@orkestrel/scaffold 0.0.107 → 0.0.108

package/dist/agents/skills/orkestrel-dispatch/scripts/sweep.js

@@ -2,14 +2,21 @@
 //   node .agents/skills/orkestrel-dispatch/scripts/sweep.ts --report
 //   node .agents/skills/orkestrel-dispatch/scripts/sweep.ts --tmp [--older-than MINUTES]
 //   node .agents/skills/orkestrel-dispatch/scripts/sweep.ts --unit UNIT [--delete]
-// --report lists leftovers under tmp/ and .orkestrel/ by age and deletes nothing.
+// --report lists leftovers under tmp/ and .orkestrel/ by age and deletes nothing. It also checks
+// every .md file under .orkestrel/: a backticked repository-relative path that git ignores prints
+// `<file>:<line> cites ignored path <path>` (a path git tracks is never reported, nor is a glob or
+// placeholder whose literal prefix git tracks), and an absolute machine path on a line prints
+// `<file>:<line> names a machine path`. Both lines are report-only.
 // --tmp deletes launch files older than the threshold (default 60 minutes), removes emptied
 // directories, and refuses while any launch file changed in the last 2 minutes.
 // --unit lists one accepted unit's files under the launch directories (the brief, report, claims,
 // journal, errors, status, pid, and last-message files whose name is UNIT followed by `-` or `.`), and
 // --delete removes them, refusing while one changed in the last 2 minutes.
+// --tmp and --unit --delete never delete a file git tracks: each prints `kept tracked <path>` and the
+// refusal ignores a tracked file; --unit alone marks a tracked file in its listing.
 // Exit 0 on success, 2 when a deletion is refused, 64 on usage.
-import { existsSync, readdirSync, rmSync } from 'node:fs';
+import { spawnSync } from 'node:child_process';
+import { existsSync, readFileSync, readdirSync, rmSync } from 'node:fs';
 import { basename, join } from 'node:path';
 import { listFiles, readMissingFlags, readOption } from "./helpers.js";
 const LAUNCH_DIRECTORIES = [
@@ -24,6 +31,13 @@ const LAUNCH_DIRECTORIES = [
 const RECENT_MS = 2 * 60_000;
 // A launch directory holds nothing a walk skips, so every file beneath it counts.
 const NOTHING_SKIPPED = new Set();
+// Git's output is bounded by the repository's file count, so a generous buffer is the only limit.
+const GIT_BUFFER = 64 * 1024 * 1024;
+// An absolute machine path: a drive-letter path, or one that opens `/Users/`, `/home/`, or `~/`. The
+// lookbehind keeps `https://`, `src/home/`, and `./home/` from matching.
+const MACHINE_PATH = /(?<![\w.-])(?:[A-Za-z]:[\\/]|\/(?:Users|home)\/|~\/)/u;
+const BACKTICKED = /`([^`\n]+)`/gu;
+const PLACEHOLDER = /[*?<{]/u;
 function formatDay(modified) {
     return new Date(modified).toISOString().slice(0, 10);
 }
@@ -67,6 +81,99 @@ function readThreshold(argv) {
     const value = Number(readOption(argv, '--older-than'));
     return Number.isFinite(value) && value > 0 ? value : undefined;
 }
+// Lists the files git tracks beneath the scope (the whole repository when empty), as forward-slash
+// paths from the root. Any git failure reads as nothing tracked, so the run keeps its old behavior.
+function listTracked(scope) {
+    const args = ['ls-files', '-z', ...(scope.length === 0 ? [] : ['--', ...scope])];
+    const run = spawnSync('git', args, { encoding: 'utf8', windowsHide: true, maxBuffer: GIT_BUFFER });
+    if (run.status !== 0)
+        return [];
+    return run.stdout.split('\0').filter((path) => path !== '');
+}
+// Names the probes git ignores, from one batched `git check-ignore`: status 0 and 1 both answer,
+// and any other status reads as nothing ignored.
+function readIgnored(probes) {
+    if (probes.length === 0)
+        return new Set();
+    const run = spawnSync('git', ['check-ignore', '--stdin', '-z'], {
+        encoding: 'utf8',
+        windowsHide: true,
+        maxBuffer: GIT_BUFFER,
+        input: probes.join('\0'),
+    });
+    if (run.status !== 0 && run.status !== 1)
+        return new Set();
+    return new Set(run.stdout.split('\0').filter((path) => path !== ''));
+}
+// Reads a backticked token as a repository-relative citation. A token counts when it has no
+// whitespace, contains `/`, and is no URL; the path stops at its first glob or placeholder character
+// and drops a trailing `/`. A machine path, a path outside the repository, and a backslash path are
+// no citation.
+function readCitation(token) {
+    if (/\s/u.test(token) || !token.includes('/') || token.includes('://'))
+        return undefined;
+    const stop = token.search(PLACEHOLDER);
+    const cut = (stop === -1 ? token : token.slice(0, stop)).replace(/^\.\//u, '');
+    const path = cut.replace(/\/+$/u, '');
+    if (path === '' || /^(?:\/|~|\.\.(?:\/|$)|-|[A-Za-z]:)/u.test(path) || path.includes('\\')) {
+        return undefined;
+    }
+    return { path, directory: cut.endsWith('/'), prefix: stop === -1 ? undefined : cut };
+}
+function listFindings(file) {
+    const lines = readFileSync(file, 'utf8').split(/\r\n|\n/u);
+    return lines.flatMap((text, index) => {
+        const line = index + 1;
+        const machine = MACHINE_PATH.test(text) ? [{ file, line, citation: undefined }] : [];
+        const cited = [...text.matchAll(BACKTICKED)].flatMap((match) => {
+            const citation = readCitation(match[1] ?? '');
+            return citation === undefined ? [] : [{ file, line, citation }];
+        });
+        return [...machine, ...cited];
+    });
+}
+function probeOf(citation) {
+    return citation.directory ? `${citation.path}/` : citation.path;
+}
+// A citation is covered when git tracks the path, a file beneath it, or a file its glob prefix opens.
+function isCovered(citation, tracked) {
+    return tracked.some((path) => path === citation.path ||
+        path.startsWith(`${citation.path}/`) ||
+        (citation.prefix !== undefined && path.startsWith(citation.prefix)));
+}
+function reportCitations() {
+    if (!existsSync('.orkestrel'))
+        return [];
+    const findings = listFiles('.orkestrel', NOTHING_SKIPPED)
+        .map((file) => file.path)
+        .filter((path) => /\.md$/iu.test(path))
+        .sort()
+        .flatMap((path) => listFindings(path));
+    const probes = new Set();
+    for (const finding of findings) {
+        if (finding.citation !== undefined)
+            probes.add(probeOf(finding.citation));
+    }
+    const ignored = readIgnored([...probes]);
+    const tracked = ignored.size === 0 ? [] : listTracked([]);
+    const seen = new Set();
+    const lines = [];
+    for (const { file, line, citation } of findings) {
+        const text = citation === undefined
+            ? 'names a machine path'
+            : ignored.has(probeOf(citation)) && !isCovered(citation, tracked)
+                ? `cites ignored path ${citation.path}`
+                : undefined;
+        if (text === undefined)
+            continue;
+        const key = `${file}:${line} ${text}`;
+        if (seen.has(key))
+            continue;
+        seen.add(key);
+        lines.push(`sweep: ${key}`);
+    }
+    return lines;
+}
 function runReport() {
     for (const directory of [...LAUNCH_DIRECTORIES, ...listCampaignDirectories()]) {
         const line = reportDirectory(directory);
@@ -76,13 +183,16 @@ function runReport() {
     const files = reportCampaignFiles();
     if (files !== undefined)
         console.log(files);
+    for (const line of reportCitations())
+        console.log(line);
     return 0;
 }
 function runSweep(thresholdMinutes) {
     const now = Date.now();
     const present = LAUNCH_DIRECTORIES.filter((directory) => existsSync(directory));
+    const tracked = new Set(listTracked(LAUNCH_DIRECTORIES));
     const files = present.flatMap((directory) => listFiles(directory, NOTHING_SKIPPED));
-    if (files.some((file) => now - file.modified < RECENT_MS)) {
+    if (files.some((file) => !tracked.has(file.path) && now - file.modified < RECENT_MS)) {
         console.error('sweep: a launch file changed within the last 2 minutes; refusing to delete');
         return 2;
     }
@@ -90,6 +200,10 @@ function runSweep(thresholdMinutes) {
     for (const file of files) {
         if (file.modified > cutoff)
             continue;
+        if (tracked.has(file.path)) {
+            console.log(`sweep: kept tracked ${file.path}`);
+            continue;
+        }
         rmSync(file.path, { force: true });
         console.log(`sweep: deleted ${file.path}`);
     }
@@ -111,11 +225,17 @@ function runUnit(unit, remove) {
         return 64;
     }
     const files = listUnitFiles(unit);
-    if (remove && files.some((file) => Date.now() - file.modified < RECENT_MS)) {
+    const tracked = new Set(listTracked(LAUNCH_DIRECTORIES));
+    if (remove &&
+        files.some((file) => !tracked.has(file.path) && Date.now() - file.modified < RECENT_MS)) {
         console.error(`sweep: a file of ${unit} changed within the last 2 minutes; refusing to delete`);
         return 2;
     }
     for (const file of files) {
+        if (tracked.has(file.path)) {
+            console.log(remove ? `sweep: kept tracked ${file.path}` : `sweep: found ${file.path} (tracked)`);
+            continue;
+        }
         if (remove)
             rmSync(file.path, { force: true });
         console.log(`sweep: ${remove ? 'deleted' : 'found'} ${file.path}`);

package/dist/bin/main.js

@@ -10,7 +10,7 @@ import { normalize } from "node:path";
 import { parseArgs } from "node:util";
 var package_default = {
 	name: "@orkestrel/scaffold",
-	version: "0.0.107",
+	version: "0.0.108",
 	description: "Scaffold workspaces with commands: new, audit, repair, catalog, and overwrite.",
 	keywords: [
 		"audit",