mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-20 15:33:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

feat(auxiliary): per-task reasoning_effort for auxiliary models (#64597)

Browse source 
Every auxiliary task block (vision, web_extract, compression,
title_generation, curator, background_review, moa_reference, ...) now
accepts a reasoning_effort shorthand:

  auxiliary:
    compression:
      reasoning_effort: low
    vision:
      reasoning_effort: none

_get_task_extra_body() folds it into extra_body.reasoning, which every
auxiliary wire already translates: chat.completions passes it through,
the Codex Responses adapter maps it to top-level reasoning/include, and
the Anthropic auxiliary adapter now forwards it into
build_anthropic_kwargs(reasoning_config=...) (previously hardcoded None).

An explicit extra_body.reasoning on the same task wins over the
shorthand. Invalid levels are ignored with a warning. Empty string
(the shipped default) is a no-op — zero behavior change.

Config: reasoning_effort added to all 16 auxiliary task blocks in
DEFAULT_CONFIG (no version bump — deep-merge handles new keys).
This commit is contained in:
Teknium 2026-07-14 14:07:43 -07:00 • committed by GitHub
parent f7198a2055
commit df5700ebe3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 195 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

16
website/docs/user-guide/configuration.md
View file

@ -974,6 +974,22 @@ Every model slot in Hermes — auxiliary tasks, compression, fallback — uses t
| `model` | Which model to request | provider's default |
| `base_url` | Custom OpenAI-compatible endpoint (overrides provider) | not set |
Auxiliary task blocks additionally accept a `reasoning_effort` knob:
| Key | What it does | Default |
|-----|-------------|---------|
| `reasoning_effort` | Thinking level for that task's LLM calls: `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`, `ultra` | not set (provider default) |
This is the per-task counterpart of the global `agent.reasoning_effort`: run compression at `low` or vision at `none` to cut side-task latency and cost when your main model is an expensive reasoning model, without touching your main chat behavior. It works on every auxiliary task block (`vision`, `web_extract`, `compression`, `title_generation`, `curator`, `background_review`, `moa_reference`, `moa_aggregator`, ...), across all three auxiliary wire formats (chat completions, Codex Responses, Anthropic Messages). An explicit `extra_body.reasoning` on the same task wins over the shorthand.
```yaml
auxiliary:
compression:
reasoning_effort: "low" # summaries don't need deep thinking
vision:
reasoning_effort: "none" # disable thinking for image description
```
When `base_url` is set, Hermes ignores the provider and calls that endpoint directly (using `api_key` or `OPENAI_API_KEY` for auth). When only `provider` is set, Hermes uses that provider's built-in auth and base URL.
Available providers for auxiliary tasks: `auto`, `main`, plus any provider in the [provider registry](/reference/environment-variables) — `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `qwen-oauth`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `minimax-oauth`, `deepseek`, `nvidia`, `xai`, `xai-oauth`, `ollama-cloud`, `alibaba`, `bedrock`, `huggingface`, `arcee`, `xiaomi`, `kilocode`, `opencode-zen`, `opencode-go`, `azure-foundry` — or any named custom provider from your `custom_providers` list (e.g. `provider: "beans"`).