desk: F4 #1191 comparison (test-only, never merged)

.github/workflows/tests.yml

@@ -1,26 +1,12 @@
 name: Tests
-
-# Builds, type-checks and runs every test suite on a clean GitHub runner, and records the file
-# list each published package would contain. Each suite is its own job so one failure does not
-# hide the others. No provider credentials or operator configuration are supplied.
-# Package suites deny external networking; scenario runtime has no external route.
-
 on:
-  pull_request:
-    branches: [main]
   workflow_dispatch:
-
 permissions:
   contents: read
-
-concurrency:
-  group: tests-${{ github.ref }}
-  cancel-in-progress: true
-
 jobs:
-  build-and-package:
+  f4-compare:
     runs-on: ubuntu-latest
-    timeout-minutes: 30
+    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
         with:
@@ -31,109 +17,5 @@ jobs:
           cache: npm
       - run: npm ci
       - run: npm run build
-      - name: Record the published file list of each package
-        run: |
-          set -euo pipefail
-          mkdir -p pack-lists
-          for p in cli daemon tui; do
-            (cd packages/$p && npm pack --dry-run --json --ignore-scripts) \
-              | node -e 'let s="";process.stdin.on("data",d=>s+=d).on("end",()=>{for(const f of JSON.parse(s)[0].files)console.log(f.path)})' \
-              | sort > pack-lists/$p.txt
-            echo "$p: $(wc -l < pack-lists/$p.txt) files"
-          done
-      - uses: actions/upload-artifact@v4
-        with:
-          name: pack-lists
-          path: pack-lists/
-
-  typecheck:
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run lint
-
-  repo-checks:
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run test:repo
-
-  package-tests:
-    # macOS, the platform OpenRig runs on: several daemon and cli tests read macOS ps columns,
-    # file-inode behaviour and release tags.
-    runs-on: macos-latest
-    timeout-minutes: 45
-    strategy:
-      fail-fast: false
-      matrix:
-        package: [daemon, cli, tui, ui]
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 22
-          cache: npm
-      - run: brew install tmux
-      - run: npm ci
-      - name: Build the packages the tests import
-        run: npm run build
-      - name: Run the suite without ambient credentials or external network
-        run: |
-          suite_root=$(mktemp -d "$RUNNER_TEMP/opr-test.XXXXXX")
-          suite_root=$(cd "$suite_root" && pwd -P)
-          mkdir -p "$suite_root/home" "$suite_root/bin"
-          # Same system bytes, nonprivileged mode; no system file is changed.
-          /usr/bin/install -m 0755 /bin/ps "$suite_root/bin/ps"
-          # Only this job's temporary sockets (including tmux) are reachable.
-          env -i HOME="$suite_root/home" PATH="$PATH" TMPDIR="$suite_root" TMUX_TMPDIR="$suite_root" \
-            CI=true TERM=xterm-256color \
-            sandbox-exec -D IPC_ROOT="$suite_root" -p '(version 1)(allow default)(deny network-outbound)(allow network-outbound (remote ip "localhost:*"))(allow network-outbound (subpath (param "IPC_ROOT")))' \
-            /bin/bash -s "${{ matrix.package }}" <<'SUITE'
-          set -euo pipefail
-          node scripts/ci-macos-process-probe.mjs
-          # The production readers use bare ps. Select real system bytes only after
-          # self/owned-child observation and network/IPC confinement are proved.
-          export PATH="$TMPDIR/bin:$PATH"
-          test "$(command -v ps)" = "$TMPDIR/bin/ps"
-          exec npm run test -w "packages/$1"
-          SUITE
-
-  installed-scenario:
-    runs-on: ubuntu-latest
-    timeout-minutes: 35
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - name: Installed package, daemon restart, and seeded durability failure
-        run: bash scripts/run-pr-scenarios.sh
-      - uses: actions/upload-artifact@v4
-        if: always()
-        with:
-          name: installed-scenario-evidence
-          path: dist/pr-scenarios/
-          if-no-files-found: error
+      - name: The F4 comparison only
+        run: npm exec -w packages/daemon -- vitest run test/f4-1191-compare.test.ts --reporter=verbose

packages/daemon/test/f4-1191-compare.test.ts

@@ -0,0 +1,96 @@
+// Desk-only comparison (never merged): one pod-aware Claude resume through the real adapter ->
+// startup -> restore mapping, with mocked terminal effects, at v0.6.10 and at the 0.6.11 candidate.
+import { afterEach, describe, expect, it, vi } from "vitest";
+import { createFullTestDb } from "./helpers/test-app.js";
+import { RigRepository } from "../src/domain/rig-repository.js";
+import { SessionRegistry } from "../src/domain/session-registry.js";
+import { EventBus } from "../src/domain/event-bus.js";
+import { SnapshotRepository } from "../src/domain/snapshot-repository.js";
+import { CheckpointStore } from "../src/domain/checkpoint-store.js";
+import { SnapshotCapture } from "../src/domain/snapshot-capture.js";
+import { RigTeardownOrchestrator } from "../src/domain/rig-teardown.js";
+import { NodeLauncher } from "../src/domain/node-launcher.js";
+import { RestoreOrchestrator } from "../src/domain/restore-orchestrator.js";
+import { ClaudeCodeAdapter } from "../src/adapters/claude-code-adapter.js";
+import { ClaudeResumeAdapter } from "../src/adapters/claude-resume.js";
+import { CodexResumeAdapter } from "../src/adapters/codex-resume.js";
+import { NativePermissionStore } from "../src/domain/native-permission-store.js";
+import type { ClaudeManagedLaunch } from "../src/domain/claude-managed-launch.js";
+import type { TmuxAdapter } from "../src/adapters/tmux.js";
+
+const token = "00000000-0000-4000-8000-000000000006";
+const autoScreen = "Restored conversation\n────────────────\n❯ \n────────────────\n  ⏵⏵ auto mode on (shift+tab to cycle) · ← for agents\n  ● high · /effort\n";
+const SCREENS: Record<string, string> = {
+  missing: `$ claude --resume ${token}\nNo conversation found with session ID: ${token}\nuser@host:~/project$ `,
+  "generic-exit": "$ claude --resume <token>\nError: simulated Claude exit (not a missing conversation)\nuser@host:~/project$ ",
+  "attention-control": autoScreen,
+};
+
+describe("F4 #1191 comparison", () => {
+  const dbs: ReturnType<typeof createFullTestDb>[] = [];
+  afterEach(() => { for (const db of dbs.splice(0)) db.close(); });
+
+  it.each(["missing", "generic-exit", "attention-control"])("%s", async (mode) => {
+    const db = createFullTestDb(); dbs.push(db);
+    const rigRepo = new RigRepository(db);
+    const sessionRegistry = new SessionRegistry(db);
+    const eventBus = new EventBus(db);
+    const snapshotRepo = new SnapshotRepository(db);
+    const checkpointStore = new CheckpointStore(db);
+    const snapshotCapture = new SnapshotCapture({ db, rigRepo, sessionRegistry, eventBus, snapshotRepo, checkpointStore });
+    const rig = rigRepo.createRig("restore-test");
+    db.prepare("INSERT INTO pods (id, rig_id, label) VALUES (?, ?, ?)").run("restore-pod", rig.id, "Test");
+    const node = rigRepo.addNode(rig.id, "test.c", { runtime: "claude-code", podId: "restore-pod" });
+    new NativePermissionStore(db).write(node.id, { runtime: "claude-code", mode: "auto" }, "fixture", "retained posture");
+    const name = "test-c@restore-test";
+    const old = sessionRegistry.registerSession(node.id, name);
+    sessionRegistry.updateStatus(old.id, "running");
+    sessionRegistry.updateResumeToken(old.id, "claude_id", token, "scrape");
+    sessionRegistry.updateBinding(node.id, { tmuxSession: name, tmuxPane: "%old" });
+    db.prepare("INSERT INTO node_startup_context (node_id, projection_entries_json, resolved_files_json, startup_actions_json, runtime) VALUES (?, ?, ?, ?, ?)").run(node.id, "[]", "[]", "[]", "claude-code");
+    let live = true;
+    const tmux = {
+      hasSession: vi.fn(async () => live),
+      probeSession: vi.fn(async () => ({ state: live ? "present" : "absent" })),
+      killSession: vi.fn(async () => { live = false; return { ok: true }; }),
+      createSession: vi.fn(async () => { live = true; return { ok: true }; }),
+      listSessions: vi.fn(async () => live ? [{ name }] : []),
+      listWindows: vi.fn(async () => []),
+      listPanes: vi.fn(async () => [{ id: "%new", index: 0, cwd: "/", width: 80, height: 24, active: true }]),
+      getPanePid: vi.fn(async () => 100),
+      getPaneCommand: vi.fn(async () => "bash"),
+      capturePaneContent: vi.fn(async () => SCREENS[mode]),
+      sendText: vi.fn(async () => ({ ok: true })),
+      sendShellCommand: vi.fn(async () => ({ ok: true })),
+      sendKeys: vi.fn(async () => ({ ok: true })),
+    } as unknown as TmuxAdapter;
+    const startedAt = "Thu Oct  1 05:53:16 2026";
+    const listProcesses = async () => [{ pid: 100, ppid: 1, pgid: 100, tpgid: 100, executableName: "bash", command: "-bash", startedAt }];
+    const down = await new RigTeardownOrchestrator({ db, rigRepo, sessionRegistry, eventBus, snapshotCapture, tmuxAdapter: tmux }).teardown(rig.id);
+    expect(down.errors).toEqual([]);
+    const adapter = new ClaudeCodeAdapter({ tmux, listProcesses, sleep: async () => {},
+      claudeManagedLaunch: { prepare: async () => ({ command: (args: readonly string[]) => `claude ${args.join(" ")}`, assertCurrent: () => {}, configDir: "/fixture", executable: "/opt/claude.exe" }) } as unknown as ClaudeManagedLaunch,
+      fsOps: { exists: () => false, readFile: () => "", writeFile: () => {}, mkdirp: () => {}, copyFile: () => {} } });
+    const nodeLauncher = new NodeLauncher({ db, rigRepo, sessionRegistry, eventBus, tmuxAdapter: tmux });
+    const restore = new RestoreOrchestrator({ db, rigRepo, sessionRegistry, eventBus, snapshotRepo, snapshotCapture,
+      checkpointStore, nodeLauncher, tmuxAdapter: tmux, claudeResume: new ClaudeResumeAdapter(tmux),
+      codexResume: new CodexResumeAdapter(tmux), listProcesses });
+    vi.mocked(tmux.killSession).mockClear(); vi.mocked(tmux.createSession).mockClear();
+    const up = await restore.restore(down.snapshotId!, { adapters: { "claude-code": adapter } });
+    const rows = db.prepare("SELECT id, status, startup_status, resume_type, resume_token FROM sessions WHERE node_id = ? ORDER BY id").all(node.id);
+    const report = {
+      mode,
+      ok: up.ok,
+      rigResult: up.ok ? (up.result as { rigResult?: unknown }).rigResult ?? null : (up as { message?: string }).message,
+      node: up.ok ? up.result.nodes[0] : null,
+      createSessionCalls: vi.mocked(tmux.createSession).mock.calls.length,
+      killSessionCalls: vi.mocked(tmux.killSession).mock.calls.map((c) => c[0]),
+      sessionLiveAfter: live,
+      oldRow: db.prepare("SELECT status, resume_type, resume_token FROM sessions WHERE id = ?").get(old.id),
+      rows,
+      binding: sessionRegistry.getBindingForNode(node.id),
+    };
+    console.log("F4_REPORT " + JSON.stringify(report));
+    expect(up.ok).toBe(true);
+  });
+});