}-node${{ steps.requested-node.outputs.node-version || steps.default-node.outputs.node-version }}-${{ hashFiles('pnpm-lock.yaml', '.github/actions/install-node-dependencies/action.yml', 'config/scripts/ensure-native-runtime.mjs', 'config/scripts/rebuild-native-deps.mjs', 'config/patches/node-pty@1.1.0.patch', 'config/patches/@vscode__windows-process-tree@0.8.0.patch', 'native/windows-registry/src/addon.cc', 'native/windows-registry/binding.gyp', 'native/windows-registry/package.json') }}
|
||||
|
||||
# pnpm's bundled gyp_main.py is not executable on fresh Linux runners.
|
||||
# pnpm's bundled gyp_main.py is not executable; Electron rebuild uses its own node-gyp API.
|
||||
- name: Use external node-gyp
|
||||
if: runner.os == 'Linux' && inputs.native-runtime != 'none'
|
||||
if: runner.os == 'Linux' && inputs.native-runtime == 'node'
|
||||
shell: bash
|
||||
env:
|
||||
NATIVE_RUNTIME: ${{ inputs.native-runtime }}
|
||||
|
||||
@@ -32,7 +32,7 @@ runs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
case "$FIXTURE" in
|
||||
headless-serve-shutdown|cli-launch-contract) ;;
|
||||
headless-serve-shutdown|cli-launch-contract|daemon-shutdown-descendants) ;;
|
||||
*) echo "Unsupported package fixture: $FIXTURE" >&2; exit 1 ;;
|
||||
esac
|
||||
archive="$RUNNER_TEMP/orca-package-fixtures/$FIXTURE.tar"
|
||||
|
||||
@@ -13,6 +13,7 @@ on:
|
||||
- '.github/actions/prepare-linux-package-fixture/**'
|
||||
- 'config/docker/headless-serve-shutdown/**'
|
||||
- 'config/docker/cli-launch-contract/**'
|
||||
- 'config/docker/daemon-shutdown-descendants/**'
|
||||
- 'package.json'
|
||||
- 'pnpm-lock.yaml'
|
||||
- 'pnpm-workspace.yaml'
|
||||
@@ -29,6 +30,7 @@ on:
|
||||
- '.github/actions/prepare-linux-package-fixture/**'
|
||||
- 'config/docker/headless-serve-shutdown/**'
|
||||
- 'config/docker/cli-launch-contract/**'
|
||||
- 'config/docker/daemon-shutdown-descendants/**'
|
||||
- 'config/scripts/ci-cache-warmup-workflow.test.mjs'
|
||||
|
||||
permissions:
|
||||
@@ -121,6 +123,10 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
persist-credentials: false
|
||||
- uses: ./.github/actions/prepare-linux-package-fixture
|
||||
with:
|
||||
fixture: daemon-shutdown-descendants
|
||||
save-cache: ${{ github.event_name != 'pull_request' }}
|
||||
- uses: ./.github/actions/prepare-linux-package-fixture
|
||||
with:
|
||||
fixture: headless-serve-shutdown
|
||||
|
||||
+57
-43
@@ -17,6 +17,16 @@ on:
|
||||
description: JSON array of changed specs; empty runs the full suite
|
||||
required: false
|
||||
type: string
|
||||
run_changed_e2e:
|
||||
description: PR detector found specs requiring the general changed-spec lane.
|
||||
required: false
|
||||
type: boolean
|
||||
default: true
|
||||
needs_build:
|
||||
description: PR detector found an Electron consumer requiring build and native cache.
|
||||
required: false
|
||||
type: boolean
|
||||
default: true
|
||||
ssh_source_changed:
|
||||
description: '"true" when the PR touches SSH execution source; gates the Docker-SSH lane'
|
||||
required: false
|
||||
@@ -38,6 +48,7 @@ on:
|
||||
jobs:
|
||||
build:
|
||||
name: build e2e app
|
||||
if: inputs.test_files == '' || github.event_name != 'pull_request' || inputs.needs_build
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 10
|
||||
|
||||
@@ -97,6 +108,7 @@ jobs:
|
||||
# this immutable cache instead of compiling the same ABI concurrently.
|
||||
prepare-native-cache:
|
||||
name: prepare Electron native cache
|
||||
if: inputs.test_files == '' || github.event_name != 'pull_request' || inputs.needs_build
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
|
||||
@@ -240,7 +252,7 @@ jobs:
|
||||
changed-e2e:
|
||||
name: changed e2e specs
|
||||
needs: [build, prepare-native-cache]
|
||||
if: inputs.test_files != ''
|
||||
if: inputs.test_files != '' && (github.event_name != 'pull_request' || inputs.run_changed_e2e)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 45
|
||||
|
||||
@@ -271,44 +283,47 @@ jobs:
|
||||
env:
|
||||
TEST_FILES_JSON: ${{ inputs.test_files }}
|
||||
run: |
|
||||
# Why the native IME spec is dropped: it test.skip()s itself without
|
||||
# ORCA_E2E_NATIVE_IBUS_HANGUL, which this lane cannot set because it has no ibus
|
||||
# session. Running it here reported a green skip as coverage.
|
||||
mapfile -t TEST_FILES < <(jq -r '.[] | select(
|
||||
. != "tests/e2e/local-ssh-browser-routing.spec.ts" and
|
||||
. != "tests/e2e/ssh-client-hosted-browser-drop-reconnect.spec.ts" and
|
||||
. != "tests/e2e/pty-input-write-queue-ssh.spec.ts" and
|
||||
. != "tests/e2e/ssh-ai-vault-session-history.spec.ts" and
|
||||
. != "tests/e2e/ssh-codex-display-artifacts-repro.spec.ts" and
|
||||
. != "tests/e2e/ssh-cold-activation-restore.spec.ts" and
|
||||
. != "tests/e2e/ssh-cold-hydration-gap-tab-seeding.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-half-open-link.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-quick-open-large-listing.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-reconnect-pane-restore.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-relay-stall-credential.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-resource-accumulation.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-transport-drop-recovery.spec.ts" and
|
||||
. != "tests/e2e/ssh-external-image-preview.spec.ts" and
|
||||
. != "tests/e2e/ssh-lost-kill-tab-resurrection.spec.ts" and
|
||||
. != "tests/e2e/ssh-pi-compatible-agent-title.spec.ts" and
|
||||
. != "tests/e2e/ssh-port-forward-lifecycle.spec.ts" and
|
||||
. != "tests/e2e/ssh-reconnect-tab-destruction.spec.ts" and
|
||||
. != "tests/e2e/ssh-restart-tab-accumulation.spec.ts" and
|
||||
. != "tests/e2e/ssh-skill-installation.spec.ts" and
|
||||
. != "tests/e2e/ssh-stale-resume-execution-host-scope.spec.ts" and
|
||||
. != "tests/e2e/ssh-terminal-window-wake-stale-grid-repro.spec.ts" and
|
||||
. != "tests/e2e/terminal-inline-images-ssh.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-watcher-isolation.spec.ts" and
|
||||
. != "tests/e2e/ssh-terminal-parking.spec.ts" and
|
||||
. != "tests/e2e/terminal-retention-budget.spec.ts" and
|
||||
. != "tests/e2e/ssh-startup-exec-readiness.spec.ts" and
|
||||
. != "tests/e2e/paired-startup-exec-readiness.spec.ts" and
|
||||
. != "tests/e2e/ssh-browser-network-execution-route.docker.unit.test.ts" and
|
||||
. != "tests/e2e/ssh-localhost.spec.ts" and
|
||||
. != "tests/e2e/terminal-ibus-hangul-native.spec.ts"
|
||||
)' <<<"$TEST_FILES_JSON")
|
||||
if [ -f config/scripts/ci-e2e-job-selection.mjs ]; then
|
||||
printf '%s\n' "$TEST_FILES_JSON" | node config/scripts/ci-e2e-job-selection.mjs > "$RUNNER_TEMP/general-e2e-specs"
|
||||
else
|
||||
# Dispatching an older ref retains its existing dedicated-owner exclusions.
|
||||
jq -r '.[] | select(
|
||||
. != "tests/e2e/local-ssh-browser-routing.spec.ts" and
|
||||
. != "tests/e2e/ssh-client-hosted-browser-drop-reconnect.spec.ts" and
|
||||
. != "tests/e2e/pty-input-write-queue-ssh.spec.ts" and
|
||||
. != "tests/e2e/ssh-ai-vault-session-history.spec.ts" and
|
||||
. != "tests/e2e/ssh-codex-display-artifacts-repro.spec.ts" and
|
||||
. != "tests/e2e/ssh-cold-activation-restore.spec.ts" and
|
||||
. != "tests/e2e/ssh-cold-hydration-gap-tab-seeding.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-half-open-link.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-quick-open-large-listing.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-reconnect-pane-restore.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-relay-stall-credential.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-resource-accumulation.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-transport-drop-recovery.spec.ts" and
|
||||
. != "tests/e2e/ssh-external-image-preview.spec.ts" and
|
||||
. != "tests/e2e/ssh-lost-kill-tab-resurrection.spec.ts" and
|
||||
. != "tests/e2e/ssh-pi-compatible-agent-title.spec.ts" and
|
||||
. != "tests/e2e/ssh-port-forward-lifecycle.spec.ts" and
|
||||
. != "tests/e2e/ssh-reconnect-tab-destruction.spec.ts" and
|
||||
. != "tests/e2e/ssh-restart-tab-accumulation.spec.ts" and
|
||||
. != "tests/e2e/ssh-skill-installation.spec.ts" and
|
||||
. != "tests/e2e/ssh-stale-resume-execution-host-scope.spec.ts" and
|
||||
. != "tests/e2e/ssh-terminal-window-wake-stale-grid-repro.spec.ts" and
|
||||
. != "tests/e2e/terminal-inline-images-ssh.spec.ts" and
|
||||
. != "tests/e2e/ssh-docker-watcher-isolation.spec.ts" and
|
||||
. != "tests/e2e/ssh-terminal-parking.spec.ts" and
|
||||
. != "tests/e2e/terminal-retention-budget.spec.ts" and
|
||||
. != "tests/e2e/ssh-startup-exec-readiness.spec.ts" and
|
||||
. != "tests/e2e/paired-startup-exec-readiness.spec.ts" and
|
||||
. != "tests/e2e/ssh-browser-network-execution-route.docker.unit.test.ts" and
|
||||
. != "tests/e2e/ssh-localhost.spec.ts" and
|
||||
. != "tests/e2e/terminal-ibus-hangul-native.spec.ts"
|
||||
)' <<<"$TEST_FILES_JSON" > "$RUNNER_TEMP/general-e2e-specs"
|
||||
fi
|
||||
mapfile -t TEST_FILES < "$RUNNER_TEMP/general-e2e-specs"
|
||||
if [ "${#TEST_FILES[@]}" -eq 0 ]; then
|
||||
echo "Changed specs are all owned by dedicated lanes."
|
||||
exit 0
|
||||
@@ -417,10 +432,9 @@ jobs:
|
||||
mv test-results "e2e-traces/watcher-isolation"
|
||||
fi
|
||||
|
||||
# Why always(): this lane gates SSH parking/retention plus startup-exec
|
||||
# readiness across live SSH, headed paired, and headless serve topologies.
|
||||
# Keep every SSH journey after a test failure; stop work on superseded commits.
|
||||
- name: Run Docker SSH terminal parking + startup readiness E2E
|
||||
if: always() && matrix.shard == 1
|
||||
if: '!cancelled() && matrix.shard == 1'
|
||||
run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 pnpm run test:e2e:ssh-docker-terminal-parking
|
||||
|
||||
- name: Keep terminal-parking traces
|
||||
@@ -433,7 +447,7 @@ jobs:
|
||||
|
||||
# Separate VMs isolate destructive SSH fixtures while keeping one worker per shard.
|
||||
- name: Run remaining Docker SSH E2E
|
||||
if: always()
|
||||
if: '!cancelled()'
|
||||
run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 pnpm run test:e2e:ssh-docker --shard=${{ matrix.shard }}/4
|
||||
|
||||
- name: Keep remaining-ssh-docker traces
|
||||
|
||||
@@ -51,6 +51,8 @@ jobs:
|
||||
package_windows: ${{ steps.readiness.outputs.reused != 'true' && steps.filter.outputs.package_windows }}
|
||||
e2e_should_run: ${{ steps.e2e_filter.outputs.should_run }}
|
||||
test_files: ${{ steps.e2e_filter.outputs.test_files }}
|
||||
e2e_run_changed: ${{ steps.e2e_filter.outputs.e2e_run_changed }}
|
||||
e2e_needs_build: ${{ steps.e2e_filter.outputs.e2e_needs_build }}
|
||||
ssh_source_changed: ${{ steps.e2e_filter.outputs.ssh_source_changed }}
|
||||
native_ime_source_changed: ${{ steps.e2e_filter.outputs.native_ime_source_changed }}
|
||||
wsl_source_changed: ${{ steps.e2e_filter.outputs.wsl_source_changed }}
|
||||
@@ -74,6 +76,7 @@ jobs:
|
||||
/config/scripts/check-readme-local-links.mjs
|
||||
/config/scripts/pr-code-change-scope.mjs
|
||||
/config/scripts/pr-e2e-source-routing.mjs
|
||||
/config/scripts/ci-e2e-job-selection.mjs
|
||||
/config/scripts/pr-ready-check-reuse.mjs
|
||||
sparse-checkout-cone-mode: false
|
||||
persist-credentials: false
|
||||
@@ -133,6 +136,7 @@ jobs:
|
||||
SSH_SOURCE_CHANGED="$(printf '%s\n' "$CHANGED" | node config/scripts/pr-e2e-source-routing.mjs --ssh-source)"
|
||||
echo "ssh_source_changed=$SSH_SOURCE_CHANGED" >> "$GITHUB_OUTPUT"
|
||||
echo "SSH source changed: $SSH_SOURCE_CHANGED"
|
||||
printf '%s\n' "$TEST_FILES_JSON" | E2E_SSH_SOURCE_CHANGED="$SSH_SOURCE_CHANGED" node config/scripts/ci-e2e-job-selection.mjs --job-outputs >> "$GITHUB_OUTPUT"
|
||||
# Why its own signal: the real-IME lane is a whole ibus session, not a spec, so it must
|
||||
# trigger on IME source rather than on a spec name in some route's list.
|
||||
NATIVE_IME_SOURCE_CHANGED="$(printf '%s\n' "$CHANGED" | node config/scripts/pr-e2e-source-routing.mjs --native-ime-source)"
|
||||
@@ -918,6 +922,12 @@ jobs:
|
||||
restore-keys: |
|
||||
electron-builder-linux-
|
||||
|
||||
- uses: ./.github/actions/prepare-linux-package-fixture
|
||||
id: daemon-fixture-cache
|
||||
background: true
|
||||
with:
|
||||
fixture: daemon-shutdown-descendants
|
||||
|
||||
- uses: ./.github/actions/install-node-dependencies
|
||||
with:
|
||||
native-runtime: electron
|
||||
@@ -930,9 +940,12 @@ jobs:
|
||||
- uses: ./.github/actions/install-mobile-dependencies
|
||||
|
||||
# The checkout must pass without depending on a historical baseline that leaks.
|
||||
- wait: daemon-fixture-cache
|
||||
|
||||
- name: Verify Linux daemon shutdown descendant cleanup
|
||||
env:
|
||||
ORCA_BACKGROUND_LAUNCH: '1'
|
||||
ORCA_DAEMON_SHUTDOWN_FIXTURE_CACHE_IMAGE: ${{ steps.daemon-fixture-cache.outputs.image }}
|
||||
run: node config/scripts/run-daemon-shutdown-descendants-docker.mjs
|
||||
|
||||
# Why --no-file-parallelism: every file here launches a full Electron stack twice, and each
|
||||
@@ -1228,6 +1241,8 @@ jobs:
|
||||
ref: ${{ github.event.pull_request.head.sha }}
|
||||
test_files: ${{ needs.code_paths.outputs.test_files }}
|
||||
ssh_source_changed: ${{ needs.code_paths.outputs.ssh_source_changed }}
|
||||
run_changed_e2e: ${{ needs.code_paths.outputs.e2e_run_changed != 'false' }}
|
||||
needs_build: ${{ needs.code_paths.outputs.e2e_needs_build != 'false' }}
|
||||
|
||||
# Why this is not in verify's needs: it is the first PR-gate run of a harness whose reliability
|
||||
# is only known from nightly main runs (20/20 green, 2026-08-09..2026-08-29, p50 3m25s). It
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { runInNewContext } from 'node:vm'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { parse } from 'yaml'
|
||||
|
||||
@@ -29,12 +30,14 @@ describe('CI dependency download caches', () => {
|
||||
])
|
||||
})
|
||||
|
||||
it('restores PR stores with setup-node keys without registering a post-job save', () => {
|
||||
it('restores PR stores except measured Windows mixed installs, without a post-job save', () => {
|
||||
const resolve = action.runs.steps.find((step) => step.id === 'pnpm-store')
|
||||
const restore = action.runs.steps.find(
|
||||
(step) => step.name === 'Restore pnpm download store without saving'
|
||||
)
|
||||
expect(resolve.if).toBe("github.event_name == 'pull_request'")
|
||||
expect(resolve.if).toBe(
|
||||
"github.event_name == 'pull_request' && (runner.os != 'Windows' || runner.arch != 'X64' || !contains(inputs.cache-dependency-path, 'mobile/pnpm-lock.yaml'))"
|
||||
)
|
||||
expect(restore.if).toBe(resolve.if)
|
||||
expect(restore.uses).toBe('actions/cache/restore@v5')
|
||||
expect(restore.with.path).toBe('${{ steps.pnpm-store.outputs.path }}')
|
||||
@@ -53,6 +56,49 @@ describe('CI dependency download caches', () => {
|
||||
expect(saves[0].if).toContain("github.ref == 'refs/heads/main'")
|
||||
expect(saves[0].if).toContain("github.event_name != 'pull_request'")
|
||||
expect(saves[0].with.path).toBe('${{ steps.verification-cache.outputs.path }}')
|
||||
const windows = workflow('pr').jobs.package_windows.steps.find((step) =>
|
||||
step.uses?.includes('install-node-dependencies')
|
||||
)
|
||||
expect(windows.with['cache-dependency-path'].trim().split('\n')).toEqual([
|
||||
'pnpm-lock.yaml',
|
||||
'mobile/pnpm-lock.yaml'
|
||||
])
|
||||
})
|
||||
|
||||
it.each([
|
||||
['Windows x64 mixed PR', 'pull_request', 'Windows', 'X64', true, false, ''],
|
||||
['Windows ARM64 mixed PR', 'pull_request', 'Windows', 'ARM64', true, true, ''],
|
||||
['Windows x86 mixed PR', 'pull_request', 'Windows', 'X86', true, true, ''],
|
||||
['Windows x64 root-only PR', 'pull_request', 'Windows', 'X64', false, true, ''],
|
||||
['Linux x64 mixed PR', 'pull_request', 'Linux', 'X64', true, true, ''],
|
||||
['Linux ARM64 mixed PR', 'pull_request', 'Linux', 'ARM64', true, true, ''],
|
||||
['macOS ARM64 mixed PR', 'pull_request', 'macOS', 'ARM64', true, true, ''],
|
||||
['Windows x64 mixed push', 'push', 'Windows', 'X64', true, false, 'pnpm'],
|
||||
['Windows x64 mixed manual run', 'workflow_dispatch', 'Windows', 'X64', true, false, 'pnpm']
|
||||
])('%s keeps its scoped store policy', (_name, event, os, arch, mixed, restore, cache) => {
|
||||
const context = {
|
||||
github: { event_name: event },
|
||||
runner: { os, arch },
|
||||
inputs: {
|
||||
'cache-dependency-path': mixed ? 'pnpm-lock.yaml\nmobile/pnpm-lock.yaml' : 'pnpm-lock.yaml'
|
||||
},
|
||||
contains: (value, search) => value.toLowerCase().includes(search.toLowerCase())
|
||||
}
|
||||
const evaluate = (expression) =>
|
||||
runInNewContext(
|
||||
expression.replaceAll('inputs.cache-dependency-path', 'inputs["cache-dependency-path"]'),
|
||||
context
|
||||
)
|
||||
for (const step of action.runs.steps.filter(
|
||||
(step) =>
|
||||
step.id === 'pnpm-store' || step.name === 'Restore pnpm download store without saving'
|
||||
)) {
|
||||
expect(evaluate(step.if)).toBe(restore)
|
||||
}
|
||||
for (const step of action.runs.steps.filter((step) => step.uses === 'actions/setup-node@v6')) {
|
||||
expect(evaluate(step.with.cache.slice(3, -2))).toBe(cache)
|
||||
expect(step.with['package-manager-cache']).toBe(false)
|
||||
}
|
||||
})
|
||||
|
||||
it('restores Windows packaging downloads from the release cache without a PR upload', () => {
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
import { pathToFileURL } from 'node:url'
|
||||
|
||||
export const DOCKER_SSH_E2E_SPECS = [
|
||||
'tests/e2e/local-ssh-browser-routing.spec.ts',
|
||||
'tests/e2e/ssh-client-hosted-browser-drop-reconnect.spec.ts',
|
||||
'tests/e2e/pty-input-write-queue-ssh.spec.ts',
|
||||
'tests/e2e/ssh-ai-vault-session-history.spec.ts',
|
||||
'tests/e2e/ssh-codex-display-artifacts-repro.spec.ts',
|
||||
'tests/e2e/ssh-cold-activation-restore.spec.ts',
|
||||
'tests/e2e/ssh-cold-hydration-gap-tab-seeding.spec.ts',
|
||||
'tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts',
|
||||
'tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts',
|
||||
'tests/e2e/ssh-docker-half-open-link.spec.ts',
|
||||
'tests/e2e/ssh-docker-quick-open-large-listing.spec.ts',
|
||||
'tests/e2e/ssh-docker-reconnect-pane-restore.spec.ts',
|
||||
'tests/e2e/ssh-docker-relay-stall-credential.spec.ts',
|
||||
'tests/e2e/ssh-docker-resource-accumulation.spec.ts',
|
||||
'tests/e2e/ssh-docker-transport-drop-recovery.spec.ts',
|
||||
'tests/e2e/ssh-external-image-preview.spec.ts',
|
||||
'tests/e2e/ssh-lost-kill-tab-resurrection.spec.ts',
|
||||
'tests/e2e/ssh-pi-compatible-agent-title.spec.ts',
|
||||
'tests/e2e/ssh-port-forward-lifecycle.spec.ts',
|
||||
'tests/e2e/ssh-reconnect-tab-destruction.spec.ts',
|
||||
'tests/e2e/ssh-restart-tab-accumulation.spec.ts',
|
||||
'tests/e2e/ssh-skill-installation.spec.ts',
|
||||
'tests/e2e/ssh-stale-resume-execution-host-scope.spec.ts',
|
||||
'tests/e2e/ssh-terminal-window-wake-stale-grid-repro.spec.ts',
|
||||
'tests/e2e/terminal-inline-images-ssh.spec.ts',
|
||||
'tests/e2e/ssh-docker-watcher-isolation.spec.ts',
|
||||
'tests/e2e/ssh-terminal-parking.spec.ts',
|
||||
'tests/e2e/terminal-retention-budget.spec.ts',
|
||||
'tests/e2e/ssh-startup-exec-readiness.spec.ts',
|
||||
'tests/e2e/paired-startup-exec-readiness.spec.ts'
|
||||
]
|
||||
|
||||
export const NODE_NETWORK_E2E_SPEC =
|
||||
'tests/e2e/ssh-browser-network-execution-route.docker.unit.test.ts'
|
||||
export const LOCALHOST_SSH_E2E_SPEC = 'tests/e2e/ssh-localhost.spec.ts'
|
||||
export const NATIVE_IME_E2E_SPEC = 'tests/e2e/terminal-ibus-hangul-native.spec.ts'
|
||||
export const DEDICATED_E2E_SPECS = [
|
||||
...DOCKER_SSH_E2E_SPECS,
|
||||
NODE_NETWORK_E2E_SPEC,
|
||||
LOCALHOST_SSH_E2E_SPEC,
|
||||
NATIVE_IME_E2E_SPEC
|
||||
]
|
||||
const dedicatedSpecs = new Set(DEDICATED_E2E_SPECS)
|
||||
const dockerSpecs = new Set(DOCKER_SSH_E2E_SPECS)
|
||||
|
||||
export function selectGeneralE2eSpecs(specs) {
|
||||
return specs.filter((spec) => !dedicatedSpecs.has(spec))
|
||||
}
|
||||
|
||||
function parseSpecs(input) {
|
||||
const specs = JSON.parse(input)
|
||||
if (!Array.isArray(specs) || specs.some((spec) => typeof spec !== 'string' || !spec)) {
|
||||
throw new Error('Expected a JSON array of nonempty E2E spec paths')
|
||||
}
|
||||
return specs
|
||||
}
|
||||
|
||||
export function classifyE2eJobs(input, sshSourceChanged = 'false') {
|
||||
const conservative = { e2e_run_changed: true, e2e_needs_build: true }
|
||||
let specs
|
||||
try {
|
||||
specs = parseSpecs(input)
|
||||
} catch {
|
||||
return conservative
|
||||
}
|
||||
// Empty evidence keeps allocations; the consumer still validates its input.
|
||||
if (specs.length === 0) {
|
||||
return conservative
|
||||
}
|
||||
const runChanged = selectGeneralE2eSpecs(specs).length > 0
|
||||
return {
|
||||
e2e_run_changed: runChanged,
|
||||
e2e_needs_build:
|
||||
runChanged ||
|
||||
sshSourceChanged !== 'false' ||
|
||||
specs.some((spec) => dockerSpecs.has(spec) || spec === LOCALHOST_SSH_E2E_SPEC)
|
||||
}
|
||||
}
|
||||
|
||||
if (process.argv[1] && import.meta.url === pathToFileURL(process.argv[1]).href) {
|
||||
let input = ''
|
||||
process.stdin.setEncoding('utf8')
|
||||
for await (const chunk of process.stdin) {
|
||||
input += chunk
|
||||
}
|
||||
if (process.argv.includes('--job-outputs')) {
|
||||
for (const [name, value] of Object.entries(
|
||||
classifyE2eJobs(input, process.env.E2E_SSH_SOURCE_CHANGED ?? 'false')
|
||||
)) {
|
||||
process.stdout.write(`${name}=${value}\n`)
|
||||
}
|
||||
} else {
|
||||
for (const spec of selectGeneralE2eSpecs(parseSpecs(input))) {
|
||||
if (/[\r\n]/.test(spec)) {
|
||||
throw new Error('E2E spec paths cannot contain newlines')
|
||||
}
|
||||
process.stdout.write(`${spec}\n`)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,147 @@
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { expect, it } from 'vitest'
|
||||
import { parse } from 'yaml'
|
||||
import { runProcess } from '../../src/shared/child-process/run-process'
|
||||
import {
|
||||
classifyE2eJobs,
|
||||
DEDICATED_E2E_SPECS,
|
||||
DOCKER_SSH_E2E_SPECS,
|
||||
LOCALHOST_SSH_E2E_SPEC,
|
||||
NATIVE_IME_E2E_SPEC,
|
||||
NODE_NETWORK_E2E_SPEC,
|
||||
selectGeneralE2eSpecs
|
||||
} from './ci-e2e-job-selection.mjs'
|
||||
import { selectPrE2eSpecs } from './pr-e2e-source-routing.mjs'
|
||||
|
||||
const workflow = parse(readFileSync('.github/workflows/e2e.yml', 'utf8'))
|
||||
const prWorkflow = parse(readFileSync('.github/workflows/pr.yml', 'utf8'))
|
||||
const classify = (specs, ssh = 'false') => classifyE2eJobs(JSON.stringify(specs), ssh)
|
||||
|
||||
it('skips the general consumer only when every requested spec has a dedicated owner', () => {
|
||||
for (const spec of DEDICATED_E2E_SPECS) {
|
||||
expect(classify([spec]).e2e_run_changed, spec).toBe(false)
|
||||
}
|
||||
expect(classify(DEDICATED_E2E_SPECS).e2e_run_changed).toBe(false)
|
||||
const future = 'tests/e2e/future-unclassified.spec.ts'
|
||||
expect(classify([future])).toEqual({ e2e_run_changed: true, e2e_needs_build: true })
|
||||
expect(selectGeneralE2eSpecs([...DEDICATED_E2E_SPECS, future])).toEqual([future])
|
||||
expect(classify([...DEDICATED_E2E_SPECS, future]).e2e_run_changed).toBe(true)
|
||||
})
|
||||
|
||||
it('keeps Electron build and native prerequisites for every consumer requiring them', () => {
|
||||
for (const spec of [...DOCKER_SSH_E2E_SPECS, LOCALHOST_SSH_E2E_SPEC]) {
|
||||
expect(classify([spec]), spec).toEqual({
|
||||
e2e_run_changed: false,
|
||||
e2e_needs_build: true
|
||||
})
|
||||
}
|
||||
for (const spec of [NODE_NETWORK_E2E_SPEC, NATIVE_IME_E2E_SPEC]) {
|
||||
expect(classify([spec]), spec).toEqual({
|
||||
e2e_run_changed: false,
|
||||
e2e_needs_build: false
|
||||
})
|
||||
expect(classify([spec], 'true').e2e_needs_build).toBe(true)
|
||||
}
|
||||
expect(workflow.jobs['ssh-browser-network-route'].needs).toBeUndefined()
|
||||
for (const name of ['e2e', 'changed-e2e', 'ssh-docker-watcher-isolation', 'ssh-localhost']) {
|
||||
expect(workflow.jobs[name].needs, name).toEqual(['build', 'prepare-native-cache'])
|
||||
}
|
||||
})
|
||||
|
||||
it('retains allocations when selection or SSH evidence is incomplete', () => {
|
||||
for (const input of ['', '[]', 'null', '{}', '[null]', '[""]', 'malformed']) {
|
||||
expect(classifyE2eJobs(input), input).toEqual({
|
||||
e2e_run_changed: true,
|
||||
e2e_needs_build: true
|
||||
})
|
||||
}
|
||||
expect(classify([NODE_NETWORK_E2E_SPEC], '').e2e_needs_build).toBe(true)
|
||||
})
|
||||
|
||||
it('preserves the requested specs across source-routed and mixed selections', () => {
|
||||
for (const files of [
|
||||
['src/main/ssh/connection.ts'],
|
||||
['src/main/browser/ssh-browser-network-execution-route.ts'],
|
||||
['src/main/agent-hooks/server.ts'],
|
||||
['src/shared/terminal-unicode-provider.ts'],
|
||||
['tests/e2e/ssh-localhost.spec.ts', 'tests/e2e/future-unclassified.spec.ts']
|
||||
]) {
|
||||
const specs = selectPrE2eSpecs(files)
|
||||
const general = selectGeneralE2eSpecs(specs)
|
||||
const dedicated = specs.filter((spec) => DEDICATED_E2E_SPECS.includes(spec))
|
||||
expect([...general, ...dedicated].sort(), files.join(', ')).toEqual(specs)
|
||||
expect(new Set([...general, ...dedicated]).size).toBe(specs.length)
|
||||
}
|
||||
})
|
||||
|
||||
it('applies allocation hints only to PRs and retains other callers and full references', () => {
|
||||
for (const name of ['run_changed_e2e', 'needs_build']) {
|
||||
expect(workflow.on.workflow_call.inputs[name]).toMatchObject({
|
||||
type: 'boolean',
|
||||
required: false,
|
||||
default: true
|
||||
})
|
||||
}
|
||||
for (const name of ['build', 'prepare-native-cache']) {
|
||||
expect(workflow.jobs[name].if).toBe(
|
||||
"inputs.test_files == '' || github.event_name != 'pull_request' || inputs.needs_build"
|
||||
)
|
||||
}
|
||||
expect(workflow.jobs.e2e.if).toBe("inputs.test_files == ''")
|
||||
const changed = workflow.jobs['changed-e2e']
|
||||
expect(changed.if).toContain("github.event_name != 'pull_request' || inputs.run_changed_e2e")
|
||||
const command = changed.steps.find((step) => step.name === 'Run changed E2E specs').run
|
||||
expect(command).toContain('node config/scripts/ci-e2e-job-selection.mjs >')
|
||||
expect(command).not.toContain('mapfile -t TEST_FILES < <(')
|
||||
const fallback = [...command.matchAll(/\. != "([^"]+)"/g)].map((match) => match[1])
|
||||
expect(fallback).toEqual(DEDICATED_E2E_SPECS)
|
||||
})
|
||||
|
||||
it('publishes conservative hints for malformed evidence and refuses a malformed consumer list', async () => {
|
||||
const program = 'config/scripts/ci-e2e-job-selection.mjs'
|
||||
const consumer = await runProcess({
|
||||
program: process.execPath,
|
||||
args: [program],
|
||||
input: 'malformed',
|
||||
timeoutMs: 10000
|
||||
})
|
||||
expect(consumer.code).not.toBe(0)
|
||||
const hints = await runProcess({
|
||||
program: process.execPath,
|
||||
args: [program, '--job-outputs'],
|
||||
input: 'malformed',
|
||||
timeoutMs: 10000
|
||||
})
|
||||
expect(hints.code, hints.stderr).toBe(0)
|
||||
expect(hints.stdout).toBe('e2e_run_changed=true\ne2e_needs_build=true\n')
|
||||
})
|
||||
|
||||
it('classifies PR consumers in the existing detector and passes conservative allocation hints', () => {
|
||||
const detector = prWorkflow.jobs.code_paths
|
||||
expect(detector.steps[0].with['sparse-checkout']).toContain(
|
||||
'/config/scripts/ci-e2e-job-selection.mjs'
|
||||
)
|
||||
for (const name of ['e2e_run_changed', 'e2e_needs_build']) {
|
||||
expect(detector.outputs[name]).toBe(`\${{ steps.e2e_filter.outputs.${name} }}`)
|
||||
}
|
||||
const command = detector.steps.find((step) => step.id === 'e2e_filter').run
|
||||
expect(command).toContain('E2E_SSH_SOURCE_CHANGED="$SSH_SOURCE_CHANGED"')
|
||||
expect(command).toContain('ci-e2e-job-selection.mjs --job-outputs >> "$GITHUB_OUTPUT"')
|
||||
expect(prWorkflow.jobs.e2e.with.run_changed_e2e).toBe(
|
||||
"${{ needs.code_paths.outputs.e2e_run_changed != 'false' }}"
|
||||
)
|
||||
expect(prWorkflow.jobs.e2e.with.needs_build).toBe(
|
||||
"${{ needs.code_paths.outputs.e2e_needs_build != 'false' }}"
|
||||
)
|
||||
})
|
||||
|
||||
it('runs remaining SSH tests after real failures and stops them when a run is cancelled', () => {
|
||||
const steps = workflow.jobs['ssh-docker-watcher-isolation'].steps
|
||||
expect(steps.find((step) => step.name === 'Run remaining Docker SSH E2E').if).toBe('!cancelled()')
|
||||
expect(
|
||||
steps.find((step) => step.name === 'Run Docker SSH terminal parking + startup readiness E2E').if
|
||||
).toBe('!cancelled() && matrix.shard == 1')
|
||||
for (const step of steps.filter((step) => step.name?.startsWith('Keep '))) {
|
||||
expect(step.if).toContain('always()')
|
||||
}
|
||||
})
|
||||
@@ -17,7 +17,7 @@ describe('CI native toolchain preparation', () => {
|
||||
expect(toolchain.env.NATIVE_CACHE_HIT).toContain(`steps.${id}.outputs.cache-hit`)
|
||||
}
|
||||
expect(index).toBeLessThan(steps.findIndex((step) => step.name === 'Prepare native runtime'))
|
||||
expect(toolchain.if).toBe("runner.os == 'Linux' && inputs.native-runtime != 'none'")
|
||||
expect(toolchain.if).toBe("runner.os == 'Linux' && inputs.native-runtime == 'node'")
|
||||
})
|
||||
|
||||
// The action's toolchain workaround only runs in Linux Bash.
|
||||
@@ -25,9 +25,7 @@ describe('CI native toolchain preparation', () => {
|
||||
['node', 'true', '0', false],
|
||||
['node', 'true', '1', true],
|
||||
['node', 'false', '0', true],
|
||||
['node', '', '0', true],
|
||||
['electron', 'true', '0', true],
|
||||
['electron', 'false', '0', true]
|
||||
['node', '', '0', true]
|
||||
])('runtime=%s cache=%s probe=%s installs=%s', (runtime, hit, probeStatus, installs) => {
|
||||
const directory = mkdtempSync(join(tmpdir(), 'orca-ci-native-toolchain-'))
|
||||
const log = join(directory, 'commands')
|
||||
@@ -66,4 +64,13 @@ describe('CI native toolchain preparation', () => {
|
||||
rmSync(directory, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
|
||||
it('prepares Electron native modules through the existing rebuild path without the global toolchain', () => {
|
||||
const preparation = steps.find((step) => step.name === 'Prepare native runtime')
|
||||
expect(preparation.if).toBe("inputs.native-runtime != 'none'")
|
||||
expect(preparation.env.NATIVE_RUNTIME).toBe('${{ inputs.native-runtime }}')
|
||||
expect(preparation.run).toBe(
|
||||
'node config/scripts/ensure-native-runtime.mjs --runtime="$NATIVE_RUNTIME"'
|
||||
)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -18,7 +18,13 @@ afterEach(() => {
|
||||
}
|
||||
})
|
||||
|
||||
function exercise({ hit = false, save = false, loadFails = false, inspectFails = false } = {}) {
|
||||
function exercise({
|
||||
hit = false,
|
||||
save = false,
|
||||
loadFails = false,
|
||||
inspectFails = false,
|
||||
fixture = 'cli-launch-contract'
|
||||
} = {}) {
|
||||
directory = mkdtempSync(join(tmpdir(), 'orca-package-cache-'))
|
||||
const bin = join(directory, 'bin')
|
||||
mkdirSync(bin)
|
||||
@@ -48,7 +54,7 @@ function exercise({ hit = false, save = false, loadFails = false, inspectFails =
|
||||
RUNNER_TEMP: directory,
|
||||
GITHUB_OUTPUT: output,
|
||||
COMMAND_LOG: commandLog,
|
||||
FIXTURE: 'cli-launch-contract',
|
||||
FIXTURE: fixture,
|
||||
CACHE_HIT: String(hit),
|
||||
SAVE_CACHE: String(save),
|
||||
LOAD_FAILS: String(loadFails),
|
||||
@@ -81,6 +87,12 @@ describe.runIf(process.platform !== 'win32')('fixture cache fallbacks', () => {
|
||||
expect(result.commands).not.toMatch(/(?:build|save) /)
|
||||
})
|
||||
|
||||
it('loads the daemon shutdown fixture without running package or source tests in the cache action', () => {
|
||||
const result = exercise({ hit: true, fixture: 'daemon-shutdown-descendants' })
|
||||
expect(result.output).toBe('image=orca-package-fixture-daemon-shutdown-descendants:cache\n')
|
||||
expect(result.commands).not.toMatch(/(?:build|save|run) /)
|
||||
})
|
||||
|
||||
it('builds and exports inline cache only when the warmer has no usable image', () => {
|
||||
const result = exercise({ save: true })
|
||||
expect(result.commands).toContain(
|
||||
@@ -105,6 +117,7 @@ it('uses exact context/platform keys and the same restore-only action in package
|
||||
step.uses?.endsWith('/prepare-linux-package-fixture')
|
||||
)
|
||||
expect(prepared.map((step) => step.with)).toEqual([
|
||||
{ fixture: 'daemon-shutdown-descendants' },
|
||||
{ fixture: 'headless-serve-shutdown' },
|
||||
{ fixture: 'cli-launch-contract' }
|
||||
])
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
import { mkdirSync, symlinkSync, writeFileSync } from 'node:fs'
|
||||
import { createRequire } from 'node:module'
|
||||
import { dirname, join, resolve } from 'node:path'
|
||||
import { describeProcessFailure, runProcessSync } from './script-child-process.mjs'
|
||||
|
||||
const require = createRequire(import.meta.url)
|
||||
|
||||
async function getPinnedTools(version) {
|
||||
const { getAppImageTools } = require('app-builder-lib/out/toolsets/linux.js')
|
||||
return getAppImageTools(version, require('builder-util').Arch.x64)
|
||||
}
|
||||
|
||||
export async function preparePrAppImageTools({
|
||||
directory: requestedDirectory,
|
||||
configuration = require('../electron-builder-pr-linux.config.cjs'),
|
||||
getTools = getPinnedTools,
|
||||
platform = process.platform,
|
||||
architecture = process.arch
|
||||
}) {
|
||||
if (platform !== 'linux' || architecture !== 'x64') {
|
||||
throw new Error('PR AppImage compression requires a Linux x64 host')
|
||||
}
|
||||
if (configuration.toolsets?.appimage !== '1.0.3') {
|
||||
throw new Error('PR AppImage compression requires pinned AppImage toolset 1.0.3')
|
||||
}
|
||||
if (
|
||||
configuration.compression === 'store' ||
|
||||
(configuration.appImage?.compression && configuration.appImage.compression !== 'zstd')
|
||||
) {
|
||||
throw new Error('PR AppImage compression requires the existing zstd configuration')
|
||||
}
|
||||
// Resolve the original override before installing the private, child-only overlay.
|
||||
const tools = await getTools(configuration.toolsets.appimage)
|
||||
const version = runProcessSync({
|
||||
program: tools.mksquashfs,
|
||||
args: ['-version'],
|
||||
timeoutMs: 10_000,
|
||||
maxOutputBytes: 64 * 1024
|
||||
})
|
||||
if (
|
||||
version.code !== 0 ||
|
||||
version.timedOut ||
|
||||
version.outputTruncated ||
|
||||
!/^mksquashfs version 4\.6\.1(?:\s|$)/m.test(version.stdout)
|
||||
) {
|
||||
throw new Error(
|
||||
`PR AppImage compression requires mksquashfs 4.6.1: ${describeProcessFailure(version)}`
|
||||
)
|
||||
}
|
||||
const directory = resolve(requestedDirectory)
|
||||
mkdirSync(directory)
|
||||
symlinkSync(tools.desktopFileValidate, join(directory, 'desktop-file-validate'))
|
||||
symlinkSync(dirname(tools.runtime), join(directory, 'runtimes'))
|
||||
symlinkSync(dirname(tools.runtimeLibraries), join(directory, 'lib'))
|
||||
writeFileSync(
|
||||
join(directory, 'mksquashfs'),
|
||||
'#!/usr/bin/env bash\nset -euo pipefail\nexec "$ORCA_PR_APPIMAGE_MKSQUASHFS" "$@" -Xcompression-level 3\n',
|
||||
{ mode: 0o755 }
|
||||
)
|
||||
return {
|
||||
APPIMAGE_TOOLS_PATH: directory,
|
||||
ORCA_PR_APPIMAGE_MKSQUASHFS: tools.mksquashfs
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,220 @@
|
||||
import {
|
||||
existsSync,
|
||||
mkdirSync,
|
||||
mkdtempSync,
|
||||
readFileSync,
|
||||
realpathSync,
|
||||
rmSync,
|
||||
statSync,
|
||||
writeFileSync
|
||||
} from 'node:fs'
|
||||
import { createRequire } from 'node:module'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join, relative } from 'node:path'
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
|
||||
import { preparePrAppImageTools } from './package-linux-formats-appimage.mjs'
|
||||
import { runProcessSync } from './script-child-process.mjs'
|
||||
|
||||
const require = createRequire(import.meta.url)
|
||||
const configuration = { toolsets: { appimage: '1.0.3' } }
|
||||
let root
|
||||
|
||||
beforeEach(() => {
|
||||
root = mkdtempSync(join(tmpdir(), 'orca pr AppImage tools-'))
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
vi.unstubAllEnvs()
|
||||
rmSync(root, { recursive: true, force: true })
|
||||
})
|
||||
|
||||
it.each([
|
||||
['linux', 'arm64'],
|
||||
['darwin', 'x64'],
|
||||
['win32', 'x64']
|
||||
])('refuses unmeasured %s/%s hosts before resolving tools', async (platform, architecture) => {
|
||||
const getTools = vi.fn()
|
||||
await expect(
|
||||
preparePrAppImageTools({
|
||||
directory: join(root, 'overlay'),
|
||||
configuration,
|
||||
getTools,
|
||||
platform,
|
||||
architecture
|
||||
})
|
||||
).rejects.toThrow('requires a Linux x64 host')
|
||||
expect(getTools).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it.each([
|
||||
[{ toolsets: { appimage: '1.0.2' } }, 'pinned AppImage toolset 1.0.3'],
|
||||
[{ ...configuration, appImage: { compression: 'gzip' } }, 'existing zstd configuration'],
|
||||
[{ ...configuration, compression: 'store' }, 'existing zstd configuration']
|
||||
])('rejects unsupported configuration %j before resolving tools', async (value, message) => {
|
||||
const getTools = vi.fn()
|
||||
await expect(
|
||||
preparePrAppImageTools({
|
||||
directory: join(root, 'overlay'),
|
||||
configuration: value,
|
||||
getTools,
|
||||
platform: 'linux',
|
||||
architecture: 'x64'
|
||||
})
|
||||
).rejects.toThrow(message)
|
||||
expect(getTools).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
describe.skipIf(process.platform === 'win32')('real executable AppImage tool overlay', () => {
|
||||
let original
|
||||
let overlay
|
||||
|
||||
beforeEach(() => {
|
||||
original = join(root, 'custom tools with spaces')
|
||||
overlay = join(root, 'private tools')
|
||||
mkdirSync(join(original, 'runtimes'), { recursive: true })
|
||||
mkdirSync(join(original, 'lib', 'x64'), { recursive: true })
|
||||
writeFileSync(join(original, 'runtimes', 'runtime-x64'), 'unchanged static runtime')
|
||||
writeFileSync(join(original, 'lib', 'x64', 'lib.so'), 'unchanged runtime library')
|
||||
writeFileSync(join(original, 'desktop-file-validate'), '#!/usr/bin/env bash\nexit 0\n', {
|
||||
mode: 0o755
|
||||
})
|
||||
writeFileSync(
|
||||
join(original, 'mksquashfs'),
|
||||
[
|
||||
'#!/usr/bin/env node',
|
||||
'if (process.argv[2] === "-version") {',
|
||||
' console.log(`mksquashfs version ${process.env.ORCA_TEST_SQUASHFS_VERSION ?? "4.6.1"}`)',
|
||||
'} else { console.log(JSON.stringify(process.argv.slice(2))) }',
|
||||
'process.exitCode = Number(process.env.ORCA_TEST_SQUASHFS_EXIT ?? 0)',
|
||||
''
|
||||
].join('\n'),
|
||||
{ mode: 0o755 }
|
||||
)
|
||||
vi.stubEnv('APPIMAGE_TOOLS_PATH', original)
|
||||
})
|
||||
|
||||
function prepare(options = {}) {
|
||||
return preparePrAppImageTools({
|
||||
directory: overlay,
|
||||
configuration,
|
||||
platform: 'linux',
|
||||
architecture: 'x64',
|
||||
...options
|
||||
})
|
||||
}
|
||||
|
||||
it('honors a custom toolset, preserving every original argument and runtime byte', async () => {
|
||||
const originalProgram = join(original, 'mksquashfs')
|
||||
const programBytes = readFileSync(originalProgram)
|
||||
const environment = await prepare()
|
||||
const args = [
|
||||
'app spaces \' " $HOME $(touch expanded) `touch expanded`',
|
||||
'output\nwith newline',
|
||||
'-offset',
|
||||
'944632',
|
||||
'-comp',
|
||||
'zstd'
|
||||
]
|
||||
const result = runProcessSync({
|
||||
program: join(overlay, 'mksquashfs'),
|
||||
args,
|
||||
cwd: root,
|
||||
env: { ...process.env, ...environment },
|
||||
timeoutMs: 10_000
|
||||
})
|
||||
expect(result.code).toBe(0)
|
||||
expect(JSON.parse(result.stdout)).toEqual([...args, '-Xcompression-level', '3'])
|
||||
expect(existsSync(join(root, 'expanded'))).toBe(false)
|
||||
expect(statSync(join(overlay, 'mksquashfs')).mode & 0o777).toBe(0o755)
|
||||
expect(readFileSync(originalProgram)).toEqual(programBytes)
|
||||
expect(process.env.APPIMAGE_TOOLS_PATH).toBe(original)
|
||||
expect(environment.ORCA_PR_APPIMAGE_MKSQUASHFS).toBe(originalProgram)
|
||||
|
||||
vi.stubEnv('APPIMAGE_TOOLS_PATH', environment.APPIMAGE_TOOLS_PATH)
|
||||
const tools = await require('app-builder-lib/out/toolsets/linux.js').getAppImageTools(
|
||||
'1.0.3',
|
||||
require('builder-util').Arch.x64
|
||||
)
|
||||
for (const [actual, expected] of [
|
||||
[tools.desktopFileValidate, join(original, 'desktop-file-validate')],
|
||||
[tools.runtime, join(original, 'runtimes', 'runtime-x64')],
|
||||
[tools.runtimeLibraries, join(original, 'lib', 'x64')]
|
||||
]) {
|
||||
expect(realpathSync(actual)).toBe(realpathSync(expected))
|
||||
}
|
||||
expect(readFileSync(tools.runtime, 'utf8')).toBe('unchanged static runtime')
|
||||
expect(readFileSync(join(tools.runtimeLibraries, 'lib.so'), 'utf8')).toBe(
|
||||
'unchanged runtime library'
|
||||
)
|
||||
})
|
||||
|
||||
it('quotes an original executable path containing shell metacharacters', async () => {
|
||||
const tools = await require('app-builder-lib/out/toolsets/linux.js').getAppImageTools(
|
||||
'1.0.3',
|
||||
require('builder-util').Arch.x64
|
||||
)
|
||||
const program = join(root, 'tool \' " $(touch expanded) `touch expanded`')
|
||||
writeFileSync(program, readFileSync(tools.mksquashfs), { mode: 0o755 })
|
||||
const environment = await prepare({ getTools: async () => ({ ...tools, mksquashfs: program }) })
|
||||
const result = runProcessSync({
|
||||
program: join(overlay, 'mksquashfs'),
|
||||
args: ['app', 'output', '-comp', 'zstd'],
|
||||
cwd: root,
|
||||
env: { ...process.env, ...environment },
|
||||
timeoutMs: 10_000
|
||||
})
|
||||
expect(result.code).toBe(0)
|
||||
expect(JSON.parse(result.stdout)).toEqual([
|
||||
'app',
|
||||
'output',
|
||||
'-comp',
|
||||
'zstd',
|
||||
'-Xcompression-level',
|
||||
'3'
|
||||
])
|
||||
expect(existsSync(join(root, 'expanded'))).toBe(false)
|
||||
})
|
||||
|
||||
it('normalizes a relative overlay into an absolute builder override', async () => {
|
||||
const environment = await prepare({ directory: relative(process.cwd(), overlay) })
|
||||
expect(environment.APPIMAGE_TOOLS_PATH).toBe(overlay)
|
||||
expect(existsSync(join(overlay, 'mksquashfs'))).toBe(true)
|
||||
})
|
||||
|
||||
it('propagates the original executable failure without a fallback', async () => {
|
||||
const environment = await prepare()
|
||||
vi.stubEnv('ORCA_TEST_SQUASHFS_EXIT', '17')
|
||||
const result = runProcessSync({
|
||||
program: join(overlay, 'mksquashfs'),
|
||||
args: ['app', 'output', '-comp', 'zstd'],
|
||||
env: { ...process.env, ...environment },
|
||||
timeoutMs: 10_000
|
||||
})
|
||||
expect(result.code).toBe(17)
|
||||
})
|
||||
|
||||
it.each([
|
||||
['ORCA_TEST_SQUASHFS_VERSION', '4.7.0'],
|
||||
['ORCA_TEST_SQUASHFS_EXIT', '2']
|
||||
])(
|
||||
'rejects an unsupported original tool (%s=%s) without creating an overlay',
|
||||
async (key, value) => {
|
||||
vi.stubEnv(key, value)
|
||||
await expect(prepare()).rejects.toThrow('requires mksquashfs 4.6.1')
|
||||
expect(existsSync(overlay)).toBe(false)
|
||||
}
|
||||
)
|
||||
|
||||
it('keeps invalid custom toolset errors instead of downloading another toolset', async () => {
|
||||
vi.stubEnv('APPIMAGE_TOOLS_PATH', join(root, 'missing custom tools'))
|
||||
await expect(prepare()).rejects.toThrow(/APPIMAGE_TOOLS_PATH|AppImage tool/)
|
||||
expect(existsSync(overlay)).toBe(false)
|
||||
})
|
||||
|
||||
it('preserves upstream rejection of unsafe custom override paths', async () => {
|
||||
vi.stubEnv('APPIMAGE_TOOLS_PATH', join(root, 'tools $(touch expanded)'))
|
||||
await expect(prepare()).rejects.toThrow('APPIMAGE_TOOLS_PATH contains shell-unsafe characters')
|
||||
expect(existsSync(overlay)).toBe(false)
|
||||
expect(existsSync(join(root, 'expanded'))).toBe(false)
|
||||
})
|
||||
})
|
||||
@@ -14,6 +14,7 @@ import {
|
||||
import { join, resolve } from 'node:path'
|
||||
import { copyPrivateTree } from './space-sharing-copy.mjs'
|
||||
import { spawnProcess } from './script-child-process.mjs'
|
||||
import { preparePrAppImageTools } from './package-linux-formats-appimage.mjs'
|
||||
|
||||
const require = createRequire(import.meta.url)
|
||||
const formats = ['AppImage', 'deb', 'rpm']
|
||||
@@ -39,12 +40,12 @@ export function linuxFormatArguments({ format, appDirectory, outputDirectory })
|
||||
]
|
||||
}
|
||||
|
||||
function runElectronBuilder(args) {
|
||||
function runElectronBuilder(args, environment) {
|
||||
return new Promise((resolveBuild, reject) => {
|
||||
const child = spawnProcess({
|
||||
program: process.execPath,
|
||||
args: [require.resolve('electron-builder/cli.js'), ...args],
|
||||
env: { ...process.env, ORCA_BACKGROUND_LAUNCH: '1' },
|
||||
env: { ...process.env, ORCA_BACKGROUND_LAUNCH: '1', ...environment },
|
||||
stdio: 'inherit'
|
||||
})
|
||||
child.once('error', reject)
|
||||
@@ -61,6 +62,7 @@ function runElectronBuilder(args) {
|
||||
export async function packageLinuxFormats({
|
||||
preparedDirectory = resolve('dist/linux-unpacked'),
|
||||
outputDirectory = resolve('dist'),
|
||||
prepareAppImageTools = preparePrAppImageTools,
|
||||
runBuilder = runElectronBuilder
|
||||
} = {}) {
|
||||
const marker = join(preparedDirectory, 'resources/package-type')
|
||||
@@ -82,8 +84,13 @@ export async function packageLinuxFormats({
|
||||
console.log(
|
||||
`[linux-package] ${format} copied in ${Math.round(performance.now() - startedFormatAt)}ms`
|
||||
)
|
||||
const environment =
|
||||
format === 'AppImage'
|
||||
? await prepareAppImageTools({ directory: join(staging, format, 'tools') })
|
||||
: {}
|
||||
await runBuilder(
|
||||
linuxFormatArguments({ format, appDirectory, outputDirectory: formatOutput })
|
||||
linuxFormatArguments({ format, appDirectory, outputDirectory: formatOutput }),
|
||||
environment
|
||||
)
|
||||
const artifacts = readdirSync(formatOutput).filter((name) => name.endsWith(`.${format}`))
|
||||
const artifactStats =
|
||||
|
||||
@@ -85,6 +85,7 @@ describe('independent Linux package formats', () => {
|
||||
await packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
prepareAppImageTools: async () => ({}),
|
||||
runBuilder: async (args) => {
|
||||
const app = valueAfter(args, '--prepackaged')
|
||||
const format = valueAfter(args, '--linux')
|
||||
@@ -127,42 +128,93 @@ describe('independent Linux package formats', () => {
|
||||
).toBe(false)
|
||||
})
|
||||
|
||||
it('settles every worker before cleanup and exposes no partial artifact on failure', async () => {
|
||||
const finished = []
|
||||
let release
|
||||
const gate = new Promise((resolve) => {
|
||||
release = resolve
|
||||
})
|
||||
await expect(
|
||||
packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
runBuilder: async (args) => {
|
||||
const format = valueAfter(args, '--linux')
|
||||
if (format === 'AppImage') {
|
||||
throw new Error('compression failed')
|
||||
}
|
||||
if (format === 'rpm') {
|
||||
release()
|
||||
}
|
||||
await gate
|
||||
const { app } = emitPackage(args)
|
||||
expect(existsSync(app)).toBe(true)
|
||||
finished.push(format)
|
||||
}
|
||||
it.each(['builder', 'tool preparation'])(
|
||||
'settles every worker before cleanup and exposes no partial artifact on %s failure',
|
||||
async (failurePhase) => {
|
||||
const finished = []
|
||||
let overlay
|
||||
let release
|
||||
const gate = new Promise((resolve) => {
|
||||
release = resolve
|
||||
})
|
||||
).rejects.toMatchObject({
|
||||
message: 'Linux package formats failed',
|
||||
errors: [
|
||||
expect.objectContaining({
|
||||
message: 'AppImage packaging failed',
|
||||
cause: expect.objectContaining({ message: 'compression failed' })
|
||||
await expect(
|
||||
packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
prepareAppImageTools: async ({ directory }) => {
|
||||
overlay = directory
|
||||
mkdirSync(directory)
|
||||
writeFileSync(join(directory, 'mksquashfs'), 'private wrapper')
|
||||
if (failurePhase === 'tool preparation') {
|
||||
throw new Error('compression failed')
|
||||
}
|
||||
return { APPIMAGE_TOOLS_PATH: directory, ORCA_PR_APPIMAGE_MKSQUASHFS: 'original tool' }
|
||||
},
|
||||
runBuilder: async (args, environment) => {
|
||||
const format = valueAfter(args, '--linux')
|
||||
if (format === 'AppImage') {
|
||||
expect(environment).toEqual({
|
||||
APPIMAGE_TOOLS_PATH: overlay,
|
||||
ORCA_PR_APPIMAGE_MKSQUASHFS: 'original tool'
|
||||
})
|
||||
throw new Error('compression failed')
|
||||
}
|
||||
expect(environment).toEqual({})
|
||||
if (format === 'rpm') {
|
||||
release()
|
||||
}
|
||||
await gate
|
||||
const { app } = emitPackage(args)
|
||||
expect(existsSync(app)).toBe(true)
|
||||
expect(existsSync(overlay)).toBe(true)
|
||||
finished.push(format)
|
||||
}
|
||||
})
|
||||
]
|
||||
).rejects.toMatchObject({
|
||||
message: 'Linux package formats failed',
|
||||
errors: [
|
||||
expect.objectContaining({
|
||||
message: 'AppImage packaging failed',
|
||||
cause: expect.objectContaining({ message: 'compression failed' })
|
||||
})
|
||||
]
|
||||
})
|
||||
expect(finished.sort()).toEqual(['deb', 'rpm'])
|
||||
expect(existsSync(overlay)).toBe(false)
|
||||
expect(readdirSync(outputDirectory)).toEqual([])
|
||||
expect(readFileSync(join(preparedDirectory, 'resources/package-type'), 'utf8')).toBe(
|
||||
'AppImage'
|
||||
)
|
||||
}
|
||||
)
|
||||
|
||||
it('passes its private tool environment only to AppImage and removes it after success', async () => {
|
||||
const originalToolsPath = process.env.APPIMAGE_TOOLS_PATH
|
||||
let overlay
|
||||
const calls = []
|
||||
await packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
prepareAppImageTools: async ({ directory }) => {
|
||||
overlay = directory
|
||||
mkdirSync(directory)
|
||||
return { APPIMAGE_TOOLS_PATH: directory, ORCA_PR_APPIMAGE_MKSQUASHFS: 'original tool' }
|
||||
},
|
||||
runBuilder: async (args, environment) => {
|
||||
const format = valueAfter(args, '--linux')
|
||||
calls.push(format)
|
||||
expect(environment).toEqual(
|
||||
format === 'AppImage'
|
||||
? { APPIMAGE_TOOLS_PATH: overlay, ORCA_PR_APPIMAGE_MKSQUASHFS: 'original tool' }
|
||||
: {}
|
||||
)
|
||||
expect(process.env.APPIMAGE_TOOLS_PATH).toBe(originalToolsPath)
|
||||
emitPackage(args)
|
||||
}
|
||||
})
|
||||
expect(finished.sort()).toEqual(['deb', 'rpm'])
|
||||
expect(readdirSync(outputDirectory)).toEqual([])
|
||||
expect(readFileSync(join(preparedDirectory, 'resources/package-type'), 'utf8')).toBe('AppImage')
|
||||
expect(calls.sort()).toEqual(targets.slice().sort())
|
||||
expect(existsSync(overlay)).toBe(false)
|
||||
expect(process.env.APPIMAGE_TOOLS_PATH).toBe(originalToolsPath)
|
||||
})
|
||||
|
||||
it('rejects missing artifacts even when the builder reports success', async () => {
|
||||
@@ -170,6 +222,7 @@ describe('independent Linux package formats', () => {
|
||||
packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
prepareAppImageTools: async () => ({}),
|
||||
runBuilder: async (args) => {
|
||||
const result = emitPackage(args)
|
||||
if (result.format === 'rpm') {
|
||||
@@ -187,6 +240,7 @@ describe('independent Linux package formats', () => {
|
||||
packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
prepareAppImageTools: async () => ({}),
|
||||
runBuilder: async (args) => {
|
||||
emitPackage(args)
|
||||
}
|
||||
@@ -202,6 +256,7 @@ describe('independent Linux package formats', () => {
|
||||
packageLinuxFormats({
|
||||
preparedDirectory,
|
||||
outputDirectory,
|
||||
prepareAppImageTools: async () => ({}),
|
||||
runBuilder: async () => {
|
||||
throw new Error('must not run')
|
||||
}
|
||||
|
||||
@@ -212,6 +212,7 @@ describe('per-job path classification', () => {
|
||||
it('runs Linux packaging when an artifact contract changes', () => {
|
||||
for (const file of [
|
||||
'config/scripts/package-linux-formats.mjs',
|
||||
'config/scripts/package-linux-formats-appimage.mjs',
|
||||
'config/scripts/script-child-process.mjs',
|
||||
'config/scripts/space-sharing-copy.mjs',
|
||||
'.github/actions/prepare-linux-package-fixture/action.yml',
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { DEDICATED_E2E_SPECS } from './ci-e2e-job-selection.mjs'
|
||||
import { existsSync, readdirSync, readFileSync } from 'node:fs'
|
||||
import { join, resolve } from 'node:path'
|
||||
import { parse as parseJsonc } from 'jsonc-parser'
|
||||
@@ -153,7 +154,9 @@ describe('PR E2E gate contract', () => {
|
||||
|
||||
it('uses one runner for changed specs and keeps full runs sharded', () => {
|
||||
expect(e2eWorkflow.jobs.e2e.if).toBe("inputs.test_files == ''")
|
||||
expect(e2eWorkflow.jobs['changed-e2e'].if).toBe("inputs.test_files != ''")
|
||||
expect(e2eWorkflow.jobs['changed-e2e'].if).toBe(
|
||||
"inputs.test_files != '' && (github.event_name != 'pull_request' || inputs.run_changed_e2e)"
|
||||
)
|
||||
expect(e2eWorkflow.jobs['changed-e2e'].strategy).toBeUndefined()
|
||||
expect(e2eWorkflow.jobs.e2e.strategy.matrix.include).toEqual(
|
||||
Array.from({ length: 14 }, (_, index) => ({
|
||||
@@ -165,12 +168,12 @@ describe('PR E2E gate contract', () => {
|
||||
(step) => step.name === 'Run changed E2E specs'
|
||||
)
|
||||
expect(changedRun.env.TEST_FILES_JSON).toBe('${{ inputs.test_files }}')
|
||||
expect(changedRun.run).toContain('. != "tests/e2e/ssh-startup-exec-readiness.spec.ts"')
|
||||
expect(changedRun.run).toContain('. != "tests/e2e/paired-startup-exec-readiness.spec.ts"')
|
||||
expect(changedRun.run).toContain(
|
||||
'. != "tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts"'
|
||||
expect(DEDICATED_E2E_SPECS).toContain('tests/e2e/ssh-startup-exec-readiness.spec.ts')
|
||||
expect(DEDICATED_E2E_SPECS).toContain('tests/e2e/paired-startup-exec-readiness.spec.ts')
|
||||
expect(DEDICATED_E2E_SPECS).toContain(
|
||||
'tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts'
|
||||
)
|
||||
expect(changedRun.run).toContain('. != "tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts"')
|
||||
expect(DEDICATED_E2E_SPECS).toContain('tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts')
|
||||
expect(changedRun.run).toContain('if [ "${#TEST_FILES[@]}" -eq 0 ]')
|
||||
expect(changedRun.run).toContain('grep -l \'@headful\' "${TEST_FILES[@]}"')
|
||||
expect(changedRun.run).toContain('E2E_PROJECT_ARGS+=(--project=electron-headful)')
|
||||
@@ -695,10 +698,7 @@ describe('PR E2E gate contract', () => {
|
||||
})
|
||||
|
||||
it('keeps the native IME spec out of the lane that would silently skip it', () => {
|
||||
const changedRun = e2eWorkflow.jobs['changed-e2e'].steps.find(
|
||||
(step) => step.name === 'Run changed E2E specs'
|
||||
)
|
||||
expect(changedRun.run).toContain('. != "tests/e2e/terminal-ibus-hangul-native.spec.ts"')
|
||||
expect(DEDICATED_E2E_SPECS).toContain('tests/e2e/terminal-ibus-hangul-native.spec.ts')
|
||||
// Why it still has to be routed: the dedicated lane is selected by the same route, so the
|
||||
// spec appearing in test_files is how a spec-only edit reaches the real-IME lane at all.
|
||||
expect(selectPrE2eSpecs(['src/shared/terminal-unicode-provider.ts'])).toContain(
|
||||
|
||||
@@ -300,6 +300,9 @@ describe('PR workflow parallelism', () => {
|
||||
steps.findIndex((step) => step.name === 'Install dependencies')
|
||||
)
|
||||
expect(steps[restoreIndex].uses).toBe('actions/cache/restore@v5')
|
||||
expect(steps[restoreIndex].if).toBe(
|
||||
"github.event_name == 'pull_request' && (runner.os != 'Windows' || runner.arch != 'X64' || !contains(inputs.cache-dependency-path, 'mobile/pnpm-lock.yaml'))"
|
||||
)
|
||||
})
|
||||
|
||||
it('uses the repository package-manager version for every direct pnpm setup', () => {
|
||||
@@ -359,7 +362,7 @@ describe('PR workflow parallelism', () => {
|
||||
expect(dependencyAction.inputs['persist-native-cache'].default).toBe('true')
|
||||
expect(
|
||||
dependencyAction.runs.steps.find((step) => step.name === 'Use external node-gyp').if
|
||||
).toBe("runner.os == 'Linux' && inputs.native-runtime != 'none'")
|
||||
).toBe("runner.os == 'Linux' && inputs.native-runtime == 'node'")
|
||||
const dependencyInstall = dependencyAction.runs.steps.find(
|
||||
(step) => step.name === 'Install dependencies'
|
||||
)
|
||||
|
||||
@@ -20,6 +20,7 @@ const manifest = JSON.parse(readFileSync(manifestPath, 'utf8'))
|
||||
const selectedFiles = new Set(['web-index.html'])
|
||||
const visitedEntries = new Set()
|
||||
const PDFJS_VIEWER_ASSET_DIRS = ['cmaps', 'standard_fonts', 'wasm']
|
||||
const TEXT_REFERENCE_OUTPUT = /\.(?:css|html|m?js|svg)$/
|
||||
|
||||
function assertEntryIsolation() {
|
||||
const entryKeys = new Set(
|
||||
@@ -96,26 +97,37 @@ function listOutputFiles(directory, prefix = '') {
|
||||
|
||||
function includeReferencedOutputs() {
|
||||
const candidates = listOutputFiles(rendererOutput).filter(
|
||||
(outputPath) => !outputPath.startsWith('.vite/') && !outputPath.endsWith('.html')
|
||||
(outputPath) =>
|
||||
!outputPath.startsWith('.vite/') &&
|
||||
!outputPath.endsWith('.html') &&
|
||||
!selectedFiles.has(outputPath) &&
|
||||
// Viewer binaries are copied unconditionally and cannot extend the reference closure.
|
||||
(TEXT_REFERENCE_OUTPUT.test(outputPath) ||
|
||||
!PDFJS_VIEWER_ASSET_DIRS.some((directory) => outputPath.startsWith(`${directory}/`)))
|
||||
)
|
||||
let foundReference = true
|
||||
const referencesByDirectory = new Map()
|
||||
|
||||
while (foundReference) {
|
||||
foundReference = false
|
||||
for (const selectedFile of selectedFiles) {
|
||||
if (!/\.(?:css|html|m?js|svg)$/.test(selectedFile)) {
|
||||
// Set iteration also visits newly discovered files, including transitive references.
|
||||
for (const selectedFile of selectedFiles) {
|
||||
if (!TEXT_REFERENCE_OUTPUT.test(selectedFile)) {
|
||||
continue
|
||||
}
|
||||
const directory = posix.dirname(selectedFile)
|
||||
let references = referencesByDirectory.get(directory)
|
||||
if (!references) {
|
||||
references = candidates.map((candidate) => ({
|
||||
candidate,
|
||||
localReference: posix.relative(directory, candidate)
|
||||
}))
|
||||
referencesByDirectory.set(directory, references)
|
||||
}
|
||||
const contents = readFileSync(join(rendererOutput, selectedFile), 'utf8')
|
||||
for (const { candidate, localReference } of references) {
|
||||
if (selectedFiles.has(candidate)) {
|
||||
continue
|
||||
}
|
||||
const contents = readFileSync(join(rendererOutput, selectedFile), 'utf8')
|
||||
for (const candidate of candidates) {
|
||||
if (selectedFiles.has(candidate)) {
|
||||
continue
|
||||
}
|
||||
const localReference = posix.relative(posix.dirname(selectedFile), candidate)
|
||||
if (contents.includes(candidate) || contents.includes(localReference)) {
|
||||
selectedFiles.add(candidate)
|
||||
foundReference = true
|
||||
}
|
||||
if (contents.includes(candidate) || contents.includes(localReference)) {
|
||||
selectedFiles.add(candidate)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,12 +1,22 @@
|
||||
import { existsSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { dirname, join, resolve } from 'node:path'
|
||||
import { spawnSync } from 'node:child_process'
|
||||
import { runProcess } from '../../src/shared/child-process/run-process'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
|
||||
const scriptPath = resolve('config/scripts/project-renderer-web-client.mjs')
|
||||
const temporaryRoots = []
|
||||
|
||||
function projectFixture(root) {
|
||||
return runProcess({
|
||||
program: process.execPath,
|
||||
args: [scriptPath],
|
||||
cwd: root,
|
||||
env: { ...process.env, ORCA_BACKGROUND_LAUNCH: '1' },
|
||||
timeoutMs: 30000
|
||||
})
|
||||
}
|
||||
|
||||
function writeFixtureFile(root, relativePath, contents) {
|
||||
const targetPath = join(root, relativePath)
|
||||
mkdirSync(dirname(targetPath), { recursive: true })
|
||||
@@ -70,14 +80,11 @@ describe('renderer web client projection', () => {
|
||||
expect(builderConfig).toContain("'!out/renderer/.vite{,/**/*}'")
|
||||
})
|
||||
|
||||
it('copies and minifies only the web dependency closure', () => {
|
||||
it('copies and minifies only the web dependency closure', async () => {
|
||||
const root = createRendererFixture()
|
||||
const result = spawnSync(process.execPath, [scriptPath], {
|
||||
cwd: root,
|
||||
encoding: 'utf8'
|
||||
})
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.status, result.stderr).toBe(0)
|
||||
expect(result.code, result.stderr).toBe(0)
|
||||
expect(result.stdout).toContain('Projected web client: 7 files')
|
||||
expect(existsSync(join(root, 'out/web/web-index.html'))).toBe(true)
|
||||
expect(existsSync(join(root, 'out/web/assets/editor.worker-fixture.js'))).toBe(true)
|
||||
@@ -87,31 +94,114 @@ describe('renderer web client projection', () => {
|
||||
expect(readFileSync(join(root, 'out/web/assets/web.css'), 'utf8')).toBe('.root{color:red}\n')
|
||||
})
|
||||
|
||||
it('fails when the renderer manifest omits the web entry', () => {
|
||||
it('follows transitive relative references and cycles with the existing substring behavior', async () => {
|
||||
const root = createRendererFixture()
|
||||
writeFixtureFile(
|
||||
root,
|
||||
'out/renderer/assets/editor.worker-fixture.js',
|
||||
'const referenced = "../workers/one.mjs"; const overlapping = "assets/token.png.backup";'
|
||||
)
|
||||
writeFixtureFile(root, 'out/renderer/workers/one.mjs', 'const icon = "../icons/link.svg";')
|
||||
writeFixtureFile(root, 'out/renderer/icons/link.svg', '<image href="../workers/one.mjs"/>')
|
||||
writeFixtureFile(root, 'out/renderer/assets/token.png', 'substring-token')
|
||||
writeFixtureFile(root, 'out/renderer/assets/token.png.backup', 'longer-token')
|
||||
writeFixtureFile(root, 'out/renderer/workers/unreferenced.mjs', 'export const absent = true;')
|
||||
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.code, result.stderr).toBe(0)
|
||||
for (const file of [
|
||||
'workers/one.mjs',
|
||||
'icons/link.svg',
|
||||
'assets/token.png',
|
||||
'assets/token.png.backup'
|
||||
]) {
|
||||
expect(existsSync(join(root, 'out/web', file)), file).toBe(true)
|
||||
}
|
||||
expect(readFileSync(join(root, 'out/web/assets/token.png'), 'utf8')).toBe('substring-token')
|
||||
expect(existsSync(join(root, 'out/web/workers/unreferenced.mjs'))).toBe(false)
|
||||
})
|
||||
|
||||
it('retains all PDFJS viewer asset directories even without textual references', async () => {
|
||||
const root = createRendererFixture()
|
||||
const assets = ['cmaps/fixture.bcmap', 'standard_fonts/fixture.pfb', 'wasm/fixture.wasm']
|
||||
for (const file of assets) {
|
||||
writeFixtureFile(root, `out/renderer/${file}`, Buffer.from([0, 255, 42]))
|
||||
}
|
||||
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.code, result.stderr).toBe(0)
|
||||
for (const file of assets) {
|
||||
expect(readFileSync(join(root, 'out/web', file))).toEqual(Buffer.from([0, 255, 42]))
|
||||
}
|
||||
})
|
||||
|
||||
it('follows referenced PDFJS text assets without expanding unreferenced viewer modules', async () => {
|
||||
const root = createRendererFixture()
|
||||
writeFixtureFile(
|
||||
root,
|
||||
'out/renderer/assets/web-entry.js',
|
||||
'const viewer = "../wasm/viewer.mjs";'
|
||||
)
|
||||
writeFixtureFile(
|
||||
root,
|
||||
'out/renderer/wasm/viewer.mjs',
|
||||
'const image = "../assets/viewer-image.png";'
|
||||
)
|
||||
writeFixtureFile(
|
||||
root,
|
||||
'out/renderer/wasm/unused.mjs',
|
||||
'const unused = "../assets/unreferenced-image.png";'
|
||||
)
|
||||
writeFixtureFile(root, 'out/renderer/assets/viewer-image.png', 'viewer-image')
|
||||
writeFixtureFile(root, 'out/renderer/assets/unreferenced-image.png', 'unreferenced-image')
|
||||
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.code, result.stderr).toBe(0)
|
||||
expect(existsSync(join(root, 'out/web/wasm/viewer.mjs'))).toBe(true)
|
||||
expect(existsSync(join(root, 'out/web/wasm/unused.mjs'))).toBe(true)
|
||||
expect(readFileSync(join(root, 'out/web/assets/viewer-image.png'), 'utf8')).toBe('viewer-image')
|
||||
expect(existsSync(join(root, 'out/web/assets/unreferenced-image.png'))).toBe(false)
|
||||
})
|
||||
|
||||
it.each(['../outside.js', '/absolute.js', 'C:/drive.js', 'assets\\backslash.js'])(
|
||||
'rejects invalid manifest output paths: %s',
|
||||
async (outputPath) => {
|
||||
const root = createRendererFixture()
|
||||
const manifestPath = join(root, 'out/renderer/.vite/manifest.json')
|
||||
const manifest = JSON.parse(readFileSync(manifestPath, 'utf8'))
|
||||
manifest['web-index.html'].file = outputPath
|
||||
writeFileSync(manifestPath, JSON.stringify(manifest))
|
||||
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.code).toBe(1)
|
||||
expect(result.stderr).toContain('Invalid renderer output path:')
|
||||
expect(readFileSync(join(root, 'out/web/stale.js'), 'utf8')).toBe('stale')
|
||||
}
|
||||
)
|
||||
|
||||
it('fails when the renderer manifest omits the web entry', async () => {
|
||||
const root = createRendererFixture()
|
||||
writeFixtureFile(root, 'out/renderer/.vite/manifest.json', '{}')
|
||||
const result = spawnSync(process.execPath, [scriptPath], {
|
||||
cwd: root,
|
||||
encoding: 'utf8'
|
||||
})
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.status).toBe(1)
|
||||
expect(result.code).toBe(1)
|
||||
expect(result.stderr).toContain('Renderer manifest is missing entry: web-index.html')
|
||||
})
|
||||
|
||||
it('rejects renderer entries that execute another entry root', () => {
|
||||
it('rejects renderer entries that execute another entry root', async () => {
|
||||
const root = createRendererFixture()
|
||||
const manifestPath = join(root, 'out/renderer/.vite/manifest.json')
|
||||
const manifest = JSON.parse(readFileSync(manifestPath, 'utf8'))
|
||||
manifest['web-index.html'].dynamicImports.push('index.html')
|
||||
writeFileSync(manifestPath, JSON.stringify(manifest))
|
||||
|
||||
const result = spawnSync(process.execPath, [scriptPath], {
|
||||
cwd: root,
|
||||
encoding: 'utf8'
|
||||
})
|
||||
const result = await projectFixture(root)
|
||||
|
||||
expect(result.status).toBe(1)
|
||||
expect(result.code).toBe(1)
|
||||
expect(result.stderr).toContain('Renderer entry web-index.html executes entry index.html')
|
||||
})
|
||||
})
|
||||
|
||||
@@ -115,7 +115,17 @@ try {
|
||||
bundles.unshift(['baseline', baseline])
|
||||
}
|
||||
|
||||
runDocker(['build', '--platform', platform, '-t', image, dockerDir])
|
||||
runDocker([
|
||||
'build',
|
||||
'--platform',
|
||||
platform,
|
||||
...(process.env.ORCA_DAEMON_SHUTDOWN_FIXTURE_CACHE_IMAGE
|
||||
? ['--cache-from', process.env.ORCA_DAEMON_SHUTDOWN_FIXTURE_CACHE_IMAGE]
|
||||
: []),
|
||||
'-t',
|
||||
image,
|
||||
dockerDir
|
||||
])
|
||||
for (const [mode, bundlePath] of bundles) {
|
||||
const result = runDocker(
|
||||
[
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { DEDICATED_E2E_SPECS } from './ci-e2e-job-selection.mjs'
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { join, resolve } from 'node:path'
|
||||
import { parse } from 'yaml'
|
||||
@@ -22,7 +23,8 @@ it('routes SSH browser specs to a lane that enables their opt-ins', () => {
|
||||
expect(runner).toContain(`'${spec}'`)
|
||||
expect(runner).toContain(`${flag}: '1'`)
|
||||
expect(workflow.jobs['ssh-docker-watcher-isolation'].if).toContain(spec)
|
||||
expect(changedRun.run).toContain(`. != "${spec}"`)
|
||||
expect(DEDICATED_E2E_SPECS).toContain(spec)
|
||||
expect(changedRun.run).toContain('node config/scripts/ci-e2e-job-selection.mjs')
|
||||
}
|
||||
})
|
||||
|
||||
@@ -42,9 +44,7 @@ it('executes both Docker network routes in a Node job with their opt-in enabled'
|
||||
expect(run.env.ORCA_RUN_DOCKER_SSH_BROWSER_E2E).toBe('1')
|
||||
expect(run.run).toContain(`vitest run --config config/vitest.config.ts ${spec}`)
|
||||
expect(run['continue-on-error']).toBeUndefined()
|
||||
expect(
|
||||
workflow.jobs['changed-e2e'].steps.find((step) => step.name === 'Run changed E2E specs').run
|
||||
).toContain(`. != "${spec}"`)
|
||||
expect(DEDICATED_E2E_SPECS).toContain(spec)
|
||||
for (const changed of [
|
||||
spec,
|
||||
'src/main/browser/ssh-browser-network-execution-route.ts',
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { DEDICATED_E2E_SPECS } from './ci-e2e-job-selection.mjs'
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { createRequire } from 'node:module'
|
||||
import { dirname, join } from 'node:path'
|
||||
@@ -22,7 +23,8 @@ it('gives every removed SSH spec a dedicated owner even for test-only edits', ()
|
||||
const changedRun = workflow.jobs['changed-e2e'].steps.find(
|
||||
(step) => step.name === 'Run changed E2E specs'
|
||||
).run
|
||||
const excluded = [...changedRun.matchAll(/\. != "([^"]+)"/g)].map((match) => match[1])
|
||||
expect(changedRun).toContain('node config/scripts/ci-e2e-job-selection.mjs')
|
||||
const excluded = DEDICATED_E2E_SPECS
|
||||
const owned = runners.flatMap(runnerSpecs)
|
||||
expect(owned.length).toBeGreaterThan(25)
|
||||
expect(new Set(owned).size).toBe(owned.length)
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { DEDICATED_E2E_SPECS } from './ci-e2e-job-selection.mjs'
|
||||
import { existsSync, readFileSync } from 'node:fs'
|
||||
import { resolve } from 'node:path'
|
||||
import { parse } from 'yaml'
|
||||
@@ -30,9 +31,7 @@ it('gives the localhost SSH journey its same-filesystem server and agent prerequ
|
||||
expect(run.run).toContain('--project=electron-headless')
|
||||
expect(run.run).not.toContain('--retries')
|
||||
expect(run['continue-on-error']).toBeUndefined()
|
||||
expect(
|
||||
workflow.jobs['changed-e2e'].steps.find((step) => step.name === 'Run changed E2E specs').run
|
||||
).toContain(`. != "${spec}"`)
|
||||
expect(DEDICATED_E2E_SPECS).toContain(spec)
|
||||
})
|
||||
|
||||
it('selects the localhost journey for its remote hook authorities', () => {
|
||||
|
||||
@@ -5,6 +5,208 @@ unit-selection evidence, headless runtime qualification, review cancellation and
|
||||
|
||||
## October 1 PR concurrency follow-up
|
||||
|
||||
### Where the next gains are
|
||||
|
||||
The [September 30 demand report](https://github.com/stablyai/orca/actions/runs/36816009362)
|
||||
samples 282 of 4,194 runs across workflow/conclusion strata. It estimates full job
|
||||
duration for runs created in the reporting window, rather than occupancy clipped
|
||||
to that window. PR CI accounts for about 537 runner-hours, including about 321
|
||||
hours of unit shards, 73 hours of E2E, 41 hours of Windows packaging, 35 hours of
|
||||
Linux packaging, 18 hours of static analysis, and 11 hours of typechecking. These
|
||||
are weighted estimates, not exact billing totals. Unassigned and incomplete jobs
|
||||
are excluded. The report predates the merged planning/setup change below.
|
||||
|
||||
The [full reference run](https://github.com/stablyai/orca/actions/runs/36841821670)
|
||||
ran 10,310 files exactly once. Across its five shards Vitest reports about 5,063
|
||||
worker-seconds importing modules, 2,838 running tests, 685 transforming source,
|
||||
267 setting up tests, and 390 preparing environments. Workers overlap, so these
|
||||
figures cannot be added to predict job elapsed time. They identify repeated
|
||||
imports and real-time test waits as larger targets than line-count reporting,
|
||||
which uses about 1.1 runner-hours in the same demand sample.
|
||||
|
||||
Parallel steps share the job's CPU and memory. Their
|
||||
[background/wait support](https://github.blog/changelog/2026-06-25-actions-steps-can-now-be-run-in-parallel/)
|
||||
saves repeated runner setup when independent checks fit together, but does not
|
||||
increase machine resources or the account's concurrent-job allowance. Cheap
|
||||
preflight checks still gate expensive unit and package jobs.
|
||||
|
||||
Organization metadata reported the Team plan on October 1. GitHub documents
|
||||
[60 standard concurrent jobs by default](https://docs.github.com/en/actions/reference/limits#job-concurrency-limits-for-github-hosted-runners)
|
||||
and allows support requests for increases. The effective configured allowance
|
||||
was not exposed by the API. A seven-second, repository-only sample at 10:48 UTC
|
||||
found 32 queued jobs and 70 assigned job records marked in progress, including
|
||||
one Blacksmith label. Those non-atomic records, runner turnover, other repositories
|
||||
and provider labels cannot establish the actual allowance or simultaneous usage.
|
||||
These changes reduce demand; they do not change account settings. If queues
|
||||
remain, ask GitHub Support to confirm the effective organization limit before
|
||||
choosing a larger allowance or paid runners.
|
||||
|
||||
The [follow-up PR](https://github.com/stablyai/orca/pull/24355) measures virtual
|
||||
readiness deadlines in captured-transcript tests, E2E allocations with no general
|
||||
consumer, renderer projection, native setup, Docker fixtures, and Windows store
|
||||
restoration. Alternating hosted comparisons check output parity. Completed
|
||||
benchmark workflows and drivers are removed; their trial commits retain the
|
||||
exact reproduction code.
|
||||
|
||||
A [three-pair hosted transcript comparison](https://github.com/stablyai/orca/actions/runs/36849458799)
|
||||
on one four-worker ARM runner measured baseline invocations at 127.001 / 114.307 /
|
||||
114.265 seconds, versus 28.903 / 28.663 / 28.455 seconds with virtual readiness
|
||||
deadlines. Median elapsed time for these five files fell about 75%. All 259
|
||||
original named tests passed in every baseline and candidate, and candidates
|
||||
also passed three repaint checks. Summed test-body time fell from a median 325.85
|
||||
to 31.80 worker-seconds. This comparison includes Vitest startup/import work but
|
||||
excludes checkout, dependency setup, and queues; it is not a measured percentage
|
||||
improvement in the full unit matrix. Real emulator setup and drains remain real,
|
||||
and the same captured bytes, readiness/refusal deadlines, and assertions run.
|
||||
|
||||
The same hosted trial passed three forced Electron native rebuilds while the
|
||||
external node-gyp path pointed to a nonexistent file. A separate fresh consumer
|
||||
then restored the native cache, required a real hit, and passed the existing
|
||||
Electron binary probe. The Linux Node-runtime workaround remains intact.
|
||||
|
||||
For a network-only E2E selection in that trial, both dedicated network jobs
|
||||
passed. The previous allocations consumed 87 seconds for the Electron build,
|
||||
34 for the native primer, and 67 for a general job whose log confirmed that
|
||||
every selected spec belonged to a dedicated lane. The candidate skipped those
|
||||
three jobs before runner allocation, avoiding 188 runner-seconds in this case.
|
||||
This single-case measurement excludes queues and does not predict savings for
|
||||
mixed selections; the existing dedicated SSH, IME, and ordinary E2E routes remain.
|
||||
|
||||
A [controlled cancellation trial](https://github.com/stablyai/orca/actions/runs/36853246785)
|
||||
verified both condition outcomes. After intentional cancellation, `always()`
|
||||
started another 60-second follow-up, while `!cancelled()` skipped it. Cleanup
|
||||
and artifact uploads succeeded in both treatments. A separate deliberately
|
||||
failed test still ran its later `!cancelled()` test and cleanup. The 60 seconds
|
||||
are synthetic condition evidence, not a measurement of a real SSH test's cost.
|
||||
Completed comparison workflows are removed after recording their evidence;
|
||||
the exact drivers and workflow remain reproducible at the trial's source commit.
|
||||
|
||||
The [first full PR validation](https://github.com/stablyai/orca/actions/runs/36849458648)
|
||||
passed all five unit shards and both Linux/Windows package checks. Its reports
|
||||
contain 10,326 unique files, each once, with zero unhandled errors. Full shard
|
||||
job durations ranged from 544 to 581 seconds. They ran a different merged source
|
||||
on different allocations from the earlier reference, so comparing their totals
|
||||
does not establish an end-to-end speedup. The alternating transcript comparison
|
||||
above is the controlled timing evidence.
|
||||
|
||||
The [updated full PR validation](https://github.com/stablyai/orca/actions/runs/36855833565)
|
||||
passed all required gates and both package checks. All 10,335 discovered files
|
||||
appear once across five passing timing reports, with zero unhandled errors;
|
||||
122 modules have the existing expected skipped status. Named merge-tree discovery
|
||||
and saved assignment replay match both successful validation runs. The latest
|
||||
unit jobs took 520–558 seconds. Refreshing weights with that same measurement set
|
||||
would reduce the largest projected load from 1,756.706 to 1,708.187 worker-seconds
|
||||
(2.76%), while retaining the same 8,540.831 total. Applying the earlier successful
|
||||
run's proposed weights to the latest measurements improves the maximum only
|
||||
1.54% and the median 0.68%. These small, variable projections do not establish
|
||||
an elapsed-time gain, so the existing weights remain.
|
||||
|
||||
A [three-pair Windows store comparison](https://github.com/stablyai/orca/actions/runs/36853246494)
|
||||
used fresh dependency trees, stores and pnpm metadata before each treatment. The
|
||||
middle pair reversed order. Cached totals include archive restoration and both
|
||||
unchanged frozen installs; the mobile install ran every existing postinstall
|
||||
generator. Setup/reset time and runner queues are excluded.
|
||||
|
||||
| Pair | First treatment | Cached total | Registry total | Registry saving |
|
||||
| ---- | --------------- | ------------ | -------------- | --------------- |
|
||||
| 1 | Cached | 71.092s | 37.500s | 33.592s |
|
||||
| 2 | Registry | 73.556s | 39.935s | 33.621s |
|
||||
| 3 | Cached | 75.660s | 37.001s | 38.659s |
|
||||
|
||||
Treatment medians were 73.556s cached and 37.500s registry; median paired saving
|
||||
was 33.621s. Cache restore and step overhead alone cost a median 27.955s. Policy
|
||||
and all six generated-output digests matched across all six treatments. Windows
|
||||
x64 PR jobs using the mixed root/mobile key now skip its download-store restore;
|
||||
PRs already skip store saves. Root-only Windows stores, Windows ARM64/x86, other
|
||||
operating systems, non-PR writers, native/Electron caches and frozen-install policy retain their existing
|
||||
behavior. The trial covers this mixed install on Windows 2022, not every Windows
|
||||
dependency key or a whole PR's elapsed time.
|
||||
|
||||
A [three-pair daemon fixture comparison](https://github.com/stablyai/orca/actions/runs/36853246776)
|
||||
reset Docker build caches and the fixture/base image before every treatment.
|
||||
Warm totals include the existing action's archive restore/load and the unchanged
|
||||
daemon descendant oracle; reset time and runner queues are excluded. The middle
|
||||
pair again reversed order.
|
||||
|
||||
| Pair | First treatment | Cold total | Warm total | Warm saving |
|
||||
| ---- | --------------- | ---------- | ---------- | ----------- |
|
||||
| 1 | Cold | 28.984s | 20.673s | 8.311s |
|
||||
| 2 | Warm | 21.798s | 28.953s | -7.155s |
|
||||
| 3 | Cold | 28.964s | 17.614s | 11.350s |
|
||||
|
||||
Treatment medians were 28.964s cold and 20.673s warm; median paired saving was
|
||||
8.311s. Oracle medians fell from 28.886s to 4.907s, while archive restore/load
|
||||
cost 13.025–24.024s (15.766s median) for a 714,643,456-byte archive. BuildKit
|
||||
confirmed warm provisioning was cached and cold provisioning was not; every
|
||||
treatment used the same immutable base image, reaped the descendant and kept
|
||||
the canary alive. The PR keeps restoration in the background during root/mobile
|
||||
installation. One serial pair was slower, so the roughly 24s oracle reduction
|
||||
is not a guaranteed total runner saving. The drivers and exact workflows remain
|
||||
available at source commit `9231d1be6c76ccc1d2fef741a4e68ae29735a5c8`.
|
||||
|
||||
A [three-pair AppImage compression comparison](https://github.com/stablyai/orca/actions/runs/36855833100)
|
||||
packaged the same complete Linux x64 app with the pinned 1.0.3 toolset and
|
||||
mksquashfs 4.6.1. Each timing includes the private app copy, electron-builder
|
||||
and blockmap generation. Tool download, app compilation, extraction, parity
|
||||
checks and queues are excluded; the middle pair reversed order.
|
||||
|
||||
| Pair | First treatment | Default zstd 15 | PR zstd 3 | Saving |
|
||||
| ---- | --------------- | --------------- | --------- | ------- |
|
||||
| 1 | Default | 22.580s | 11.760s | 10.820s |
|
||||
| 2 | PR | 22.612s | 12.560s | 10.052s |
|
||||
| 3 | Default | 22.512s | 11.815s | 10.697s |
|
||||
|
||||
Median packaging time fell from 22.580s to 11.815s (47.7%); median package size
|
||||
grew from 213,873,601 to 237,570,611 bytes (11.1%). All six extracted manifests
|
||||
matched every path, byte, mode and symlink target: 4,096 files and 601,194,650
|
||||
file bytes. The runtime prefix matched the pinned runtime exactly, and stored
|
||||
SquashFS options confirmed the actual level-3 override. All static checks passed;
|
||||
the representative baseline and candidate each passed the unchanged headless
|
||||
and CLI journeys, including all entrypoints and both shutdown signals. The
|
||||
directory build passed the existing glibc floor checks on all 19 native binaries.
|
||||
|
||||
Only the PR Linux x64 AppImage child receives the private tool overlay. It resolves
|
||||
the existing custom-tool override first, checks the pinned tool/version and zstd
|
||||
configuration, and reuses the original runtime, validator and libraries. Cleanup
|
||||
waits for every package worker even on failure. Release settings, Linux ARM,
|
||||
Debian/RPM packaging and all native/package gates retain their existing behavior.
|
||||
The isolated AppImage result does not establish the full three-format job's gain.
|
||||
|
||||
The same hosted comparison projected one already-built renderer three times per
|
||||
treatment, again alternating order. Baseline times were 8.079 / 8.219 / 8.129s;
|
||||
candidate times were 2.568 / 2.477 / 2.403s. Median projection fell from 8.129s to
|
||||
2.477s (69.5%, 5.653s saved). All six web snapshots matched all 1,137 files and
|
||||
51,957,014 bytes, and the renderer input remained unchanged after every run.
|
||||
These timings include the projector process but exclude renderer compilation,
|
||||
checkout, setup and queues. The drivers and workflow remain available at source
|
||||
commit `8ba5c9bf9f734d585f5e89945519aef4f607face`.
|
||||
|
||||
Two local cache screens do not justify enabling Node's compile cache. A 96-file
|
||||
screen with an explicit worker flush produced a small, noisy difference. A larger
|
||||
256-file screen retained all 2,088 tests: baseline elapsed times were
|
||||
54.630 / 55.105 / 55.171 seconds, fresh caches 53.719 / 54.577, and a warm cache
|
||||
53.732. The roughly 1.7% median difference is too small to justify cache transfer
|
||||
and another test hook without stronger hosted evidence.
|
||||
|
||||
Vitest 4.1.11's experimental filesystem module cache is more promising locally,
|
||||
but raw reuse is unsafe. A 96-file screen fell from about 8.4 to 5.9 seconds with
|
||||
a warm cache, while a cold cache cost about 3%. Negative controls then reproduced
|
||||
false passes after adding a preferred import extension, retargeting a symlink,
|
||||
changing package exports, or changing transform inputs. Cache-disabled controls
|
||||
failed correctly. A cache key must cover resolution and transform inputs as well
|
||||
as file contents before any production trial; source hashes alone do not suffice.
|
||||
|
||||
Affected-test selection remains in shadow mode. Its first merge was September
|
||||
28, so October 1 cannot satisfy the documented week of evidence. Seven sampled
|
||||
complete reference reports included one red run, but only two evaluated a smaller
|
||||
candidate set; each omitted about 177–179 worker-seconds out of 8,073–8,392. Five
|
||||
full fallbacks are not selection-validation evidence, and two other sampled red
|
||||
runs had no review artifact. These samples support keeping the conservative
|
||||
policy, rather than claiming that omitting roughly 12% of files would omit the
|
||||
same fraction of work.
|
||||
|
||||
### Shared planning and typechecking
|
||||
|
||||
PR planning now shares checkout and dependency setup with typechecking. Planning
|
||||
runs in the background, with an explicit failure-propagating join before its
|
||||
artifact is published. Static analysis remains on a separate runner. Its existing
|
||||
@@ -590,3 +792,180 @@ only one potential idle allocation per day, and active development usually
|
||||
requires that build. Defer another release-graph change until skip frequency
|
||||
justifies it. The substantive remaining release occupancy opportunity is the
|
||||
separately documented asynchronous signing policy decision.
|
||||
|
||||
## Persistent Vitest transform cache: rejected for now
|
||||
|
||||
A local 96-file import-heavy sample with Vitest 4.1.11 took 8.31/8.53 seconds
|
||||
without its filesystem module cache, 8.63/8.69 seconds cold, and 5.91/5.91
|
||||
seconds warm: about 30% faster warm. The cache held 3,770 modules and 83 MiB.
|
||||
These timings exclude hosted cache transfer and do not establish a PR saving.
|
||||
|
||||
Correctness probes found eight changes that incorrectly kept a test passing
|
||||
against the old transformed import or compiler output:
|
||||
|
||||
| Change after warming | Raw cache | Startup fingerprint |
|
||||
| ----------------------------------------------------------------- | ---------- | ------------------- |
|
||||
| Add preferred `value.js` beside previously resolved `value.ts` | False pass | Correctly fails |
|
||||
| Retarget a source symlink while its old target still exists | False pass | Correctly fails |
|
||||
| Change an inlined package's `exports` to another existing file | False pass | Correctly fails |
|
||||
| Add a preferred extension in a generated source directory | False pass | Correctly fails |
|
||||
| Change TypeScript's JSX factory in `tsconfig.json` | False pass | Correctly fails |
|
||||
| Create the preferred file from setup after startup fingerprinting | False pass | False pass |
|
||||
| Add a preferred file inside an external symlinked directory | False pass | False pass |
|
||||
| Change an external file read by a transform plugin | False pass | False pass |
|
||||
|
||||
The fingerprint included file names/types, symlink targets, package/config/
|
||||
TypeScript metadata contents, and effective alias/define options. Following
|
||||
external symlink inventories and hashing declared transform inputs repaired the
|
||||
last two rows, but did not repair files created after fingerprinting. All ten
|
||||
cache-disabled changed-input controls failed correctly; initial and repeated
|
||||
warm controls passed. Effective alias and simple define changes also invalidated
|
||||
correctly without the added fingerprint.
|
||||
|
||||
The [Vitest 4.1.11 documentation](https://github.com/vitest-dev/vitest/blob/v4.1.11/docs/config/experimental.md#known-issues)
|
||||
documents incomplete plugin-input tracking. Its
|
||||
[cache implementation](https://github.com/vitest-dev/vitest/blob/v4.1.11/packages/vitest/src/node/cache/fsModuleCache.ts)
|
||||
hashes the module and selected configuration, but retains previously resolved
|
||||
import URLs. [Upstream fix #11381](https://github.com/vitest-dev/vitest/pull/11381)
|
||||
merged September 29 and revalidates those URLs. A disposable Vitest 5.0.3 probe,
|
||||
which contains that fix, reproduced all eight false-pass categories: the old
|
||||
target still exists, so checking its resolved URL misses a newly preferred file
|
||||
or changed package export. Upgrading alone does not make reuse safe.
|
||||
|
||||
To reproduce the simplest negative control outside the worktree:
|
||||
|
||||
1. Create `value.ts` containing `export const value = 1`, and a test importing
|
||||
`./value` and asserting `expect(value).toBe(1)`. Use an isolated config/cache,
|
||||
one fork worker, `ORCA_BACKGROUND_LAUNCH=1`, and
|
||||
`NODE_DISABLE_COMPILE_CACHE=1`.
|
||||
2. Run the installed CLI with `--experimental.fsModuleCache=true` to warm it.
|
||||
Add `value.js` containing `export const value = 2`; retain `value.ts` and the
|
||||
unchanged test. The same cached invocation incorrectly passes.
|
||||
3. Repeat with `--experimental.fsModuleCache=false`. The assertion correctly
|
||||
fails. Vitest 5 uses `--fsModuleCache` for the equivalent controls.
|
||||
4. For the startup-inventory control, use unchanged setup code that creates
|
||||
`value.js` only when a runtime environment switch is enabled. Remove that
|
||||
file before each invocation/fingerprint; warm with the switch off, then run
|
||||
with it on. The cached importer still points at `value.ts`, while the fresh
|
||||
module graph correctly fails. This is an additional persistent-cache error,
|
||||
not a claim that normal in-process module reuse supports arbitrary mutation.
|
||||
|
||||
Orca currently resolves only pinned Vitest/Vite built-in transform plugins.
|
||||
Its setup files install runtime guards/shims and temporary user data, rather
|
||||
than custom transforms. A narrower policy could cache only proven immutable
|
||||
source/dependency inputs and leave tests, setup, virtual modules, external
|
||||
fixtures, and unknown plugins cold. That requires a validated transitive input
|
||||
boundary and mutation policy; hashing every source tree on each lookup would
|
||||
also spend the gain. Until that policy and hosted transfer cost are measured,
|
||||
the local warm result does not justify adding a persistent cache to CI.
|
||||
|
||||
## Test fixture imports: reuse the existing narrow builder
|
||||
|
||||
The pointer-drag test imported only `makeWorktree` from `store-test-helpers`,
|
||||
which also loads the real store slices. Its existing identical export in
|
||||
`worktrees-slice-test-fixtures` supplies the same defaults without that graph.
|
||||
Changing this single import preserves the five tests, fork workers,
|
||||
isolation, and disabled filesystem/Node compile caches.
|
||||
|
||||
Three local interleaved before/after pairs took 2.066/2.047/2.031 seconds versus
|
||||
0.351/0.388/0.353 seconds: the isolated median fell 82.7%, from 2.047 to 0.353
|
||||
seconds. Transformed modules fell from 1,086 to 15. This is an isolated test
|
||||
result, not a whole-shard estimate: other tests need the store modules anyway.
|
||||
A broader 20-file screening sample saved only 0.295 seconds at its median,
|
||||
which does not justify splitting the fixture module across those consumers.
|
||||
|
||||
Two further import-only reuses passed the same six-run controls. The kanban
|
||||
lane test mocks its card component, so switching its builder import reduced
|
||||
the isolated median from 2.202 to 0.495 seconds (77.5%) and transformed modules
|
||||
from 1,082 to 13, with all six tests unchanged. The autosave fixture needs
|
||||
the real editor slice, but not every store slice: the same import change across
|
||||
its three consuming suites reduced the median from 3.027 to 1.301 seconds
|
||||
(57.0%), with 1,107 to 320 modules and all 17 tests unchanged. These
|
||||
results also measure isolated file groups; they are not additive shard savings.
|
||||
The remaining inspected builder-only imports already load the full store as
|
||||
their subject, or use builders whose defaults differ from existing exports.
|
||||
|
||||
## Vitest threads: retain forks after the scoped pilot
|
||||
|
||||
Three local interleaved comparisons kept four workers, `isolate: true`, both
|
||||
persistent caches disabled, and the same test assertions/module graph. The
|
||||
94-file happy-dom renderer cohort passed all 570 tests: forks took
|
||||
17.480/17.382/17.657 seconds and threads 15.048/14.890/15.013 seconds, a 14.1%
|
||||
median reduction. A 23-file shared JavaScript cohort passed all 248 tests,
|
||||
with its median falling from 1.435 to 1.274 seconds (11.2%). No main-process
|
||||
module or native addon loaded; guards reject native loading, `chdir`, and
|
||||
process signals. These Mac/Node 24 timings motivated the hosted comparison.
|
||||
|
||||
The [pinned Vitest pool documentation](https://github.com/vitest-dev/vitest/blob/v4.1.11/docs/config/pool.md)
|
||||
defaults to forks and documents thread limitations around process APIs and
|
||||
native libraries. [Node's worker documentation](https://nodejs.org/docs/latest-v24.x/api/worker_threads.html#new-workerfilename-options)
|
||||
also excludes V8 flags from worker `execArgv`. Orca's `--expose-gc` worker flag
|
||||
fails with `ERR_WORKER_INVALID_EXEC_ARGV` under threads. The experiment starts
|
||||
both parent processes with that flag, retains it on fork workers, and removes
|
||||
it only from thread worker arguments; GC availability is checked in every
|
||||
test environment. Process, native, lifecycle, and GC-retention tests stay out
|
||||
of this comparison.
|
||||
|
||||
The [hosted pilot](https://github.com/stablyai/orca/actions/runs/36855833033)
|
||||
passed on Linux ARM64, four CPUs, Node 24.21.0, and Ubuntu image
|
||||
`20260927.135.1`. Three alternating pairs preserved source hashes and complete
|
||||
module graphs, with no main-process module or native addon loaded:
|
||||
|
||||
| Audited cohort | Forks, seconds | Threads, seconds | Median saving |
|
||||
| -------------------------------------- | ------------------------ | ------------------------ | --------------------- |
|
||||
| 94 renderer files / 570 tests | 48.591 / 48.144 / 47.299 | 42.486 / 42.402 / 42.221 | 5.742 seconds (11.9%) |
|
||||
| 23 shared JavaScript files / 248 tests | 3.386 / 3.330 / 3.424 | 3.203 / 3.237 / 3.278 | 0.149 seconds (4.4%) |
|
||||
|
||||
Each timed group also included two isolation sentinels: totals were 96 files /
|
||||
572 tests and 25 files / 250 tests, respectively, with no skips.
|
||||
Their graph hashes matched in every pair (4,015 and 251 modules). Separate
|
||||
single-worker positive controls passed both sentinels in each pool. With
|
||||
isolation disabled, the second sentinel correctly failed on leaked state.
|
||||
Missing GC failed setup, and native loading, `chdir`, and process-signal probes
|
||||
failed at the guard in both pools. Those expected failures did not pass silently.
|
||||
|
||||
The fixed 117-file sample accounts for about 1.5% of the baseline's aggregate
|
||||
module time; its isolated gains are not a whole-suite estimate. Maintaining
|
||||
that exact file list for this benefit is not justified. A broader route needs
|
||||
a safe eligibility policy, Node 26/Windows evidence, and a mixed full-shard
|
||||
comparison: separate Vitest projects can repeat shared transforms and erase
|
||||
the pool-startup saving. A renderer path alone does not prove that future
|
||||
imports avoid process or native behavior. Production retains forks, and the
|
||||
temporary workflow, driver, and cohort list were removed after measurement.
|
||||
|
||||
## Oxlint scan consolidation: rejected
|
||||
|
||||
The [hosted comparison](https://github.com/stablyai/orca/actions/runs/36855833063)
|
||||
used one Linux ARM64/four-CPU runner, Node 24.21.0, and three alternating
|
||||
baseline/candidate pairs. The baseline kept root lint and anti-slop in parallel,
|
||||
then native and type-aware audits in parallel. The candidate merged the first
|
||||
three scans and ran the unchanged type-aware audit alongside them.
|
||||
|
||||
| Pair/order | Baseline stage | Candidate stage | Change |
|
||||
| ------------------ | -------------- | --------------- | ------ |
|
||||
| 1: baseline first | 49.409 s | 53.197 s | +7.7% |
|
||||
| 2: candidate first | 50.249 s | 60.297 s | +20.0% |
|
||||
| 3: baseline first | 50.040 s | 56.672 s | +13.3% |
|
||||
| Median | 50.040 s | 56.672 s | +13.3% |
|
||||
|
||||
These complete stage timings include anti-slop synchronization in both variants
|
||||
and candidate configuration generation. Candidate preparation took only
|
||||
0.141–0.255 seconds. The unchanged type-aware scan took 16.386–17.279 seconds
|
||||
in the baseline wave, versus 33.561–55.736 seconds beside the merged scan;
|
||||
these timings are consistent with contention on the four-CPU runner.
|
||||
|
||||
The corrected local Mac/16-CPU comparison had reduced the median from 16.676
|
||||
to 14.381 seconds (13.8%). Both comparisons limited each Oxlint invocation to
|
||||
four threads and used identical source configuration hashes. The hosted result
|
||||
shows why the local gain did not justify adoption on the actual CI runner.
|
||||
|
||||
Coverage controls passed: the merged scan matched the exact 28,621-file union
|
||||
with no missing or extra files. Thirty-one fault fixture files produced the
|
||||
exact 16-diagnostic union, including all seven active root JavaScript rules.
|
||||
Eighteen focused controls preserved nested-mobile exemptions, type-aware
|
||||
exclusions, and exit behavior. The native audit's warnings still failed its
|
||||
original `--deny-warnings` gate and became errors in the merged scan; root
|
||||
warnings remained non-fatal. Every full-repository scan passed cleanly.
|
||||
|
||||
Keep the existing production waves. The temporary workflow and 601-line
|
||||
benchmark driver were removed after recording this rejected result.
|
||||
|
||||
@@ -91,3 +91,22 @@ export async function createTranscriptPane(
|
||||
}
|
||||
return { runtime, handle: terminal.handle }
|
||||
}
|
||||
|
||||
/** Advance readiness deadlines after real pane creation and emulator drains. */
|
||||
export async function waitForTranscriptIdle(
|
||||
pane: Awaited<ReturnType<typeof createTranscriptPane>>,
|
||||
timeoutMs: number
|
||||
) {
|
||||
vi.useFakeTimers({
|
||||
toFake: ['Date', 'setTimeout', 'clearTimeout', 'setInterval', 'clearInterval']
|
||||
})
|
||||
try {
|
||||
const waiting = pane.runtime.waitForTerminal(pane.handle, { condition: 'tui-idle', timeoutMs })
|
||||
// Expected refusals must have a rejection handler before advancing their deadline.
|
||||
void waiting.catch(() => {})
|
||||
await vi.advanceTimersByTimeAsync(timeoutMs)
|
||||
return await waiting
|
||||
} finally {
|
||||
vi.useRealTimers()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,5 +1,9 @@
|
||||
import { describe, expect, it, vi } from 'vitest'
|
||||
import { createTranscriptPane, TRANSCRIPT_PANE_PTY_ID } from './agent-transcript-pane-test-harness'
|
||||
import {
|
||||
createTranscriptPane,
|
||||
TRANSCRIPT_PANE_PTY_ID,
|
||||
waitForTranscriptIdle
|
||||
} from './agent-transcript-pane-test-harness'
|
||||
import {
|
||||
readRuntimeFixture,
|
||||
replayTranscript,
|
||||
@@ -200,13 +204,15 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
|
||||
describe('through the runtime', () => {
|
||||
async function codexPane(name: string, size?: { cols: number; rows: number }) {
|
||||
return createTranscriptPane({
|
||||
const created = await createTranscriptPane({
|
||||
paneTitle: 'Terminal',
|
||||
foregroundProcess: 'codex',
|
||||
launchAgent: 'codex',
|
||||
data: readRuntimeFixture(name),
|
||||
size
|
||||
})
|
||||
await created.runtime.readTerminal(created.handle, { screen: true })
|
||||
return created
|
||||
}
|
||||
|
||||
it.each(ALL_FIXTURES)(
|
||||
@@ -214,9 +220,10 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
async (name) => {
|
||||
const { runtime, handle } = await codexPane(name, { cols: 120, rows: 40 })
|
||||
// Why 8s: quiescence (3s) plus the 2s poll re-reading the grid.
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 8_000 })
|
||||
).resolves.toMatchObject({ condition: 'tui-idle', satisfied: true })
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 8_000)).resolves.toMatchObject({
|
||||
condition: 'tui-idle',
|
||||
satisfied: true
|
||||
})
|
||||
},
|
||||
15_000
|
||||
)
|
||||
@@ -235,10 +242,9 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
data: provisional,
|
||||
size: { cols: 120, rows: 40 }
|
||||
})
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
// Why 6s: past the 3s quiescence, so the quiet lane's provisional veto is what holds.
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 6_000 })
|
||||
).rejects.toThrow(/timeout/)
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 6_000)).rejects.toThrow(/timeout/)
|
||||
}, 15_000)
|
||||
|
||||
// Why no bytes: worker-start waits on a pane that has printed nothing yet, which is when the
|
||||
@@ -251,6 +257,7 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
data: '',
|
||||
size: { cols: 120, rows: 40 }
|
||||
})
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
const readVisibleScreen = vi.spyOn(runtime, 'readTerminal').mockResolvedValue({
|
||||
handle,
|
||||
status: 'running',
|
||||
@@ -267,9 +274,7 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
nextCursor: null,
|
||||
source: 'screen'
|
||||
})
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 2_500 })
|
||||
).rejects.toThrow(/timeout/)
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 2_500)).rejects.toThrow(/timeout/)
|
||||
// Presence precondition: the visible-screen probe actually ran.
|
||||
expect(readVisibleScreen).toHaveBeenCalled()
|
||||
}, 15_000)
|
||||
@@ -282,6 +287,7 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
launchAgent: 'codex',
|
||||
data: ''
|
||||
})
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
runtime.seedTerminalRestoreTail(TRANSCRIPT_PANE_PTY_ID, {
|
||||
text: [
|
||||
'╭──────────────────────────────────────────╮',
|
||||
@@ -302,16 +308,15 @@ describe('Codex 0.157 header readiness from captured bytes', () => {
|
||||
nextCursor: null,
|
||||
source: 'screen-unavailable'
|
||||
})
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 2_500 })
|
||||
).resolves.toMatchObject({ condition: 'tui-idle', satisfied: true })
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 2_500)).resolves.toMatchObject({
|
||||
condition: 'tui-idle',
|
||||
satisfied: true
|
||||
})
|
||||
}, 15_000)
|
||||
|
||||
it('keeps timing out on the garbled 80x24 default grid, as before', async () => {
|
||||
const { runtime, handle } = await codexPane(EFFORT_OVERRIDE)
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 6_000 })
|
||||
).rejects.toThrow(/timeout/)
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 6_000)).rejects.toThrow(/timeout/)
|
||||
}, 15_000)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -2,7 +2,7 @@ import { readFileSync } from 'node:fs'
|
||||
import { join } from 'node:path'
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import type { TuiAgent } from '../../shared/tui-agent'
|
||||
import { createTranscriptPane } from './agent-transcript-pane-test-harness'
|
||||
import { createTranscriptPane, waitForTranscriptIdle } from './agent-transcript-pane-test-harness'
|
||||
import {
|
||||
readRuntimeFixture,
|
||||
replayTranscript,
|
||||
@@ -435,21 +435,24 @@ describe('through the runtime', () => {
|
||||
// Why 0.158 alone: its header carries no `model:`, so only this lane settles it.
|
||||
const CODEX_0158 = 'codex-0-158-0-timed-turn'
|
||||
async function pane(name: string, launchAgent: TuiAgent, size?: { cols: number; rows: number }) {
|
||||
return createTranscriptPane({
|
||||
const created = await createTranscriptPane({
|
||||
paneTitle: 'Terminal',
|
||||
foregroundProcess: launchAgent,
|
||||
launchAgent,
|
||||
data: readRuntimeFixture(name),
|
||||
size
|
||||
})
|
||||
await created.runtime.readTerminal(created.handle, { screen: true })
|
||||
return created
|
||||
}
|
||||
|
||||
// Why 8s: quiescence (3s) plus the 2s poll re-reading the grid.
|
||||
it('codex 0.158: a tui-idle wait settles once the composer is quiet', async () => {
|
||||
const { runtime, handle } = await pane(CODEX_0158, 'codex', { cols: 120, rows: 40 })
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 8_000 })
|
||||
).resolves.toMatchObject({ condition: 'tui-idle', satisfied: true })
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 8_000)).resolves.toMatchObject({
|
||||
condition: 'tui-idle',
|
||||
satisfied: true
|
||||
})
|
||||
}, 15_000)
|
||||
|
||||
it('keeps a Claude pane showing the same screen pending', async () => {
|
||||
@@ -457,8 +460,6 @@ describe('through the runtime', () => {
|
||||
cols: 120,
|
||||
rows: 40
|
||||
})
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 6_000 })
|
||||
).rejects.toThrow(/timeout/)
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 6_000)).rejects.toThrow(/timeout/)
|
||||
}, 15_000)
|
||||
})
|
||||
|
||||
@@ -1,6 +1,10 @@
|
||||
// One replay suite for every agent whose readiness its live screen decides (terminal-wait-detection.ts).
|
||||
import { describe, expect, it, vi } from 'vitest'
|
||||
import { createTranscriptPane, TRANSCRIPT_PANE_PTY_ID } from './agent-transcript-pane-test-harness'
|
||||
import {
|
||||
createTranscriptPane,
|
||||
TRANSCRIPT_PANE_PTY_ID,
|
||||
waitForTranscriptIdle
|
||||
} from './agent-transcript-pane-test-harness'
|
||||
import {
|
||||
finalReadProjection,
|
||||
finalReplayFrame,
|
||||
@@ -96,8 +100,11 @@ export function describeScreenRuledAgentTranscripts(suite: ScreenRuledAgentSuite
|
||||
async (fixture) => {
|
||||
const { runtime, handle } = await pane(fixture)
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: READY_TIMEOUT_MS })
|
||||
).resolves.toMatchObject({ condition: 'tui-idle', satisfied: true })
|
||||
waitForTranscriptIdle({ runtime, handle }, READY_TIMEOUT_MS)
|
||||
).resolves.toMatchObject({
|
||||
condition: 'tui-idle',
|
||||
satisfied: true
|
||||
})
|
||||
},
|
||||
READY_TIMEOUT_MS + PANE_SETUP_SLACK_MS
|
||||
)
|
||||
@@ -106,9 +113,9 @@ export function describeScreenRuledAgentTranscripts(suite: ScreenRuledAgentSuite
|
||||
'$name: a tui-idle wait does not settle ready',
|
||||
async (fixture) => {
|
||||
const { runtime, handle } = await pane(fixture)
|
||||
const result = await runtime
|
||||
.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: REFUSAL_TIMEOUT_MS })
|
||||
.catch((error: unknown) => ({ satisfied: false, error: String(error) }))
|
||||
const result = await waitForTranscriptIdle({ runtime, handle }, REFUSAL_TIMEOUT_MS).catch(
|
||||
(error: unknown) => ({ satisfied: false, error: String(error) })
|
||||
)
|
||||
expect(result.satisfied).toBe(false)
|
||||
},
|
||||
REFUSAL_TIMEOUT_MS + PANE_SETUP_SLACK_MS
|
||||
@@ -128,9 +135,9 @@ export function describeScreenRuledAgentTranscripts(suite: ScreenRuledAgentSuite
|
||||
const { runtime, handle } = await createTranscriptPane(options)
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
options.size = { cols: fixture.cols, rows: fixture.rows }
|
||||
const result = await runtime
|
||||
.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: READY_TIMEOUT_MS })
|
||||
.catch(() => ({ satisfied: false }))
|
||||
const result = await waitForTranscriptIdle({ runtime, handle }, READY_TIMEOUT_MS).catch(
|
||||
() => ({ satisfied: false })
|
||||
)
|
||||
expect(result.satisfied).toBe(suite.readyWithoutScreen.includes(fixture.name))
|
||||
},
|
||||
READY_TIMEOUT_MS + PANE_SETUP_SLACK_MS
|
||||
@@ -157,9 +164,9 @@ export function describeScreenRuledAgentTranscripts(suite: ScreenRuledAgentSuite
|
||||
// Why: an echo of the reflowed size sends no SIGWINCH, so nothing repaints.
|
||||
runtime.onExternalPtyResize(TRANSCRIPT_PANE_PTY_ID, firstReady.cols, firstReady.rows)
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
const result = await runtime
|
||||
.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: READY_TIMEOUT_MS })
|
||||
.catch(() => ({ satisfied: false }))
|
||||
const result = await waitForTranscriptIdle({ runtime, handle }, READY_TIMEOUT_MS).catch(
|
||||
() => ({ satisfied: false })
|
||||
)
|
||||
expect(result.satisfied).toBe(suite.readyWithoutScreen.includes(firstReady.name))
|
||||
},
|
||||
READY_TIMEOUT_MS + PANE_SETUP_SLACK_MS
|
||||
@@ -184,9 +191,9 @@ export function describeScreenRuledAgentTranscripts(suite: ScreenRuledAgentSuite
|
||||
nextCursor: null,
|
||||
source: 'screen'
|
||||
})
|
||||
const result = await runtime
|
||||
.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 2_500 })
|
||||
.catch(() => ({ satisfied: false }))
|
||||
const result = await waitForTranscriptIdle({ runtime, handle }, 2_500).catch(() => ({
|
||||
satisfied: false
|
||||
}))
|
||||
// Presence precondition: the visible-screen probe actually ran.
|
||||
expect(read).toHaveBeenCalled()
|
||||
return result.satisfied === true
|
||||
@@ -207,6 +214,33 @@ export function describeScreenRuledAgentTranscripts(suite: ScreenRuledAgentSuite
|
||||
},
|
||||
15_000
|
||||
)
|
||||
|
||||
it('waits for quiet again after a ready pane repaints', async () => {
|
||||
const { runtime, handle } = await pane(firstReady)
|
||||
vi.useFakeTimers({
|
||||
toFake: ['Date', 'setTimeout', 'clearTimeout', 'setInterval', 'clearInterval']
|
||||
})
|
||||
try {
|
||||
const settled = vi.fn()
|
||||
const waiting = runtime.waitForTerminal(handle, {
|
||||
condition: 'tui-idle',
|
||||
timeoutMs: READY_TIMEOUT_MS
|
||||
})
|
||||
void waiting.then(settled, () => {})
|
||||
await vi.advanceTimersByTimeAsync(2_000)
|
||||
expect(settled).not.toHaveBeenCalled()
|
||||
|
||||
runtime.onPtyData(TRANSCRIPT_PANE_PTY_ID, readRuntimeFixture(firstReady.name), Date.now())
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
await vi.advanceTimersByTimeAsync(2_000)
|
||||
expect(settled).not.toHaveBeenCalled()
|
||||
|
||||
await vi.advanceTimersByTimeAsync(2_000)
|
||||
await expect(waiting).resolves.toMatchObject({ condition: 'tui-idle', satisfied: true })
|
||||
} finally {
|
||||
vi.useRealTimers()
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
it('never reads the screen for another agent', async () => {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, expect, it, vi } from 'vitest'
|
||||
import { createTranscriptPane } from './agent-transcript-pane-test-harness'
|
||||
import { createTranscriptPane, waitForTranscriptIdle } from './agent-transcript-pane-test-harness'
|
||||
import { readRuntimeFixture } from './agent-transcript-replay-test-harness'
|
||||
|
||||
vi.mock('electron', () => ({
|
||||
@@ -24,8 +24,9 @@ describe('screen-rule trust stays with screen-ruled agents', () => {
|
||||
const { runtime, handle } = await createTranscriptPane(options)
|
||||
await runtime.readTerminal(handle, { screen: true })
|
||||
options.size = { cols: 100, rows: 30 }
|
||||
await expect(
|
||||
runtime.waitForTerminal(handle, { condition: 'tui-idle', timeoutMs: 8_000 })
|
||||
).resolves.toMatchObject({ condition: 'tui-idle', satisfied: true })
|
||||
await expect(waitForTranscriptIdle({ runtime, handle }, 8_000)).resolves.toMatchObject({
|
||||
condition: 'tui-idle',
|
||||
satisfied: true
|
||||
})
|
||||
}, 20_000)
|
||||
})
|
||||
|
||||
@@ -5,7 +5,7 @@ import { vi } from 'vitest'
|
||||
import { createStore, type StoreApi } from 'zustand/vanilla'
|
||||
import { createEditorSlice } from '@/store/slices/editor'
|
||||
import type { AppState } from '@/store'
|
||||
import { makeWorktree } from '@/store/slices/store-test-helpers'
|
||||
import { makeWorktree } from '@/store/slices/worktrees-slice-test-fixtures'
|
||||
|
||||
export type FakeEditorDisk = {
|
||||
files: Map<string, string>
|
||||
|
||||
@@ -14,7 +14,7 @@ import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import type { Repo } from '../../../../shared/repo-types'
|
||||
import type { Worktree } from '../../../../shared/worktree/types'
|
||||
import { getWorktreeHostIdentity } from '../../../../shared/worktree/host-qualified-identity'
|
||||
import { makeWorktree } from '../../store/slices/store-test-helpers'
|
||||
import { makeWorktree } from '../../store/slices/worktrees-slice-test-fixtures'
|
||||
|
||||
const WINDOW_START = 20
|
||||
const WINDOW_END = 25
|
||||
|
||||
@@ -3,7 +3,7 @@ import {
|
||||
resolveWorkspaceKanbanPointerDragSelection,
|
||||
shouldStartWorkspaceKanbanCardPointerDrag
|
||||
} from './use-workspace-kanban-card-pointer-drag'
|
||||
import { makeWorktree } from '../../store/slices/store-test-helpers'
|
||||
import { makeWorktree } from '../../store/slices/worktrees-slice-test-fixtures'
|
||||
|
||||
function pointerEvent(overrides: Partial<PointerEvent> = {}): PointerEvent {
|
||||
return {
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest'
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
|
||||
import { sendFollowupPromptWhenAgentReady } from './agent-followup-delivery'
|
||||
import {
|
||||
inspectRuntimeTerminalProcess,
|
||||
@@ -21,11 +21,17 @@ const INTERPRETER_WRAPPED_AGENTS = [
|
||||
describe('sendFollowupPromptWhenAgentReady — interpreter-wrapped agents', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
vi.useFakeTimers({ toFake: ['setTimeout', 'clearTimeout'] })
|
||||
vi.stubGlobal('globalThis', globalThis)
|
||||
// Deliver the prompt write eagerly so the test does not depend on retries.
|
||||
vi.mocked(sendRuntimePtyInputVerified).mockResolvedValue(true)
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
vi.useRealTimers()
|
||||
vi.unstubAllGlobals()
|
||||
})
|
||||
|
||||
for (const { agent, expectedProcess } of INTERPRETER_WRAPPED_AGENTS) {
|
||||
it(`types the prompt once ${agent} is up behind a python3 wrapper with a live child`, async () => {
|
||||
// The console-script agent is running: foreground comm is python3 and the
|
||||
@@ -35,13 +41,16 @@ describe('sendFollowupPromptWhenAgentReady — interpreter-wrapped agents', () =
|
||||
hasChildProcesses: true
|
||||
})
|
||||
|
||||
const delivered = await sendFollowupPromptWhenAgentReady({
|
||||
const delivery = sendFollowupPromptWhenAgentReady({
|
||||
ptyId: 'pty-1',
|
||||
expectedProcess,
|
||||
prompt: 'ship it',
|
||||
settings: null
|
||||
})
|
||||
|
||||
await vi.advanceTimersByTimeAsync(4 * 150)
|
||||
const delivered = await delivery
|
||||
|
||||
expect(delivered).toBe(true)
|
||||
expect(sendRuntimePtyInputVerified).toHaveBeenCalledWith(null, 'pty-1', 'ship it\r', 'launch')
|
||||
})
|
||||
@@ -54,13 +63,16 @@ describe('sendFollowupPromptWhenAgentReady — interpreter-wrapped agents', () =
|
||||
hasChildProcesses: false
|
||||
})
|
||||
|
||||
const delivered = await sendFollowupPromptWhenAgentReady({
|
||||
const delivery = sendFollowupPromptWhenAgentReady({
|
||||
ptyId: 'pty-1',
|
||||
expectedProcess,
|
||||
prompt: 'ship it',
|
||||
settings: null
|
||||
})
|
||||
|
||||
await vi.advanceTimersByTimeAsync(29 * 150)
|
||||
const delivered = await delivery
|
||||
|
||||
expect(delivered).toBe(false)
|
||||
expect(sendRuntimePtyInputVerified).not.toHaveBeenCalled()
|
||||
})
|
||||
@@ -71,13 +83,16 @@ describe('sendFollowupPromptWhenAgentReady — interpreter-wrapped agents', () =
|
||||
hasChildProcesses: false
|
||||
})
|
||||
|
||||
const delivered = await sendFollowupPromptWhenAgentReady({
|
||||
const delivery = sendFollowupPromptWhenAgentReady({
|
||||
ptyId: 'pty-1',
|
||||
expectedProcess,
|
||||
prompt: 'ship it',
|
||||
settings: null
|
||||
})
|
||||
|
||||
await vi.advanceTimersByTimeAsync(29 * 150)
|
||||
const delivered = await delivery
|
||||
|
||||
expect(delivered).toBe(false)
|
||||
expect(sendRuntimePtyInputVerified).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user