fix(codex): Hermes owns its own Codex auth; stop touching ~/.codex/auth.json (#12360)

Codex OAuth refresh tokens are single-use and rotate on every refresh.
Sharing them with the Codex CLI / VS Code via ~/.codex/auth.json made
concurrent use of both tools a race: whoever refreshed last invalidated
the other side's refresh_token.  On top of that, the silent auto-import
path picked up placeholder / aborted-auth data from ~/.codex/auth.json
(e.g. literal {"access_token":"access-new","refresh_token":"refresh-new"})
and seeded it into the Hermes pool as an entry the selector could
eventually pick.

Hermes now owns its own Codex auth state end-to-end:

Removed
- agent/credential_pool.py: _sync_codex_entry_from_cli() method,
  its pre-refresh + retry + _available_entries call sites, and the
  post-refresh write-back to ~/.codex/auth.json.
- agent/credential_pool.py: auto-import from ~/.codex/auth.json in
  _seed_from_singletons() — users now run `hermes auth openai-codex`
  explicitly.
- hermes_cli/auth.py: silent runtime migration in
  resolve_codex_runtime_credentials() — now surfaces
  `codex_auth_missing` directly (message already points to `hermes auth`).
- hermes_cli/auth.py: post-refresh write-back in
  _refresh_codex_auth_tokens().
- hermes_cli/auth.py: dead helper _write_codex_cli_tokens() and its 4
  tests in test_auth_codex_provider.py.

Kept
- hermes_cli/auth.py: _import_codex_cli_tokens() — still used by the
  interactive `hermes auth openai-codex` setup flow for a user-gated
  one-time import (with "a separate login is recommended" messaging).

User-visible impact
- On existing installs with Hermes auth already present: no change.
- On a fresh install where the user has only logged in via Codex CLI:
  `hermes chat --provider openai-codex` now fails with "No Codex
  credentials stored. Run `hermes auth` to authenticate." The
  interactive setup flow then detects ~/.codex/auth.json and offers a
  one-time import.
- On an install where Codex CLI later refreshes its token: Hermes is
  unaffected (we no longer read from that file at runtime).

Tests
- tests/hermes_cli/test_auth_codex_provider.py: 15/15 pass.
- tests/hermes_cli/test_auth_commands.py: 20/20 pass.
- tests/agent/test_credential_pool.py: 31/31 pass.
- Live E2E on openai-codex/gpt-5.4: 1 API call, 1.7s latency,
  3 log lines, no refresh events, no auth drama.

The related 14:52 refresh-loop bug (hundreds of rotations/minute on a
single entry) is a separate issue — that requires a refresh-attempt
cap on the auth-recovery path in run_agent.py, which remains open.
This commit is contained in:
Teknium
2026-04-18 19:19:46 -07:00
committed by GitHub
parent bd01ec7885
commit b02833f32d
3 changed files with 9 additions and 282 deletions

View File

@@ -22,8 +22,6 @@ from hermes_cli.auth import (
_auth_store_lock,
_codex_access_token_is_expiring,
_decode_jwt_claims,
_import_codex_cli_tokens,
_write_codex_cli_tokens,
_load_auth_store,
_load_provider_state,
_resolve_kimi_base_url,
@@ -457,39 +455,6 @@ class CredentialPool:
logger.debug("Failed to sync from credentials file: %s", exc)
return entry
def _sync_codex_entry_from_cli(self, entry: PooledCredential) -> PooledCredential:
"""Sync an openai-codex pool entry from ~/.codex/auth.json if tokens differ.
OpenAI OAuth refresh tokens are single-use and rotate on every refresh.
When the Codex CLI (or another Hermes profile) refreshes its token,
the pool entry's refresh_token becomes stale. This method detects that
by comparing against ~/.codex/auth.json and syncing the fresh pair.
"""
if self.provider != "openai-codex":
return entry
try:
cli_tokens = _import_codex_cli_tokens()
if not cli_tokens:
return entry
cli_refresh = cli_tokens.get("refresh_token", "")
cli_access = cli_tokens.get("access_token", "")
if cli_refresh and cli_refresh != entry.refresh_token:
logger.debug("Pool entry %s: syncing tokens from ~/.codex/auth.json (refresh token changed)", entry.id)
updated = replace(
entry,
access_token=cli_access,
refresh_token=cli_refresh,
last_status=None,
last_status_at=None,
last_error_code=None,
)
self._replace_entry(entry, updated)
self._persist()
return updated
except Exception as exc:
logger.debug("Failed to sync from ~/.codex/auth.json: %s", exc)
return entry
def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
"""Write refreshed pool entry tokens back to auth.json providers.
@@ -585,13 +550,6 @@ class CredentialPool:
except Exception as wexc:
logger.debug("Failed to write refreshed token to credentials file: %s", wexc)
elif self.provider == "openai-codex":
# Proactively sync from ~/.codex/auth.json before refresh.
# The Codex CLI (or another Hermes profile) may have already
# consumed our refresh_token. Syncing first avoids a
# "refresh_token_reused" error when the CLI has a newer pair.
synced = self._sync_codex_entry_from_cli(entry)
if synced is not entry:
entry = synced
refreshed = auth_mod.refresh_codex_oauth_pure(
entry.access_token,
entry.refresh_token,
@@ -677,45 +635,6 @@ class CredentialPool:
# Credentials file had a valid (non-expired) token — use it directly
logger.debug("Credentials file has valid token, using without refresh")
return synced
# For openai-codex: the refresh_token may have been consumed by
# the Codex CLI between our proactive sync and the refresh call.
# Re-sync and retry once.
if self.provider == "openai-codex":
synced = self._sync_codex_entry_from_cli(entry)
if synced.refresh_token != entry.refresh_token:
logger.debug("Retrying Codex refresh with synced token from ~/.codex/auth.json")
try:
refreshed = auth_mod.refresh_codex_oauth_pure(
synced.access_token,
synced.refresh_token,
)
updated = replace(
synced,
access_token=refreshed["access_token"],
refresh_token=refreshed["refresh_token"],
last_refresh=refreshed.get("last_refresh"),
last_status=STATUS_OK,
last_status_at=None,
last_error_code=None,
)
self._replace_entry(synced, updated)
self._persist()
self._sync_device_code_entry_to_auth_store(updated)
try:
_write_codex_cli_tokens(
updated.access_token,
updated.refresh_token,
last_refresh=updated.last_refresh,
)
except Exception as wexc:
logger.debug("Failed to write refreshed Codex tokens to CLI file (retry): %s", wexc)
return updated
except Exception as retry_exc:
logger.debug("Codex retry refresh also failed: %s", retry_exc)
elif not self._entry_needs_refresh(synced):
logger.debug("Codex CLI has valid token, using without refresh")
self._sync_device_code_entry_to_auth_store(synced)
return synced
self._mark_exhausted(entry, None)
return None
@@ -734,17 +653,6 @@ class CredentialPool:
# _seed_from_singletons() on the next load_pool() sees fresh state
# instead of re-seeding stale/consumed tokens.
self._sync_device_code_entry_to_auth_store(updated)
# Write refreshed tokens back to ~/.codex/auth.json so Codex CLI
# and VS Code don't hit "refresh_token_reused" on their next refresh.
if self.provider == "openai-codex":
try:
_write_codex_cli_tokens(
updated.access_token,
updated.refresh_token,
last_refresh=updated.last_refresh,
)
except Exception as wexc:
logger.debug("Failed to write refreshed Codex tokens to CLI file: %s", wexc)
return updated
def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -790,16 +698,6 @@ class CredentialPool:
if synced is not entry:
entry = synced
cleared_any = True
# For openai-codex entries, sync from ~/.codex/auth.json before
# any status/refresh checks. This picks up tokens refreshed by
# the Codex CLI or another Hermes profile.
if (self.provider == "openai-codex"
and entry.last_status == STATUS_EXHAUSTED
and entry.refresh_token):
synced = self._sync_codex_entry_from_cli(entry)
if synced is not entry:
entry = synced
cleared_any = True
if entry.last_status == STATUS_EXHAUSTED:
exhausted_until = _exhausted_until(entry)
if exhausted_until is not None and now < exhausted_until:
@@ -1218,8 +1116,8 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
elif provider == "openai-codex":
# Respect user suppression — `hermes auth remove openai-codex` marks
# the device_code source as suppressed so it won't be re-seeded from
# either the Hermes auth store or ~/.codex/auth.json. Without this
# gate the removal is instantly undone on the next load_pool() call.
# the Hermes auth store. Without this gate the removal is instantly
# undone on the next load_pool() call.
codex_suppressed = False
try:
from hermes_cli.auth import is_source_suppressed
@@ -1231,23 +1129,12 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
state = _load_provider_state(auth_store, "openai-codex")
tokens = state.get("tokens") if isinstance(state, dict) else None
# Fallback: import from Codex CLI (~/.codex/auth.json) if Hermes auth
# store has no tokens. This mirrors resolve_codex_runtime_credentials()
# so that load_pool() and list_authenticated_providers() detect tokens
# that only exist in the Codex CLI shared file.
if not (isinstance(tokens, dict) and tokens.get("access_token")):
try:
from hermes_cli.auth import _import_codex_cli_tokens, _save_codex_tokens
cli_tokens = _import_codex_cli_tokens()
if cli_tokens:
logger.info("Importing Codex CLI tokens into Hermes auth store.")
_save_codex_tokens(cli_tokens)
# Re-read state after import
auth_store = _load_auth_store()
state = _load_provider_state(auth_store, "openai-codex")
tokens = state.get("tokens") if isinstance(state, dict) else None
except Exception as exc:
logger.debug("Codex CLI token import failed: %s", exc)
# Hermes owns its own Codex auth state — we do NOT auto-import from
# ~/.codex/auth.json at pool-load time. OAuth refresh tokens are
# single-use, so sharing them with Codex CLI / VS Code causes
# refresh_token_reused race failures. Users who want to adopt
# existing Codex CLI credentials get a one-time, explicit prompt
# via `hermes auth openai-codex`.
if isinstance(tokens, dict) and tokens.get("access_token"):
active_sources.add("device_code")
changed |= _upsert_entry(

View File

@@ -1434,49 +1434,6 @@ def _read_codex_tokens(*, _lock: bool = True) -> Dict[str, Any]:
}
def _write_codex_cli_tokens(
access_token: str,
refresh_token: str,
*,
last_refresh: Optional[str] = None,
) -> None:
"""Write refreshed tokens back to ~/.codex/auth.json.
OpenAI OAuth refresh tokens are single-use and rotate on every refresh.
When Hermes refreshes a token it consumes the old refresh_token; if we
don't write the new pair back, the Codex CLI (or VS Code extension) will
fail with ``refresh_token_reused`` on its next refresh attempt.
This mirrors the Anthropic write-back to ~/.claude/.credentials.json
via ``_write_claude_code_credentials()``.
"""
codex_home = os.getenv("CODEX_HOME", "").strip()
if not codex_home:
codex_home = str(Path.home() / ".codex")
auth_path = Path(codex_home).expanduser() / "auth.json"
try:
existing: Dict[str, Any] = {}
if auth_path.is_file():
existing = json.loads(auth_path.read_text(encoding="utf-8"))
if not isinstance(existing, dict):
existing = {}
tokens_dict = existing.get("tokens")
if not isinstance(tokens_dict, dict):
tokens_dict = {}
tokens_dict["access_token"] = access_token
tokens_dict["refresh_token"] = refresh_token
existing["tokens"] = tokens_dict
if last_refresh is not None:
existing["last_refresh"] = last_refresh
auth_path.parent.mkdir(parents=True, exist_ok=True)
auth_path.write_text(json.dumps(existing, indent=2), encoding="utf-8")
auth_path.chmod(0o600)
except (OSError, IOError) as exc:
logger.debug("Failed to write refreshed tokens to %s: %s", auth_path, exc)
def _save_codex_tokens(tokens: Dict[str, str], last_refresh: str = None) -> None:
"""Save Codex OAuth tokens to Hermes auth store (~/.hermes/auth.json)."""
if last_refresh is None:
@@ -1604,12 +1561,6 @@ def _refresh_codex_auth_tokens(
updated_tokens["refresh_token"] = refreshed["refresh_token"]
_save_codex_tokens(updated_tokens)
# Write back to ~/.codex/auth.json so Codex CLI / VS Code stay in sync.
_write_codex_cli_tokens(
refreshed["access_token"],
refreshed["refresh_token"],
last_refresh=refreshed.get("last_refresh"),
)
return updated_tokens
@@ -1654,25 +1605,7 @@ def resolve_codex_runtime_credentials(
refresh_skew_seconds: int = CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
) -> Dict[str, Any]:
"""Resolve runtime credentials from Hermes's own Codex token store."""
try:
data = _read_codex_tokens()
except AuthError as orig_err:
# Only attempt migration when there are NO tokens stored at all
# (code == "codex_auth_missing"), not when tokens exist but are invalid.
if orig_err.code != "codex_auth_missing":
raise
# Migration: user had Codex as active provider with old storage (~/.codex/).
cli_tokens = _import_codex_cli_tokens()
if cli_tokens:
logger.info("Migrating Codex credentials from ~/.codex/ to Hermes auth store")
print("⚠️ Migrating Codex credentials to Hermes's own auth store.")
print(" This avoids conflicts with Codex CLI and VS Code.")
print(" Run `hermes auth` to create a fully independent session.\n")
_save_codex_tokens(cli_tokens)
data = _read_codex_tokens()
else:
raise
data = _read_codex_tokens()
tokens = dict(data["tokens"])
access_token = str(tokens.get("access_token", "") or "").strip()
refresh_timeout_seconds = float(os.getenv("HERMES_CODEX_REFRESH_TIMEOUT_SECONDS", "20"))

View File

@@ -14,7 +14,6 @@ from hermes_cli.auth import (
PROVIDER_REGISTRY,
_read_codex_tokens,
_save_codex_tokens,
_write_codex_cli_tokens,
_import_codex_cli_tokens,
get_codex_auth_status,
get_provider_auth_state,
@@ -182,98 +181,6 @@ def test_codex_tokens_not_written_to_shared_file(tmp_path, monkeypatch):
assert data["tokens"]["access_token"] == "hermes-at"
def test_write_codex_cli_tokens_creates_file(tmp_path, monkeypatch):
"""_write_codex_cli_tokens creates ~/.codex/auth.json with refreshed tokens."""
codex_home = tmp_path / "codex-cli"
monkeypatch.setenv("CODEX_HOME", str(codex_home))
_write_codex_cli_tokens("new-access", "new-refresh", last_refresh="2026-04-12T00:00:00Z")
auth_path = codex_home / "auth.json"
assert auth_path.exists()
data = json.loads(auth_path.read_text())
assert data["tokens"]["access_token"] == "new-access"
assert data["tokens"]["refresh_token"] == "new-refresh"
assert data["last_refresh"] == "2026-04-12T00:00:00Z"
# Verify file permissions are restricted
assert (auth_path.stat().st_mode & 0o777) == 0o600
def test_write_codex_cli_tokens_preserves_existing(tmp_path, monkeypatch):
"""_write_codex_cli_tokens preserves extra fields in existing auth.json."""
codex_home = tmp_path / "codex-cli"
codex_home.mkdir(parents=True, exist_ok=True)
monkeypatch.setenv("CODEX_HOME", str(codex_home))
existing = {
"tokens": {
"access_token": "old-access",
"refresh_token": "old-refresh",
"extra_field": "preserved",
},
"last_refresh": "2026-01-01T00:00:00Z",
"custom_key": "keep_me",
}
(codex_home / "auth.json").write_text(json.dumps(existing))
_write_codex_cli_tokens("updated-access", "updated-refresh")
data = json.loads((codex_home / "auth.json").read_text())
assert data["tokens"]["access_token"] == "updated-access"
assert data["tokens"]["refresh_token"] == "updated-refresh"
assert data["tokens"]["extra_field"] == "preserved"
assert data["custom_key"] == "keep_me"
# last_refresh not updated since we didn't pass it
assert data["last_refresh"] == "2026-01-01T00:00:00Z"
def test_write_codex_cli_tokens_handles_missing_dir(tmp_path, monkeypatch):
"""_write_codex_cli_tokens creates parent directories if missing."""
codex_home = tmp_path / "does" / "not" / "exist"
monkeypatch.setenv("CODEX_HOME", str(codex_home))
_write_codex_cli_tokens("at", "rt")
assert (codex_home / "auth.json").exists()
data = json.loads((codex_home / "auth.json").read_text())
assert data["tokens"]["access_token"] == "at"
def test_refresh_codex_auth_tokens_writes_back_to_cli(tmp_path, monkeypatch):
"""After refreshing, _refresh_codex_auth_tokens writes back to ~/.codex/auth.json."""
from hermes_cli.auth import _refresh_codex_auth_tokens
hermes_home = tmp_path / "hermes"
codex_home = tmp_path / "codex-cli"
hermes_home.mkdir(parents=True, exist_ok=True)
codex_home.mkdir(parents=True, exist_ok=True)
(hermes_home / "auth.json").write_text(json.dumps({"version": 1, "providers": {}}))
monkeypatch.setenv("HERMES_HOME", str(hermes_home))
monkeypatch.setenv("CODEX_HOME", str(codex_home))
# Write initial CLI tokens
(codex_home / "auth.json").write_text(json.dumps({
"tokens": {"access_token": "old-at", "refresh_token": "old-rt"},
}))
# Mock the pure refresh to return new tokens
monkeypatch.setattr("hermes_cli.auth.refresh_codex_oauth_pure", lambda *a, **kw: {
"access_token": "refreshed-at",
"refresh_token": "refreshed-rt",
"last_refresh": "2026-04-12T01:00:00Z",
})
_refresh_codex_auth_tokens(
{"access_token": "old-at", "refresh_token": "old-rt"},
timeout_seconds=10,
)
# Verify CLI file was updated
cli_data = json.loads((codex_home / "auth.json").read_text())
assert cli_data["tokens"]["access_token"] == "refreshed-at"
assert cli_data["tokens"]["refresh_token"] == "refreshed-rt"
def test_resolve_returns_hermes_auth_store_source(tmp_path, monkeypatch):
hermes_home = tmp_path / "hermes"
_setup_hermes_auth(hermes_home)