feat: add Ollama Cloud as built-in provider

Add ollama-cloud as a first-class provider with full parity to existing API-key providers (gemini, zai, minimax, etc.): - PROVIDER_REGISTRY entry with OLLAMA_API_KEY env var - Provider aliases: ollama -> custom (local), ollama_cloud -> ollama-cloud - models.dev integration for accurate context lengths - URL-to-provider mapping (ollama.com -> ollama-cloud) - Passthrough model normalization (preserves Ollama model:tag format) - Default auxiliary model (nemotron-3-nano:30b) - HermesOverlay in providers.py - CLI --provider choices, CANONICAL_PROVIDERS entry - Dynamic model discovery with disk caching (1hr TTL) - 37 provider-specific tests Cherry-picked from PR #6038 by kshitijk4poor. Closes #3926
2026-04-15 22:32:05 -07:00
parent 8021a735c2
commit 1b61ec470b
12 changed files with 563 additions and 37 deletions
--- a/hermes_cli/auth.py
+++ b/hermes_cli/auth.py
@@ -70,6 +70,7 @@ DEFAULT_CODEX_BASE_URL = "https://chatgpt.com/backend-api/codex"
 DEFAULT_QWEN_BASE_URL = "https://portal.qwen.ai/v1"
 DEFAULT_GITHUB_MODELS_BASE_URL = "https://api.githubcopilot.com"
 DEFAULT_COPILOT_ACP_BASE_URL = "acp://copilot"
+DEFAULT_OLLAMA_CLOUD_BASE_URL = "https://ollama.com/v1"
 CODEX_OAUTH_CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann"
 CODEX_OAUTH_TOKEN_URL = "https://auth.openai.com/oauth/token"
 CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120
@@ -274,6 +275,14 @@ PROVIDER_REGISTRY: Dict[str, ProviderConfig] = {
        api_key_env_vars=("XIAOMI_API_KEY",),
        base_url_env_var="XIAOMI_BASE_URL",
    ),
+    "ollama-cloud": ProviderConfig(
+        id="ollama-cloud",
+        name="Ollama Cloud",
+        auth_type="api_key",
+        inference_base_url=DEFAULT_OLLAMA_CLOUD_BASE_URL,
+        api_key_env_vars=("OLLAMA_API_KEY",),
+        base_url_env_var="OLLAMA_BASE_URL",
+    ),
    "bedrock": ProviderConfig(
        id="bedrock",
        name="AWS Bedrock",
@@ -937,7 +946,8 @@ def resolve_provider(
        "kilo": "kilocode", "kilo-code": "kilocode", "kilo-gateway": "kilocode",
        # Local server aliases — route through the generic custom provider
        "lmstudio": "custom", "lm-studio": "custom", "lm_studio": "custom",
-        "ollama": "custom", "vllm": "custom", "llamacpp": "custom",
+        "ollama": "custom", "ollama_cloud": "ollama-cloud",
+        "vllm": "custom", "llamacpp": "custom",
        "llama.cpp": "custom", "llama-cpp": "custom",
    }
    normalized = _PROVIDER_ALIASES.get(normalized, normalized)
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -1024,6 +1024,22 @@ OPTIONAL_ENV_VARS = {
        "category": "provider",
        "advanced": True,
    },
+    "OLLAMA_API_KEY": {
+        "description": "Ollama Cloud API key (ollama.com — cloud-hosted open models)",
+        "prompt": "Ollama Cloud API key",
+        "url": "https://ollama.com/settings",
+        "password": True,
+        "category": "provider",
+        "advanced": True,
+    },
+    "OLLAMA_BASE_URL": {
+        "description": "Ollama Cloud base URL override (default: https://ollama.com/v1)",
+        "prompt": "Ollama base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
    "XIAOMI_API_KEY": {
        "description": "Xiaomi MiMo API key for MiMo models (mimo-v2-pro, mimo-v2-omni, mimo-v2-flash)",
        "prompt": "Xiaomi MiMo API Key",
--- a/hermes_cli/main.py
+++ b/hermes_cli/main.py
@@ -1141,7 +1141,7 @@ def select_provider_and_model(args=None):
        _model_flow_kimi(config, current_model)
    elif selected_provider == "bedrock":
        _model_flow_bedrock(config, current_model)
-    elif selected_provider in ("gemini", "deepseek", "xai", "zai", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface", "xiaomi", "arcee"):
+    elif selected_provider in ("gemini", "deepseek", "xai", "zai", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "opencode-zen", "opencode-go", "ai-gateway", "alibaba", "huggingface", "xiaomi", "arcee", "ollama-cloud"):
        _model_flow_api_key_provider(config, selected_provider, current_model)

    # ── Post-switch cleanup: clear stale OPENAI_BASE_URL ──────────────
@@ -2734,34 +2734,43 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
    #   1. models.dev registry (cached, filtered for agentic/tool-capable models)
    #   2. Curated static fallback list (offline insurance)
    #   3. Live /models endpoint probe (small providers without models.dev data)
-    curated = _PROVIDER_MODELS.get(provider_id, [])
-
-    # Try models.dev first — returns tool-capable models, filtered for noise
-    mdev_models: list = []
-    try:
-        from agent.models_dev import list_agentic_models
-        mdev_models = list_agentic_models(provider_id)
-    except Exception:
-        pass
-
-    if mdev_models:
-        model_list = mdev_models
-        print(f"  Found {len(model_list)} model(s) from models.dev registry")
-    elif curated and len(curated) >= 8:
-        # Curated list is substantial — use it directly, skip live probe
-        model_list = curated
-        print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
-    else:
+    #
+    # Ollama Cloud: dedicated merged discovery (live API + models.dev + disk cache)
+    if provider_id == "ollama-cloud":
+        from hermes_cli.models import fetch_ollama_cloud_models
        api_key_for_probe = existing_key or (get_env_value(key_env) if key_env else "")
-        live_models = fetch_api_models(api_key_for_probe, effective_base)
-        if live_models and len(live_models) >= len(curated):
-            model_list = live_models
-            print(f"  Found {len(model_list)} model(s) from {pconfig.name} API")
-        else:
+        model_list = fetch_ollama_cloud_models(api_key=api_key_for_probe, base_url=effective_base)
+        if model_list:
+            print(f"  Found {len(model_list)} model(s) from Ollama Cloud")
+    else:
+        curated = _PROVIDER_MODELS.get(provider_id, [])
+
+        # Try models.dev first — returns tool-capable models, filtered for noise
+        mdev_models: list = []
+        try:
+            from agent.models_dev import list_agentic_models
+            mdev_models = list_agentic_models(provider_id)
+        except Exception:
+            pass
+
+        if mdev_models:
+            model_list = mdev_models
+            print(f"  Found {len(model_list)} model(s) from models.dev registry")
+        elif curated and len(curated) >= 8:
+            # Curated list is substantial — use it directly, skip live probe
            model_list = curated
-            if model_list:
-                print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
-        # else: no defaults either, will fall through to raw input
+            print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
+        else:
+            api_key_for_probe = existing_key or (get_env_value(key_env) if key_env else "")
+            live_models = fetch_api_models(api_key_for_probe, effective_base)
+            if live_models and len(live_models) >= len(curated):
+                model_list = live_models
+                print(f"  Found {len(model_list)} model(s) from {pconfig.name} API")
+            else:
+                model_list = curated
+                if model_list:
+                    print(f"  Showing {len(model_list)} curated models — use \"Enter custom model name\" for others.")
+            # else: no defaults either, will fall through to raw input

    if provider_id in {"opencode-zen", "opencode-go"}:
        model_list = [normalize_opencode_model_id(provider_id, mid) for mid in model_list]
@@ -4860,7 +4869,7 @@ For more help on a command:
    )
    chat_parser.add_argument(
        "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee"],
        default=None,
        help="Inference provider (default: auto)"
    )
--- a/hermes_cli/model_normalize.py
+++ b/hermes_cli/model_normalize.py
@@ -96,6 +96,7 @@ _MATCHING_PREFIX_STRIP_PROVIDERS: frozenset[str] = frozenset({
    "qwen-oauth",
    "xiaomi",
    "arcee",
+    "ollama-cloud",
    "custom",
 })

--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -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"
@@ -547,6 +549,7 @@ 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 +562,7 @@ 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 +615,8 @@ _PROVIDER_ALIASES = {
    "grok": "xai",
    "x-ai": "xai",
    "x.ai": "xai",
+    "ollama": "custom",  # bare "ollama" = local; use "ollama-cloud" for cloud
+    "ollama_cloud": "ollama-cloud",
 }


@@ -1786,6 +1792,125 @@ 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],
--- a/hermes_cli/providers.py
+++ b/hermes_cli/providers.py
@@ -141,6 +141,10 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
        base_url_override="https://api.arcee.ai/api/v1",
        base_url_env_var="ARCEE_BASE_URL",
    ),
+    "ollama-cloud": HermesOverlay(
+        transport="openai_chat",
+        base_url_env_var="OLLAMA_BASE_URL",
+    ),
 }


@@ -250,7 +254,7 @@ ALIASES: Dict[str, str] = {
    "lmstudio": "lmstudio",
    "lm-studio": "lmstudio",
    "lm_studio": "lmstudio",
-    "ollama": "ollama-cloud",
+    "ollama": "custom",  # bare "ollama" = local; use "ollama-cloud" for cloud
    "vllm": "local",
    "llamacpp": "local",
    "llama.cpp": "local",
@@ -269,6 +273,7 @@ _LABEL_OVERRIDES: Dict[str, str] = {
    "xiaomi": "Xiaomi MiMo",
    "local": "Local endpoint",
    "bedrock": "AWS Bedrock",
+    "ollama-cloud": "Ollama Cloud",
 }