mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: add Xiaomi MiMo to all provider docs + fix MiMo-V2-Flash ctx len

Browse source 
- environment-variables.md: XIAOMI_API_KEY, XIAOMI_BASE_URL, provider list
- cli-commands.md: --provider choices
- integrations/providers.md: provider table, Chinese providers section,
  config example, base URL list, choosing table, fallback providers list
- fallback-providers.md: supported providers table, auto-detection chain
- Fix XiaomiMiMo/MiMo-V2-Flash context length 32768 → 256000 (OpenRouter entry)
This commit is contained in:
Teknium 2026-04-11 11:02:58 -07:00 • committed by Teknium
parent 6693e2a497
commit d4bb44d4b9
7 changed files with 20 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

1
agent/auxiliary_client.py
View file

@ -109,7 +109,6 @@ _API_KEY_PROVIDER_AUX_MODELS: Dict[str, str] = {
"opencode-zen": "gemini-3-flash",
"opencode-go": "glm-5",
"kilocode": "google/gemini-3-flash-preview",
"xiaomi": "mimo-v2-flash",
}
# Vision-specific model overrides for direct providers.

2
agent/model_metadata.py
View file

@ -151,7 +151,7 @@ DEFAULT_CONTEXT_LENGTHS = {
"moonshotai/Kimi-K2.5": 262144,
"moonshotai/Kimi-K2-Thinking": 262144,
"MiniMaxAI/MiniMax-M2.5": 204800,
"XiaomiMiMo/MiMo-V2-Flash": 32768,
"XiaomiMiMo/MiMo-V2-Flash": 256000,
"mimo-v2-pro": 1000000,
"mimo-v2-omni": 256000,
"mimo-v2-flash": 256000,

8
tests/hermes_cli/test_xiaomi_provider.py
View file

@ -285,12 +285,12 @@ class TestXiaomiProvidersModule:
class TestXiaomiAuxiliary:
"""Xiaomi should have a default auxiliary model and a vision model override."""
"""Xiaomi auxiliary routing: vision → omni, non-vision → user's main model, never flash."""
def test_aux_model_defined(self):
def test_no_flash_in_aux_models(self):
"""mimo-v2-flash must NEVER be used for automatic aux routing."""
from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
assert "xiaomi" in _API_KEY_PROVIDER_AUX_MODELS
assert _API_KEY_PROVIDER_AUX_MODELS["xiaomi"] == "mimo-v2-flash"
assert "xiaomi" not in _API_KEY_PROVIDER_AUX_MODELS
def test_vision_model_override(self):
"""Xiaomi vision tasks should use mimo-v2-omni (multimodal), not the main model."""

13
website/docs/integrations/providers.md
View file

@ -27,6 +27,7 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
| **MiniMax China** | `MINIMAX_CN_API_KEY` in `~/.hermes/.env` (provider: `minimax-cn`) |
| **Alibaba Cloud** | `DASHSCOPE_API_KEY` in `~/.hermes/.env` (provider: `alibaba`, aliases: `dashscope`, `qwen`) |
| **Kilo Code** | `KILOCODE_API_KEY` in `~/.hermes/.env` (provider: `kilocode`) |
| **Xiaomi MiMo** | `XIAOMI_API_KEY` in `~/.hermes/.env` (provider: `xiaomi`, aliases: `mimo`, `xiaomi-mimo`) |
| **OpenCode Zen** | `OPENCODE_ZEN_API_KEY` in `~/.hermes/.env` (provider: `opencode-zen`) |
| **OpenCode Go** | `OPENCODE_GO_API_KEY` in `~/.hermes/.env` (provider: `opencode-go`) |
| **DeepSeek** | `DEEPSEEK_API_KEY` in `~/.hermes/.env` (provider: `deepseek`) |
@ -157,16 +158,20 @@ hermes chat --provider minimax-cn --model MiniMax-M2.7
# Alibaba Cloud / DashScope (Qwen models)
hermes chat --provider alibaba --model qwen3.5-plus
# Requires: DASHSCOPE_API_KEY in ~/.hermes/.env
# Xiaomi MiMo
hermes chat --provider xiaomi --model mimo-v2-pro
# Requires: XIAOMI_API_KEY in ~/.hermes/.env
```
Or set the provider permanently in `config.yaml`:
```yaml
model:
provider: "zai" # or: kimi-coding, minimax, minimax-cn, alibaba
provider: "zai" # or: kimi-coding, minimax, minimax-cn, alibaba, xiaomi
default: "glm-5"
```
Base URLs can be overridden with `GLM_BASE_URL`, `KIMI_BASE_URL`, `MINIMAX_BASE_URL`, `MINIMAX_CN_BASE_URL`, or `DASHSCOPE_BASE_URL` environment variables.
Base URLs can be overridden with `GLM_BASE_URL`, `KIMI_BASE_URL`, `MINIMAX_BASE_URL`, `MINIMAX_CN_BASE_URL`, `DASHSCOPE_BASE_URL`, or `XIAOMI_BASE_URL` environment variables.
:::note Z.AI Endpoint Auto-Detection
When using the Z.AI / GLM provider, Hermes automatically probes multiple endpoints (global, China, coding variants) to find one that accepts your API key. You don't need to set `GLM_BASE_URL` manually — the working endpoint is detected and cached automatically.
@ -849,7 +854,7 @@ You can also select named custom providers from the interactive `hermes model` m
| **Cost optimization** | ClawRouter or OpenRouter with `sort: "price"` |
| **Maximum privacy** | Ollama, vLLM, or llama.cpp (fully local) |
| **Enterprise / Azure** | Azure OpenAI with custom endpoint |
| **Chinese AI models** | z.ai (GLM), Kimi/Moonshot, or MiniMax (first-class providers) |
| **Chinese AI models** | z.ai (GLM), Kimi/Moonshot, MiniMax, or Xiaomi MiMo (first-class providers) |
:::tip
You can switch between providers at any time with `hermes model` — no restart required. Your conversation history, memory, and skills carry over regardless of which provider you use.
@ -924,7 +929,7 @@ fallback_model:
When activated, the fallback swaps the model and provider mid-session without losing your conversation. It fires **at most once** per session.
Supported providers: `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `deepseek`, `ai-gateway`, `opencode-zen`, `opencode-go`, `kilocode`, `alibaba`, `custom`.
Supported providers: `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `deepseek`, `ai-gateway`, `opencode-zen`, `opencode-go`, `kilocode`, `xiaomi`, `alibaba`, `custom`.
:::tip
Fallback is configured exclusively through `config.yaml` — there are no environment variables for it. For full details on when it triggers, supported providers, and how it interacts with auxiliary tasks and delegation, see [Fallback Providers](/docs/user-guide/features/fallback-providers).

2
website/docs/reference/cli-commands.md
View file

@ -76,7 +76,7 @@ Common options:
| `-q`, `--query "..."` | One-shot, non-interactive prompt. |
| `-m`, `--model <model>` | Override the model for this run. |
| `-t`, `--toolsets <csv>` | Enable a comma-separated set of toolsets. |
| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot-acp`, `copilot`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `deepseek`, `ai-gateway`, `opencode-zen`, `opencode-go`, `kilocode`, `alibaba`. |
| `--provider <provider>` | Force a provider: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot-acp`, `copilot`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `deepseek`, `ai-gateway`, `opencode-zen`, `opencode-go`, `kilocode`, `xiaomi`, `alibaba`. |
| `-s`, `--skills <name>` | Preload one or more skills for the session (can be repeated or comma-separated). |
| `-v`, `--verbose` | Verbose output. |
| `-Q`, `--quiet` | Programmatic mode: suppress banner/spinner/tool previews. |

4
website/docs/reference/environment-variables.md
View file

@ -37,6 +37,8 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
| `MINIMAX_CN_BASE_URL` | Override MiniMax China base URL (default: `https://api.minimaxi.com/v1`) |
| `KILOCODE_API_KEY` | Kilo Code API key ([kilo.ai](https://kilo.ai)) |
| `KILOCODE_BASE_URL` | Override Kilo Code base URL (default: `https://api.kilo.ai/api/gateway`) |
| `XIAOMI_API_KEY` | Xiaomi MiMo API key ([platform.xiaomimimo.com](https://platform.xiaomimimo.com)) |
| `XIAOMI_BASE_URL` | Override Xiaomi MiMo base URL (default: `https://api.xiaomimimo.com/v1`) |
| `HF_TOKEN` | Hugging Face token for Inference Providers ([huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)) |
| `HF_BASE_URL` | Override Hugging Face base URL (default: `https://router.huggingface.co/v1`) |
| `GOOGLE_API_KEY` | Google AI Studio API key ([aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)) |
@ -65,7 +67,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
| Variable | Description |
|----------|-------------|
| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`, `alibaba`, `deepseek`, `opencode-zen`, `opencode-go`, `ai-gateway` (default: `auto`) |
| `HERMES_INFERENCE_PROVIDER` | Override provider selection: `auto`, `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `huggingface`, `zai`, `kimi-coding`, `minimax`, `minimax-cn`, `kilocode`, `xiaomi`, `alibaba`, `deepseek`, `opencode-zen`, `opencode-go`, `ai-gateway` (default: `auto`) |
| `HERMES_PORTAL_BASE_URL` | Override Nous Portal URL (for development/testing) |
| `NOUS_INFERENCE_BASE_URL` | Override Nous inference API URL |
| `HERMES_NOUS_MIN_KEY_TTL_SECONDS` | Min agent key TTL before re-mint (default: 1800 = 30min) |

3
website/docs/user-guide/features/fallback-providers.md
View file

@ -50,6 +50,7 @@ Both `provider` and `model` are **required**. If either is missing, the fallback
| OpenCode Zen | `opencode-zen` | `OPENCODE_ZEN_API_KEY` |
| OpenCode Go | `opencode-go` | `OPENCODE_GO_API_KEY` |
| Kilo Code | `kilocode` | `KILOCODE_API_KEY` |
| Xiaomi MiMo | `xiaomi` | `XIAOMI_API_KEY` |
| Alibaba / DashScope | `alibaba` | `DASHSCOPE_API_KEY` |
| Hugging Face | `huggingface` | `HF_TOKEN` |
| Custom endpoint | `custom` | `base_url` + `api_key_env` (see below) |
@ -169,7 +170,7 @@ When a task's provider is set to `"auto"` (the default), Hermes tries providers
```text
OpenRouter → Nous Portal → Custom endpoint → Codex OAuth →
API-key providers (z.ai, Kimi, MiniMax, Hugging Face, Anthropic) → give up
API-key providers (z.ai, Kimi, MiniMax, Xiaomi MiMo, Hugging Face, Anthropic) → give up
```
**For vision tasks:**