fix(providers): complete NVIDIA NIM parity with other providers

Follow-up on the native NVIDIA NIM provider salvage. The original PR wired PROVIDER_REGISTRY + HERMES_OVERLAYS correctly but missed several touchpoints required for full parity with other OpenAI-compatible providers (xai, huggingface, deepseek, zai). Gaps closed: - hermes_cli/main.py: - Add 'nvidia' to the _model_flow_api_key_provider dispatch tuple so selecting 'NVIDIA NIM' in `hermes model` actually runs the api-key provider flow (previously fell through silently). - Add 'nvidia' to `hermes chat --provider` argparse choices so the documented test command (`hermes chat --provider nvidia --model ...`) parses successfully. - hermes_cli/config.py: Register NVIDIA_API_KEY and NVIDIA_BASE_URL in OPTIONAL_ENV_VARS so setup wizard can prompt for them and they're auto-added to the subprocess env blocklist. - hermes_cli/doctor.py: Add NVIDIA NIM row to `_apikey_providers` so `hermes doctor` probes https://integrate.api.nvidia.com/v1/models. - hermes_cli/dump.py: Add NVIDIA_API_KEY → 'nvidia' mapping for `hermes dump` credential masking. - tests/tools/test_local_env_blocklist.py: Extend registry_vars fixture with NVIDIA_API_KEY to verify it's blocked from leaking into subprocesses. - agent/model_metadata.py: Add 'nemotron' → 131072 context-length entry so all Nemotron variants get 128K context via substring match (rather than falling back to MINIMUM_CONTEXT_LENGTH). - hermes_cli/models.py: Fix hallucinated model ID 'nvidia/nemotron-3-nano-8b-a4b' → 'nvidia/nemotron-3-nano-30b-a3b' (verified against live integrate.api.nvidia.com/v1/models catalog). Expand curated list from 5 to 9 agentic models mapping to OpenRouter defaults per provider-guide convention: add qwen3.5-397b-a17b, deepseek-v3.2, llama-3.3-nemotron-super-49b-v1.5, gpt-oss-120b. - cli-config.yaml.example: Document 'nvidia' provider option. - scripts/release.py: Map asurla@nvidia.com → anniesurla in AUTHOR_MAP for CI attribution. E2E verified: `hermes chat --provider nvidia ...` now reaches NVIDIA's endpoint (returns 401 with bogus key instead of argparse error); `hermes doctor` detects NVIDIA NIM when NVIDIA_API_KEY is set.
2026-04-28 06:51:16 +08:00 · 2026-04-17 13:09:14 -07:00
parent 3b569ff576
commit f362083c64
9 changed files with 35 additions and 5 deletions
--- a/agent/model_metadata.py
+++ b/agent/model_metadata.py
@@ -159,6 +159,8 @@ DEFAULT_CONTEXT_LENGTHS = {
    "grok": 131072,             # catch-all (grok-beta, unknown grok-*)
    # Kimi
    "kimi": 262144,
+    # Nemotron — NVIDIA's open-weights series (128K context across all sizes)
+    "nemotron": 131072,
    # Arcee
    "trinity": 262144,
    # OpenRouter
--- a/cli-config.yaml.example
+++ b/cli-config.yaml.example
@@ -24,6 +24,7 @@ model:
  #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
  #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
  #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
+  #   "nvidia"       - NVIDIA NIM / build.nvidia.com (requires: NVIDIA_API_KEY)
  #   "xiaomi"       - Xiaomi MiMo (requires: XIAOMI_API_KEY)
  #   "arcee"        - Arcee AI Trinity models (requires: ARCEEAI_API_KEY)
  #   "ollama-cloud" - Ollama Cloud (requires: OLLAMA_API_KEY — https://ollama.com/settings)
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -861,6 +861,22 @@ OPTIONAL_ENV_VARS = {
        "category": "provider",
        "advanced": True,
    },
+    "NVIDIA_API_KEY": {
+        "description": "NVIDIA NIM API key (build.nvidia.com or local NIM endpoint)",
+        "prompt": "NVIDIA NIM API key",
+        "url": "https://build.nvidia.com/",
+        "password": True,
+        "category": "provider",
+        "advanced": True,
+    },
+    "NVIDIA_BASE_URL": {
+        "description": "NVIDIA NIM base URL override (e.g. http://localhost:8000/v1 for local NIM)",
+        "prompt": "NVIDIA NIM base URL (leave empty for default)",
+        "url": None,
+        "password": False,
+        "category": "provider",
+        "advanced": True,
+    },
    "GLM_API_KEY": {
        "description": "Z.AI / GLM API key (also recognized as ZAI_API_KEY / Z_AI_API_KEY)",
        "prompt": "Z.AI / GLM API key",
--- a/hermes_cli/doctor.py
+++ b/hermes_cli/doctor.py
@@ -825,6 +825,7 @@ def run_doctor(args):
        ("Arcee AI",         ("ARCEEAI_API_KEY",),                            "https://api.arcee.ai/api/v1/models",  "ARCEE_BASE_URL", True),
        ("DeepSeek",         ("DEEPSEEK_API_KEY",),                           "https://api.deepseek.com/v1/models",  "DEEPSEEK_BASE_URL", True),
        ("Hugging Face",     ("HF_TOKEN",),                                   "https://router.huggingface.co/v1/models", "HF_BASE_URL", True),
+        ("NVIDIA NIM",       ("NVIDIA_API_KEY",),                             "https://integrate.api.nvidia.com/v1/models", "NVIDIA_BASE_URL", True),
        ("Alibaba/DashScope", ("DASHSCOPE_API_KEY",),                         "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/models", "DASHSCOPE_BASE_URL", True),
        # MiniMax: the /anthropic endpoint doesn't support /models, but the /v1 endpoint does.
        ("MiniMax",          ("MINIMAX_API_KEY",),                            "https://api.minimax.io/v1/models",    "MINIMAX_BASE_URL", True),
--- a/hermes_cli/dump.py
+++ b/hermes_cli/dump.py
@@ -296,6 +296,7 @@ def run_dump(args):
        ("DEEPSEEK_API_KEY", "deepseek"),
        ("DASHSCOPE_API_KEY", "dashscope"),
        ("HF_TOKEN", "huggingface"),
+        ("NVIDIA_API_KEY", "nvidia"),
        ("AI_GATEWAY_API_KEY", "ai_gateway"),
        ("OPENCODE_ZEN_API_KEY", "opencode_zen"),
        ("OPENCODE_GO_API_KEY", "opencode_go"),
--- a/hermes_cli/main.py
+++ b/hermes_cli/main.py
@@ -1143,7 +1143,7 @@ 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", "ollama-cloud"):
+    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", "nvidia", "ollama-cloud"):
        _model_flow_api_key_provider(config, selected_provider, current_model)

    # ── Post-switch cleanup: clear stale OPENAI_BASE_URL ──────────────
@@ -4954,7 +4954,7 @@ For more help on a command:
    )
    chat_parser.add_argument(
        "--provider",
-        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "xai", "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee"],
+        choices=["auto", "openrouter", "nous", "openai-codex", "copilot-acp", "copilot", "anthropic", "gemini", "xai", "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "kilocode", "xiaomi", "arcee", "nvidia"],
        default=None,
        help="Inference provider (default: auto)"
    )
--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -156,11 +156,18 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
        "grok-4-1-fast-reasoning",
    ],
    "nvidia": [
+        # NVIDIA flagship reasoning models
        "nvidia/nemotron-3-super-120b-a12b",
-        "nvidia/nemotron-3-nano-8b-a4b",
-        "z-ai/glm5",
+        "nvidia/nemotron-3-nano-30b-a3b",
+        "nvidia/llama-3.3-nemotron-super-49b-v1.5",
+        # Third-party agentic models hosted on build.nvidia.com
+        # (map to OpenRouter defaults — users get familiar picks on NIM)
+        "qwen/qwen3.5-397b-a17b",
+        "deepseek-ai/deepseek-v3.2",
        "moonshotai/kimi-k2.5",
        "minimaxai/minimax-m2.5",
+        "z-ai/glm5",
+        "openai/gpt-oss-120b",
    ],
    "kimi-coding": [
        "kimi-k2.5",
@@ -543,6 +550,7 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
    ProviderEntry("anthropic",      "Anthropic",                "Anthropic (Claude models — API key or Claude Code)"),
    ProviderEntry("openai-codex",   "OpenAI Codex",             "OpenAI Codex"),
    ProviderEntry("xiaomi",         "Xiaomi MiMo",              "Xiaomi MiMo (MiMo-V2 models — pro, omni, flash)"),
+    ProviderEntry("nvidia",         "NVIDIA NIM",               "NVIDIA NIM (Nemotron models — build.nvidia.com or local NIM)"),
    ProviderEntry("qwen-oauth",     "Qwen OAuth (Portal)",      "Qwen OAuth (reuses local Qwen CLI login)"),
    ProviderEntry("copilot",        "GitHub Copilot",           "GitHub Copilot (uses GITHUB_TOKEN or gh auth token)"),
    ProviderEntry("copilot-acp",    "GitHub Copilot ACP",       "GitHub Copilot ACP (spawns `copilot --acp --stdio`)"),
@@ -551,7 +559,6 @@ CANONICAL_PROVIDERS: list[ProviderEntry] = [
    ProviderEntry("google-gemini-cli", "Google Gemini (OAuth)",   "Google Gemini via OAuth + Code Assist (free tier supported; no API key needed)"),
    ProviderEntry("deepseek",       "DeepSeek",                 "DeepSeek (DeepSeek-V3, R1, coder — direct API)"),
    ProviderEntry("xai",            "xAI",                      "xAI (Grok models — direct API)"),
-    ProviderEntry("nvidia",         "NVIDIA NIM",               "NVIDIA NIM (Nemotron models — build.nvidia.com or local NIM)"),
    ProviderEntry("zai",            "Z.AI / GLM",               "Z.AI / GLM (Zhipu AI direct API)"),
    ProviderEntry("kimi-coding",    "Kimi / Kimi Coding Plan",  "Kimi Coding Plan (api.kimi.com) & Moonshot API"),
    ProviderEntry("kimi-coding-cn", "Kimi / Moonshot (China)",  "Kimi / Moonshot China (Moonshot CN direct API)"),
--- a/scripts/release.py
+++ b/scripts/release.py
@@ -256,6 +256,7 @@ AUTHOR_MAP = {
    "anthhub@163.com": "anthhub",
    "shenuu@gmail.com": "shenuu",
    "xiayh17@gmail.com": "xiayh0107",
+    "asurla@nvidia.com": "anniesurla",
 }


--- a/tests/tools/test_local_env_blocklist.py
+++ b/tests/tools/test_local_env_blocklist.py
@@ -86,6 +86,7 @@ class TestProviderEnvBlocklist:
            "MINIMAX_API_KEY": "mm-key",
            "MINIMAX_CN_API_KEY": "mmcn-key",
            "DEEPSEEK_API_KEY": "deepseek-key",
+            "NVIDIA_API_KEY": "nvidia-key",
        }
        result_env = _run_with_env(extra_os_env=registry_vars)