hermes-agent/plugins/model-providers
teknium1 cd9470f416 fix(deepseek): wire thinking-mode via DeepSeekProfile, not legacy fallback
The cherry-picked PR #15251 from @tw2818 correctly identified the
DeepSeek 400 root cause but placed the fix in the legacy fallback path
of `build_kwargs`, which DeepSeek never reaches — DeepSeek has a
registered ProviderProfile and goes through `_build_kwargs_from_profile`
instead. The legacy-path block was therefore dead code.

This commit pivots the fix to where it actually fires:

- New `DeepSeekProfile` in `plugins/model-providers/deepseek/__init__.py`
  overrides `build_api_kwargs_extras` to emit DeepSeek's expected wire
  format (mirrors `KimiProfile`):

      {"reasoning_effort": "<low|medium|high|max>",
       "extra_body": {"thinking": {"type": "enabled" | "disabled"}}}

- Model gating: only `deepseek-v4-*` and `deepseek-reasoner` emit
  thinking control. `deepseek-chat` (V3) is untouched — current behavior.

- Effort mapping: low/medium/high passthrough, xhigh/max → max, unset →
  omitted (DeepSeek server applies its own default).

- Revert the legacy-path additions from PR #15251 — they were dead code,
  and the `_copy_reasoning_content_for_api` strip block specifically
  would have nullified the existing reasoning_content padding machinery
  (`_needs_deepseek_tool_reasoning` → space-pad on replay) that the
  active provider already relies on for replay correctness.

- Unit tests pin the wire-shape contract and the model gating rules
  (26 tests, all passing). Existing transport + provider profile suites
  (321 tests) continue to pass.

- AUTHOR_MAP: map twebefy@gmail.com → tw2818 for release notes credit.

Closes #15700, #17212, #17825.
Co-authored-by: tw2818 <twebefy@gmail.com>
2026-05-15 17:03:26 -07:00
..
ai-gateway feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
alibaba feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
alibaba-coding-plan feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -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(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -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 feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
deepseek fix(deepseek): wire thinking-mode via DeepSeekProfile, not legacy fallback 2026-05-15 17:03:26 -07:00
gemini feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -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 feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
minimax feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -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 feat(providers): make all 33 providers pluggable under plugins/model-providers/ 2026-05-05 13:40:01 -07:00
openrouter feat(openrouter): wire Pareto Code router with min_coding_score knob (#22838) 2026-05-09 14:47:00 -07:00
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(doctor): skip /models health check for providers that don't support it 2026-05-12 17:12:25 -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.