forked from kent/consciousness
Wire vLLM priority scheduling through all agent paths
The priority field existed in agent definitions and was serialized into vLLM requests, but was never actually set — every request went out with no priority, so vLLM treated them equally. This meant background graph maintenance agents could preempt the main conversation. Add priority to AgentState and set it at each call site: 0 = interactive (main conversation) 1 = surface agent (needs to feed memories promptly) 2 = other subconscious agents 10 = unconscious/standalone agents (batch) Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
parent
b115cec096
commit
bf503b571e
4 changed files with 15 additions and 2 deletions
|
|
@ -143,6 +143,7 @@ impl AutoAgent {
|
|||
let mut st = agent.state.lock().await;
|
||||
st.provenance = format!("standalone:{}", self.name);
|
||||
st.tools = self.tools.clone();
|
||||
st.priority = Some(10);
|
||||
}
|
||||
|
||||
let mut backend = Backend(agent);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue