consciousness/src/user/learn.rs
Kent Overstreet 2b632d568b learn: nanosecond timestamps, token ranges for /score
Two related changes to the learn subsystem:

1. AST node timestamps are now non-optional — both Leaf and Branch
   variants carry a DateTime<Utc>. UNIX_EPOCH means "unset" (old entries
   deserialized from on-disk conversation logs).

   Training uses timestamps as unique keys for dedup, so we promote to
   nanosecond precision: node_timestamp_ns(), TrainData.timestamp_ns,
   FinetuneCandidate.timestamp_ns, mark_trained(ns).

2. build_token_ids() now also returns token-position ranges of assistant
   messages. These are passed to vLLM's /score endpoint via the new
   score_ranges field so only scored-position logprobs are returned —
   cuts bandwidth/compute when scoring small windows.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-16 11:48:37 -04:00

264 lines
9.4 KiB
Rust

// learn.rs — F6: fine-tuning review screen
//
// Shows responses identified as training candidates (high divergence
// when memories stripped). Queue for review before sending to /finetune.
use ratatui::{
layout::{Constraint, Layout, Rect},
style::{Color, Modifier, Style},
text::{Line, Span},
widgets::{Block, Borders, List, ListItem, ListState, Paragraph, Wrap},
Frame,
};
use ratatui::crossterm::event::{Event, KeyCode, KeyEvent};
use super::{App, ScreenView, screen_legend};
/// A candidate response identified for fine-tuning.
#[derive(Clone, Debug)]
pub struct FinetuneCandidate {
/// Index in conversation entries.
pub entry_idx: usize,
/// Divergence score (higher = more dependent on memories).
pub divergence: f64,
/// The assistant response text.
pub response_text: String,
/// Status: pending, approved, rejected, sent.
pub status: CandidateStatus,
/// Token IDs for context.
pub context_ids: Vec<u32>,
/// Token IDs for continuation (what we're training on).
pub continuation_ids: Vec<u32>,
/// What the model would have said without memories (if generated).
pub alternate_text: Option<String>,
/// Timestamp in nanos — used as unique key for trained-set dedup.
pub timestamp_ns: i64,
}
#[derive(Clone, Debug, PartialEq)]
pub enum CandidateStatus {
Pending,
Approved,
Rejected,
Sent,
}
impl From<crate::subconscious::learn::FinetuneCandidate> for FinetuneCandidate {
fn from(c: crate::subconscious::learn::FinetuneCandidate) -> Self {
FinetuneCandidate {
entry_idx: c.entry_idx,
divergence: c.divergence,
response_text: c.response_text,
status: CandidateStatus::Pending,
context_ids: c.context_ids,
continuation_ids: c.continuation_ids,
alternate_text: c.alternate_text,
timestamp_ns: c.timestamp_ns,
}
}
}
pub(crate) struct LearnScreen {
list_state: ListState,
}
impl LearnScreen {
pub fn new() -> Self {
Self {
list_state: ListState::default(),
}
}
fn selected_idx(&self) -> Option<usize> {
self.list_state.selected()
}
}
impl ScreenView for LearnScreen {
fn label(&self) -> &'static str { "learn" }
fn tick(&mut self, frame: &mut Frame, area: Rect,
events: &[Event], app: &mut App) {
// Handle input first (before borrowing candidates for rendering)
let candidate_count = app.finetune_candidates.len();
for event in events {
if let Event::Key(KeyEvent { code, .. }) = event {
match code {
KeyCode::Up | KeyCode::Char('k') => {
let i = self.list_state.selected().unwrap_or(0);
self.list_state.select(Some(i.saturating_sub(1)));
}
KeyCode::Down | KeyCode::Char('j') => {
let i = self.list_state.selected().unwrap_or(0);
let max = candidate_count.saturating_sub(1);
self.list_state.select(Some((i + 1).min(max)));
}
KeyCode::Char('a') => {
if let Some(idx) = self.selected_idx() {
app.finetune_action(idx, CandidateStatus::Approved);
}
}
KeyCode::Char('r') => {
if let Some(idx) = self.selected_idx() {
app.finetune_action(idx, CandidateStatus::Rejected);
}
}
KeyCode::Char('g') => {
// Toggle alternate generation and persist
let current = crate::subconscious::learn::alternates_enabled();
crate::subconscious::learn::set_alternates(!current);
}
KeyCode::Char('s') => {
app.finetune_send_approved();
}
_ => {}
}
}
}
// Ensure selection is valid
if candidate_count > 0 {
let sel = self.list_state.selected().unwrap_or(0).min(candidate_count - 1);
self.list_state.select(Some(sel));
}
// Get scoring progress from mind state
let progress = app.mind_state.as_ref()
.map(|ms| ms.finetune_progress.as_str())
.unwrap_or("");
// Now render
let gen_on = crate::subconscious::learn::alternates_enabled();
let title_right = if !progress.is_empty() {
format!(" {} ", progress)
} else if gen_on {
" learn [gen] ".to_string()
} else {
" learn ".to_string()
};
let block = Block::default()
.title_top(Line::from(screen_legend()).left_aligned())
.title_top(Line::from(title_right).right_aligned())
.borders(Borders::ALL)
.border_style(Style::default().fg(Color::Magenta));
let inner = block.inner(area);
frame.render_widget(block, area);
let candidates = &app.finetune_candidates;
if candidates.is_empty() {
let msg = if progress.is_empty() {
" No candidates yet — scoring runs after each turn."
} else {
" Scoring in progress..."
};
frame.render_widget(
Paragraph::new(Line::styled(msg, Style::default().fg(Color::DarkGray))),
inner,
);
return;
}
// Layout: list on left, detail on right
let [list_area, detail_area] = Layout::horizontal([
Constraint::Percentage(40),
Constraint::Percentage(60),
]).areas(inner);
// Render candidate list
let items: Vec<ListItem> = candidates.iter().map(|c| {
let status_char = match c.status {
CandidateStatus::Pending => ' ',
CandidateStatus::Approved => '+',
CandidateStatus::Rejected => '-',
CandidateStatus::Sent => '*',
};
let style = match c.status {
CandidateStatus::Pending => Style::default(),
CandidateStatus::Approved => Style::default().fg(Color::Green),
CandidateStatus::Rejected => Style::default().fg(Color::DarkGray),
CandidateStatus::Sent => Style::default().fg(Color::Cyan),
};
ListItem::new(Line::from(vec![
Span::styled(format!("[{}] ", status_char), style),
Span::styled(format!("{:.2} ", c.divergence), Style::default().fg(Color::Yellow)),
Span::raw(truncate(&c.response_text, 30)),
]))
}).collect();
let list = List::new(items)
.block(Block::default().borders(Borders::RIGHT).title(" candidates "))
.highlight_style(Style::default().add_modifier(Modifier::REVERSED));
frame.render_stateful_widget(list, list_area, &mut self.list_state);
// Render detail for selected candidate
if let Some(idx) = self.selected_idx() {
if let Some(candidate) = candidates.get(idx) {
render_detail(frame, candidate, detail_area);
}
}
// Render help at bottom
let help = Line::from(vec![
Span::styled(" j/k/\u{2191}\u{2193}", Style::default().fg(Color::Cyan)),
Span::raw("=nav "),
Span::styled("a", Style::default().fg(Color::Green)),
Span::raw("=approve "),
Span::styled("r", Style::default().fg(Color::Red)),
Span::raw("=reject "),
Span::styled("g", Style::default().fg(Color::Yellow)),
Span::raw("=gen "),
Span::styled("s", Style::default().fg(Color::Magenta)),
Span::raw("=send "),
]);
let help_area = Rect {
y: area.y + area.height - 1,
height: 1,
..area
};
frame.render_widget(Paragraph::new(help), help_area);
}
}
fn render_detail(frame: &mut Frame, c: &FinetuneCandidate, area: Rect) {
let [header_area, content_area] = Layout::vertical([
Constraint::Length(3),
Constraint::Min(1),
]).areas(area);
// Header: divergence, status
let alt_status = if c.alternate_text.is_some() { "yes" } else { "no" };
let header = Paragraph::new(vec![
Line::from(vec![
Span::raw(" divergence: "),
Span::styled(format!("{:.3}", c.divergence), Style::default().fg(Color::Yellow)),
Span::raw(format!(" entry: {} alt: {}", c.entry_idx, alt_status)),
]),
]);
frame.render_widget(header, header_area);
// Content: response and alternate (if available)
let content_block = Block::default()
.borders(Borders::TOP)
.title(" response ");
let text = match &c.alternate_text {
Some(alt) => format!(" {}\n\n─── without memories ───\n\n {}", c.response_text, alt),
None => format!(" {}", c.response_text),
};
let content = Paragraph::new(text)
.block(content_block)
.wrap(Wrap { trim: false });
frame.render_widget(content, content_area);
}
fn truncate(s: &str, max: usize) -> String {
let first_line = s.lines().next().unwrap_or("");
if first_line.len() > max {
format!("{}...", &first_line[..max])
} else {
first_line.to_string()
}
}