hermes-agent/plugins/model-providers
kshitij c0106e50e7 fix(kimi): send Hermes attribution headers instead of claude-code/0.1.0
The Kimi team noticed that traffic from Hermes Coding Plan users
identifies itself as Claude (User-Agent: claude-code/0.1.0) rather
than the actual client. They asked us to update the UA so they can
properly attribute traffic and understand how their services are
accessed — especially important as they open up to more third-party
agents.

Three code paths were sending wrong/attribution-less headers to Kimi:

1. run_agent.py — _apply_client_headers_for_base_url sent
   {"User-Agent": "claude-code/0.1.0"} for api.kimi.com. Now sends
   the same _AI_GATEWAY_HEADERS set used for Vercel AI Gateway:
   HTTP-Referer + X-Title + HermesAgent/{version} User-Agent.

2. agent/anthropic_adapter.py — the Anthropic Messages path for
   api.kimi.com/coding sent 'claude-code/0.1.0'. Now sends the same
   three-header attribution set.

3. plugins/model-providers/kimi-coding/__init__.py — both kimi and
   kimi_cn profiles sent a static 'hermes-agent/1.0' with no
   HTTP-Referer or X-Title. Now sends the full three-header set with
   a dynamic version, matching the pattern used by the gmi, fireworks,
   xai, and ai-gateway provider profiles.

The attribution header set (HTTP-Referer + X-Title + User-Agent) is
the canonical Hermes pattern used for OpenRouter, Vercel AI Gateway,
Fireworks, and other providers that read these headers for traffic
attribution.
2026-08-11 13:25:37 +05:30
..
actual fix: adapt Actual provider salvage to current main 2026-08-05 14:08:32 -07:00
ai-gateway Revert "remove Vercel AI Gateway and Vercel Sandbox (#33067)" 2026-07-29 19:48:37 -07:00
alibaba
…
alibaba-coding-plan chore(model-picker): refresh provider picker descriptions 2026-05-31 15:02:26 -07:00
anthropic fix(security): cover remaining catalog credential paths 2026-07-11 12:28:55 +05:30
arcee
…
azure-foundry
…
bedrock fix(models): pass model.base_url to fetch_models in /model picker 2026-06-16 13:09:40 -07:00
copilot fix(copilot): clamp reasoning effort to the nearest supported level, not xhigh->high 2026-07-16 08:47:10 -07:00
copilot-acp fix(models): pass model.base_url to fetch_models in /model picker 2026-06-16 13:09:40 -07:00
custom fix(ollama): emit top-level reasoning_effort=none on /v1/chat/completions (#25758) 2026-07-15 06:38:28 -07:00
deepinfra fix(secrets): scope tier-3 credential reads (teams_pipeline, deepinfra models, FAL/XAI/VERCEL/DAYTONA/GITHUB presence, HERMES_API_KEY display) 2026-08-02 10:04:48 -07:00
deepseek fix(deepseek): drop retired models from picker and provider defaults 2026-07-26 16:28:41 -07:00
fireworks add Hermes headers to Fireworks provider (#81321) 2026-08-07 20:56:29 +00:00
gemini fix(gemini): bump native provider aux default to gemini-3.6-flash 2026-07-28 11:54:46 -07:00
gmi fix: align gmi fallback_models ordering with curated list 2026-07-20 02:25:44 -07:00
huggingface
…
kilocode fix(gemini): sweep hardcoded Gemini default models to gemini-3.6-flash (#32360) 2026-07-28 18:17:56 -07:00
kimi-coding fix(kimi): send Hermes attribution headers instead of claude-code/0.1.0 2026-08-11 13:25:37 +05:30
minimax fix: route minimax m3 reasoning controls through profile 2026-06-15 07:08:43 -07:00
nous perf(sessions): resolve the titling model from the provider's live catalog 2026-08-08 17:07:21 -05:00
novita
…
nvidia
…
ollama-cloud fix(ollama-cloud): capability-gate reasoning_effort + correct disable semantics 2026-07-16 07:58:04 -07:00
openai-codex
…
opencode-zen chore: map Axmr1 email + update stale Go routing docstring 2026-08-08 14:47:11 +05:30
openrouter fix(cache): scope prompt_cache_key by session to stop cross-session bucket sharing 2026-08-05 12:42:46 +05:30
qwen-oauth perf: avoid broad message prep deepcopies 2026-07-09 14:35:14 +05:30
stepfun
…
upstage fix(upstage): collapse unknown future efforts to high; behavior-contract tests 2026-07-15 00:09:24 +05:30
vertex fix(gemini): sweep hardcoded Gemini default models to gemini-3.6-flash (#32360) 2026-07-28 18:17:56 -07:00
xai chore(xai): drop noisy default_headers comment 2026-07-27 17:47:28 -07:00
xiaomi fix(vision): proactive downgrade for providers rejecting list-type tool content (#41072) 2026-06-07 21:50:57 -07:00
zai feat(reasoning): add max and ultra effort levels (#62650) 2026-07-12 00:26:49 -07:00
README.md
…

README.md

Model Provider Plugins

Each subdirectory is a self-contained provider profile plugin. The directory layout mirrors plugins/platforms/:

plugins/model-providers/
├── openrouter/
│   ├── __init__.py      # registers the ProviderProfile
│   └── plugin.yaml      # manifest: name, kind, version, description
├── anthropic/
│   ├── __init__.py
│   └── plugin.yaml
└── ...

How discovery works

providers/__init__.py._discover_providers() scans this directory (and $HERMES_HOME/plugins/model-providers/) the first time anything calls get_provider_profile() or list_providers(). Each __init__.py is imported and expected to call providers.register_provider(profile).

User plugins at $HERMES_HOME/plugins/model-providers/<name>/ override bundled plugins of the same name — last-writer-wins in register_provider(). Drop a file there to replace a built-in.

Adding a new provider

  1. Create plugins/model-providers/<your_provider>/__init__.py:

    from providers import register_provider
    from providers.base import ProviderProfile
    
    my_provider = ProviderProfile(
        name="your-provider",
        aliases=("alias1", "alias2"),
        display_name="Your Provider",
        description="One-line description shown in the setup picker",
        signup_url="https://your-provider.example.com/keys",
        env_vars=("YOUR_PROVIDER_API_KEY", "YOUR_PROVIDER_BASE_URL"),
        base_url="https://api.your-provider.example.com/v1",
        default_aux_model="your-cheap-model",
    )
    
    register_provider(my_provider)
    
  2. Create plugins/model-providers/<your_provider>/plugin.yaml:

    name: your-provider-profile
    kind: model-provider
    version: 1.0.0
    description: Short sentence about the provider
    author: Your Name
    

Nothing else needs to change. auth.py, config.py, models.py, doctor.py, model_metadata.py, runtime_provider.py, and the chat_completions transport all auto-wire from the registry.

Non-trivial profiles

Override the ProviderProfile hooks in a subclass for per-provider quirks — see plugins/model-providers/openrouter/__init__.py for build_extra_body and build_api_kwargs_extras examples, and plugins/model-providers/gemini/__init__.py for thinking_config translation.