refactor(cli, auth): Add Codex/OpenAI OAuth Support - finalized

- Replace `hermes login` with `hermes model` for selecting providers and managing authentication.
- Update documentation and CLI commands to reflect the new provider selection process.
- Introduce a new redaction system for logging sensitive information.
- Enhance Codex model discovery by integrating API fetching and local cache.
- Adjust max turns configuration logic for better clarity and precedence.
- Improve error handling and user feedback during authentication processes.
This commit is contained in:
teknium1
2026-02-28 21:56:05 -08:00
parent 500f0eab4a
commit 95b0610f36
3 changed files with 124 additions and 2 deletions

115
agent/redact.py Normal file
View File

@@ -0,0 +1,115 @@
"""Regex-based secret redaction for logs and tool output.
Applies pattern matching to mask API keys, tokens, and credentials
before they reach log files, verbose output, or gateway logs.
Short tokens (< 18 chars) are fully masked. Longer tokens preserve
the first 6 and last 4 characters for debuggability.
"""
import logging
import re
from typing import Optional
logger = logging.getLogger(__name__)
# Known API key prefixes -- match the prefix + contiguous token chars
_PREFIX_PATTERNS = [
r"sk-[A-Za-z0-9_-]{10,}", # OpenAI / OpenRouter
r"ghp_[A-Za-z0-9]{10,}", # GitHub PAT (classic)
r"github_pat_[A-Za-z0-9_]{10,}", # GitHub PAT (fine-grained)
r"xox[baprs]-[A-Za-z0-9-]{10,}", # Slack tokens
r"AIza[A-Za-z0-9_-]{30,}", # Google API keys
r"pplx-[A-Za-z0-9]{10,}", # Perplexity
r"fal_[A-Za-z0-9_-]{10,}", # Fal.ai
r"fc-[A-Za-z0-9]{10,}", # Firecrawl
r"bb_live_[A-Za-z0-9_-]{10,}", # BrowserBase
r"gAAAA[A-Za-z0-9_=-]{20,}", # Codex encrypted tokens
]
# ENV assignment patterns: KEY=value where KEY contains a secret-like name
_SECRET_ENV_NAMES = r"(?:API_?KEY|TOKEN|SECRET|PASSWORD|PASSWD|CREDENTIAL|AUTH)"
_ENV_ASSIGN_RE = re.compile(
rf"([A-Z_]*{_SECRET_ENV_NAMES}[A-Z_]*)\s*=\s*(['\"]?)(\S+)\2",
re.IGNORECASE,
)
# JSON field patterns: "apiKey": "value", "token": "value", etc.
_JSON_KEY_NAMES = r"(?:api_?[Kk]ey|token|secret|password|access_token|refresh_token|auth_token|bearer)"
_JSON_FIELD_RE = re.compile(
rf'("{_JSON_KEY_NAMES}")\s*:\s*"([^"]+)"',
re.IGNORECASE,
)
# Authorization headers
_AUTH_HEADER_RE = re.compile(
r"(Authorization:\s*Bearer\s+)(\S+)",
re.IGNORECASE,
)
# Telegram bot tokens: bot<digits>:<token> or <digits>:<alphanum>
_TELEGRAM_RE = re.compile(
r"(bot)?(\d{8,}):([-A-Za-z0-9_]{30,})",
)
# Compile known prefix patterns into one alternation
_PREFIX_RE = re.compile(
r"(?<![A-Za-z0-9_-])(" + "|".join(_PREFIX_PATTERNS) + r")(?![A-Za-z0-9_-])"
)
def _mask_token(token: str) -> str:
"""Mask a token, preserving prefix for long tokens."""
if len(token) < 18:
return "***"
return f"{token[:6]}...{token[-4:]}"
def redact_sensitive_text(text: str) -> str:
"""Apply all redaction patterns to a block of text.
Safe to call on any string -- non-matching text passes through unchanged.
"""
if not text:
return text
# Known prefixes (sk-, ghp_, etc.)
text = _PREFIX_RE.sub(lambda m: _mask_token(m.group(1)), text)
# ENV assignments: OPENAI_API_KEY=sk-abc...
def _redact_env(m):
name, quote, value = m.group(1), m.group(2), m.group(3)
return f"{name}={quote}{_mask_token(value)}{quote}"
text = _ENV_ASSIGN_RE.sub(_redact_env, text)
# JSON fields: "apiKey": "value"
def _redact_json(m):
key, value = m.group(1), m.group(2)
return f'{key}: "{_mask_token(value)}"'
text = _JSON_FIELD_RE.sub(_redact_json, text)
# Authorization headers
text = _AUTH_HEADER_RE.sub(
lambda m: m.group(1) + _mask_token(m.group(2)),
text,
)
# Telegram bot tokens
def _redact_telegram(m):
prefix = m.group(1) or ""
digits = m.group(2)
return f"{prefix}{digits}:***"
text = _TELEGRAM_RE.sub(_redact_telegram, text)
return text
class RedactingFormatter(logging.Formatter):
"""Log formatter that redacts secrets from all log messages."""
def __init__(self, fmt=None, datefmt=None, style='%', **kwargs):
super().__init__(fmt, datefmt, style, **kwargs)
def format(self, record: logging.LogRecord) -> str:
original = super().format(record)
return redact_sensitive_text(original)

View File

@@ -2027,7 +2027,8 @@ async def start_gateway(config: Optional[GatewayConfig] = None) -> bool:
maxBytes=5 * 1024 * 1024,
backupCount=3,
)
file_handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(name)s: %(message)s'))
from agent.redact import RedactingFormatter
file_handler.setFormatter(RedactingFormatter('%(asctime)s %(levelname)s %(name)s: %(message)s'))
logging.getLogger().addHandler(file_handler)
logging.getLogger().setLevel(logging.INFO)

View File

@@ -247,13 +247,19 @@ class AIAgent:
self._use_prompt_caching = is_openrouter and is_claude
self._cache_ttl = "5m" # Default 5-minute TTL (1.25x write cost)
# Configure logging
# Configure logging with secret redaction
from agent.redact import RedactingFormatter
if self.verbose_logging:
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
datefmt='%H:%M:%S'
)
for handler in logging.getLogger().handlers:
handler.setFormatter(RedactingFormatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s',
datefmt='%H:%M:%S',
))
# Keep third-party libraries at WARNING level to reduce noise
# We have our own retry and error logging that's more informative
logging.getLogger('openai').setLevel(logging.WARNING)