Remove dead files: parse-claude-conversation.rs, test-conversation.rs
Orphaned binaries — not in Cargo.toml, not declared as modules. ~395 lines of dead code. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet
parent
7de816022a
commit
9598e8b86c
2 changed files with 0 additions and 395 deletions
|
|
@ -1,330 +0,0 @@
|
|||
// parse-claude-conversation: debug tool for inspecting what's in the context window
|
||||
//
|
||||
// Two-layer design:
|
||||
// 1. extract_context_items() — walks JSONL from last compaction, yields
|
||||
// structured records representing what's in the context window
|
||||
// 2. format_as_context() — renders those records as they appear to Claude
|
||||
//
|
||||
// The transcript is mmap'd and scanned backwards from EOF using brace-depth
|
||||
// tracking to find complete JSON objects, avoiding a full forward scan of
|
||||
// what can be a 500MB+ file.
|
||||
//
|
||||
// Usage:
|
||||
// parse-claude-conversation [TRANSCRIPT_PATH]
|
||||
// parse-claude-conversation --last # use the last stashed session
|
||||
|
||||
use clap::Parser;
|
||||
use memmap2::Mmap;
|
||||
use poc_memory::transcript::{JsonlBackwardIter, find_last_compaction};
|
||||
use serde_json::Value;
|
||||
use std::fs;
|
||||
|
||||
#[derive(Parser)]
|
||||
#[command(name = "parse-claude-conversation")]
|
||||
struct Args {
|
||||
/// Transcript JSONL path (or --last to use stashed session)
|
||||
path: Option<String>,
|
||||
|
||||
/// Use the last stashed session from memory-search
|
||||
#[arg(long)]
|
||||
last: bool,
|
||||
|
||||
/// Dump raw JSONL objects. Optional integer: number of extra objects
|
||||
/// to include before the compaction boundary.
|
||||
#[arg(long, num_args = 0..=1, default_missing_value = "0")]
|
||||
raw: Option<usize>,
|
||||
}
|
||||
|
||||
// --- Context extraction ---
|
||||
|
||||
/// A single item in the context window, as Claude sees it.
|
||||
enum ContextItem {
|
||||
UserText(String),
|
||||
SystemReminder(String),
|
||||
AssistantText(String),
|
||||
AssistantThinking,
|
||||
ToolUse { name: String, input: String },
|
||||
ToolResult(String),
|
||||
}
|
||||
|
||||
/// Extract context items from the transcript, starting from the last compaction.
|
||||
fn extract_context_items(data: &[u8]) -> Vec<ContextItem> {
|
||||
let start = find_last_compaction(data).unwrap_or(0);
|
||||
let region = &data[start..];
|
||||
|
||||
let mut items = Vec::new();
|
||||
|
||||
// Forward scan through JSONL lines from compaction onward
|
||||
for line in region.split(|&b| b == b'\n') {
|
||||
if line.is_empty() { continue; }
|
||||
|
||||
let obj: Value = match serde_json::from_slice(line) {
|
||||
Ok(v) => v,
|
||||
Err(_) => continue,
|
||||
};
|
||||
|
||||
let msg_type = obj.get("type").and_then(|v| v.as_str()).unwrap_or("");
|
||||
|
||||
match msg_type {
|
||||
"user" => {
|
||||
if let Some(content) = obj.get("message").and_then(|m| m.get("content")) {
|
||||
extract_user_content(content, &mut items);
|
||||
}
|
||||
}
|
||||
"assistant" => {
|
||||
if let Some(content) = obj.get("message").and_then(|m| m.get("content")) {
|
||||
extract_assistant_content(content, &mut items);
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
items
|
||||
}
|
||||
|
||||
/// Parse user message content into context items.
|
||||
fn extract_user_content(content: &Value, items: &mut Vec<ContextItem>) {
|
||||
match content {
|
||||
Value::String(s) => {
|
||||
split_system_reminders(s, items, false);
|
||||
}
|
||||
Value::Array(arr) => {
|
||||
for block in arr {
|
||||
let btype = block.get("type").and_then(|v| v.as_str()).unwrap_or("");
|
||||
match btype {
|
||||
"text" => {
|
||||
if let Some(t) = block.get("text").and_then(|v| v.as_str()) {
|
||||
split_system_reminders(t, items, false);
|
||||
}
|
||||
}
|
||||
"tool_result" => {
|
||||
let result_text = extract_tool_result_text(block);
|
||||
if !result_text.is_empty() {
|
||||
split_system_reminders(&result_text, items, true);
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
/// Extract text from a tool_result block (content can be string or array).
|
||||
fn extract_tool_result_text(block: &Value) -> String {
|
||||
match block.get("content") {
|
||||
Some(Value::String(s)) => s.clone(),
|
||||
Some(Value::Array(arr)) => {
|
||||
arr.iter()
|
||||
.filter_map(|b| b.get("text").and_then(|v| v.as_str()))
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n")
|
||||
}
|
||||
_ => String::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Split text on <system-reminder> tags. Non-reminder text emits UserText
|
||||
/// or ToolResult depending on `is_tool_result`.
|
||||
fn split_system_reminders(text: &str, items: &mut Vec<ContextItem>, is_tool_result: bool) {
|
||||
let mut remaining = text;
|
||||
|
||||
loop {
|
||||
if let Some(start) = remaining.find("<system-reminder>") {
|
||||
let before = remaining[..start].trim();
|
||||
if !before.is_empty() {
|
||||
if is_tool_result {
|
||||
items.push(ContextItem::ToolResult(before.to_string()));
|
||||
} else {
|
||||
items.push(ContextItem::UserText(before.to_string()));
|
||||
}
|
||||
}
|
||||
|
||||
let after_open = &remaining[start + "<system-reminder>".len()..];
|
||||
if let Some(end) = after_open.find("</system-reminder>") {
|
||||
let reminder = after_open[..end].trim();
|
||||
if !reminder.is_empty() {
|
||||
items.push(ContextItem::SystemReminder(reminder.to_string()));
|
||||
}
|
||||
remaining = &after_open[end + "</system-reminder>".len()..];
|
||||
} else {
|
||||
let reminder = after_open.trim();
|
||||
if !reminder.is_empty() {
|
||||
items.push(ContextItem::SystemReminder(reminder.to_string()));
|
||||
}
|
||||
break;
|
||||
}
|
||||
} else {
|
||||
let trimmed = remaining.trim();
|
||||
if !trimmed.is_empty() {
|
||||
if is_tool_result {
|
||||
items.push(ContextItem::ToolResult(trimmed.to_string()));
|
||||
} else {
|
||||
items.push(ContextItem::UserText(trimmed.to_string()));
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Parse assistant message content into context items.
|
||||
fn extract_assistant_content(content: &Value, items: &mut Vec<ContextItem>) {
|
||||
match content {
|
||||
Value::String(s) => {
|
||||
let trimmed = s.trim();
|
||||
if !trimmed.is_empty() {
|
||||
items.push(ContextItem::AssistantText(trimmed.to_string()));
|
||||
}
|
||||
}
|
||||
Value::Array(arr) => {
|
||||
for block in arr {
|
||||
let btype = block.get("type").and_then(|v| v.as_str()).unwrap_or("");
|
||||
match btype {
|
||||
"text" => {
|
||||
if let Some(t) = block.get("text").and_then(|v| v.as_str()) {
|
||||
let trimmed = t.trim();
|
||||
if !trimmed.is_empty() {
|
||||
items.push(ContextItem::AssistantText(trimmed.to_string()));
|
||||
}
|
||||
}
|
||||
}
|
||||
"tool_use" => {
|
||||
let name = block.get("name")
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("?")
|
||||
.to_string();
|
||||
let input = block.get("input")
|
||||
.map(|v| v.to_string())
|
||||
.unwrap_or_default();
|
||||
items.push(ContextItem::ToolUse { name, input });
|
||||
}
|
||||
"thinking" => {
|
||||
items.push(ContextItem::AssistantThinking);
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
|
||||
// --- Formatting layer ---
|
||||
|
||||
fn truncate(s: &str, max: usize) -> String {
|
||||
if s.len() <= max {
|
||||
s.to_string()
|
||||
} else {
|
||||
format!("{}...({} total)", &s[..max], s.len())
|
||||
}
|
||||
}
|
||||
|
||||
fn format_as_context(items: &[ContextItem]) {
|
||||
for item in items {
|
||||
match item {
|
||||
ContextItem::UserText(text) => {
|
||||
println!("USER: {}", truncate(text, 300));
|
||||
println!();
|
||||
}
|
||||
ContextItem::SystemReminder(text) => {
|
||||
println!("<system-reminder>");
|
||||
println!("{}", truncate(text, 500));
|
||||
println!("</system-reminder>");
|
||||
println!();
|
||||
}
|
||||
ContextItem::AssistantText(text) => {
|
||||
println!("ASSISTANT: {}", truncate(text, 300));
|
||||
println!();
|
||||
}
|
||||
ContextItem::AssistantThinking => {
|
||||
println!("[thinking]");
|
||||
println!();
|
||||
}
|
||||
ContextItem::ToolUse { name, input } => {
|
||||
println!("TOOL_USE: {} {}", name, truncate(input, 200));
|
||||
println!();
|
||||
}
|
||||
ContextItem::ToolResult(text) => {
|
||||
println!("TOOL_RESULT: {}", truncate(text, 300));
|
||||
println!();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn main() {
|
||||
let args = Args::parse();
|
||||
|
||||
let path = if args.last {
|
||||
let stash_path = dirs::home_dir().unwrap_or_default()
|
||||
.join(".consciousness/sessions/last-input.json");
|
||||
let stash = fs::read_to_string(&stash_path)
|
||||
.expect("No stashed input");
|
||||
let json: Value = serde_json::from_str(&stash).expect("Bad JSON");
|
||||
json["transcript_path"]
|
||||
.as_str()
|
||||
.expect("No transcript_path")
|
||||
.to_string()
|
||||
} else if let Some(p) = args.path {
|
||||
p
|
||||
} else {
|
||||
eprintln!("error: provide a transcript path or --last");
|
||||
std::process::exit(1);
|
||||
};
|
||||
|
||||
let file = fs::File::open(&path).expect("Can't open transcript");
|
||||
let mmap = unsafe { Mmap::map(&file).expect("Failed to mmap") };
|
||||
|
||||
eprintln!(
|
||||
"Transcript: {} ({:.1} MB)",
|
||||
&path,
|
||||
mmap.len() as f64 / 1_000_000.0
|
||||
);
|
||||
|
||||
let compaction_offset = find_last_compaction(&mmap).unwrap_or(0);
|
||||
eprintln!("Compaction at byte offset: {}", compaction_offset);
|
||||
|
||||
if let Some(extra) = args.raw {
|
||||
use std::io::Write;
|
||||
|
||||
// Collect `extra` JSON objects before the compaction boundary
|
||||
let mut before = Vec::new();
|
||||
if extra > 0 && compaction_offset > 0 {
|
||||
for obj_bytes in JsonlBackwardIter::new(&mmap[..compaction_offset]) {
|
||||
if let Ok(obj) = serde_json::from_slice::<Value>(obj_bytes) {
|
||||
let t = obj.get("type").and_then(|v| v.as_str()).unwrap_or("");
|
||||
if t == "file-history-snapshot" { continue; }
|
||||
}
|
||||
before.push(obj_bytes.to_vec());
|
||||
if before.len() >= extra {
|
||||
break;
|
||||
}
|
||||
}
|
||||
before.reverse();
|
||||
}
|
||||
|
||||
for obj in &before {
|
||||
std::io::stdout().write_all(obj).ok();
|
||||
println!();
|
||||
}
|
||||
|
||||
// Then dump everything from compaction onward
|
||||
let region = &mmap[compaction_offset..];
|
||||
for line in region.split(|&b| b == b'\n') {
|
||||
if line.is_empty() { continue; }
|
||||
if let Ok(obj) = serde_json::from_slice::<Value>(line) {
|
||||
let t = obj.get("type").and_then(|v| v.as_str()).unwrap_or("");
|
||||
if t == "file-history-snapshot" { continue; }
|
||||
std::io::stdout().write_all(line).ok();
|
||||
println!();
|
||||
}
|
||||
}
|
||||
} else {
|
||||
let items = extract_context_items(&mmap);
|
||||
eprintln!("Context items: {}", items.len());
|
||||
format_as_context(&items);
|
||||
}
|
||||
}
|
||||
|
|
@ -1,65 +0,0 @@
|
|||
// Test tool for the conversation resolver.
|
||||
// Usage: POC_SESSION_ID=<id> cargo run --bin test-conversation
|
||||
// or: cargo run --bin test-conversation -- <transcript-path>
|
||||
|
||||
use std::time::Instant;
|
||||
|
||||
fn main() {
|
||||
let path = std::env::args().nth(1).unwrap_or_else(|| {
|
||||
let session_id = std::env::var("POC_SESSION_ID")
|
||||
.expect("pass a transcript path or set POC_SESSION_ID");
|
||||
let projects = poc_memory::config::get().projects_dir.clone();
|
||||
eprintln!("session: {}", session_id);
|
||||
eprintln!("projects dir: {}", projects.display());
|
||||
|
||||
let mut found = None;
|
||||
if let Ok(dirs) = std::fs::read_dir(&projects) {
|
||||
for dir in dirs.filter_map(|e| e.ok()) {
|
||||
let path = dir.path().join(format!("{}.jsonl", session_id));
|
||||
eprintln!(" checking: {}", path.display());
|
||||
if path.exists() {
|
||||
found = Some(path);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
let path = found.expect("transcript not found");
|
||||
path.to_string_lossy().to_string()
|
||||
});
|
||||
|
||||
let meta = std::fs::metadata(&path).expect("can't stat file");
|
||||
eprintln!("transcript: {} ({} bytes)", path, meta.len());
|
||||
|
||||
let t0 = Instant::now();
|
||||
let iter = poc_memory::transcript::TailMessages::open(&path)
|
||||
.expect("can't open transcript");
|
||||
|
||||
let mut count = 0;
|
||||
let mut total_bytes = 0;
|
||||
let mut last_report = Instant::now();
|
||||
|
||||
for (role, content, ts) in iter {
|
||||
count += 1;
|
||||
total_bytes += content.len();
|
||||
|
||||
if last_report.elapsed().as_secs() >= 2 {
|
||||
eprintln!(" ... {} messages, {}KB so far ({:.1}s)",
|
||||
count, total_bytes / 1024, t0.elapsed().as_secs_f64());
|
||||
last_report = Instant::now();
|
||||
}
|
||||
|
||||
if count <= 5 {
|
||||
let preview: String = content.chars().take(80).collect();
|
||||
eprintln!(" [{}] {} {}: {}...",
|
||||
count, &ts[..ts.len().min(19)], role, preview);
|
||||
}
|
||||
|
||||
if total_bytes >= 200_000 {
|
||||
eprintln!(" hit 200KB budget at {} messages", count);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
let elapsed = t0.elapsed();
|
||||
eprintln!("done: {} messages, {}KB in {:.3}s", count, total_bytes / 1024, elapsed.as_secs_f64());
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue