forked from kent/consciousness
2b632d568b
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>
87 lines
2.7 KiB
Rust
87 lines
2.7 KiB
Rust
use anyhow::{Context, Result};
|
|
use std::fs::{File, OpenOptions};
|
|
use std::io::Write;
|
|
use std::path::{Path, PathBuf};
|
|
use crate::agent::context::AstNode;
|
|
use crate::hippocampus::transcript::JsonlBackwardIter;
|
|
use memmap2::Mmap;
|
|
|
|
pub struct ConversationLog {
|
|
path: PathBuf,
|
|
}
|
|
|
|
impl ConversationLog {
|
|
pub fn new(path: PathBuf) -> Result<Self> {
|
|
if let Some(parent) = path.parent() {
|
|
std::fs::create_dir_all(parent)
|
|
.with_context(|| format!("creating log dir {}", parent.display()))?;
|
|
}
|
|
Ok(Self { path })
|
|
}
|
|
|
|
pub fn append_node(&self, node: &AstNode) -> Result<()> {
|
|
let mut file = OpenOptions::new()
|
|
.create(true)
|
|
.append(true)
|
|
.open(&self.path)
|
|
.with_context(|| format!("opening log {}", self.path.display()))?;
|
|
|
|
let line = serde_json::to_string(node)
|
|
.context("serializing node for log")?;
|
|
writeln!(file, "{}", line)
|
|
.context("writing to conversation log")?;
|
|
file.sync_all()
|
|
.context("syncing conversation log")?;
|
|
Ok(())
|
|
}
|
|
|
|
/// Read nodes from the tail of the log, newest first.
|
|
/// Caller decides when to stop (budget, count, etc).
|
|
pub fn read_tail(&self) -> Result<TailNodes> {
|
|
if !self.path.exists() {
|
|
anyhow::bail!("log does not exist");
|
|
}
|
|
let file = File::open(&self.path)
|
|
.with_context(|| format!("opening log {}", self.path.display()))?;
|
|
if file.metadata()?.len() == 0 {
|
|
anyhow::bail!("log is empty");
|
|
}
|
|
let mmap = unsafe { Mmap::map(&file)? };
|
|
Ok(TailNodes { _file: file, mmap })
|
|
}
|
|
|
|
pub fn path(&self) -> &Path {
|
|
&self.path
|
|
}
|
|
|
|
pub fn oldest_timestamp(&self) -> Option<chrono::DateTime<chrono::Utc>> {
|
|
// Read forward from the start to find first non-epoch timestamp
|
|
let file = File::open(&self.path).ok()?;
|
|
let mmap = unsafe { Mmap::map(&file).ok()? };
|
|
for line in mmap.split(|&b| b == b'\n') {
|
|
if line.is_empty() { continue; }
|
|
if let Ok(node) = serde_json::from_slice::<AstNode>(line) {
|
|
if let Some(leaf) = node.leaf() {
|
|
let ts = leaf.timestamp();
|
|
if ts != chrono::DateTime::UNIX_EPOCH {
|
|
return Some(ts);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
None
|
|
}
|
|
}
|
|
|
|
/// Iterates over conversation log nodes newest-first, using mmap + backward scan.
|
|
pub struct TailNodes {
|
|
_file: File,
|
|
mmap: Mmap,
|
|
}
|
|
|
|
impl TailNodes {
|
|
pub fn iter(&self) -> impl Iterator<Item = AstNode> + '_ {
|
|
JsonlBackwardIter::new(&self.mmap)
|
|
.filter_map(|bytes| serde_json::from_slice::<AstNode>(bytes).ok())
|
|
}
|
|
}
|