chore(scripts): replace worktree-remap with cwd-based remap using pending_messages.cwd
The old worktree-remap.ts tried to reconstruct per-session cwd by regex-
matching absolute paths that incidentally leaked into observation free-text
(files_read, source_input_summary, metadata, user_prompt). That source is
derived and lossy: it only hit 1/3498 plain-project sessions in practice.
pending_messages.cwd is the structured, authoritative cwd captured from
every hook payload — 7,935 of 8,473 rows are populated. cwd-remap.ts uses
that column as the source of truth:
1. Pull every distinct cwd from pending_messages.cwd
2. For each cwd, classify with git:
- rev-parse --absolute-git-dir vs --git-common-dir → main vs worktree
- rev-parse --show-toplevel for the correct leaf (handles cwds that
are subdirs of the worktree root)
Parent project name = basename(dirname(common-dir)); composite is
parent/worktree for worktrees, basename(toplevel) for main repos.
3. For each session, take the EARLIEST pending_messages.cwd (not the
dominant one — claude-mem's own hooks run from nested .context/
claude-mem/ directories and would otherwise poison the count).
4. Apply UPDATEs in a single transaction across sdk_sessions,
observations, and session_summaries. Auto-backs-up the DB first.
Result on a real DB: 41 sessions remapped (vs 1 previously),
1,694 observations and 3,091 session_summaries updated to match.
43 cwds skipped (deleted worktrees / non-repos) are left untouched —
no inference when the data isn't there.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Alex Newman
@@ -0,0 +1,174 @@
|
|||||||
|
#!/usr/bin/env bun
|
||||||
|
/**
|
||||||
|
* cwd-remap — Rewrite sdk_sessions.project (+ observations.project,
|
||||||
|
* session_summaries.project) using the cwd captured per-message in
|
||||||
|
* pending_messages.cwd as the single source of truth.
|
||||||
|
*
|
||||||
|
* For each distinct cwd:
|
||||||
|
* - git -C <cwd> rev-parse --git-dir AND --git-common-dir
|
||||||
|
* If they differ → worktree. parent = basename(dirname(common-dir)),
|
||||||
|
* project = parent/<basename(cwd)>.
|
||||||
|
* Else → project = basename(cwd).
|
||||||
|
* - If the directory doesn't exist, or git errors, skip that cwd.
|
||||||
|
*
|
||||||
|
* Usage:
|
||||||
|
* bun scripts/cwd-remap.ts # dry-run (default)
|
||||||
|
* bun scripts/cwd-remap.ts --apply # write updates in a single transaction
|
||||||
|
*/
|
||||||
|
|
||||||
|
import { Database } from 'bun:sqlite';
|
||||||
|
import { homedir } from 'os';
|
||||||
|
import { join, basename, dirname } from 'path';
|
||||||
|
import { existsSync, copyFileSync } from 'fs';
|
||||||
|
import { spawnSync } from 'child_process';
|
||||||
|
|
||||||
|
const DB_PATH = join(homedir(), '.claude-mem', 'claude-mem.db');
|
||||||
|
const APPLY = process.argv.includes('--apply');
|
||||||
|
|
||||||
|
type Classification =
|
||||||
|
| { kind: 'main'; project: string }
|
||||||
|
| { kind: 'worktree'; project: string; parent: string }
|
||||||
|
| { kind: 'skip'; reason: string };
|
||||||
|
|
||||||
|
function git(cwd: string, args: string[]): string | null {
|
||||||
|
const r = spawnSync('git', ['-C', cwd, ...args], { encoding: 'utf8' });
|
||||||
|
if (r.status !== 0) return null;
|
||||||
|
return r.stdout.trim();
|
||||||
|
}
|
||||||
|
|
||||||
|
function classify(cwd: string): Classification {
|
||||||
|
if (!existsSync(cwd)) return { kind: 'skip', reason: 'cwd-missing' };
|
||||||
|
|
||||||
|
const gitDir = git(cwd, ['rev-parse', '--absolute-git-dir']);
|
||||||
|
if (!gitDir) return { kind: 'skip', reason: 'not-a-git-repo' };
|
||||||
|
|
||||||
|
const commonDir = git(cwd, ['rev-parse', '--path-format=absolute', '--git-common-dir']);
|
||||||
|
if (!commonDir) return { kind: 'skip', reason: 'no-common-dir' };
|
||||||
|
|
||||||
|
// Use the worktree root, not the cwd — a session may be in a subdir.
|
||||||
|
const toplevel = git(cwd, ['rev-parse', '--show-toplevel']);
|
||||||
|
if (!toplevel) return { kind: 'skip', reason: 'no-toplevel' };
|
||||||
|
const leaf = basename(toplevel);
|
||||||
|
|
||||||
|
if (gitDir === commonDir) {
|
||||||
|
return { kind: 'main', project: leaf };
|
||||||
|
}
|
||||||
|
|
||||||
|
// worktree: common-dir = <parent-repo>/.git (or <parent>.git for bare)
|
||||||
|
const parentRepoDir = commonDir.endsWith('/.git') ? dirname(commonDir) : dirname(commonDir);
|
||||||
|
const parent = basename(parentRepoDir);
|
||||||
|
return { kind: 'worktree', project: `${parent}/${leaf}`, parent };
|
||||||
|
}
|
||||||
|
|
||||||
|
function main() {
|
||||||
|
if (!existsSync(DB_PATH)) {
|
||||||
|
console.error(`DB not found at ${DB_PATH}`);
|
||||||
|
process.exit(1);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (APPLY) {
|
||||||
|
const backup = `${DB_PATH}.bak-cwd-remap-${Date.now()}`;
|
||||||
|
copyFileSync(DB_PATH, backup);
|
||||||
|
console.log(`Backup created: ${backup}`);
|
||||||
|
}
|
||||||
|
|
||||||
|
const db = new Database(DB_PATH);
|
||||||
|
|
||||||
|
const cwdRows = db.prepare(`
|
||||||
|
SELECT cwd, COUNT(*) AS messages
|
||||||
|
FROM pending_messages
|
||||||
|
WHERE cwd IS NOT NULL AND cwd != ''
|
||||||
|
GROUP BY cwd
|
||||||
|
`).all() as Array<{ cwd: string; messages: number }>;
|
||||||
|
|
||||||
|
console.log(`Classifying ${cwdRows.length} distinct cwds via git...`);
|
||||||
|
|
||||||
|
const byCwd = new Map<string, Classification>();
|
||||||
|
const counts = { main: 0, worktree: 0, skip: 0 };
|
||||||
|
for (const { cwd } of cwdRows) {
|
||||||
|
const c = classify(cwd);
|
||||||
|
byCwd.set(cwd, c);
|
||||||
|
counts[c.kind]++;
|
||||||
|
}
|
||||||
|
console.log(` main=${counts.main} worktree=${counts.worktree} skip=${counts.skip}`);
|
||||||
|
|
||||||
|
// Skipped cwds (so user sees what's missing)
|
||||||
|
const skipped = [...byCwd.entries()].filter(([, c]) => c.kind === 'skip') as Array<[string, Extract<Classification, { kind: 'skip' }>]>;
|
||||||
|
if (skipped.length) {
|
||||||
|
console.log('\nSkipped cwds:');
|
||||||
|
for (const [cwd, c] of skipped) console.log(` [${c.reason}] ${cwd}`);
|
||||||
|
}
|
||||||
|
|
||||||
|
// Per-session target: use the EARLIEST pending_messages.cwd for each session.
|
||||||
|
// (Dominant-cwd is wrong: claude-mem's own hooks run from nested dirs like
|
||||||
|
// `.context/claude-mem/` and dominate the count, misattributing the session.)
|
||||||
|
const sessionRows = db.prepare(`
|
||||||
|
SELECT s.id AS session_id, s.memory_session_id, s.content_session_id, s.project AS old_project, p.cwd
|
||||||
|
FROM sdk_sessions s
|
||||||
|
JOIN pending_messages p ON p.content_session_id = s.content_session_id
|
||||||
|
WHERE p.cwd IS NOT NULL AND p.cwd != ''
|
||||||
|
AND p.id = (
|
||||||
|
SELECT MIN(p2.id) FROM pending_messages p2
|
||||||
|
WHERE p2.content_session_id = s.content_session_id
|
||||||
|
AND p2.cwd IS NOT NULL AND p2.cwd != ''
|
||||||
|
)
|
||||||
|
`).all() as Array<{ session_id: number; memory_session_id: string | null; content_session_id: string; old_project: string; cwd: string }>;
|
||||||
|
|
||||||
|
type Target = { sessionId: number; memorySessionId: string | null; contentSessionId: string; oldProject: string; newProject: string; cwd: string };
|
||||||
|
const perSession = new Map<number, Target>();
|
||||||
|
|
||||||
|
for (const r of sessionRows) {
|
||||||
|
const c = byCwd.get(r.cwd);
|
||||||
|
if (!c || c.kind === 'skip') continue;
|
||||||
|
perSession.set(r.session_id, {
|
||||||
|
sessionId: r.session_id,
|
||||||
|
memorySessionId: r.memory_session_id,
|
||||||
|
contentSessionId: r.content_session_id,
|
||||||
|
oldProject: r.old_project,
|
||||||
|
newProject: c.project,
|
||||||
|
cwd: r.cwd,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
const targets = [...perSession.values()].filter(t => t.oldProject !== t.newProject);
|
||||||
|
|
||||||
|
console.log(`\nSessions linked to a classified cwd: ${perSession.size}`);
|
||||||
|
console.log(`Sessions whose project would change: ${targets.length}`);
|
||||||
|
|
||||||
|
const summary = new Map<string, number>();
|
||||||
|
for (const t of targets) {
|
||||||
|
const key = `${t.oldProject} → ${t.newProject}`;
|
||||||
|
summary.set(key, (summary.get(key) ?? 0) + 1);
|
||||||
|
}
|
||||||
|
const rows = [...summary.entries()]
|
||||||
|
.map(([mapping, n]) => ({ mapping, sessions: n }))
|
||||||
|
.sort((a, b) => b.sessions - a.sessions);
|
||||||
|
console.log('\nTop mappings:');
|
||||||
|
console.table(rows.slice(0, 30));
|
||||||
|
if (rows.length > 30) console.log(` …and ${rows.length - 30} more mappings`);
|
||||||
|
|
||||||
|
if (!APPLY) {
|
||||||
|
console.log('\nDry-run only. Re-run with --apply to perform UPDATEs.');
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
const updSession = db.prepare('UPDATE sdk_sessions SET project = ? WHERE id = ?');
|
||||||
|
const updObs = db.prepare('UPDATE observations SET project = ? WHERE memory_session_id = ?');
|
||||||
|
const updSum = db.prepare('UPDATE session_summaries SET project = ? WHERE memory_session_id = ?');
|
||||||
|
|
||||||
|
let sessionN = 0, obsN = 0, sumN = 0;
|
||||||
|
const tx = db.transaction(() => {
|
||||||
|
for (const t of targets) {
|
||||||
|
sessionN += updSession.run(t.newProject, t.sessionId).changes;
|
||||||
|
if (t.memorySessionId) {
|
||||||
|
obsN += updObs.run(t.newProject, t.memorySessionId).changes;
|
||||||
|
sumN += updSum.run(t.newProject, t.memorySessionId).changes;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
});
|
||||||
|
tx();
|
||||||
|
|
||||||
|
console.log(`\nApplied. sessions=${sessionN} observations=${obsN} session_summaries=${sumN}`);
|
||||||
|
}
|
||||||
|
|
||||||
|
main();
|
||||||
@@ -1,170 +0,0 @@
|
|||||||
#!/usr/bin/env bun
|
|
||||||
/**
|
|
||||||
* worktree-remap — Retroactively reattribute past sessions that were written
|
|
||||||
* with a plain project name (e.g. `claude-mem`) to the `parent/worktree`
|
|
||||||
* composite name when the original worktree can be inferred from the paths
|
|
||||||
* in the session's observations or user prompt.
|
|
||||||
*
|
|
||||||
* Only sessions with HIGH-CONFIDENCE worktree path signatures are remapped.
|
|
||||||
* Everything else is left alone.
|
|
||||||
*
|
|
||||||
* Usage:
|
|
||||||
* bun scripts/worktree-remap.ts # dry-run (default)
|
|
||||||
* bun scripts/worktree-remap.ts --apply # write changes in a transaction
|
|
||||||
*/
|
|
||||||
|
|
||||||
import { Database } from 'bun:sqlite';
|
|
||||||
import { homedir } from 'os';
|
|
||||||
import { join } from 'path';
|
|
||||||
import { existsSync, copyFileSync } from 'fs';
|
|
||||||
|
|
||||||
const DB_PATH = join(homedir(), '.claude-mem', 'claude-mem.db');
|
|
||||||
const APPLY = process.argv.includes('--apply');
|
|
||||||
|
|
||||||
const WORKTREE_PATTERNS: Array<{ name: string; regex: RegExp }> = [
|
|
||||||
{ name: 'conductor', regex: /\/conductor\/workspaces\/([^/]+)\/([^/"'\s)]+)/ },
|
|
||||||
{ name: 'superset', regex: /\/\.superset\/worktrees\/([^/]+)\/([^/"'\s)]+)/ },
|
|
||||||
];
|
|
||||||
|
|
||||||
interface SessionRow {
|
|
||||||
id: number;
|
|
||||||
memory_session_id: string | null;
|
|
||||||
project: string;
|
|
||||||
user_prompt: string | null;
|
|
||||||
}
|
|
||||||
|
|
||||||
function allMatches(text: string | null | undefined): Array<{ parent: string; worktree: string }> {
|
|
||||||
if (!text) return [];
|
|
||||||
const results: Array<{ parent: string; worktree: string }> = [];
|
|
||||||
for (const p of WORKTREE_PATTERNS) {
|
|
||||||
const global = new RegExp(p.regex.source, 'g');
|
|
||||||
let m: RegExpExecArray | null;
|
|
||||||
while ((m = global.exec(text)) !== null) {
|
|
||||||
results.push({ parent: m[1], worktree: m[2] });
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return results;
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Collects every worktree path match across the session's observations + user prompt,
|
|
||||||
* then picks the inference using this priority:
|
|
||||||
* 1. A match whose worktree basename === the session's current plain project name.
|
|
||||||
* (Pre-#1820 sessions stored the worktree basename as `project` — these are trusted.)
|
|
||||||
* 2. If none match the current project, and there's a single unambiguous (parent, worktree)
|
|
||||||
* across ALL signals, use it.
|
|
||||||
* 3. Otherwise skip (ambiguous — likely cross-worktree reads).
|
|
||||||
*/
|
|
||||||
function inferWorktree(
|
|
||||||
db: Database,
|
|
||||||
memorySessionId: string | null,
|
|
||||||
userPrompt: string | null,
|
|
||||||
currentProject: string
|
|
||||||
): { parent: string; worktree: string } | null {
|
|
||||||
const matches: Array<{ parent: string; worktree: string }> = [];
|
|
||||||
|
|
||||||
if (memorySessionId) {
|
|
||||||
const rows = db.prepare(`
|
|
||||||
SELECT files_read, files_modified, source_input_summary, metadata
|
|
||||||
FROM observations
|
|
||||||
WHERE memory_session_id = ?
|
|
||||||
AND (files_read LIKE '%/conductor/workspaces/%' OR files_modified LIKE '%/conductor/workspaces/%'
|
|
||||||
OR source_input_summary LIKE '%/conductor/workspaces/%' OR metadata LIKE '%/conductor/workspaces/%'
|
|
||||||
OR files_read LIKE '%.superset/worktrees/%' OR files_modified LIKE '%.superset/worktrees/%'
|
|
||||||
OR source_input_summary LIKE '%.superset/worktrees/%' OR metadata LIKE '%.superset/worktrees/%')
|
|
||||||
`).all(memorySessionId) as Array<{ files_read: string | null; files_modified: string | null; source_input_summary: string | null; metadata: string | null }>;
|
|
||||||
|
|
||||||
for (const r of rows) {
|
|
||||||
matches.push(...allMatches(r.files_read));
|
|
||||||
matches.push(...allMatches(r.files_modified));
|
|
||||||
matches.push(...allMatches(r.source_input_summary));
|
|
||||||
matches.push(...allMatches(r.metadata));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
matches.push(...allMatches(userPrompt));
|
|
||||||
if (matches.length === 0) return null;
|
|
||||||
|
|
||||||
const wtMatch = matches.find(m => m.worktree === currentProject);
|
|
||||||
if (wtMatch) return wtMatch;
|
|
||||||
|
|
||||||
const signatures = new Set(matches.map(m => `${m.parent}/${m.worktree}`));
|
|
||||||
if (signatures.size === 1) return matches[0];
|
|
||||||
|
|
||||||
return null;
|
|
||||||
}
|
|
||||||
|
|
||||||
function main() {
|
|
||||||
if (!existsSync(DB_PATH)) {
|
|
||||||
console.error(`DB not found at ${DB_PATH}`);
|
|
||||||
process.exit(1);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (APPLY) {
|
|
||||||
const backup = `${DB_PATH}.bak-worktree-remap-${Date.now()}`;
|
|
||||||
copyFileSync(DB_PATH, backup);
|
|
||||||
console.log(`Backup created: ${backup}`);
|
|
||||||
}
|
|
||||||
|
|
||||||
const db = new Database(DB_PATH);
|
|
||||||
|
|
||||||
const sessions = db.prepare(`
|
|
||||||
SELECT id, memory_session_id, project, user_prompt
|
|
||||||
FROM sdk_sessions
|
|
||||||
WHERE project NOT LIKE '%/%' AND project != ''
|
|
||||||
`).all() as SessionRow[];
|
|
||||||
|
|
||||||
console.log(`Scanning ${sessions.length} plain-project sessions...`);
|
|
||||||
|
|
||||||
type Remap = { sessionId: number; memorySessionId: string | null; oldProject: string; newProject: string };
|
|
||||||
const remaps: Remap[] = [];
|
|
||||||
const summary = new Map<string, { count: number; firstExample: number }>();
|
|
||||||
|
|
||||||
for (const s of sessions) {
|
|
||||||
const hit = inferWorktree(db, s.memory_session_id, s.user_prompt, s.project);
|
|
||||||
if (!hit) continue;
|
|
||||||
|
|
||||||
const newProject = `${hit.parent}/${hit.worktree}`;
|
|
||||||
if (newProject === s.project) continue;
|
|
||||||
|
|
||||||
remaps.push({ sessionId: s.id, memorySessionId: s.memory_session_id, oldProject: s.project, newProject });
|
|
||||||
const key = `${s.project} → ${newProject}`;
|
|
||||||
const entry = summary.get(key);
|
|
||||||
if (entry) entry.count++;
|
|
||||||
else summary.set(key, { count: 1, firstExample: s.id });
|
|
||||||
}
|
|
||||||
|
|
||||||
const rows = Array.from(summary.entries())
|
|
||||||
.map(([mapping, v]) => ({ mapping, sessions: v.count, exampleSessionId: v.firstExample }))
|
|
||||||
.sort((a, b) => b.sessions - a.sessions);
|
|
||||||
|
|
||||||
console.log('\nRemap summary:');
|
|
||||||
console.table(rows);
|
|
||||||
console.log(`\nTotal sessions to remap: ${remaps.length}`);
|
|
||||||
|
|
||||||
if (!APPLY) {
|
|
||||||
console.log('\nDry-run only. Re-run with --apply to perform UPDATEs.');
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
console.log('\nApplying updates in a single transaction...');
|
|
||||||
const updateSession = db.prepare('UPDATE sdk_sessions SET project=? WHERE id=?');
|
|
||||||
const updateObs = db.prepare('UPDATE observations SET project=? WHERE memory_session_id=?');
|
|
||||||
const updateSum = db.prepare('UPDATE session_summaries SET project=? WHERE memory_session_id=?');
|
|
||||||
|
|
||||||
let sessionUpdates = 0, obsUpdates = 0, sumUpdates = 0;
|
|
||||||
const tx = db.transaction(() => {
|
|
||||||
for (const r of remaps) {
|
|
||||||
sessionUpdates += updateSession.run(r.newProject, r.sessionId).changes;
|
|
||||||
if (r.memorySessionId) {
|
|
||||||
obsUpdates += updateObs.run(r.newProject, r.memorySessionId).changes;
|
|
||||||
sumUpdates += updateSum.run(r.newProject, r.memorySessionId).changes;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
});
|
|
||||||
tx();
|
|
||||||
|
|
||||||
console.log(`Done. sessions=${sessionUpdates} observations=${obsUpdates} session_summaries=${sumUpdates}`);
|
|
||||||
}
|
|
||||||
|
|
||||||
main();
|
|
||||||
Reference in New Issue
Block a user