Harden Codex harness control surfaces (#77459)

* fix(scripts): find codex protocol source from worktrees * fix(test): keep codex harness docker caches writable * fix(test): relax live codex cache mount permissions * test(codex): add live docker harness debug output * fix(test): detect numeric ci env in codex docker harness * fix(codex): skip duplicate agent-command telemetry * fix(tooling): skip sparse-missing oxlint tsconfig * fix(tooling): route changed checks through testbox * fix(qa): keep coverage json source-clean * fix(test): preflight codex docker auth * fix(codex): validate bind option values * fix(codex): parse quoted command arguments * fix(codex): reject extra control args * fix(codex): use content for blank bound prompts * fix(codex): decode local image file urls * fix(codex): treat local media urls as images * fix(codex): keep windows media paths local * fix(codex): reject malformed diagnostics confirmations * fix(codex): reject malformed resume commands * fix(codex): reject malformed thread actions * fix(codex): reject malformed turn controls * fix(codex): reject malformed model controls * fix(codex): resolve empty user input prompts * fix(codex): enforce user input options * fix(codex): reject ambiguous computer-use actions * fix(codex): ignore stale bound turn notifications * test(gateway): close task registries in gateway harness * test(gateway): route cleanup through task seams * fix(codex): describe current permission approvals * fix(codex): disclose command approval amendments * fix(codex): preserve approval detail under truncation * fix(codex): propagate dynamic tool failures * test(codex): align dynamic tool block contract * fix(codex): reject extra read-only command operands * fix(codex): escape command readout fields * fix(codex): escape status probe errors * fix(codex): narrow formatted thread details * fix(codex): escape successful status summaries * fix(codex): escape bound control replies * fix(codex): escape user input prompts * fix(codex): escape control failure replies * fix(codex): escape approval prompt text * test(codex): narrow escaped reply assertions * test(codex): complete strict reply fixtures * test(codex): preserve account fixture literals * test(codex): align status probe fixtures * fix(codex): satisfy sanitizer regex lint * fix(codex): harden command readouts * fix(codex): harden bound image inputs * fix(codex): sanitize command failure replies * test(codex): complete rate limit fixture * test(tooling): isolate postinstall compile cache fixture * fix(codex): keep app-server event ownership explicit --------- Co-authored-by: pashpashpash <nik@vault77.ai>
2026-05-06 15:00:41 +00:00 · 2026-05-04 15:23:41 -07:00
parent b3e42bf327
commit ac3cd1a0ca
42 changed files with 2672 additions and 245 deletions
--- a/scripts/check-changed.mjs
+++ b/scripts/check-changed.mjs
@@ -33,6 +33,52 @@ export function createChangedCheckChildEnv(baseEnv = process.env) {
  };
 }

+function isTruthyEnvFlag(value) {
+  const normalized = String(value ?? "")
+    .trim()
+    .toLowerCase();
+  return normalized !== "" && normalized !== "0" && normalized !== "false" && normalized !== "no";
+}
+
+export function shouldDelegateChangedCheckToTestbox(argv = [], env = process.env) {
+  if (!isTruthyEnvFlag(env.OPENCLAW_TESTBOX)) {
+    return false;
+  }
+  if (isTruthyEnvFlag(env.OPENCLAW_TESTBOX_REMOTE_RUN)) {
+    return false;
+  }
+  if (isTruthyEnvFlag(env.CI) || isTruthyEnvFlag(env.GITHUB_ACTIONS)) {
+    return false;
+  }
+  if (argv.includes("--dry-run")) {
+    return false;
+  }
+  return true;
+}
+
+export function buildChangedCheckTestboxArgs(argv = []) {
+  return [
+    "testbox:run",
+    "--",
+    "OPENCLAW_TESTBOX=1",
+    "OPENCLAW_TESTBOX_REMOTE_RUN=1",
+    "pnpm",
+    "check:changed",
+    ...argv,
+  ];
+}
+
+export async function runChangedCheckViaTestbox(argv = [], env = process.env) {
+  console.error(
+    "[check:changed] OPENCLAW_TESTBOX=1 set; delegating to Blacksmith Testbox via `pnpm testbox:run`.",
+  );
+  return await runManagedCommand({
+    bin: "pnpm",
+    args: buildChangedCheckTestboxArgs(argv),
+    env,
+  });
+}
+
 export function createChangedCheckPlan(result, options = {}) {
  const commands = [];
  const baseEnv = createChangedCheckChildEnv(options.env ?? process.env);
@@ -283,21 +329,26 @@ function isDirectRun() {
 }

 if (isDirectRun()) {
-  const args = parseArgs(process.argv.slice(2));
-  const paths =
-    args.paths.length > 0
-      ? args.paths
-      : args.staged
-        ? listStagedChangedPaths()
-        : listChangedPathsFromGit({ base: args.base, head: args.head });
-  const result = detectChangedLanesForPaths({
-    paths,
-    base: args.base,
-    head: args.head,
-    staged: args.staged,
-  });
-  process.exitCode = await runChangedCheck(result, {
-    ...args,
-    explicitPaths: args.paths.length > 0,
-  });
+  const argv = process.argv.slice(2);
+  if (shouldDelegateChangedCheckToTestbox(argv, process.env)) {
+    process.exitCode = await runChangedCheckViaTestbox(argv, process.env);
+  } else {
+    const args = parseArgs(argv);
+    const paths =
+      args.paths.length > 0
+        ? args.paths
+        : args.staged
+          ? listStagedChangedPaths()
+          : listChangedPathsFromGit({ base: args.base, head: args.head });
+    const result = detectChangedLanesForPaths({
+      paths,
+      base: args.base,
+      head: args.head,
+      staged: args.staged,
+    });
+    process.exitCode = await runChangedCheck(result, {
+      ...args,
+      explicitPaths: args.paths.length > 0,
+    });
+  }
 }