waffles/consciousness
1
0
Fork 0
forked from kent/consciousness
Code Pull requests Activity

amygdala: F8 screen for live concept-readout projections

Browse source 
Per-token residual-stream projections from the vLLM server's readout
pipeline surfaced as a TUI bar chart. Flow:

* agent/readout.rs — SharedReadoutBuffer (manifest + ring of last ~200
  token entries). Lives on Agent and is shared across forks (single
  stream, one landing pad).
* agent/mod.rs — Agent::new now probes /v1/readout/manifest at startup
  (non-fatal; 404 leaves manifest None, which disables the screen).
* agent/context.rs — the streaming token handler pushes every token
  with attached readout onto the shared buffer.
* user/amygdala.rs — F8 screen. Top-K concepts by |value| as
  horizontal bars (green positive, red negative), plus a 4-line
  recent-tokens panel showing each token's top concept at the selected
  layer. Keys: 1..9 select layer, t toggles current/mean-over-recent.

Disabled state renders a hint pointing at VLLM_READOUT_MANIFEST /
VLLM_READOUT_VECTORS so users can tell the feature apart from
"server up but no tokens yet".

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet 2026-04-18 01:20:30 -04:00
commit c8976660f4
5 changed files with 410 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/agent/context.rs
View file

@ -682,7 +682,12 @@ impl ResponseParser {
let mut full_text = String::new();
while let Some(event) = stream.recv().await {
match event {
super::api::StreamToken::Token { id, readout: _ } => {
super::api::StreamToken::Token { id, readout } => {
if let Some(r) = readout {
if let Ok(mut buf) = agent.readout.lock() {
buf.push(id, r);
}
}
let text = super::tokenizer::decode(&[id]);
full_text.push_str(&text);
let mut ctx = agent.context.lock().await;