common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:NousResearch/hermes-agent into feat/ink-refactor

Browse Source
This commit is contained in:
Brooklyn Nicholson
2026-04-16 08:23:20 -05:00
parent 8e06db56fd dc7d47a6b8
commit f81dba0da2
128 changed files with 8357 additions and 842 deletions
Download Patch File Download Diff File Expand all files Collapse all files

177
hermes_cli/models.py
View File

@@ -11,7 +11,9 @@ import json
import os
import urllib.request
import urllib.error
import time
from difflib import get_close_matches
from pathlib import Path
from typing import Any, NamedTuple, Optional
COPILOT_BASE_URL = "https://api.githubcopilot.com"
@@ -143,17 +145,8 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
"glm-4.5-flash",
],
"xai": [
"grok-4.20-0309-reasoning",
"grok-4.20-0309-non-reasoning",
"grok-4.20-multi-agent-0309",
"grok-4.20-reasoning",
"grok-4-1-fast-reasoning",
"grok-4-1-fast-non-reasoning",
"grok-4-fast-reasoning",
"grok-4-fast-non-reasoning",
"grok-4-0709",
"grok-code-fast-1",
"grok-3",
"grok-3-mini",
],
"kimi-coding": [
"kimi-for-coding",
@@ -547,6 +540,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
ProviderEntry("minimax", "MiniMax", "MiniMax (global direct API)"),
ProviderEntry("minimax-cn", "MiniMax (China)", "MiniMax China (domestic direct API)"),
ProviderEntry("alibaba", "Alibaba Cloud (DashScope)","Alibaba Cloud / DashScope Coding (Qwen + multi-provider)"),
ProviderEntry("ollama-cloud", "Ollama Cloud", "Ollama Cloud (cloud-hosted open models — ollama.com)"),
ProviderEntry("arcee", "Arcee AI", "Arcee AI (Trinity models — direct API)"),
ProviderEntry("kilocode", "Kilo Code", "Kilo Code (Kilo Gateway API)"),
ProviderEntry("opencode-zen", "OpenCode Zen", "OpenCode Zen (35+ curated models, pay-as-you-go)"),
@@ -559,6 +553,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
_PROVIDER_LABELS = {p.slug: p.label for p in CANONICAL_PROVIDERS}
_PROVIDER_LABELS["custom"] = "Custom endpoint" # special case: not a named provider
_PROVIDER_ALIASES = {
"glm": "zai",
"z-ai": "zai",
@@ -611,6 +606,8 @@ _PROVIDER_ALIASES = {
"grok": "xai",
"x-ai": "xai",
"x.ai": "xai",
"ollama": "custom", # bare "ollama" = local; use "ollama-cloud" for cloud
"ollama_cloud": "ollama-cloud",
}
@@ -1064,7 +1061,8 @@ def detect_provider_for_model(
break
if direct_match:
# Check if we have credentials for this provider
# Check if we have credentials for this provider — env vars,
# credential pool, or auth store entries.
has_creds = False
try:
from hermes_cli.auth import PROVIDER_REGISTRY
@@ -1077,16 +1075,28 @@ def detect_provider_for_model(
break
except Exception:
pass
# Also check credential pool and auth store — covers OAuth,
# Claude Code tokens, and other non-env-var credentials (#10300).
if not has_creds:
try:
from agent.credential_pool import load_pool
pool = load_pool(direct_match)
if pool.has_credentials():
has_creds = True
except Exception:
pass
if not has_creds:
try:
from hermes_cli.auth import _load_auth_store
store = _load_auth_store()
if direct_match in store.get("providers", {}) or direct_match in store.get("credential_pool", {}):
has_creds = True
except Exception:
pass
if has_creds:
return (direct_match, name)
# No direct creds — try to find this model on OpenRouter instead
or_slug = _find_openrouter_slug(name)
if or_slug:
return ("openrouter", or_slug)
# Still return the direct provider — credential resolution will
# give a clear error rather than silently using the wrong provider
# Always return the direct provider match. If credentials are
# missing, the client init will give a clear error rather than
# silently routing through the wrong provider (#10300).
return (direct_match, name)
# --- Step 2: check OpenRouter catalog ---
@@ -1560,6 +1570,11 @@ def copilot_model_api_mode(
primary signal. Falls back to the catalog's ``supported_endpoints``
only for models not covered by the pattern check.
"""
# Fetch the catalog once so normalize + endpoint check share it
# (avoids two redundant network calls for non-GPT-5 models).
if catalog is None and api_key:
catalog = fetch_github_model_catalog(api_key=api_key)
normalized = normalize_copilot_model_id(model_id, catalog=catalog, api_key=api_key)
if not normalized:
return "chat_completions"
@@ -1569,9 +1584,6 @@ def copilot_model_api_mode(
return "codex_responses"
# Secondary: check catalog for non-GPT-5 models (Claude via /v1/messages, etc.)
if catalog is None and api_key:
catalog = fetch_github_model_catalog(api_key=api_key)
if catalog:
catalog_entry = next((item for item in catalog if item.get("id") == normalized), None)
if isinstance(catalog_entry, dict):
@@ -1786,6 +1798,125 @@ def fetch_api_models(
return probe_api_models(api_key, base_url, timeout=timeout).get("models")
# ---------------------------------------------------------------------------
# Ollama Cloud — merged model discovery with disk cache
# ---------------------------------------------------------------------------
_OLLAMA_CLOUD_CACHE_TTL = 3600 # 1 hour
def _ollama_cloud_cache_path() -> Path:
"""Return the path for the Ollama Cloud model cache."""
from hermes_constants import get_hermes_home
return get_hermes_home() / "ollama_cloud_models_cache.json"
def _load_ollama_cloud_cache(*, ignore_ttl: bool = False) -> Optional[dict]:
"""Load cached Ollama Cloud models from disk.
Args:
ignore_ttl: If True, return data even if the TTL has expired (stale fallback).
"""
try:
cache_path = _ollama_cloud_cache_path()
if not cache_path.exists():
return None
with open(cache_path, encoding="utf-8") as f:
data = json.load(f)
if not isinstance(data, dict):
return None
models = data.get("models")
if not (isinstance(models, list) and models):
return None
if not ignore_ttl:
cached_at = data.get("cached_at", 0)
if (time.time() - cached_at) > _OLLAMA_CLOUD_CACHE_TTL:
return None # stale
return data
except Exception:
pass
return None
def _save_ollama_cloud_cache(models: list[str]) -> None:
"""Persist the merged Ollama Cloud model list to disk."""
try:
from utils import atomic_json_write
cache_path = _ollama_cloud_cache_path()
cache_path.parent.mkdir(parents=True, exist_ok=True)
atomic_json_write(cache_path, {"models": models, "cached_at": time.time()}, indent=None)
except Exception:
pass
def fetch_ollama_cloud_models(
api_key: Optional[str] = None,
base_url: Optional[str] = None,
*,
force_refresh: bool = False,
) -> list[str]:
"""Fetch Ollama Cloud models by merging live API + models.dev, with disk cache.
Resolution order:
1. Disk cache (if fresh, < 1 hour, and not force_refresh)
2. Live ``/v1/models`` endpoint (primary — freshest source)
3. models.dev registry (secondary — fills gaps for unlisted models)
4. Merge: live models first, then models.dev additions (deduped)
Returns a list of model IDs (never None — empty list on total failure).
"""
# 1. Check disk cache
if not force_refresh:
cached = _load_ollama_cloud_cache()
if cached is not None:
return cached["models"]
# 2. Live API probe
if not api_key:
api_key = os.getenv("OLLAMA_API_KEY", "")
if not base_url:
base_url = os.getenv("OLLAMA_BASE_URL", "") or "https://ollama.com/v1"
live_models: list[str] = []
if api_key:
result = fetch_api_models(api_key, base_url, timeout=8.0)
if result:
live_models = result
# 3. models.dev registry
mdev_models: list[str] = []
try:
from agent.models_dev import list_agentic_models
mdev_models = list_agentic_models("ollama-cloud")
except Exception:
pass
# 4. Merge: live first, then models.dev additions (deduped, order-preserving)
if live_models or mdev_models:
seen: set[str] = set()
merged: list[str] = []
for m in live_models:
if m and m not in seen:
seen.add(m)
merged.append(m)
for m in mdev_models:
if m and m not in seen:
seen.add(m)
merged.append(m)
if merged:
_save_ollama_cloud_cache(merged)
return merged
# Total failure — return stale cache if available (ignore TTL)
stale = _load_ollama_cloud_cache(ignore_ttl=True)
if stale is not None:
return stale["models"]
return []
def validate_requested_model(
model_name: str,
provider: Optional[str],