feat(copilot): add 401 auth recovery with automatic token refresh and client rebuild

When using GitHub Copilot as provider, HTTP 401 errors could cause
Hermes to silently fall back to the next model in the chain instead
of recovering. This adds a one-shot retry mechanism that:

1. Re-resolves the Copilot token via the standard priority chain
   (COPILOT_GITHUB_TOKEN -> GH_TOKEN -> GITHUB_TOKEN -> gh auth token)
2. Rebuilds the OpenAI client with fresh credentials and Copilot headers
3. Retries the failed request before falling back

The fix handles the common case where the gho_* OAuth token remains
valid but the httpx client state becomes stale (e.g. after startup
race conditions or long-lived sessions).

Key design decisions:
- Always rebuild client even if token string unchanged (recovers stale state)
- Uses _apply_client_headers_for_base_url() for canonical header management
- One-shot flag guard prevents infinite 401 loops (matches existing pattern
  used by Codex/Nous/Anthropic providers)
- No token exchange via /copilot_internal/v2/token (returns 404 for some
  account types; direct gho_* auth works reliably)

Tests: 3 new test cases covering end-to-end 401->refresh->retry,
client rebuild verification, and same-token rebuild scenarios.
Docs: Updated providers.md with Copilot auth behavior section.
This commit is contained in:
l0hde 2026-04-15 10:28:17 +02:00 committed by Teknium
parent 7d2f93a97f
commit 2cab8129d1
3 changed files with 143 additions and 0 deletions

View file

@ -5135,6 +5135,41 @@ class AIAgent:
return True
def _try_refresh_copilot_client_credentials(self) -> bool:
"""Refresh Copilot credentials and rebuild the shared OpenAI client.
Copilot tokens may remain the same string across refreshes (`gh auth token`
returns a stable OAuth token in many setups). We still rebuild the client
on 401 so retries recover from stale auth/client state without requiring
a session restart.
"""
if self.provider != "copilot":
return False
try:
from hermes_cli.copilot_auth import resolve_copilot_token
new_token, token_source = resolve_copilot_token()
except Exception as exc:
logger.debug("Copilot credential refresh failed: %s", exc)
return False
if not isinstance(new_token, str) or not new_token.strip():
return False
new_token = new_token.strip()
self.api_key = new_token
self._client_kwargs["api_key"] = self.api_key
self._client_kwargs["base_url"] = self.base_url
self._apply_client_headers_for_base_url(str(self.base_url or ""))
if not self._replace_primary_openai_client(reason="copilot_credential_refresh"):
return False
logger.info("Copilot credentials refreshed from %s", token_source)
return True
def _try_refresh_anthropic_client_credentials(self) -> bool:
if self.api_mode != "anthropic_messages" or not hasattr(self, "_anthropic_api_key"):
return False
@ -9375,6 +9410,7 @@ class AIAgent:
codex_auth_retry_attempted=False
anthropic_auth_retry_attempted=False
nous_auth_retry_attempted=False
copilot_auth_retry_attempted=False
thinking_sig_retry_attempted = False
has_retried_429 = False
restart_with_compressed_messages = False
@ -10338,6 +10374,15 @@ class AIAgent:
print(f"{self.log_prefix} • Check credits / billing: https://portal.nousresearch.com")
print(f"{self.log_prefix} • Verify stored credentials: {_dhh}/auth.json")
print(f"{self.log_prefix} • Switch providers temporarily: /model <model> --provider openrouter")
if (
self.provider == "copilot"
and status_code == 401
and not copilot_auth_retry_attempted
):
copilot_auth_retry_attempted = True
if self._try_refresh_copilot_client_credentials():
self._vprint(f"{self.log_prefix}🔐 Copilot credentials refreshed after 401. Retrying request...")
continue
if (
self.api_mode == "anthropic_messages"
and status_code == 401