hermes-agent/plugins/model-providers
Siddharth Balyan 183d86b3e0
fix(openrouter): route reasoning_effort to verbosity for adaptive Anthropic models (#43436)
* fix(openrouter): route reasoning_effort to verbosity for adaptive Anthropic models

Reasoning-mandatory Anthropic models (Claude 4.6+/fable/mythos-class) over
OpenRouter ignore reasoning.effort and use adaptive thinking. #42991 correctly
stopped Hermes from sending a reasoning field to them (it 400s), but put nothing
in its place — leaving agent.reasoning_effort a silent no-op on the OpenRouter
path: the model always ran at its adaptive default (high) regardless of config.

OpenRouter honors the requested effort on the top-level verbosity field instead
(maps to Anthropic output_config.effort). Route the existing
reasoning_config[effort] there for these models while still never emitting a
reasoning field, preserving the #42991 fix. No new config arg — the value the
user already sets via agent.reasoning_effort now flows to verbosity.

- low/medium/high/xhigh/max pass through verbatim (OpenRouter accepts the
  extended scale for Claude; verified live HTTP 200 + monotonic token spend).
- effort unset/none/disabled omits verbosity so the model keeps its default.
- native Anthropic transport already correct; unchanged.

Fixes #43432

* test(openrouter): cover real effort range (add minimal, frame max as passthrough)

Adversarial review noted the verbosity tests looped over 'max' — a value
parse_reasoning_effort can never produce — while omitting 'minimal', which it
can. Align the routing test with the real config range
(VALID_REASONING_EFFORTS = minimal/low/medium/high/xhigh) and keep a separate
value-agnostic passthrough test that documents why xhigh/max must survive
verbatim (TypedDict, no runtime literal validation; OpenRouter accepts the
extended scale for Claude).

* docs: explain reasoning_effort -> verbosity routing for adaptive Anthropic models

Document that reasoning_effort transparently maps to OpenRouter's verbosity
field for adaptive-thinking Anthropic models (Claude 4.6+/Fable/Mythos), where
reasoning.effort is ignored. Note xhigh is the configurable ceiling (max is wire-
only). Add verbosity as a top-level-kwarg example in the provider-plugin guide.
2026-06-10 15:03:01 +05:30
..
alibaba feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
alibaba-coding-plan chore(model-picker): refresh provider picker descriptions 2026-05-31 15:02:26 -07:00
anthropic feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
arcee feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
azure-foundry feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
bedrock feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
copilot feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
copilot-acp feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
custom fix(ollama): set default_max_tokens for custom/Ollama provider 2026-06-07 21:50:25 -07:00
deepseek chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
gemini fix(models): add gemini-3.5-flash to Gemini OAuth + API-key pickers (#37046) 2026-06-01 16:31:13 -07:00
gmi refactor(gmi): move User-Agent to profile.default_headers 2026-05-08 03:22:11 -07:00
huggingface feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
kilocode feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
kimi-coding fix(kimi): send thinking xor reasoning_effort, never both 2026-06-07 01:24:29 -07:00
minimax fix(minimax): align default_aux_model with M3 frontier on minimax + minimax-cn 2026-06-04 05:53:35 -07:00
nous feat(nous): unified client=hermes-client-v<version> tag on every Portal request (#24779) 2026-05-12 20:49:20 -07:00
novita docs: update NovitaAI provider positioning (#25532) 2026-05-14 01:31:12 -07:00
nvidia feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
ollama-cloud feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
openai-codex feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
opencode-zen fix(opencode-go): gate thinking when reasoning_effort set to avoid HTTP 400 2026-06-07 01:24:29 -07:00
openrouter fix(openrouter): route reasoning_effort to verbosity for adaptive Anthropic models (#43436) 2026-06-10 15:03:01 +05:30
qwen-oauth feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
stepfun feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
xai feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -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(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
README.md feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00

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.