mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
5879b3ef82
Plugin context from pre_llm_call hooks was injected into the system prompt, breaking the prompt cache prefix every turn when content changed (typical for memory plugins). Now all plugin context goes into the current turn's user message — the system prompt stays identical across turns, preserving cached tokens. The system prompt is reserved for Hermes internals. Plugins contribute context alongside the user's input. Also adds comprehensive documentation for all 6 plugin hooks: pre_tool_call, post_tool_call, pre_llm_call, post_llm_call, on_session_start, on_session_end — each with full callback signatures, parameter tables, firing conditions, and examples. Supersedes #5138 which identified the same cache-busting bug and proposed an uncached system suffix approach. This fix goes further by removing system prompt injection entirely. Co-identified-by: OutThisLife (PR #5138) |
||
|---|---|---|
| .. | ||
| _category_.json | ||
| build-a-hermes-plugin.md | ||
| daily-briefing-bot.md | ||
| migrate-from-openclaw.md | ||
| python-library.md | ||
| team-telegram-assistant.md | ||
| tips.md | ||
| use-mcp-with-hermes.md | ||
| use-soul-with-hermes.md | ||
| use-voice-mode-with-hermes.md | ||