メモリーに関するクレート作成・ファイル構造の実装

This commit is contained in:
2026-04-27 13:33:31 +09:00
parent c7a873bcf9
commit f2e47629d0
33 changed files with 2780 additions and 32 deletions
+138
View File
@@ -0,0 +1,138 @@
//! Walks `<workspace>/memory/{decisions,requests}/`, `memory/workflow/`,
//! and `<workspace>/knowledge/` to collect the slug set the linter
//! needs for reference-integrity and same-slug-duplication checks.
//!
//! No caching: each lint call walks fresh. Tree size is expected to
//! stay small (hundreds of files, not thousands).
use std::collections::{HashMap, HashSet};
use std::io;
use std::path::Path;
use crate::schema::{
DecisionFrontmatter, KnowledgeFrontmatter, RequestFrontmatter, WorkflowFrontmatter,
split_frontmatter,
};
use crate::slug::Slug;
use crate::workspace::{RecordKind, WorkspaceLayout};
/// Snapshot of every record currently on disk under the workspace.
///
/// Carries enough metadata to answer:
/// - "does slug X of kind K exist?" (same-slug duplication, reference checks)
/// - "what is X's `replaced_by`?" (cycle detection)
/// - "what other slugs of kind K exist?" (similar-slug warning)
#[derive(Debug, Default, Clone)]
pub struct ExistingRecords {
decisions: HashMap<Slug, DecisionMeta>,
requests: HashSet<Slug>,
knowledge: HashSet<Slug>,
workflow: HashSet<Slug>,
}
#[derive(Debug, Clone)]
pub struct DecisionMeta {
pub replaced_by: Option<Slug>,
}
impl ExistingRecords {
pub fn contains(&self, kind: RecordKind, slug: &Slug) -> bool {
match kind {
RecordKind::Decision => self.decisions.contains_key(slug),
RecordKind::Request => self.requests.contains(slug),
RecordKind::Knowledge => self.knowledge.contains(slug),
RecordKind::Workflow => self.workflow.contains(slug),
RecordKind::Summary => false,
}
}
pub fn decision(&self, slug: &Slug) -> Option<&DecisionMeta> {
self.decisions.get(slug)
}
pub fn slugs(&self, kind: RecordKind) -> Vec<&Slug> {
match kind {
RecordKind::Decision => self.decisions.keys().collect(),
RecordKind::Request => self.requests.iter().collect(),
RecordKind::Knowledge => self.knowledge.iter().collect(),
RecordKind::Workflow => self.workflow.iter().collect(),
RecordKind::Summary => Vec::new(),
}
}
}
/// Walk the workspace and collect every record.
pub fn scan_existing(layout: &WorkspaceLayout) -> io::Result<ExistingRecords> {
let mut out = ExistingRecords::default();
scan_dir(&layout.decisions_dir(), |path, slug| {
let meta = read_decision_meta(path);
out.decisions.insert(slug, meta);
})?;
scan_dir(&layout.requests_dir(), |path, slug| {
// Parse to validate but discard contents — only slug existence
// matters for reference checks. Parse failure is silently
// ignored: existing record corruption isn't this write's
// responsibility to fix.
let _ = parse_silent::<RequestFrontmatter>(path);
out.requests.insert(slug);
})?;
scan_dir(&layout.knowledge_dir(), |path, slug| {
let _ = parse_silent::<KnowledgeFrontmatter>(path);
out.knowledge.insert(slug);
})?;
scan_dir(&layout.workflow_dir(), |path, slug| {
let _ = parse_silent::<WorkflowFrontmatter>(path);
out.workflow.insert(slug);
})?;
Ok(out)
}
fn scan_dir<F>(dir: &Path, mut visit: F) -> io::Result<()>
where
F: FnMut(&Path, Slug),
{
let entries = match std::fs::read_dir(dir) {
Ok(e) => e,
Err(err) if err.kind() == io::ErrorKind::NotFound => return Ok(()),
Err(err) => return Err(err),
};
for entry in entries {
let entry = entry?;
let path = entry.path();
if !path.is_file() {
continue;
}
let stem = match path.file_stem().and_then(|s| s.to_str()) {
Some(s) => s,
None => continue,
};
let ext = path.extension().and_then(|s| s.to_str()).unwrap_or("");
if ext != "md" {
continue;
}
if let Ok(slug) = Slug::parse(stem) {
visit(&path, slug);
}
}
Ok(())
}
fn read_decision_meta(path: &Path) -> DecisionMeta {
match parse_silent::<DecisionFrontmatter>(path) {
Some(fm) => DecisionMeta {
replaced_by: fm.replaced_by,
},
None => DecisionMeta { replaced_by: None },
}
}
fn parse_silent<F>(path: &Path) -> Option<F>
where
F: serde::de::DeserializeOwned,
{
let content = std::fs::read_to_string(path).ok()?;
let (yaml, _) = split_frontmatter(&content).ok()?;
serde_yaml::from_str::<F>(yaml).ok()
}
+67
View File
@@ -0,0 +1,67 @@
//! YAML frontmatter parsing helpers shared by every kind.
use serde::de::DeserializeOwned;
use crate::error::LintError;
/// Strict YAML deserialization that maps serde errors into the linter's
/// `MissingField` / `InvalidField` / `MalformedFrontmatter` taxonomy
/// when possible.
pub fn deserialize_strict<F: DeserializeOwned>(yaml: &str) -> Result<F, LintError> {
serde_yaml::from_str::<F>(yaml).map_err(map_serde_error)
}
fn map_serde_error(err: serde_yaml::Error) -> LintError {
let msg = err.to_string();
// `missing field \`X\`` is the exact pattern serde uses for missing
// required fields. Hoist into the typed variant so the LLM sees a
// crisp message it can act on.
if let Some(field) = parse_missing_field(&msg) {
return LintError::MissingField(field);
}
if let Some((field, message)) = parse_invalid_status(&msg) {
if field == "status" {
return LintError::InvalidStatus(message);
}
return LintError::InvalidField { field, message };
}
LintError::MalformedFrontmatter(msg)
}
fn parse_missing_field(msg: &str) -> Option<&'static str> {
let needle = "missing field `";
let start = msg.find(needle)? + needle.len();
let end = msg[start..].find('`')? + start;
let field_name = &msg[start..end];
static FIELDS: &[&str] = &[
"created_at",
"updated_at",
"sources",
"status",
"kind",
"description",
"model_invokation",
"user_invocable",
"last_sources",
"auto_invoke",
"requires",
];
FIELDS.iter().copied().find(|n| *n == field_name)
}
fn parse_invalid_status(msg: &str) -> Option<(&'static str, String)> {
// serde renders enum failures as: "unknown variant `Foo`, expected one of ..."
// We can't reliably attribute it to a specific field from the message
// alone, so we conservatively label it as `status` only when the
// message mentions one of the DecisionStatus variants in the
// expected set.
if msg.contains("unknown variant") && msg.contains("`open`") {
let needle = "unknown variant `";
let start = msg.find(needle)? + needle.len();
let end = msg[start..].find('`')? + start;
let bad = msg[start..end].to_string();
return Some(("status", bad));
}
None
}
+435
View File
@@ -0,0 +1,435 @@
//! Pre-write Linter for the memory subsystem.
//!
//! The linter is pure: given a [`WorkspaceLayout`], a target path, and
//! the proposed file content (raw bytes), it returns a [`LintReport`]
//! aggregating every applicable rule violation. The memory tool calls
//! this *before* committing to fs and surfaces a non-empty `errors`
//! collection back to the LLM as `ToolError::InvalidArgument`.
//!
//! Reference-integrity checks (`replaced_by` / `requires` existence,
//! cycle detection) walk the whole `memory/` and `knowledge/` trees
//! each call. No caching; the trees are expected to be small.
mod existing;
mod frontmatter;
mod references;
mod size;
mod warnings;
use std::path::Path;
use serde::de::DeserializeOwned;
use crate::error::{LintError, LintWarning};
use crate::schema::{
DecisionFrontmatter, KnowledgeFrontmatter, RequestFrontmatter, SummaryFrontmatter,
WorkflowFrontmatter, split_frontmatter,
};
use crate::workspace::{ClassifiedPath, RecordKind, WorkspaceLayout};
pub use existing::{ExistingRecords, scan_existing};
/// Aggregated linter result. `errors` empty ⇒ write proceeds.
#[derive(Debug, Default, Clone)]
pub struct LintReport {
pub errors: Vec<LintError>,
pub warnings: Vec<LintWarning>,
}
impl LintReport {
pub fn has_errors(&self) -> bool {
!self.errors.is_empty()
}
pub fn extend_errors(&mut self, more: impl IntoIterator<Item = LintError>) {
self.errors.extend(more);
}
pub fn push_error(&mut self, err: LintError) {
self.errors.push(err);
}
pub fn push_warning(&mut self, w: LintWarning) {
self.warnings.push(w);
}
}
/// Operation context: is this a brand-new file or an update of an
/// existing one? Affects same-slug duplication check.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum WriteMode {
Create,
Update,
}
/// Stateless entry point holding the workspace layout. Cheap to clone.
#[derive(Debug, Clone)]
pub struct Linter {
layout: WorkspaceLayout,
}
impl Linter {
pub fn new(layout: WorkspaceLayout) -> Self {
Self { layout }
}
pub fn layout(&self) -> &WorkspaceLayout {
&self.layout
}
/// Lint a proposed write to `path` with the given UTF-8 `content`.
///
/// `mode` tells the linter whether the path already existed at the
/// moment of write — Create triggers same-slug duplication checks,
/// Update doesn't.
pub fn lint(&self, path: &Path, content: &str, mode: WriteMode) -> LintReport {
let mut report = LintReport::default();
// 1. Path classification.
let classified = match self.layout.classify(path) {
Ok(Some(cp)) => cp,
Ok(None) => {
report.push_error(LintError::InvalidPath(path.to_path_buf()));
return report;
}
Err(e) => {
report.push_error(e);
return report;
}
};
// 2. Workflow paths are sub-Worker-forbidden at the tool layer.
if classified.kind == RecordKind::Workflow {
report.push_error(LintError::WorkflowWriteForbidden);
return report;
}
// 3. Frontmatter parse + kind-specific structural checks +
// size limits. Reference-integrity needs the existing
// record set, fetched once below.
let existing = match existing::scan_existing(&self.layout) {
Ok(e) => e,
Err(e) => {
report.push_error(LintError::MalformedFrontmatter(format!(
"failed to scan existing records: {e}"
)));
return report;
}
};
// Same-slug check on Create.
if mode == WriteMode::Create {
if let Some(slug) = &classified.slug {
if existing.contains(classified.kind, slug) {
report.push_error(LintError::SlugAlreadyExists(slug.to_string()));
}
}
}
// Frontmatter parse dispatch by kind.
match classified.kind {
RecordKind::Decision => {
self.check_decision(content, &classified, &existing, &mut report);
}
RecordKind::Request => {
self.check_kind::<RequestFrontmatter>(content, &classified, &mut report);
}
RecordKind::Knowledge => {
self.check_knowledge(content, &classified, &mut report);
}
RecordKind::Summary => {
self.check_kind::<SummaryFrontmatter>(content, &classified, &mut report);
}
RecordKind::Workflow => unreachable!("guarded above"),
}
report
}
fn check_kind<F>(&self, content: &str, cp: &ClassifiedPath, report: &mut LintReport)
where
F: DeserializeOwned + crate::schema::Frontmatter,
{
let parsed = match parse_frontmatter::<F>(content) {
Ok(p) => p,
Err(e) => {
report.push_error(e);
return;
}
};
let body = parsed.body;
size::check_body::<F>(body, report);
warnings::check_warnings_kindless(cp, body, report);
let _ = parsed.frontmatter; // discarded after structural checks
}
fn check_decision(
&self,
content: &str,
cp: &ClassifiedPath,
existing: &ExistingRecords,
report: &mut LintReport,
) {
let parsed = match parse_frontmatter::<DecisionFrontmatter>(content) {
Ok(p) => p,
Err(e) => {
report.push_error(e);
return;
}
};
let fm = parsed.frontmatter;
size::check_body::<DecisionFrontmatter>(parsed.body, report);
// replaced_by structural rules.
if let Some(target) = &fm.replaced_by {
if let Some(self_slug) = &cp.slug {
if target == self_slug {
report.push_error(LintError::ReplacedBySelf);
}
}
references::check_replaced_by(
cp.slug.as_ref(),
target,
existing,
report,
);
}
warnings::check_warnings_with_sources(parsed.body, fm.sources.len(), report);
}
fn check_knowledge(
&self,
content: &str,
cp: &ClassifiedPath,
report: &mut LintReport,
) {
let parsed = match parse_frontmatter::<KnowledgeFrontmatter>(content) {
Ok(p) => p,
Err(e) => {
report.push_error(e);
return;
}
};
let fm = parsed.frontmatter;
size::check_body::<KnowledgeFrontmatter>(parsed.body, report);
if fm.model_invokation
&& fm.description.chars().count()
> crate::schema::KNOWLEDGE_DESCRIPTION_HARD_CAP
{
report.push_error(LintError::DescriptionTooLong {
actual: fm.description.chars().count(),
limit: crate::schema::KNOWLEDGE_DESCRIPTION_HARD_CAP,
});
}
warnings::check_warnings_with_sources(parsed.body, fm.last_sources.len(), report);
let _ = cp;
}
}
/// Workflow frontmatter validator exposed for human-edit paths
/// (CLI / pre-commit). Not used by the memory tool, which rejects
/// workflow writes outright.
pub fn lint_workflow_frontmatter(content: &str) -> Result<WorkflowFrontmatter, LintError> {
let parsed = parse_frontmatter::<WorkflowFrontmatter>(content)?;
Ok(parsed.frontmatter)
}
struct Parsed<'a, F> {
frontmatter: F,
body: &'a str,
}
fn parse_frontmatter<F: DeserializeOwned>(content: &str) -> Result<Parsed<'_, F>, LintError> {
let (yaml, body) = split_frontmatter(content)?;
let fm = frontmatter::deserialize_strict::<F>(yaml)?;
Ok(Parsed {
frontmatter: fm,
body,
})
}
#[cfg(test)]
mod tests {
use super::*;
use chrono::Utc;
use std::path::PathBuf;
use tempfile::TempDir;
fn write(p: &std::path::Path, content: &str) {
if let Some(parent) = p.parent() {
std::fs::create_dir_all(parent).unwrap();
}
std::fs::write(p, content).unwrap();
}
fn iso_now() -> String {
Utc::now().to_rfc3339()
}
fn workspace() -> (TempDir, Linter) {
let dir = TempDir::new().unwrap();
let layout = WorkspaceLayout::new(dir.path().to_path_buf());
let linter = Linter::new(layout);
(dir, linter)
}
#[test]
fn workflow_write_rejected() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/workflow/wf.md");
let content = format!(
"---\nupdated_at: {now}\ndescription: x\nauto_invoke: false\nuser_invocable: true\n---\nbody",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(e, LintError::WorkflowWriteForbidden)));
}
#[test]
fn outside_memory_tree_rejected() {
let (dir, linter) = workspace();
let path = dir.path().join("src/main.rs");
let report = linter.lint(&path, "ignored", WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(e, LintError::InvalidPath(_))));
}
#[test]
fn decision_with_unknown_replaced_by_errors() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/decisions/foo.md");
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: replaced\nreplaced_by: ghost\n---\nbody\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(
e,
LintError::UnknownReference { .. }
)));
}
#[test]
fn decision_replaced_by_self_errors() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/decisions/foo.md");
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: replaced\nreplaced_by: foo\n---\nbody\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Update);
assert!(report.errors.iter().any(|e| matches!(e, LintError::ReplacedBySelf)));
}
#[test]
fn decision_replaced_by_existing_ok() {
let (dir, linter) = workspace();
// Pre-create the target.
let target = dir.path().join("memory/decisions/bar.md");
write(
&target,
&format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: open\n---\nbar body\n",
now = iso_now()
),
);
let path = dir.path().join("memory/decisions/foo.md");
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: replaced\nreplaced_by: bar\n---\nbody\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(!report.has_errors(), "got errors: {:?}", report.errors);
}
#[test]
fn missing_required_field_errors() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/decisions/foo.md");
// Missing `status`.
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\n---\nbody\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(
e,
LintError::MissingField(_) | LintError::MalformedFrontmatter(_)
)));
}
#[test]
fn knowledge_long_description_with_model_invokation_errors() {
let (dir, linter) = workspace();
let path = dir.path().join("knowledge/foo.md");
let big_desc = "x".repeat(2000);
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nkind: rule\ndescription: {big_desc}\nmodel_invokation: true\nuser_invocable: true\nlast_sources: []\n---\nbody\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(e, LintError::DescriptionTooLong { .. })));
}
#[test]
fn knowledge_long_description_without_model_invokation_ok() {
let (dir, linter) = workspace();
let path = dir.path().join("knowledge/foo.md");
let big_desc = "x".repeat(2000);
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nkind: rule\ndescription: {big_desc}\nmodel_invokation: false\nuser_invocable: true\nlast_sources: []\n---\nbody\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(!report.has_errors(), "got errors: {:?}", report.errors);
}
#[test]
fn summary_path_accepted() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/summary.md");
let content = format!(
"---\nupdated_at: {now}\n---\nsummary body\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Update);
assert!(!report.has_errors(), "got errors: {:?}", report.errors);
}
#[test]
fn create_when_existing_errors() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/decisions/foo.md");
write(
&path,
&format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: open\n---\nold\n",
now = iso_now()
),
);
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: open\n---\nnew\n",
now = iso_now()
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(e, LintError::SlugAlreadyExists(_))));
}
#[test]
fn body_size_limit_errors() {
let (dir, linter) = workspace();
let path = dir.path().join("memory/decisions/foo.md");
let big_body = "x".repeat(8001);
let content = format!(
"---\ncreated_at: {now}\nupdated_at: {now}\nsources: []\nstatus: open\n---\n{body}",
now = iso_now(),
body = big_body
);
let report = linter.lint(&path, &content, WriteMode::Create);
assert!(report.errors.iter().any(|e| matches!(e, LintError::BodyTooLong { .. })));
// Sanity: ensure path was treated as PathBuf consistently.
let _ = PathBuf::from(path);
}
}
+73
View File
@@ -0,0 +1,73 @@
//! Reference-integrity checks: `replaced_by` existence + cycle detection.
//!
//! `requires` (Workflow) is checked symmetrically when/if the Workflow
//! linter is invoked from a human-edit path; the memory tool itself
//! never writes Workflow records.
use std::collections::HashSet;
use crate::error::LintError;
use crate::linter::ExistingRecords;
use crate::linter::LintReport;
use crate::slug::Slug;
use crate::workspace::RecordKind;
/// Validate a Decision's `replaced_by` against the existing record set.
///
/// `self_slug` is the slug of the record currently being written (None
/// only when the path was malformed and we shouldn't even reach here).
pub fn check_replaced_by(
self_slug: Option<&Slug>,
target: &Slug,
existing: &ExistingRecords,
report: &mut LintReport,
) {
// Existence: target must already be a Decision on disk.
if !existing.contains(RecordKind::Decision, target) {
report.push_error(LintError::UnknownReference {
field: "replaced_by",
kind: "decision",
slug: target.to_string(),
});
return;
}
// Cycle: walk the chain target → target.replaced_by → ... and
// ensure we never revisit `self_slug` or any node twice.
let mut visited = HashSet::new();
if let Some(s) = self_slug {
visited.insert(s.clone());
}
let mut cursor = Some(target.clone());
let mut chain: Vec<String> = Vec::new();
while let Some(node) = cursor {
if !visited.insert(node.clone()) {
chain.push(node.to_string());
report.push_error(LintError::ReplacedByCycle {
chain: chain.join(" -> "),
});
return;
}
chain.push(node.to_string());
cursor = existing
.decision(&node)
.and_then(|m| m.replaced_by.clone());
}
}
#[cfg(test)]
mod tests {
use super::*;
// Smoke test: cycle detection terminates on a 2-node loop where the
// existing tree already contains A↔B and the new write would close
// the loop. A direct unit test against `check_replaced_by` is
// exercised by linter::tests; here we just guard the loop bound.
#[test]
fn empty_chain_terminates() {
let mut report = LintReport::default();
let existing = ExistingRecords::default();
let target = Slug::parse("foo").unwrap();
check_replaced_by(None, &target, &existing, &mut report);
assert_eq!(report.errors.len(), 1);
}
}
+15
View File
@@ -0,0 +1,15 @@
//! Body size limit checks.
use crate::error::LintError;
use crate::linter::LintReport;
use crate::schema::Frontmatter;
pub fn check_body<F: Frontmatter>(body: &str, report: &mut LintReport) {
let chars = body.chars().count();
if chars > F::BODY_LIMIT {
report.push_error(LintError::BodyTooLong {
actual: chars,
limit: F::BODY_LIMIT,
});
}
}
+34
View File
@@ -0,0 +1,34 @@
//! Soft warnings: low-importance large records, sources accumulation.
//!
//! Similar-slug warnings need the existing record set and are
//! integrated into the main linter pass when implemented; this file
//! covers per-write checks that only need the proposed content.
use crate::error::LintWarning;
use crate::linter::LintReport;
use crate::workspace::ClassifiedPath;
const LARGE_BODY_THRESHOLD: usize = 1500;
const SOURCES_OVERFLOW_THRESHOLD: usize = 10;
/// For kinds that don't carry a `sources` array (Summary), emit only
/// the body-size warning.
pub fn check_warnings_kindless(_cp: &ClassifiedPath, body: &str, _report: &mut LintReport) {
let _ = body;
// Summary intentionally has no warning band — the per-record
// size:importance heuristic doesn't apply to a single rolling file.
}
/// For kinds with `sources` (Decisions / Requests / Knowledge), consult
/// both the body length and the sources count.
pub fn check_warnings_with_sources(body: &str, source_count: usize, report: &mut LintReport) {
let chars = body.chars().count();
if source_count <= 1 && chars >= LARGE_BODY_THRESHOLD {
report.push_warning(LintWarning::LowImportanceLargeRecord { chars });
}
if source_count > SOURCES_OVERFLOW_THRESHOLD {
report.push_warning(LintWarning::SourcesOverflow {
count: source_count,
});
}
}