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: move pre_llm_call plugin context to user message, preserve prompt cache (#5146)

Browse source 
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)
This commit is contained in:
Teknium 2026-04-04 16:55:44 -07:00 • committed by GitHub
parent 96e96a79ad
commit 5879b3ef82
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 653 additions and 57 deletions
Download patch file Download diff file Expand all files Collapse all files

12
website/docs/user-guide/features/plugins.md
View file

@ -103,12 +103,12 @@ Plugins can register callbacks for these lifecycle events. See the **[Event Hook
| Hook | Fires when |
|------|-----------|
| `pre_tool_call` | Before any tool executes |
| `post_tool_call` | After any tool returns |
| `pre_llm_call` | Once per turn, before the LLM loop — can return `{"context": "..."}` to inject into the system prompt |
| `post_llm_call` | Once per turn, after the LLM loop completes |
| `on_session_start` | New session created (first turn only) |
| `on_session_end` | End of every `run_conversation` call |
| [`pre_tool_call`](/docs/user-guide/features/hooks#pre_tool_call) | Before any tool executes |
| [`post_tool_call`](/docs/user-guide/features/hooks#post_tool_call) | After any tool returns |
| [`pre_llm_call`](/docs/user-guide/features/hooks#pre_llm_call) | Once per turn, before the LLM loop — can return `{"context": "..."}` to [inject context into the user message](/docs/user-guide/features/hooks#pre_llm_call) |
| [`post_llm_call`](/docs/user-guide/features/hooks#post_llm_call) | Once per turn, after the LLM loop (successful turns only) |
| [`on_session_start`](/docs/user-guide/features/hooks#on_session_start) | New session created (first turn only) |
| [`on_session_end`](/docs/user-guide/features/hooks#on_session_end) | End of every `run_conversation` call + CLI exit handler |
## Managing plugins