extract truncation helpers, fix clippy warnings, dedup batching loop

Add util::truncate() and util::first_n_chars() to replace 16 call
sites doing the same floor_char_boundary or chars().take().collect()
patterns. Deduplicate the batching loop in consolidate.rs (4 copies
→ 1 loop over an array). Fix all clippy warnings: redundant closures,
needless borrows, collapsible if, unnecessary cast, manual strip_prefix.

Net: -44 lines across 16 files.
This commit is contained in:
ProofOfConcept 2026-03-08 21:13:02 -04:00
parent e24dee6bdf
commit 52523403c5
16 changed files with 85 additions and 129 deletions

View file

@ -66,40 +66,18 @@ pub fn consolidate_full_with_progress(
if plan.run_health {
runs.push(("health", 0));
}
if plan.replay_count > 0 {
let batch = 5;
let mut remaining = plan.replay_count;
let batch_size = 5;
for (name, count) in [
("replay", plan.replay_count),
("linker", plan.linker_count),
("separator", plan.separator_count),
("transfer", plan.transfer_count),
] {
let mut remaining = count;
while remaining > 0 {
let this_batch = remaining.min(batch);
runs.push(("replay", this_batch));
remaining -= this_batch;
}
}
if plan.linker_count > 0 {
let batch = 5;
let mut remaining = plan.linker_count;
while remaining > 0 {
let this_batch = remaining.min(batch);
runs.push(("linker", this_batch));
remaining -= this_batch;
}
}
if plan.separator_count > 0 {
let batch = 5;
let mut remaining = plan.separator_count;
while remaining > 0 {
let this_batch = remaining.min(batch);
runs.push(("separator", this_batch));
remaining -= this_batch;
}
}
if plan.transfer_count > 0 {
let batch = 5;
let mut remaining = plan.transfer_count;
while remaining > 0 {
let this_batch = remaining.min(batch);
runs.push(("transfer", this_batch));
remaining -= this_batch;
let batch = remaining.min(batch_size);
runs.push((name, batch));
remaining -= batch;
}
}

View file

@ -104,7 +104,7 @@ fn job_experience_mine(ctx: &ExecutionContext, path: &str, segment: Option<usize
let mut store = crate::store::Store::load()?;
ctx.log_line("mining");
let count = crate::enrich::experience_mine(&mut store, &path, segment)?;
ctx.log_line(&format!("{} entries mined", count));
ctx.log_line(format!("{count} entries mined"));
Ok(())
})
}
@ -116,7 +116,7 @@ fn job_fact_mine(ctx: &ExecutionContext, path: &str) -> Result<(), TaskError> {
let p = std::path::Path::new(&path);
let progress = |msg: &str| { ctx.set_progress(msg); };
let count = crate::fact_mine::mine_and_store(p, Some(&progress))?;
ctx.log_line(&format!("{} facts stored", count));
ctx.log_line(format!("{count} facts stored"));
Ok(())
})
}
@ -140,7 +140,7 @@ fn job_knowledge_loop(ctx: &ExecutionContext) -> Result<(), TaskError> {
};
ctx.log_line("running agents");
let results = crate::knowledge::run_knowledge_loop(&config)?;
ctx.log_line(&format!("{} cycles, {} actions",
ctx.log_line(format!("{} cycles, {} actions",
results.len(),
results.iter().map(|r| r.total_applied).sum::<usize>()));
Ok(())
@ -505,7 +505,7 @@ pub fn run_daemon() -> Result<(), String> {
if extract_pending > 0 { parts.push(format!("{} extract", extract_pending)); }
if fact_pending > 0 { parts.push(format!("{} fact", fact_pending)); }
if still_open > 0 { parts.push(format!("{} open", still_open)); }
ctx.set_progress(&parts.join(", "));
ctx.set_progress(parts.join(", "));
} else {
ctx.set_progress("idle");
}
@ -575,7 +575,7 @@ pub fn run_daemon() -> Result<(), String> {
digest.depend_on(&knowledge);
*last_daily_sched.lock().unwrap() = Some(today);
ctx.set_progress(&format!("daily pipeline triggered ({})", today));
ctx.set_progress(format!("daily pipeline triggered ({today})"));
}
// Prune finished tasks from registry

View file

@ -15,6 +15,7 @@ use std::collections::BTreeSet;
// --- Digest level descriptors ---
#[allow(clippy::type_complexity)]
struct DigestLevel {
name: &'static str,
title: &'static str,

View file

@ -165,11 +165,7 @@ pub fn split_on_compaction(messages: Vec<(usize, String, String, String)>) -> Ve
fn format_conversation(messages: &[(usize, String, String, String)]) -> String {
messages.iter()
.map(|(line, role, text, ts)| {
let text = if text.len() > 2000 {
format!("{}...[truncated]", &text[..text.floor_char_boundary(1800)])
} else {
text.clone()
};
let text = crate::util::truncate(text, 1800, "...[truncated]");
if ts.is_empty() {
format!("L{} [{}]: {}", line, role, text)
} else {
@ -424,13 +420,8 @@ pub fn experience_mine(
let _ = store.upsert_node(node);
count += 1;
let preview = if content.len() > 80 {
let end = content.floor_char_boundary(77);
&content[..end]
} else {
content
};
println!(" + [{}] {}...", ts, preview);
let preview = crate::util::truncate(content, 77, "...");
println!(" + [{}] {}", ts, preview);
}
// Record this transcript/segment as mined (even if count == 0, to prevent re-runs)

View file

@ -144,13 +144,7 @@ fn extract_conversation(path: &Path) -> Vec<Message> {
fn format_for_extraction(messages: &[Message]) -> String {
messages.iter()
.map(|msg| {
let text = if msg.text.len() > 3000 {
// Find a char boundary near 2800
let trunc = msg.text.floor_char_boundary(2800);
format!("{}\n[...truncated...]", &msg.text[..trunc])
} else {
msg.text.clone()
};
let text = crate::util::truncate(&msg.text, 2800, "\n[...truncated...]");
let ts = if msg.timestamp.len() >= 19 { &msg.timestamp[..19] } else { "" };
if ts.is_empty() {
format!("[{}] {}", msg.role, text)
@ -244,8 +238,7 @@ pub fn mine_transcript(
if dry_run {
for (i, (offset, chunk)) in chunks.iter().enumerate() {
eprintln!("\n--- Chunk {} (offset {}, {} chars) ---", i + 1, offset, chunk.len());
let preview = if chunk.len() > 500 { &chunk[..chunk.floor_char_boundary(500)] } else { chunk };
eprintln!("{}", preview);
eprintln!("{}", crate::util::truncate(chunk, 500, ""));
if chunk.len() > 500 {
eprintln!(" ... ({} more chars)", chunk.len() - 500);
}

View file

@ -631,8 +631,8 @@ pub fn run_challenger(store: &Store, graph: &Graph, batch_size: usize) -> Result
let template = load_prompt("challenger")?;
let topology = get_graph_topology(store, graph);
let mut candidates: Vec<(&String, usize)> = store.nodes.iter()
.map(|(k, _)| (k, graph.degree(k)))
let mut candidates: Vec<(&String, usize)> = store.nodes.keys()
.map(|k| (k, graph.degree(k)))
.collect();
candidates.sort_by(|a, b| b.1.cmp(&a.1));

View file

@ -83,7 +83,7 @@ fn call_model(agent: &str, model: &str, prompt: &str) -> Result<String, String>
Ok(response)
} else {
let stderr = String::from_utf8_lossy(&output.stderr);
let preview: String = stderr.chars().take(500).collect();
let preview = crate::util::first_n_chars(&stderr, 500);
log_usage(agent, model, prompt, &preview, elapsed, false);
Err(format!("claude exited {}: {}", output.status, preview.trim()))
}
@ -129,7 +129,7 @@ pub(crate) fn parse_json_response(response: &str) -> Result<serde_json::Value, S
}
}
let preview: String = cleaned.chars().take(200).collect();
let preview = crate::util::first_n_chars(cleaned, 200);
Err(format!("no valid JSON in response: {preview}..."))
}

View file

@ -637,10 +637,11 @@ fn cmd_search(terms: &[String], expand: bool) -> Result<(), String> {
let weight = view.node_weight(k);
println!(" ~ [{:.2}] {}", weight, k);
if let Some(content) = view.node_content(k) {
let snippet: String = content.lines()
.find(|l| !l.trim().is_empty() && !l.starts_with('#'))
.unwrap_or("")
.chars().take(100).collect();
let snippet = util::first_n_chars(
content.lines()
.find(|l| !l.trim().is_empty() && !l.starts_with('#'))
.unwrap_or(""),
100);
if !snippet.is_empty() {
println!(" {}", snippet);
}
@ -671,13 +672,11 @@ fn cmd_init() -> Result<(), String> {
let mut store = store::Store::load()?;
let count = store.init_from_markdown()?;
for key in &cfg.core_nodes {
if !store.nodes.contains_key(key.as_str()) {
if key == "identity" {
let default = include_str!("../defaults/identity.md");
store.upsert(key, default)
.map_err(|e| format!("seed {}: {}", key, e))?;
println!("Seeded {} in store", key);
}
if !store.nodes.contains_key(key) && key == "identity" {
let default = include_str!("../defaults/identity.md");
store.upsert(key, default)
.map_err(|e| format!("seed {}: {}", key, e))?;
println!("Seeded {} in store", key);
}
}
store.save()?;
@ -1319,12 +1318,7 @@ fn cmd_trace(key: &[String]) -> Result<(), String> {
}
// Show content preview
let preview = if node.content.len() > 200 {
let end = node.content.floor_char_boundary(200);
format!("{}...", &node.content[..end])
} else {
node.content.clone()
};
let preview = util::truncate(&node.content, 200, "...");
println!("\n{}\n", preview);
// Walk neighbors, grouped by node type
@ -1354,7 +1348,7 @@ fn cmd_trace(key: &[String]) -> Result<(), String> {
if !episodic_weekly.is_empty() {
println!("Weekly digests:");
for (k, s, n) in &episodic_weekly {
let preview = n.content.lines().next().unwrap_or("").chars().take(80).collect::<String>();
let preview = util::first_n_chars(n.content.lines().next().unwrap_or(""), 80);
println!(" [{:.2}] {}{}", s, k, preview);
}
}
@ -1362,7 +1356,7 @@ fn cmd_trace(key: &[String]) -> Result<(), String> {
if !episodic_daily.is_empty() {
println!("Daily digests:");
for (k, s, n) in &episodic_daily {
let preview = n.content.lines().next().unwrap_or("").chars().take(80).collect::<String>();
let preview = util::first_n_chars(n.content.lines().next().unwrap_or(""), 80);
println!(" [{:.2}] {}{}", s, k, preview);
}
}
@ -1370,9 +1364,11 @@ fn cmd_trace(key: &[String]) -> Result<(), String> {
if !episodic_session.is_empty() {
println!("Session entries:");
for (k, s, n) in &episodic_session {
let preview = n.content.lines()
.find(|l| !l.is_empty() && !l.starts_with("<!--"))
.unwrap_or("").chars().take(80).collect::<String>();
let preview = util::first_n_chars(
n.content.lines()
.find(|l| !l.is_empty() && !l.starts_with("<!--"))
.unwrap_or(""),
80);
println!(" [{:.2}] {}", s, k);
if !n.source_ref.is_empty() {
println!(" ↳ source: {}", n.source_ref);
@ -1625,7 +1621,7 @@ fn cmd_journal_ts_migrate() -> Result<(), String> {
}
}
if let Some(node) = store.nodes.get_mut(key) {
node.created_at = node.timestamp as i64;
node.created_at = node.timestamp;
node.version += 1;
updated += 1;
}
@ -1811,7 +1807,7 @@ fn cmd_history(key: &[String], full: bool) -> Result<(), String> {
node.version, ts, node.provenance.label(), node.weight, content_len);
eprintln!("{}", node.content);
} else {
let preview: String = node.content.chars().take(120).collect();
let preview = util::first_n_chars(&node.content, 120);
let preview = preview.replace('\n', "\\n");
eprintln!(" v{:<3} {} {:24} w={:.3} {}b",
node.version, ts, node.provenance.label(), node.weight, content_len);
@ -2065,18 +2061,12 @@ fn extract_title(content: &str) -> String {
let stripped = line.trim();
if stripped.is_empty() { continue; }
if date_re.is_match(stripped) && stripped.len() < 25 { continue; }
if stripped.starts_with("## ") {
return stripped[3..].to_string();
} else if stripped.starts_with("# ") {
return stripped[2..].to_string();
if let Some(h) = stripped.strip_prefix("## ") {
return h.to_string();
} else if let Some(h) = stripped.strip_prefix("# ") {
return h.to_string();
} else {
return if stripped.len() > 70 {
let mut end = 67;
while !stripped.is_char_boundary(end) { end -= 1; }
format!("{}...", &stripped[..end])
} else {
stripped.to_string()
};
return util::truncate(stripped, 67, "...");
}
}
String::from("(untitled)")

View file

@ -118,9 +118,9 @@ fn format_nodes_section(store: &Store, items: &[ReplayItem], graph: &Graph) -> S
// Content (truncated for large nodes)
let content = &node.content;
if content.len() > 1500 {
let end = content.floor_char_boundary(1500);
out.push_str(&format!("\nContent ({} chars, truncated):\n{}\n[...]\n\n",
content.len(), &content[..end]));
let truncated = crate::util::truncate(content, 1500, "\n[...]");
out.push_str(&format!("\nContent ({} chars, truncated):\n{}\n\n",
content.len(), truncated));
} else {
out.push_str(&format!("\nContent:\n{}\n\n", content));
}
@ -248,12 +248,7 @@ fn format_pairs_section(
// Node A
out.push_str(&format!("\n### {} ({})\n", a, ca));
if let Some(node) = store.nodes.get(a) {
let content = if node.content.len() > 500 {
let end = node.content.floor_char_boundary(500);
format!("{}...", &node.content[..end])
} else {
node.content.clone()
};
let content = crate::util::truncate(&node.content, 500, "...");
out.push_str(&format!("Weight: {:.2}\n{}\n",
node.weight, content));
}
@ -261,12 +256,7 @@ fn format_pairs_section(
// Node B
out.push_str(&format!("\n### {} ({})\n", b, cb));
if let Some(node) = store.nodes.get(b) {
let content = if node.content.len() > 500 {
let end = node.content.floor_char_boundary(500);
format!("{}...", &node.content[..end])
} else {
node.content.clone()
};
let content = crate::util::truncate(&node.content, 500, "...");
out.push_str(&format!("Weight: {:.2}\n{}\n",
node.weight, content));
}

View file

@ -106,10 +106,11 @@ pub fn differentiate_hub_with_graph(store: &Store, hub_key: &str, graph: &Graph)
// Only propose move if there's a reasonable match
if best_sim > 0.05 && !best_section.is_empty() {
let snippet = neighbor_content.lines()
.find(|l| !l.is_empty() && !l.starts_with("<!--") && !l.starts_with("##"))
.unwrap_or("")
.chars().take(80).collect::<String>();
let snippet = crate::util::first_n_chars(
neighbor_content.lines()
.find(|l| !l.is_empty() && !l.starts_with("<!--") && !l.starts_with("##"))
.unwrap_or(""),
80);
moves.push(LinkMove {
neighbor_key: neighbor_key.to_string(),

View file

@ -102,7 +102,7 @@ pub fn replay_queue_with_graph(
let pos = positions.get(key);
let outlier_score = pos.map(|p| p.outlier_score).unwrap_or(0.0);
let classification = pos
.map(|p| spectral::classify_position(p))
.map(spectral::classify_position)
.unwrap_or("unknown");
let priority = consolidation_priority(

View file

@ -404,13 +404,13 @@ fn execute_parsed(
has_sort = true;
let asc = *ascending;
results.sort_by(|a, b| {
let va = a.fields.get(field).and_then(|v| as_num(v));
let vb = b.fields.get(field).and_then(|v| as_num(v));
let va = a.fields.get(field).and_then(as_num);
let vb = b.fields.get(field).and_then(as_num);
let ord = match (va, vb) {
(Some(a), Some(b)) => a.total_cmp(&b),
_ => {
let sa = a.fields.get(field).map(|v| as_str(v)).unwrap_or_default();
let sb = b.fields.get(field).map(|v| as_str(v)).unwrap_or_default();
let sa = a.fields.get(field).map(as_str).unwrap_or_default();
let sb = b.fields.get(field).map(as_str).unwrap_or_default();
sa.cmp(&sb)
}
};

View file

@ -89,12 +89,7 @@ pub fn search(query: &str, store: &impl StoreView) -> Vec<SearchResult> {
.take(3)
.map(|l| {
let t = l.trim();
if t.len() > 100 {
let end = t.floor_char_boundary(97);
format!("{}...", &t[..end])
} else {
t.to_string()
}
crate::util::truncate(t, 97, "...")
})
.collect::<Vec<_>>()
.join("\n ");

View file

@ -26,6 +26,7 @@ use std::time::{SystemTime, UNIX_EPOCH};
macro_rules! capnp_enum {
($rust_type:ident, $capnp_type:path, [$($variant:ident),+ $(,)?]) => {
impl $rust_type {
#[allow(clippy::wrong_self_convention)]
pub(crate) fn to_capnp(&self) -> $capnp_type {
match self {
$(Self::$variant => <$capnp_type>::$variant,)+

View file

@ -106,7 +106,7 @@ impl StoreView for MmapView {
fn for_each_node<F: FnMut(&str, &str, f32)>(&self, mut f: F) {
let snap = self.snapshot();
for (key, node) in snap.nodes.iter() {
f(&key, &node.content, node.weight);
f(key, &node.content, node.weight);
}
}

View file

@ -12,3 +12,19 @@ pub fn memory_subdir(name: &str) -> Result<PathBuf, String> {
.map_err(|e| format!("create {}: {}", dir.display(), e))?;
Ok(dir)
}
/// Truncate text to `max_len` bytes at a char boundary, appending `suffix`.
/// Returns the original string if it's already short enough.
pub fn truncate(text: &str, max_len: usize, suffix: &str) -> String {
if text.len() <= max_len {
text.to_string()
} else {
let end = text.floor_char_boundary(max_len);
format!("{}{}", &text[..end], suffix)
}
}
/// Take the first `n` chars from a string.
pub fn first_n_chars(s: &str, n: usize) -> String {
s.chars().take(n).collect()
}