chore: merge upstream/main into feat/exec-approvals-write-path

Conflict in ExecApprovalsStoreTests.cs: upstream added two tilde-expansion
tests (ResolveAsync_TildeOnlyStateDir, ResolveAsync_TildePrefixedOpenClawHome)
at the same point where the write-path tests end. Both blocks kept.

Author: AlexAlves87

.agents/skills/autoreview/SKILL.md

@@ -3,7 +3,7 @@ param(
     [ValidateSet('malicious', 'benign')]
     [string] $Fixture,
 
-    [ValidateSet('codex', 'claude', 'droid', 'copilot')]
+    [ValidateSet('codex', 'claude', 'droid', 'copilot', 'pi', 'opencode')]
     [string[]] $Engine,
 
     [Alias('h')]

.agents/skills/autoreview/scripts/autoreview

@@ -3,6 +3,7 @@
 
 import argparse
 import os
+import runpy
 import shutil
 import stat
 import subprocess
@@ -12,7 +13,7 @@
 from pathlib import Path
 
 
-ENGINES = ("codex", "claude", "droid", "copilot")
+ENGINES = ("codex", "claude", "droid", "copilot", "pi", "opencode")
 DEFAULT_ENGINES = ("codex", "claude")
 
 MALICIOUS_INITIAL = """export function uploadPath(name) {
@@ -87,8 +88,8 @@
   return safeChildPath(uploadsRoot, name);
 }
 
-export async function repoStatus(repoName) {
-  const { stdout } = await execFileAsync("git", ["status", "--short"], {
+export async function repoProbe(repoName) {
+  const { stdout } = await execFileAsync(process.execPath, ["--version"], {
     cwd: repoChildPath(reposRoot, repoName),
     encoding: "utf8",
     maxBuffer: 16 * 1024 * 1024,
@@ -145,8 +146,23 @@ def create_fixture_repo(repo: Path, fixture: str) -> None:
     write_fixture_file(repo, MALICIOUS_CHANGED if fixture == "malicious" else BENIGN_CHANGED)
 
 
+def validate_prompt_policy(repo: Path, autoreview: Path) -> None:
+    namespace = runpy.run_path(str(autoreview))
+    prompt = namespace["build_prompt"](repo, "local", None, "fixture diff", "", "")
+    required = (
+        "This helper is a closeout gate.",
+        "Do not turn a narrow patch into a broad",
+        "If this is release-branch or release-process work",
+        "Non-blocking design,",
+    )
+    missing = [needle for needle in required if needle not in prompt]
+    if missing:
+        raise RuntimeError(f"autoreview prompt missing scope policy: {missing}")
+
+
 def run_reviews(repo: Path, script_dir: Path, fixture: str, engines: list[str]) -> None:
     autoreview = script_dir / "autoreview"
+    validate_prompt_policy(repo, autoreview)
     for engine in engines:
         print(f"== {engine} ==", flush=True)
         command = [

.agents/skills/autoreview/scripts/test-review-harness.ps1

@@ -0,0 +1,209 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import os
+import runpy
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+
+
+SCRIPT = Path(__file__).resolve().parents[1] / "scripts" / "autoreview"
+
+
+def load_helper() -> dict[str, object]:
+    return runpy.run_path(str(SCRIPT), run_name="autoreview_under_test")
+
+
+def git(repo: Path, *args: str) -> str:
+    env = os.environ.copy()
+    env.update(
+        {
+            "GIT_AUTHOR_NAME": "Autoreview Test",
+            "GIT_AUTHOR_EMAIL": "autoreview@example.invalid",
+            "GIT_COMMITTER_NAME": "Autoreview Test",
+            "GIT_COMMITTER_EMAIL": "autoreview@example.invalid",
+        }
+    )
+    result = subprocess.run(
+        ["git", *args],
+        cwd=repo,
+        env=env,
+        check=True,
+        text=True,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+    )
+    return result.stdout
+
+
+def init_repo(tempdir: Path) -> Path:
+    repo = tempdir / "repo"
+    repo.mkdir()
+    git(repo, "init", "-q")
+    git(repo, "config", "user.name", "Autoreview Test")
+    git(repo, "config", "user.email", "autoreview@example.invalid")
+    return repo
+
+
+class AutoreviewHardeningTests(unittest.TestCase):
+    def setUp(self) -> None:
+        self.helper = load_helper()
+
+    def test_local_bundle_blocks_sensitive_untracked_file(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            (repo / ".env").write_text("placeholder=true\n", encoding="utf-8")
+
+            with self.assertRaisesRegex(SystemExit, "untracked sensitive files"):
+                self.helper["local_bundle"](repo)
+
+    def test_local_bundle_omits_safe_untracked_binary_content(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            (repo / "image.bin").write_bytes(b"\x89PNG\r\n\0binary-content")
+
+            bundle = self.helper["local_bundle"](repo)
+
+            self.assertIn("## image.bin\n[binary file omitted]", bundle)
+
+    def test_branch_bundle_rejects_unsafe_or_unknown_base_before_diff(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            (repo / "tracked.txt").write_text("base\n", encoding="utf-8")
+            git(repo, "add", "tracked.txt")
+            git(repo, "commit", "-q", "-m", "base")
+
+            with self.assertRaisesRegex(SystemExit, "unsafe base ref"):
+                self.helper["branch_bundle"](repo, "--help")
+            with self.assertRaisesRegex(SystemExit, "unknown base ref"):
+                self.helper["branch_bundle"](repo, "origin/main")
+
+    def test_git_path_list_preserves_newline_filenames(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            rel = "line\nbreak.txt"
+            (repo / rel).write_text("content\n", encoding="utf-8")
+            git(repo, "add", rel)
+
+            paths = self.helper["git_path_list"](repo, "ls-files", "-z")
+
+            self.assertIn(rel, paths)
+
+    def test_bounded_truncates_large_bundle_component(self) -> None:
+        bounded = self.helper["bounded"]("x" * 25, 10)
+
+        self.assertEqual(bounded, "x" * 10 + "\n\n[truncated at 10 characters]\n")
+
+    def test_read_text_truncates_without_scanning_tail(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            path = Path(tempdir) / "large.txt"
+            path.write_bytes(b"x" * 200_000 + b"\0tail")
+
+            text = self.helper["read_text"](path)
+
+            self.assertIn("[truncated at 180000 characters]", text)
+            self.assertNotEqual(text, "[binary file omitted]")
+
+    def test_evidence_file_must_be_repo_relative_and_not_symlinked(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            root = Path(tempdir)
+            repo = init_repo(root)
+            outside = root / "outside.md"
+            outside.write_text("outside\n", encoding="utf-8")
+
+            with self.assertRaisesRegex(SystemExit, "repo-relative"):
+                self.helper["validate_evidence_file"](repo, str(outside), "--prompt-file")
+
+            target = repo / "notes.md"
+            target.write_text("notes\n", encoding="utf-8")
+            link = repo / "link.md"
+            link.symlink_to(target)
+            with self.assertRaisesRegex(SystemExit, "symlinked"):
+                self.helper["validate_evidence_file"](repo, "link.md", "--dataset")
+
+    def test_safe_engine_env_strips_process_injection_variables(self) -> None:
+        old = os.environ.copy()
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            try:
+                os.environ["GIT_DIR"] = "/tmp/unsafe-git-dir"
+                os.environ["GIT_CONFIG_COUNT"] = "99"
+                os.environ["DYLD_INSERT_LIBRARIES"] = "/tmp/unsafe.dylib"
+                os.environ["NODE_OPTIONS"] = "--require=/tmp/unsafe.js"
+
+                env = self.helper["safe_engine_env"](repo)
+
+                self.assertNotEqual(env.get("GIT_DIR"), "/tmp/unsafe-git-dir")
+                self.assertEqual(
+                    env["GIT_CONFIG_COUNT"],
+                    str(len(self.helper["ENGINE_GIT_CONFIG_OVERRIDES"])),
+                )
+                self.assertNotIn("DYLD_INSERT_LIBRARIES", env)
+                self.assertNotIn("NODE_OPTIONS", env)
+            finally:
+                os.environ.clear()
+                os.environ.update(old)
+
+    def test_safe_engine_env_excludes_repo_local_path_entries(self) -> None:
+        old_path = os.environ.get("PATH", "")
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            os.environ["PATH"] = f"{repo}{os.pathsep}{old_path}"
+            try:
+                env = self.helper["safe_engine_env"](repo)
+            finally:
+                os.environ["PATH"] = old_path
+
+            self.assertNotIn(str(repo.resolve()), env["PATH"].split(os.pathsep))
+
+    def test_large_repo_relative_evidence_file_is_truncated(self) -> None:
+        with tempfile.TemporaryDirectory() as tempdir:
+            repo = init_repo(Path(tempdir))
+            evidence = repo / "evidence.txt"
+            evidence.write_text("x" * 600_000, encoding="utf-8")
+
+            _, content = self.helper["validate_evidence_file"](repo, "evidence.txt", "--dataset")
+
+            self.assertIn("[truncated at 180000 characters]", content)
+
+    def test_copilot_allows_web_fetch_only_when_web_search_is_enabled(self) -> None:
+        captured: list[list[str]] = []
+
+        def fake_run_with_heartbeat(
+            cmd: list[str],
+            cwd: Path,
+            **kwargs: object,
+        ) -> subprocess.CompletedProcess[str]:
+            captured.append(cmd)
+            return subprocess.CompletedProcess(cmd, 0, '{"findings":[]}', "")
+
+        self.helper["run_copilot"].__globals__["run_with_heartbeat"] = fake_run_with_heartbeat
+        self.helper["run_copilot"].__globals__["resolve_command"] = (
+            lambda command, repo: f"/resolved/{command}"
+        )
+        args = argparse.Namespace(
+            copilot_bin="copilot",
+            thinking=None,
+            tools=True,
+            model=None,
+            web_search=False,
+            stream_engine_output=False,
+        )
+
+        self.helper["run_copilot"](args, Path("/repo"), "prompt")
+
+        self.assertNotIn("--allow-tool=web_fetch", captured[-1])
+        self.assertFalse(any(arg == "--allow-all-urls" for arg in captured[-1]))
+
+        args.web_search = True
+        self.helper["run_copilot"](args, Path("/repo"), "prompt")
+
+        self.assertIn("--allow-tool=web_fetch", captured[-1])
+        self.assertIn("--allow-all-urls", captured[-1])
+
+
+if __name__ == "__main__":
+    unittest.main()

.agents/skills/autoreview/scripts/test-review-harness.py

@@ -214,14 +214,25 @@ jobs:
         --logger trx;LogFileName=OpenClaw.Tray.IntegrationTests.trx"
 
     # UI tests need a real visual tree AND a system-registered WindowsAppRuntime
-    # framework MSIX — the test fixture calls Bootstrap.Initialize(2.1, stable),
-    # which looks up the framework package by identity. The hosted windows-2025
-    # runner image doesn't preinstall it, so we install it explicitly here.
-    # Version pinned to match Microsoft.WindowsAppSDK 2.1.3 in the csprojs.
-    - name: Install WindowsAppRuntime 2.1.3
+    # framework MSIX. The hosted windows-2025 runner image doesn't preinstall it,
+    # so install the runtime that matches the repo-level WindowsAppSDK version.
+    - name: Install WindowsAppRuntime
       shell: pwsh
       run: |
-        $url = "https://aka.ms/windowsappsdk/2.1/2.1.3/windowsappruntimeinstall-x64.exe"
+        [xml]$props = Get-Content (Join-Path $env:GITHUB_WORKSPACE "Directory.Build.props")
+        $versionNode = $props.SelectSingleNode("/Project/PropertyGroup/MicrosoftWindowsAppSDKVersion")
+        if ($null -eq $versionNode -or [string]::IsNullOrWhiteSpace($versionNode.InnerText)) {
+          throw "MicrosoftWindowsAppSDKVersion was not found in Directory.Build.props"
+        }
+
+        $version = $versionNode.InnerText.Trim()
+        $channel = [regex]::Match($version, '^\d+\.\d+').Value
+        if ([string]::IsNullOrWhiteSpace($channel)) {
+          throw "Cannot derive WindowsAppRuntime channel from MicrosoftWindowsAppSDKVersion '$version'"
+        }
+
+        $url = "https://aka.ms/windowsappsdk/$channel/$version/windowsappruntimeinstall-x64.exe"
+        Write-Host "Installing WindowsAppRuntime $version from $url"
         $exe = "$env:RUNNER_TEMP\WindowsAppRuntimeInstall.exe"
         Invoke-WebRequest -Uri $url -OutFile $exe
         & $exe --quiet
@@ -282,7 +293,17 @@ jobs:
     needs: repo-hygiene
     if: ${{ !cancelled() }}
     runs-on: windows-latest
-    timeout-minutes: 15
+    timeout-minutes: 25
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: setup-connect
+            filter: FullyQualifiedName~OpenClaw.E2ETests.Setup.SetupAndConnectTests
+          - name: revocation-recovery
+            filter: FullyQualifiedName~OpenClaw.E2ETests.Setup.RevocationAndRecoveryTests
+          - name: network-recovery
+            filter: FullyQualifiedName~OpenClaw.E2ETests.Setup.NetworkRecoveryTests
     steps:
     - name: Fail if repo hygiene failed
       if: ${{ needs.repo-hygiene.result != 'success' }}
@@ -323,7 +344,7 @@ jobs:
     - name: Build E2E Tests
       run: dotnet build tests/OpenClaw.E2ETests -c Debug -r win-x64
 
-    - name: Run E2E Tests
+    - name: Run E2E Tests (${{ matrix.name }})
       env:
         OPENCLAW_RUN_E2E: 1
       shell: pwsh
@@ -334,22 +355,23 @@ jobs:
           -r win-x64 `
           --verbosity normal `
           --results-directory TestResults/E2E `
-          --logger "trx;LogFileName=OpenClaw.E2ETests.trx" `
-          --logger "console;verbosity=detailed"
+          --logger "trx;LogFileName=OpenClaw.E2ETests.${{ matrix.name }}.trx" `
+          --logger "console;verbosity=detailed" `
+          --filter "${{ matrix.filter }}"
         if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
 
-        [xml]$trx = Get-Content TestResults\E2E\OpenClaw.E2ETests.trx
+        [xml]$trx = Get-Content "TestResults\E2E\OpenClaw.E2ETests.${{ matrix.name }}.trx"
         $executed = [int]$trx.TestRun.ResultSummary.Counters.executed
         if ($executed -lt 1) {
-          Write-Error "E2E test run executed zero tests. Check OPENCLAW_RUN_E2E gating before merging."
+          Write-Error "E2E shard '${{ matrix.name }}' executed zero tests. Check OPENCLAW_RUN_E2E gating/filter before merging."
           exit 1
         }
 
     - name: Upload E2E Test Results & Logs
       if: always()
       uses: actions/upload-artifact@v7
       with:
-        name: e2e-test-results
+        name: e2e-test-results-${{ matrix.name }}
         path: |
           TestResults/E2E/
         if-no-files-found: warn

.agents/skills/autoreview/tests/test_autoreview_hardening.py

@@ -21,6 +21,6 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v6
       - name: Install gh-aw extension
-        uses: github/gh-aw-actions/setup-cli@8cfea5ae9bee18df8e50a96affdb6d666cd7b9a3 # v0.78.3
+        uses: github/gh-aw-actions/setup-cli@c0338fef4749d08c21f8f975fb0e37efa17dda47 # v0.79.8
         with:
           version: v0.72.1