feat(xai-oauth): add xAI Grok OAuth (SuperGrok Subscription) provider

Adds a new authentication provider that lets SuperGrok subscribers sign
in to Hermes with their xAI account via the standard OAuth 2.0 PKCE
loopback flow, instead of pasting a raw API key from console.x.ai.

Highlights
----------
* OAuth 2.0 PKCE loopback login against accounts.x.ai with discovery,
  state/nonce, and a strict CORS-origin allowlist on the callback.
* Authorize URL carries `plan=generic` (required for non-allowlisted
  loopback clients) and `referrer=hermes-agent` for best-effort
  attribution in xAI's OAuth server logs.
* Token storage in `auth.json` with file-locked atomic writes; JWT
  `exp`-based expiry detection with skew; refresh-token rotation
  synced both ways between the singleton store and the credential
  pool so multi-process / multi-profile setups don't tear each other's
  refresh tokens.
* Reactive 401 retry: on a 401 from the xAI Responses API, the agent
  refreshes the token, swaps it back into `self.api_key`, and retries
  the call once. Guarded against silent account swaps when the active
  key was sourced from a different (manual) pool entry.
* Auxiliary tasks (curator, vision, embeddings, etc.) route through a
  dedicated xAI Responses-mode auxiliary client instead of falling back
  to OpenRouter billing.
* Direct HTTP tools (`tools/xai_http.py`, transcription, TTS, image-gen
  plugin) resolve credentials through a unified runtime → singleton →
  env-var fallback chain so xai-oauth users get them for free.
* `hermes auth add xai-oauth` and `hermes auth remove xai-oauth N` are
  wired through the standard auth-commands surface; remove cleans up
  the singleton loopback_pkce entry so it doesn't silently reinstate.
* `hermes model` provider picker shows
  "xAI Grok OAuth (SuperGrok Subscription)" and the model-flow falls
  back to pool credentials when the singleton is missing.

Hardening
---------
* Discovery and refresh responses validate the returned
  `token_endpoint` host against the same `*.x.ai` allowlist as the
  authorization endpoint, blocking MITM persistence of a hostile
  endpoint.
* Discovery / refresh / token-exchange `response.json()` calls are
  wrapped to raise typed `AuthError` on malformed bodies (captive
  portals, proxy error pages) instead of leaking JSONDecodeError
  tracebacks.
* `prompt_cache_key` is routed through `extra_body` on the codex
  transport (sending it as a top-level kwarg trips xAI's SDK with a
  TypeError).
* Credential-pool sync-back preserves `active_provider` so refreshing
  an OAuth entry doesn't silently flip the active provider out from
  under the running agent.

Testing
-------
* New `tests/hermes_cli/test_auth_xai_oauth_provider.py` (~63 tests)
  covers JWT expiry, OAuth URL params (plan + referrer), CORS origins,
  redirect URI validation, singleton↔pool sync, concurrency races,
  refresh error paths, runtime resolution, and malformed-JSON guards.
* Extended `test_credential_pool.py`, `test_codex_transport.py`, and
  `test_run_agent_codex_responses.py` cover the pool sync-back,
  `extra_body` routing, and 401 reactive refresh paths.
* 165 tests passing on this branch via `scripts/run_tests.sh`.
This commit is contained in:
Jaaneek 2026-05-15 16:10:38 +01:00 committed by Teknium
parent 9fb40e6a3d
commit b62c997973
27 changed files with 3843 additions and 131 deletions

View file

@ -33,7 +33,7 @@ from hermes_constants import OPENROUTER_BASE_URL
# Providers that support OAuth login in addition to API keys.
_OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex", "qwen-oauth", "google-gemini-cli", "minimax-oauth"}
_OAUTH_CAPABLE_PROVIDERS = {"anthropic", "nous", "openai-codex", "xai-oauth", "qwen-oauth", "google-gemini-cli", "minimax-oauth"}
def _get_custom_provider_names() -> list:
@ -77,6 +77,8 @@ def _normalize_provider(provider: str) -> str:
normalized = (provider or "").strip().lower()
if normalized in {"or", "open-router"}:
return "openrouter"
if normalized in {"grok-oauth", "xai-oauth", "x-ai-oauth", "xai-grok-oauth"}:
return "xai-oauth"
# Check if it matches a custom provider name
custom_key = _resolve_custom_provider_input(normalized)
if custom_key:
@ -170,7 +172,7 @@ def auth_add_command(args) -> None:
if provider.startswith(CUSTOM_POOL_PREFIX):
requested_type = AUTH_TYPE_API_KEY
else:
requested_type = AUTH_TYPE_OAUTH if provider in {"anthropic", "nous", "openai-codex", "qwen-oauth", "google-gemini-cli", "minimax-oauth"} else AUTH_TYPE_API_KEY
requested_type = AUTH_TYPE_OAUTH if provider in _OAUTH_CAPABLE_PROVIDERS else AUTH_TYPE_API_KEY
pool = load_pool(provider)
@ -333,6 +335,31 @@ def auth_add_command(args) -> None:
print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
return
if provider == "xai-oauth":
creds = auth_mod._xai_oauth_loopback_login(
timeout_seconds=getattr(args, "timeout", None) or 20.0,
open_browser=not getattr(args, "no_browser", False),
)
label = (getattr(args, "label", None) or "").strip() or label_from_token(
creds["tokens"]["access_token"],
_oauth_default_label(provider, len(pool.entries()) + 1),
)
entry = PooledCredential(
provider=provider,
id=uuid.uuid4().hex[:6],
label=label,
auth_type=AUTH_TYPE_OAUTH,
priority=0,
source=f"{SOURCE_MANUAL}:xai_pkce",
access_token=creds["tokens"]["access_token"],
refresh_token=creds["tokens"].get("refresh_token"),
base_url=creds.get("base_url"),
last_refresh=creds.get("last_refresh"),
)
pool.add_entry(entry)
print(f'Added {provider} OAuth credential #{len(pool.entries())}: "{entry.label}"')
return
if provider == "google-gemini-cli":
from agent.google_oauth import run_gemini_oauth_login_pure