seb/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge main into bb/gui.

Browse Source 
Resolve merge conflicts while preserving bb/gui dashboard paths and STT provider support.
This commit is contained in:
Brooklyn Nicholson
2026-05-15 15:33:28 -05:00
parent e5bbeb9f1e 931caf2b2d
commit 6640a9d3ab
415 changed files with 38391 additions and 20402 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hermes_cli/config.py
+81 -23
View File
@@ -731,6 +731,12 @@ DEFAULT_CONFIG = {
"target_ratio": 0.20, # fraction of threshold to preserve as recent tail
"protect_last_n": 20, # minimum recent messages to keep uncompressed
"hygiene_hard_message_limit": 400, # gateway session-hygiene force-compress threshold by message count
"protect_first_n": 3, # non-system head messages always preserved
# verbatim, in ADDITION to the system prompt
# (which is always implicitly protected). Set to
# 0 for long-running rolling-compaction sessions
# where you want nothing pinned except the
# system prompt + rolling summary + recent tail.
},
# Anthropic prompt caching (Claude via OpenRouter or native Anthropic API).
@@ -971,6 +977,21 @@ DEFAULT_CONFIG = {
# Web dashboard settings
"dashboard": {
"theme": "default", # Dashboard visual theme: "default", "midnight", "ember", "mono", "cyberpunk", "rose"
# Hide the token/cost analytics surfaces (Analytics page, token bars and
# cost figures on the Models page) by default. The numbers shown there
# are a local debug estimate: they only count successful main-agent
# responses with a usable ``response.usage``, and silently exclude every
# auxiliary call (context compression, title generation, vision,
# session search, web extract, smart approval, MCP routing, plugin LLM
# access) plus provider-side retries, fallback attempts, and any call
# whose usage block didn't come back. Cache writes are also missing
# from the API response. On models with heavy auxiliary traffic
# (Kimi K2.6, MiniMax M2.7) the local total can be 10x-100x lower than
# the provider bill, which is worse than hiding the numbers entirely
# because they look precise enough to compare against the provider.
# Set this to True to re-enable the surfaces with the understanding
# that the numbers are a local lower-bound estimate, not billing.
"show_token_analytics": False,
},
# Privacy settings
@@ -1235,6 +1256,9 @@ DEFAULT_CONFIG = {
"free_response_channels": "", # Comma-separated channel IDs where bot responds without mention
"allowed_channels": "", # If set, bot ONLY responds in these channel IDs (whitelist)
"auto_thread": True, # Auto-create threads on @mention in channels (like Slack)
"thread_require_mention": False, # If True, require @mention in threads too (multi-bot threads)
"history_backfill": True, # If True, prepend recent channel scrollback when bot is triggered (recovers messages missed while require_mention gated them out)
"history_backfill_limit": 50, # Max number of recent messages to scan when assembling the backfill block
"reactions": True, # Add 👀/✅/❌ reactions to messages during processing
"channel_prompts": {}, # Per-channel ephemeral system prompts (forum parents apply to child threads)
# Opt-in DM role-based auth (#12136). By default, DISCORD_ALLOWED_ROLES
@@ -2113,26 +2137,10 @@ OPTIONAL_ENV_VARS = {
"category": "tool",
},
"FAL_KEY": {
"description": "FAL API key for image generation",
"description": "FAL API key for image and video generation",
"prompt": "FAL API key",
"url": "https://fal.ai/",
"tools": ["image_generate"],
"password": True,
"category": "tool",
},
"TINKER_API_KEY": {
"description": "Tinker API key for RL training",
"prompt": "Tinker API key",
"url": "https://tinker-console.thinkingmachines.ai/keys",
"tools": ["rl_start_training", "rl_check_status", "rl_stop_training"],
"password": True,
"category": "tool",
},
"WANDB_API_KEY": {
"description": "Weights & Biases API key for experiment tracking",
"prompt": "WandB API key",
"url": "https://wandb.ai/authorize",
"tools": ["rl_get_results", "rl_check_status"],
"tools": ["image_generate", "video_generate"],
"password": True,
"category": "tool",
},
@@ -4326,10 +4334,34 @@ def load_env() -> Dict[str, str]:
concatenated KEY=VALUE pairs on a single line) are handled
gracefully instead of producing mangled values such as duplicated
bot tokens. See #8908.
The parsed dict is memoised keyed on the .env file mtime, because
``get_env_value()`` is called dozens-to-hundreds of times per
interactive menu render (`hermes tools`, `hermes setup`, status
panels). Sanitisation is O(lines × known-keys), so re-parsing the
same file on every call was burning ~300ms of CPU per `hermes tools`
menu paint on top of the OAuth-refresh slowness. The mtime check
invalidates the cache when the user edits .env mid-process.
"""
global _env_cache
env_path = get_env_path()
env_vars = {}
try:
mtime = env_path.stat().st_mtime
size = env_path.stat().st_size
cache_key = (str(env_path), mtime, size)
except FileNotFoundError:
cache_key = (str(env_path), None, None)
except Exception:
cache_key = None
if cache_key is not None and _env_cache is not None:
cached_key, cached_vars = _env_cache
if cached_key == cache_key:
return dict(cached_vars)
env_vars: Dict[str, str] = {}
if env_path.exists():
# On Windows, open() defaults to the system locale (cp1252) which can
# fail on UTF-8 .env files. Always use explicit UTF-8; tolerate BOM
@@ -4345,10 +4377,33 @@ def load_env() -> Dict[str, str]:
if line and not line.startswith('#') and '=' in line:
key, _, value = line.partition('=')
env_vars[key.strip()] = value.strip().strip('"\'')
if cache_key is not None:
_env_cache = (cache_key, dict(env_vars))
return env_vars
# Module-level memo for load_env(), keyed on (path, mtime, size).
# Editing .env bumps mtime → next load_env() rebuilds. invalidate_env_cache()
# is the explicit knob for writers that update .env via this module
# (set_env_value, save_env, etc.) without relying on filesystem mtime
# resolution.
_env_cache: Optional[Tuple[Tuple[str, Optional[float], Optional[int]], Dict[str, str]]] = None
def invalidate_env_cache() -> None:
"""Clear the load_env() process-level memo.
Writers that mutate .env (set_env_value, save_env, etc.) call this
to guarantee the next load_env() sees their change even on
filesystems with coarse mtime resolution. Reads invalidate naturally
via the mtime/size check.
"""
global _env_cache
_env_cache = None
def _sanitize_env_lines(lines: list) -> list:
"""Fix corrupted .env lines before reading or writing.
@@ -4451,6 +4506,7 @@ def sanitize_env_file() -> int:
pass
raise
_secure_file(env_path)
invalidate_env_cache()
return fixes
@@ -4562,6 +4618,7 @@ def save_env_value(key: str, value: str):
_secure_file(env_path)
os.environ[key] = value
invalidate_env_cache()
def remove_env_value(key: str) -> bool:
@@ -4617,6 +4674,7 @@ def remove_env_value(key: str) -> bool:
_secure_file(env_path)
os.environ.pop(key, None)
invalidate_env_cache()
return found
@@ -4803,6 +4861,7 @@ def show_config():
print(f" Threshold: {compression.get('threshold', 0.50) * 100:.0f}%")
print(f" Target ratio: {compression.get('target_ratio', 0.20) * 100:.0f}% of threshold preserved")
print(f" Protect last: {compression.get('protect_last_n', 20)} messages")
print(f" Protect first: {compression.get('protect_first_n', 3)} non-system head messages")
_aux_comp = config.get('auxiliary', {}).get('compression', {})
_sm = _aux_comp.get('model', '') or '(auto)'
print(f" Model: {_sm}")
@@ -4922,8 +4981,7 @@ def set_config_value(key: str, value: str):
'FAL_KEY', 'TELEGRAM_BOT_TOKEN', 'DISCORD_BOT_TOKEN',
'TERMINAL_SSH_HOST', 'TERMINAL_SSH_USER', 'TERMINAL_SSH_KEY',
'SUDO_PASSWORD', 'SLACK_BOT_TOKEN', 'SLACK_APP_TOKEN',
'GITHUB_TOKEN', 'HONCHO_API_KEY', 'WANDB_API_KEY',
'TINKER_API_KEY',
'GITHUB_TOKEN', 'HONCHO_API_KEY',
]
if key.upper() in api_keys or key.upper().endswith(('_API_KEY', '_TOKEN')) or key.upper().startswith('TERMINAL_SSH'):