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

fix: prevent agent from stopping mid-task — compression floor, budget overhaul, activity tracking

Browse source 
Three root causes of the 'agent stops mid-task' gateway bug:

1. Compression threshold floor (64K tokens minimum)
   - The 50% threshold on a 100K-context model fired at 50K tokens,
     causing premature compression that made models lose track of
     multi-step plans.  Now threshold_tokens = max(50% * context, 64K).
   - Models with <64K context are rejected at startup with a clear error.

2. Budget warning removal — grace call instead
   - Removed the 70%/90% iteration budget warnings entirely.  These
     injected '[BUDGET WARNING: Provide your final response NOW]' into
     tool results, causing models to abandon complex tasks prematurely.
   - Now: no warnings during normal execution.  When the budget is
     actually exhausted (90/90), inject a user message asking the model
     to summarise, allow one grace API call, and only then fall back
     to _handle_max_iterations.

3. Activity touches during long terminal execution
   - _wait_for_process polls every 0.2s but never reported activity.
     The gateway's inactivity timeout (default 1800s) would fire during
     long-running commands that appeared 'idle.'
   - Now: thread-local activity callback fires every 10s during the
     poll loop, keeping the gateway's activity tracker alive.
   - Agent wires _touch_activity into the callback before each tool call.

Also: docs update noting 64K minimum context requirement.

Closes #7915 (root cause was agent-loop termination, not Weixin delivery limits).
This commit is contained in:
Teknium 2026-04-11 16:18:57 -07:00 • committed by GitHub
parent 08f35076c9
commit c8aff74632
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 140 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

4
website/docs/getting-started/quickstart.md
View file

@ -64,6 +64,10 @@ hermes setup # Or configure everything at once
| **Vercel AI Gateway** | Vercel AI Gateway routing | Set `AI_GATEWAY_API_KEY` |
| **Custom Endpoint** | VLLM, SGLang, Ollama, or any OpenAI-compatible API | Set base URL + API key |
:::caution Minimum context: 64K tokens
Hermes Agent requires a model with at least **64,000 tokens** of context. Models with smaller windows cannot maintain enough working memory for multi-step tool-calling workflows and will be rejected at startup. Most hosted models (Claude, GPT, Gemini, Qwen, DeepSeek) meet this easily. If you're running a local model, set its context size to at least 64K (e.g. `--ctx-size 65536` for llama.cpp or `-c 65536` for Ollama).
:::
:::tip
You can switch providers at any time with `hermes model` — no code changes, no lock-in. When configuring a custom endpoint, Hermes will prompt for the context window size and auto-detect it when possible. See [Context Length Detection](../integrations/providers.md#context-length-detection) for details.
:::