7ddd896b36
Adds the newly available GLM-5.1 model to the hardcoded Z.AI provider model list so it appears in the model dropdown. Fixes #17. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
641 lines
26 KiB
Python
641 lines
26 KiB
Python
"""
|
|
Hermes Web UI -- Shared configuration, constants, and global state.
|
|
Imported by all other api/* modules and by server.py.
|
|
|
|
Discovery order for all paths:
|
|
1. Explicit environment variable
|
|
2. Filesystem heuristics (sibling checkout, parent dir, common install locations)
|
|
3. Hardened defaults relative to $HOME
|
|
4. Fail loudly with a human-readable fix-it message if required modules are missing
|
|
"""
|
|
import collections
|
|
import json
|
|
import os
|
|
import sys
|
|
import threading
|
|
import time
|
|
import traceback
|
|
import uuid
|
|
from pathlib import Path
|
|
from urllib.parse import parse_qs, urlparse
|
|
|
|
# ── Basic layout ──────────────────────────────────────────────────────────────
|
|
HOME = Path.home()
|
|
# REPO_ROOT is the directory that contains this file's parent (api/ -> repo root)
|
|
REPO_ROOT = Path(__file__).parent.parent.resolve()
|
|
|
|
# ── Network config (env-overridable) ─────────────────────────────────────────
|
|
HOST = os.getenv('HERMES_WEBUI_HOST', '127.0.0.1')
|
|
PORT = int(os.getenv('HERMES_WEBUI_PORT', '8787'))
|
|
|
|
# ── State directory (env-overridable, never inside repo) ──────────────────────
|
|
STATE_DIR = Path(os.getenv(
|
|
'HERMES_WEBUI_STATE_DIR',
|
|
str(HOME / '.hermes' / 'webui-mvp')
|
|
)).expanduser().resolve()
|
|
|
|
SESSION_DIR = STATE_DIR / 'sessions'
|
|
WORKSPACES_FILE = STATE_DIR / 'workspaces.json'
|
|
SESSION_INDEX_FILE = SESSION_DIR / '_index.json'
|
|
SETTINGS_FILE = STATE_DIR / 'settings.json'
|
|
LAST_WORKSPACE_FILE = STATE_DIR / 'last_workspace.txt'
|
|
PROJECTS_FILE = STATE_DIR / 'projects.json'
|
|
|
|
# ── Hermes agent directory discovery ─────────────────────────────────────────
|
|
def _discover_agent_dir() -> Path:
|
|
"""
|
|
Locate the hermes-agent checkout using a multi-strategy search.
|
|
|
|
Priority:
|
|
1. HERMES_WEBUI_AGENT_DIR env var -- explicit override always wins
|
|
2. HERMES_HOME / hermes-agent -- e.g. ~/.hermes/hermes-agent
|
|
3. Sibling of this repo -- ../hermes-agent
|
|
4. Parent of this repo -- ../../hermes-agent (nested layout)
|
|
5. Common install paths -- ~/.hermes/hermes-agent (again as fallback)
|
|
6. HOME / hermes-agent -- ~/hermes-agent (simple flat layout)
|
|
"""
|
|
candidates = []
|
|
|
|
# 1. Explicit env var
|
|
if os.getenv('HERMES_WEBUI_AGENT_DIR'):
|
|
candidates.append(Path(os.getenv('HERMES_WEBUI_AGENT_DIR')).expanduser().resolve())
|
|
|
|
# 2. HERMES_HOME / hermes-agent
|
|
hermes_home = os.getenv('HERMES_HOME', str(HOME / '.hermes'))
|
|
candidates.append(Path(hermes_home).expanduser() / 'hermes-agent')
|
|
|
|
# 3. Sibling: <repo-root>/../hermes-agent
|
|
candidates.append(REPO_ROOT.parent / 'hermes-agent')
|
|
|
|
# 4. Parent is the agent repo itself (repo cloned inside hermes-agent/)
|
|
if (REPO_ROOT.parent / 'run_agent.py').exists():
|
|
candidates.append(REPO_ROOT.parent)
|
|
|
|
# 5. ~/.hermes/hermes-agent (explicit common path)
|
|
candidates.append(HOME / '.hermes' / 'hermes-agent')
|
|
|
|
# 6. ~/hermes-agent
|
|
candidates.append(HOME / 'hermes-agent')
|
|
|
|
for path in candidates:
|
|
if path.exists() and (path / 'run_agent.py').exists():
|
|
return path.resolve()
|
|
|
|
return None
|
|
|
|
|
|
def _discover_python(agent_dir: Path) -> str:
|
|
"""
|
|
Locate a Python executable that has the Hermes agent dependencies installed.
|
|
|
|
Priority:
|
|
1. HERMES_WEBUI_PYTHON env var
|
|
2. Agent venv at <agent_dir>/venv/bin/python
|
|
3. Local .venv inside this repo
|
|
4. System python3
|
|
"""
|
|
if os.getenv('HERMES_WEBUI_PYTHON'):
|
|
return os.getenv('HERMES_WEBUI_PYTHON')
|
|
|
|
if agent_dir:
|
|
venv_py = agent_dir / 'venv' / 'bin' / 'python'
|
|
if venv_py.exists():
|
|
return str(venv_py)
|
|
|
|
# Windows layout
|
|
venv_py_win = agent_dir / 'venv' / 'Scripts' / 'python.exe'
|
|
if venv_py_win.exists():
|
|
return str(venv_py_win)
|
|
|
|
# Local .venv inside this repo
|
|
local_venv = REPO_ROOT / '.venv' / 'bin' / 'python'
|
|
if local_venv.exists():
|
|
return str(local_venv)
|
|
|
|
# Fall back to system python3
|
|
import shutil
|
|
for name in ('python3', 'python'):
|
|
found = shutil.which(name)
|
|
if found:
|
|
return found
|
|
|
|
return 'python3'
|
|
|
|
|
|
# Run discovery
|
|
_AGENT_DIR = _discover_agent_dir()
|
|
PYTHON_EXE = _discover_python(_AGENT_DIR)
|
|
|
|
# ── Inject agent dir into sys.path so Hermes modules are importable ───────────
|
|
if _AGENT_DIR is not None:
|
|
if str(_AGENT_DIR) not in sys.path:
|
|
sys.path.insert(0, str(_AGENT_DIR))
|
|
_HERMES_FOUND = True
|
|
else:
|
|
_HERMES_FOUND = False
|
|
|
|
# ── Config file (optional YAML) ──────────────────────────────────────────────
|
|
CONFIG_PATH = Path(os.getenv(
|
|
'HERMES_CONFIG_PATH',
|
|
str(HOME / '.hermes' / 'config.yaml')
|
|
)).expanduser()
|
|
|
|
try:
|
|
import yaml as _yaml
|
|
cfg = _yaml.safe_load(CONFIG_PATH.read_text()) if CONFIG_PATH.exists() else {}
|
|
except Exception:
|
|
cfg = {}
|
|
|
|
# ── Default workspace discovery ───────────────────────────────────────────────
|
|
def _discover_default_workspace() -> Path:
|
|
"""
|
|
Resolve the default workspace in order:
|
|
1. HERMES_WEBUI_DEFAULT_WORKSPACE env var
|
|
2. ~/workspace (common Hermes convention)
|
|
3. STATE_DIR / workspace (isolated fallback)
|
|
"""
|
|
if os.getenv('HERMES_WEBUI_DEFAULT_WORKSPACE'):
|
|
return Path(os.getenv('HERMES_WEBUI_DEFAULT_WORKSPACE')).expanduser().resolve()
|
|
|
|
common = HOME / 'workspace'
|
|
if common.exists():
|
|
return common.resolve()
|
|
|
|
return (STATE_DIR / 'workspace').resolve()
|
|
|
|
DEFAULT_WORKSPACE = _discover_default_workspace()
|
|
DEFAULT_MODEL = os.getenv('HERMES_WEBUI_DEFAULT_MODEL', 'openai/gpt-5.4-mini')
|
|
|
|
# ── Startup diagnostics ───────────────────────────────────────────────────────
|
|
def print_startup_config():
|
|
"""Print detected configuration at startup so the user can verify what was found."""
|
|
ok = '\033[32m[ok]\033[0m'
|
|
warn = '\033[33m[!!]\033[0m'
|
|
err = '\033[31m[XX]\033[0m'
|
|
|
|
lines = [
|
|
'',
|
|
' Hermes Web UI -- startup config',
|
|
' --------------------------------',
|
|
f' repo root : {REPO_ROOT}',
|
|
f' agent dir : {_AGENT_DIR if _AGENT_DIR else "NOT FOUND"} {ok if _AGENT_DIR else err}',
|
|
f' python : {PYTHON_EXE}',
|
|
f' state dir : {STATE_DIR}',
|
|
f' workspace : {DEFAULT_WORKSPACE}',
|
|
f' host:port : {HOST}:{PORT}',
|
|
f' config file : {CONFIG_PATH} {"(found)" if CONFIG_PATH.exists() else "(not found, using defaults)"}',
|
|
'',
|
|
]
|
|
print('\n'.join(lines), flush=True)
|
|
|
|
if not _HERMES_FOUND:
|
|
print(
|
|
f'{err} Could not find the Hermes agent directory.\n'
|
|
' The server will start but agent features will not work.\n'
|
|
'\n'
|
|
' To fix, set one of:\n'
|
|
' export HERMES_WEBUI_AGENT_DIR=/path/to/hermes-agent\n'
|
|
' export HERMES_HOME=/path/to/.hermes\n'
|
|
'\n'
|
|
' Or clone hermes-agent as a sibling of this repo:\n'
|
|
' git clone <hermes-agent-repo> ../hermes-agent\n',
|
|
flush=True
|
|
)
|
|
|
|
def verify_hermes_imports():
|
|
"""
|
|
Attempt to import the key Hermes modules.
|
|
Returns (ok: bool, missing: list[str]).
|
|
"""
|
|
required = ['run_agent']
|
|
missing = []
|
|
for mod in required:
|
|
try:
|
|
__import__(mod)
|
|
except ImportError:
|
|
missing.append(mod)
|
|
return (len(missing) == 0), missing
|
|
|
|
# ── Limits ───────────────────────────────────────────────────────────────────
|
|
MAX_FILE_BYTES = 200_000
|
|
MAX_UPLOAD_BYTES = 20 * 1024 * 1024
|
|
|
|
# ── File type maps ───────────────────────────────────────────────────────────
|
|
IMAGE_EXTS = {'.png', '.jpg', '.jpeg', '.gif', '.svg', '.webp', '.ico', '.bmp'}
|
|
MD_EXTS = {'.md', '.markdown', '.mdown'}
|
|
CODE_EXTS = {'.py', '.js', '.ts', '.jsx', '.tsx', '.css', '.html', '.json',
|
|
'.yaml', '.yml', '.toml', '.sh', '.bash', '.txt', '.log', '.env',
|
|
'.csv', '.xml', '.sql', '.rs', '.go', '.java', '.c', '.cpp', '.h'}
|
|
MIME_MAP = {
|
|
'.png':'image/png', '.jpg':'image/jpeg', '.jpeg':'image/jpeg',
|
|
'.gif':'image/gif', '.svg':'image/svg+xml', '.webp':'image/webp',
|
|
'.ico':'image/x-icon', '.bmp':'image/bmp',
|
|
'.pdf':'application/pdf', '.json':'application/json',
|
|
}
|
|
|
|
# ── Toolsets (from config.yaml or hardcoded default) ─────────────────────────
|
|
CLI_TOOLSETS = cfg.get('platform_toolsets', {}).get('cli', [
|
|
'browser', 'clarify', 'code_execution', 'cronjob', 'delegation', 'file',
|
|
'image_gen', 'memory', 'session_search', 'skills', 'terminal', 'todo',
|
|
'web', 'webhook',
|
|
])
|
|
|
|
# ── Model / provider discovery ───────────────────────────────────────────────
|
|
|
|
# Hardcoded fallback models (used when no config.yaml or agent is available)
|
|
_FALLBACK_MODELS = [
|
|
{'provider': 'OpenAI', 'id': 'openai/gpt-5.4-mini', 'label': 'GPT-5.4 Mini'},
|
|
{'provider': 'OpenAI', 'id': 'openai/gpt-4o', 'label': 'GPT-4o'},
|
|
{'provider': 'OpenAI', 'id': 'openai/o3', 'label': 'o3'},
|
|
{'provider': 'OpenAI', 'id': 'openai/o4-mini', 'label': 'o4-mini'},
|
|
{'provider': 'Anthropic', 'id': 'anthropic/claude-sonnet-4.6', 'label': 'Claude Sonnet 4.6'},
|
|
{'provider': 'Anthropic', 'id': 'anthropic/claude-sonnet-4-5', 'label': 'Claude Sonnet 4.5'},
|
|
{'provider': 'Anthropic', 'id': 'anthropic/claude-haiku-3-5', 'label': 'Claude Haiku 3.5'},
|
|
{'provider': 'Other', 'id': 'google/gemini-2.5-pro', 'label': 'Gemini 2.5 Pro'},
|
|
{'provider': 'Other', 'id': 'deepseek/deepseek-chat-v3-0324', 'label': 'DeepSeek V3'},
|
|
{'provider': 'Other', 'id': 'meta-llama/llama-4-scout', 'label': 'Llama 4 Scout'},
|
|
]
|
|
|
|
# Provider display names for known Hermes provider IDs
|
|
_PROVIDER_DISPLAY = {
|
|
'nous': 'Nous Portal', 'openrouter': 'OpenRouter', 'anthropic': 'Anthropic',
|
|
'openai': 'OpenAI', 'openai-codex': 'OpenAI Codex', 'copilot': 'GitHub Copilot',
|
|
'zai': 'Z.AI / GLM', 'kimi-coding': 'Kimi / Moonshot', 'deepseek': 'DeepSeek',
|
|
'minimax': 'MiniMax', 'google': 'Google', 'meta-llama': 'Meta Llama',
|
|
'huggingface': 'HuggingFace', 'alibaba': 'Alibaba',
|
|
'ollama': 'Ollama', 'lmstudio': 'LM Studio',
|
|
}
|
|
|
|
# Well-known models per provider (used to populate dropdown for direct API providers)
|
|
_PROVIDER_MODELS = {
|
|
'anthropic': [
|
|
{'id': 'claude-opus-4.6', 'label': 'Claude Opus 4.6'},
|
|
{'id': 'claude-sonnet-4.6', 'label': 'Claude Sonnet 4.6'},
|
|
{'id': 'claude-sonnet-4-5', 'label': 'Claude Sonnet 4.5'},
|
|
{'id': 'claude-haiku-3-5', 'label': 'Claude Haiku 3.5'},
|
|
],
|
|
'openai': [
|
|
{'id': 'gpt-5.4-mini', 'label': 'GPT-5.4 Mini'},
|
|
{'id': 'gpt-4o', 'label': 'GPT-4o'},
|
|
{'id': 'o3', 'label': 'o3'},
|
|
{'id': 'o4-mini', 'label': 'o4-mini'},
|
|
],
|
|
'openai-codex': [
|
|
{'id': 'codex-mini-latest', 'label': 'Codex Mini'},
|
|
],
|
|
'google': [
|
|
{'id': 'gemini-2.5-pro', 'label': 'Gemini 2.5 Pro'},
|
|
],
|
|
'deepseek': [
|
|
{'id': 'deepseek-chat-v3-0324', 'label': 'DeepSeek V3'},
|
|
{'id': 'deepseek-reasoner', 'label': 'DeepSeek Reasoner'},
|
|
],
|
|
'nous': [
|
|
{'id': 'claude-opus-4.6', 'label': 'Claude Opus 4.6 (via Nous)'},
|
|
{'id': 'claude-sonnet-4.6', 'label': 'Claude Sonnet 4.6 (via Nous)'},
|
|
{'id': 'gpt-5.4-mini', 'label': 'GPT-5.4 Mini (via Nous)'},
|
|
{'id': 'gemini-2.5-pro', 'label': 'Gemini 2.5 Pro (via Nous)'},
|
|
],
|
|
'zai': [
|
|
{'id': 'glm-5.1', 'label': 'GLM-5.1'},
|
|
{'id': 'glm-5', 'label': 'GLM-5'},
|
|
{'id': 'glm-5-turbo', 'label': 'GLM-5 Turbo'},
|
|
{'id': 'glm-4.7', 'label': 'GLM-4.7'},
|
|
{'id': 'glm-4.5', 'label': 'GLM-4.5'},
|
|
{'id': 'glm-4.5-flash', 'label': 'GLM-4.5 Flash'},
|
|
],
|
|
'kimi-coding': [
|
|
{'id': 'moonshot-v1-8k', 'label': 'Moonshot v1 8k'},
|
|
{'id': 'moonshot-v1-32k', 'label': 'Moonshot v1 32k'},
|
|
{'id': 'moonshot-v1-128k', 'label': 'Moonshot v1 128k'},
|
|
{'id': 'kimi-latest', 'label': 'Kimi Latest'},
|
|
],
|
|
'minimax': [
|
|
{'id': 'MiniMax-M2.7', 'label': 'MiniMax M2.7'},
|
|
{'id': 'MiniMax-M2.7-highspeed', 'label': 'MiniMax M2.7 Highspeed'},
|
|
{'id': 'MiniMax-M2.5', 'label': 'MiniMax M2.5'},
|
|
{'id': 'MiniMax-M2.5-highspeed', 'label': 'MiniMax M2.5 Highspeed'},
|
|
{'id': 'MiniMax-M2.1', 'label': 'MiniMax M2.1'},
|
|
],
|
|
}
|
|
|
|
|
|
def resolve_model_provider(model_id: str):
|
|
"""Resolve bare model name, provider, and base_url for AIAgent.
|
|
|
|
Model IDs from the dropdown may include a provider prefix
|
|
(e.g. 'anthropic/claude-sonnet-4.6'). Direct-API providers expect
|
|
bare model names, while OpenRouter expects the full provider/model path.
|
|
|
|
Also reads base_url from config.yaml so providers with custom endpoints
|
|
(e.g. MiniMax, Z.AI) are routed correctly.
|
|
|
|
Returns (model, provider, base_url) where provider and base_url may be None.
|
|
"""
|
|
config_provider = None
|
|
config_base_url = None
|
|
model_cfg = cfg.get('model', {})
|
|
if isinstance(model_cfg, dict):
|
|
config_provider = model_cfg.get('provider')
|
|
config_base_url = model_cfg.get('base_url')
|
|
|
|
model_id = (model_id or '').strip()
|
|
if not model_id:
|
|
return model_id, config_provider, config_base_url
|
|
|
|
if '/' in model_id:
|
|
prefix, bare = model_id.split('/', 1)
|
|
# If prefix matches config provider, strip it and use that provider directly
|
|
if config_provider and prefix == config_provider:
|
|
return bare, config_provider, config_base_url
|
|
# If the config provider is openrouter (or unset/None), pass the full
|
|
# provider/model string through -- OpenRouter uses this as its model ID.
|
|
# Only strip the prefix and switch to a direct-API provider when the
|
|
# config is explicitly set to that direct provider.
|
|
if config_provider and config_provider != 'openrouter' and prefix in _PROVIDER_MODELS:
|
|
return bare, prefix, None
|
|
|
|
return model_id, config_provider, config_base_url
|
|
|
|
|
|
def get_available_models() -> dict:
|
|
"""
|
|
Return available models grouped by provider.
|
|
|
|
Discovery order:
|
|
1. Read config.yaml 'model' section for active provider info
|
|
2. Check for known API keys in env or ~/.hermes/.env
|
|
3. Fetch models from custom endpoint if base_url is configured
|
|
4. Fall back to hardcoded model list (OpenRouter-style)
|
|
|
|
Returns: {
|
|
'active_provider': str|None,
|
|
'default_model': str,
|
|
'groups': [{'provider': str, 'models': [{'id': str, 'label': str}]}]
|
|
}
|
|
"""
|
|
active_provider = None
|
|
default_model = DEFAULT_MODEL
|
|
groups = []
|
|
|
|
# 1. Read config.yaml model section
|
|
model_cfg = cfg.get('model', {})
|
|
if isinstance(model_cfg, str):
|
|
default_model = model_cfg
|
|
elif isinstance(model_cfg, dict):
|
|
active_provider = model_cfg.get('provider')
|
|
cfg_default = model_cfg.get('default', '')
|
|
cfg_base_url = model_cfg.get('base_url', '')
|
|
if cfg_default:
|
|
default_model = cfg_default
|
|
|
|
# 2. Also check env vars for model override
|
|
env_model = os.getenv('HERMES_MODEL') or os.getenv('OPENAI_MODEL') or os.getenv('LLM_MODEL')
|
|
if env_model:
|
|
default_model = env_model.strip()
|
|
|
|
# 3. Try to read auth store for active provider (if hermes is installed)
|
|
if not active_provider:
|
|
auth_store_path = HOME / '.hermes' / 'auth.json'
|
|
if auth_store_path.exists():
|
|
try:
|
|
import json as _j
|
|
auth_store = _j.loads(auth_store_path.read_text())
|
|
active_provider = auth_store.get('active_provider')
|
|
except Exception:
|
|
pass
|
|
|
|
# 4. Check for API keys that imply available providers
|
|
hermes_env_path = HOME / '.hermes' / '.env'
|
|
env_keys = {}
|
|
if hermes_env_path.exists():
|
|
try:
|
|
for line in hermes_env_path.read_text().splitlines():
|
|
line = line.strip()
|
|
if line and not line.startswith('#') and '=' in line:
|
|
k, v = line.split('=', 1)
|
|
env_keys[k.strip()] = v.strip().strip('"').strip("'")
|
|
except Exception:
|
|
pass
|
|
|
|
# Merge with actual env
|
|
all_env = {**env_keys}
|
|
for k in ('ANTHROPIC_API_KEY', 'OPENAI_API_KEY', 'OPENROUTER_API_KEY',
|
|
'GOOGLE_API_KEY', 'GLM_API_KEY', 'KIMI_API_KEY', 'DEEPSEEK_API_KEY'):
|
|
val = os.getenv(k)
|
|
if val:
|
|
all_env[k] = val
|
|
|
|
detected_providers = set()
|
|
if active_provider:
|
|
detected_providers.add(active_provider)
|
|
if all_env.get('ANTHROPIC_API_KEY'):
|
|
detected_providers.add('anthropic')
|
|
if all_env.get('OPENAI_API_KEY'):
|
|
detected_providers.add('openai')
|
|
if all_env.get('OPENROUTER_API_KEY'):
|
|
detected_providers.add('openrouter')
|
|
if all_env.get('GOOGLE_API_KEY'):
|
|
detected_providers.add('google')
|
|
if all_env.get('GLM_API_KEY'):
|
|
detected_providers.add('zai')
|
|
if all_env.get('KIMI_API_KEY'):
|
|
detected_providers.add('kimi-coding')
|
|
if all_env.get('MINIMAX_API_KEY') or all_env.get('MINIMAX_CN_API_KEY'):
|
|
detected_providers.add('minimax')
|
|
if all_env.get('DEEPSEEK_API_KEY'):
|
|
detected_providers.add('deepseek')
|
|
|
|
# 3. Fetch models from custom endpoint if base_url is configured
|
|
auto_detected_models = []
|
|
if cfg_base_url:
|
|
try:
|
|
import ipaddress
|
|
import urllib.request
|
|
|
|
# Normalize the base_url and build models endpoint
|
|
base_url = cfg_base_url.strip()
|
|
if base_url.endswith('/v1'):
|
|
endpoint_url = base_url[:-3] + '/models'
|
|
else:
|
|
endpoint_url = base_url + '/v1/models'
|
|
|
|
# Detect provider from base_url
|
|
provider = 'custom'
|
|
parsed = urlparse(base_url if '://' in base_url else f'http://{base_url}')
|
|
host = (parsed.netloc or parsed.path).lower()
|
|
|
|
if parsed.hostname:
|
|
try:
|
|
addr = ipaddress.ip_address(parsed.hostname)
|
|
if addr.is_private or addr.is_loopback or addr.is_link_local:
|
|
if 'ollama' in host or '127.0.0.1' in host or 'localhost' in host:
|
|
provider = 'ollama'
|
|
elif 'lmstudio' in host or 'lm-studio' in host:
|
|
provider = 'lmstudio'
|
|
else:
|
|
provider = 'local'
|
|
except ValueError:
|
|
pass
|
|
|
|
# Resolve API key from environment
|
|
headers = {}
|
|
api_key_vars = ('HERMES_API_KEY', 'HERMES_OPENAI_API_KEY', 'OPENAI_API_KEY',
|
|
'LOCAL_API_KEY', 'OPENROUTER_API_KEY', 'API_KEY')
|
|
for key in api_key_vars:
|
|
api_key = os.getenv(key)
|
|
if api_key:
|
|
headers['Authorization'] = f'Bearer {api_key}'
|
|
break
|
|
|
|
# Fetch model list from endpoint
|
|
req = urllib.request.Request(endpoint_url, method='GET')
|
|
for k, v in headers.items():
|
|
req.add_header(k, v)
|
|
with urllib.request.urlopen(req, timeout=10) as response:
|
|
data = json.loads(response.read().decode('utf-8'))
|
|
|
|
# Handle both OpenAI-compatible and llama.cpp response formats
|
|
models_list = []
|
|
if 'data' in data and isinstance(data['data'], list):
|
|
models_list = data['data']
|
|
elif 'models' in data and isinstance(data['models'], list):
|
|
models_list = data['models']
|
|
|
|
for model in models_list:
|
|
if not isinstance(model, dict):
|
|
continue
|
|
model_id = model.get('id', '') or model.get('name', '') or model.get('model', '')
|
|
model_name = model.get('name', '') or model.get('model', '') or model_id
|
|
if model_id and model_name:
|
|
auto_detected_models.append({'id': model_id, 'label': model_name})
|
|
detected_providers.add(provider.lower())
|
|
except Exception as e:
|
|
logger.debug(f"Failed to fetch models from custom endpoint: {e}")
|
|
|
|
# 5. Build model groups
|
|
if detected_providers:
|
|
for pid in sorted(detected_providers):
|
|
provider_name = _PROVIDER_DISPLAY.get(pid, pid.title())
|
|
if pid == 'openrouter':
|
|
# OpenRouter uses provider/model format -- show the fallback list
|
|
groups.append({
|
|
'provider': 'OpenRouter',
|
|
'models': [{'id': m['id'], 'label': m['label']} for m in _FALLBACK_MODELS],
|
|
})
|
|
elif pid in _PROVIDER_MODELS:
|
|
groups.append({
|
|
'provider': provider_name,
|
|
'models': _PROVIDER_MODELS[pid],
|
|
})
|
|
else:
|
|
# Unknown provider -- use auto-detected models if available,
|
|
# otherwise fall back to default model placeholder
|
|
if auto_detected_models:
|
|
groups.append({
|
|
'provider': provider_name,
|
|
'models': auto_detected_models,
|
|
})
|
|
else:
|
|
groups.append({
|
|
'provider': provider_name,
|
|
'models': [{'id': default_model, 'label': default_model.split('/')[-1]}],
|
|
})
|
|
else:
|
|
# No providers detected -- use fallback grouped list
|
|
by_provider = {}
|
|
for m in _FALLBACK_MODELS:
|
|
by_provider.setdefault(m['provider'], []).append(
|
|
{'id': m['id'], 'label': m['label']}
|
|
)
|
|
for provider_name, models in by_provider.items():
|
|
groups.append({'provider': provider_name, 'models': models})
|
|
|
|
return {
|
|
'active_provider': active_provider,
|
|
'default_model': default_model,
|
|
'groups': groups,
|
|
}
|
|
|
|
|
|
# ── Static file path ─────────────────────────────────────────────────────────
|
|
_INDEX_HTML_PATH = REPO_ROOT / 'static' / 'index.html'
|
|
|
|
# ── Thread synchronisation ───────────────────────────────────────────────────
|
|
LOCK = threading.Lock()
|
|
SESSIONS_MAX = 100
|
|
CHAT_LOCK = threading.Lock()
|
|
STREAMS: dict = {}
|
|
STREAMS_LOCK = threading.Lock()
|
|
CANCEL_FLAGS: dict = {}
|
|
SERVER_START_TIME = time.time()
|
|
|
|
# ── Thread-local env context ─────────────────────────────────────────────────
|
|
_thread_ctx = threading.local()
|
|
|
|
def _set_thread_env(**kwargs):
|
|
_thread_ctx.env = kwargs
|
|
|
|
def _clear_thread_env():
|
|
_thread_ctx.env = {}
|
|
|
|
# ── Per-session agent locks ───────────────────────────────────────────────────
|
|
SESSION_AGENT_LOCKS: dict = {}
|
|
SESSION_AGENT_LOCKS_LOCK = threading.Lock()
|
|
|
|
def _get_session_agent_lock(session_id: str) -> threading.Lock:
|
|
with SESSION_AGENT_LOCKS_LOCK:
|
|
if session_id not in SESSION_AGENT_LOCKS:
|
|
SESSION_AGENT_LOCKS[session_id] = threading.Lock()
|
|
return SESSION_AGENT_LOCKS[session_id]
|
|
|
|
# ── Settings persistence ─────────────────────────────────────────────────────
|
|
|
|
_SETTINGS_DEFAULTS = {
|
|
'default_model': DEFAULT_MODEL,
|
|
'default_workspace': str(DEFAULT_WORKSPACE),
|
|
}
|
|
|
|
def load_settings() -> dict:
|
|
"""Load settings from disk, merging with defaults for any missing keys."""
|
|
settings = dict(_SETTINGS_DEFAULTS)
|
|
if SETTINGS_FILE.exists():
|
|
try:
|
|
stored = json.loads(SETTINGS_FILE.read_text(encoding='utf-8'))
|
|
if isinstance(stored, dict):
|
|
settings.update(stored)
|
|
except Exception:
|
|
pass
|
|
return settings
|
|
|
|
_SETTINGS_ALLOWED_KEYS = set(_SETTINGS_DEFAULTS.keys())
|
|
|
|
def save_settings(settings: dict) -> dict:
|
|
"""Save settings to disk. Returns the merged settings. Ignores unknown keys."""
|
|
current = load_settings()
|
|
for k, v in settings.items():
|
|
if k in _SETTINGS_ALLOWED_KEYS:
|
|
current[k] = v
|
|
SETTINGS_FILE.write_text(
|
|
json.dumps(current, ensure_ascii=False, indent=2),
|
|
encoding='utf-8',
|
|
)
|
|
# Update runtime defaults so new sessions use them immediately
|
|
global DEFAULT_MODEL, DEFAULT_WORKSPACE
|
|
if 'default_model' in current:
|
|
DEFAULT_MODEL = current['default_model']
|
|
if 'default_workspace' in current:
|
|
DEFAULT_WORKSPACE = Path(current['default_workspace']).expanduser().resolve()
|
|
return current
|
|
|
|
# Apply saved settings on startup (override env-derived defaults)
|
|
_startup_settings = load_settings()
|
|
if SETTINGS_FILE.exists():
|
|
if _startup_settings.get('default_model'):
|
|
DEFAULT_MODEL = _startup_settings['default_model']
|
|
if _startup_settings.get('default_workspace'):
|
|
DEFAULT_WORKSPACE = Path(_startup_settings['default_workspace']).expanduser().resolve()
|
|
|
|
# ── SESSIONS in-memory cache (LRU OrderedDict) ───────────────────────────────
|
|
SESSIONS: collections.OrderedDict = collections.OrderedDict()
|