[F005,F006] grok auth: directory mount + atomic-write fallback

F005: the single-file bind mount of auth.json pinned the inode, so the
orchestrator's atomic refresh (tmp+rename within ~/.grok) never reached a
running grok container — a long-lived container hung at the login prompt
when the original ~6h token expired. Mount the host ~/.grok DIRECTORY (ro)
at /home/agent/.grok-auth-ro; the entrypoint symlinks ~/.grok/auth.json at
that RO mount so grok + the --check backstop read the live credential (the
directory mount sees the host-side rename) while grok's writable state
(config.toml, sessions/) stays in the image's ~/.grok.

F006: a rotated refresh_token is single-use — xAI invalidates the old one
the instant it issues the new one. If the atomic write failed after the
rotation, the file kept the now-dead old refresh_token and the credential
was permanently lost on the next refresh. _atomic_write now falls back to a
direct write when tmp+replace fails, so the rotated token always lands on
disk (losing the write is catastrophic; losing atomicity is not).

TDD: RED tests watched fail, then GREEN. ruff+mypy clean; 32 grok tests
green, no regressions.

tests/unit/llm/providers/test_grok_auth.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import json
+import pathlib
 from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Any
 
@@ -126,6 +127,38 @@ def test_refresh_failed_when_no_access_token(tmp_path: Path) -> None:
     assert ga.refresh_if_stale(path, post=lambda _u, _f: {"expires_in": 1}) == "failed"
 
 
+def test_refresh_persists_rotated_token_when_atomic_write_fails(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    """F006: a rotated refresh_token is single-use — xAI invalidates the old one
+    the moment it issues the new one. If the atomic write (tmp+replace) fails
+    after the rotation, the file keeps the now-dead old refresh_token and the
+    credential is permanently lost on the next refresh. The write must fall back
+    to a direct write so the rotated refresh_token survives even when the atomic
+    replace can't."""
+    path = tmp_path / "auth.json"
+    _write(path, _bundle(_PAST))
+
+    def _post(_url: str, _form: dict[str, str]) -> dict[str, Any]:
+        return {
+            "access_token": "new-access",
+            "refresh_token": "rotated-rt",
+            "expires_in": 21600,
+        }
+
+    # Force the atomic tmp.replace to fail; the direct-write fallback must still
+    # land the rotated refresh_token on disk.
+    def _boom_replace(_self: pathlib.Path, _target: pathlib.Path) -> pathlib.Path:
+        raise OSError("replace failed (simulated)")
+
+    monkeypatch.setattr(pathlib.Path, "replace", _boom_replace)
+
+    assert ga.refresh_if_stale(path, post=_post) == "refreshed"
+    creds = next(iter(json.loads(path.read_text()).values()))
+    assert creds["refresh_token"] == "rotated-rt"  # survived the write failure
+    assert creds["key"] == "new-access"
+
+
 def test_main_check_exit_codes(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
     home = tmp_path / ".grok"
     home.mkdir()

tests/unit/llm/test_providers.py

@@ -241,7 +241,11 @@ async def test_grok_spawn_mounts_auth_when_present(_isolate_grok_auth: Path) ->
     ) as exec_mock:
         await provider.spawn(_config())
     cmd = list(exec_mock.call_args.args)
-    expected = f"{_isolate_grok_auth / 'auth.json'}:/home/agent/.grok/auth.json:ro"
+    # F005: mount the host ~/.grok DIRECTORY (ro), not the single auth.json
+    # file — a single-file bind mount pins the inode, so the orchestrator's
+    # atomic auth.json refresh (rename) never reaches a running container.
+    # The entrypoint symlinks ~/.grok/auth.json at this RO dir mount.
+    expected = f"{_isolate_grok_auth}:/home/agent/.grok-auth-ro:ro"
     assert expected in cmd
 
 
@@ -254,7 +258,7 @@ async def test_grok_spawn_omits_auth_mount_when_absent() -> None:
     ) as exec_mock:
         await provider.spawn(_config())
     cmd = list(exec_mock.call_args.args)
-    assert not any("/home/agent/.grok/auth.json" in c for c in cmd)
+    assert not any("/home/agent/.grok-auth-ro" in c for c in cmd)
 
 
 async def test_grok_spawn_prompt_is_injection_safe() -> None:

tests/unit/runtime/test_interactive_grok_spawn.py

@@ -82,7 +82,8 @@ def test_intake_grok_mounts_subscription_auth_when_present(
     cmd = AgentOrchestrator._build_intake_run_cmd(
         _intake_spec("grok", base_url="https://api.x.ai/v1", token="xai-key")
     )
-    assert f"{grok_dir / 'auth.json'}:/home/agent/.grok/auth.json:ro" in cmd
+    # F005: directory mount (ro), not the single-file inode-pinning mount.
+    assert f"{grok_dir}:/home/agent/.grok-auth-ro:ro" in cmd
 
 
 def test_intake_anthropic_keeps_anthropic_env() -> None: