@theronap/cortex-mcp 0.9.7 → 0.9.9

package/bin/cortex-mcp.mjs

@@ -7,6 +7,7 @@
  *   setup <TOKEN>     wire BOTH the MCP server + capture hook into your Claude config
  *   doctor            live health check — is the token actually working? (no restart needed)
  *   capture           the Stop-hook capturer (invoked by Claude Code, not by hand)
+ *   ingest-folder <path>  ingest a local markdown folder as your authored records
  *   snapshot-context  save the exact startup context served by Cortex to a local log file
  *   --version | -v
  *   --help | -h
@@ -47,6 +48,7 @@ if (cmd === '--help' || cmd === '-h' || cmd === 'help') {
     `  skills          install/repair the managed Cortex skills (also wired by setup)\n` +
     `  snapshot-context save the exact startup context Cortex served to a local snapshot\n` +
     `  capture         Stop-hook capturer (invoked by Claude Code)\n` +
+    `  ingest-folder <path>   ingest a local markdown folder as your authored records\n` +
     `  (no args)       run the MCP server (used by your Claude config)\n\n` +
     `Get your token from the Cortex console → Connect your AI.\n`,
   )
@@ -88,6 +90,11 @@ if (cmd === 'setup') {
   await runCapture()
   const { closeFetch } = await import('../lib/diagnose.mjs')
   await closeFetch()
+} else if (cmd === 'ingest-folder') {
+  const { runIngestFolder } = await import('../lib/ingest_folder.mjs')
+  await runIngestFolder(rest)
+  const { closeFetch } = await import('../lib/diagnose.mjs')
+  await closeFetch()
 } else if (cmd === 'snapshot-context') {
   const { runSnapshotContext } = await import('../lib/context_log.mjs')
   process.exitCode = await runSnapshotContext()

package/lib/ingest_folder.mjs

@@ -0,0 +1,170 @@
+import { readFileSync, readdirSync, statSync } from 'node:fs'
+import { join, relative, basename, extname } from 'node:path'
+import { fetchCortex, classify, resolveBase } from './diagnose.mjs'
+
+// `cortex-mcp ingest-folder <path>` — walk a local markdown folder and upsert each file as an
+// AUTHORED record in Cortex (source='brain'), so a user's personal digest is built from THEIR
+// notes (Robin parity). Only an EXCERPT of each file leaves the machine (frontmatter + first
+// ~800 chars), never the full body. The server clamps privacy for source='brain' and treats
+// sessionId (the file's relative path) as the stable dedupe key, so re-running updates in place.
+
+const sleep = (ms) => new Promise((r) => setTimeout(r, ms))
+
+const MD_EXT = new Set(['.md', '.markdown'])
+// Directories that are never user notes — skip them and any dotfile dir.
+const SKIP_DIRS = new Set(['node_modules', '.git', '.obsidian', '.trash'])
+
+// Recursively collect markdown file paths under `root`. Uses withFileTypes so we can prune
+// skipped directories without stat-ing every entry.
+function walkMarkdown(root) {
+  const out = []
+  let entries
+  try {
+    entries = readdirSync(root, { withFileTypes: true })
+  } catch {
+    return out
+  }
+  for (const ent of entries) {
+    const full = join(root, ent.name)
+    if (ent.isDirectory()) {
+      if (SKIP_DIRS.has(ent.name) || ent.name.startsWith('.')) continue
+      out.push(...walkMarkdown(full))
+    } else if (ent.isFile() && MD_EXT.has(extname(ent.name).toLowerCase())) {
+      out.push(full)
+    }
+  }
+  return out
+}
+
+// Tiny hand-rolled YAML frontmatter parser. Only the leading `---\n…\n---` block; flat
+// `key: value` lines. Collects title/tags/project/people if present. No dependencies — this is
+// deliberately minimal (not a full YAML parser). Returns { frontmatter, frontLines, bodyStart }.
+function parseFrontmatter(content) {
+  if (!content.startsWith('---\n') && !content.startsWith('---\r\n')) {
+    return { frontmatter: {}, frontLines: [], bodyStart: 0 }
+  }
+  const lines = content.split('\n')
+  // lines[0] is the opening '---'; find the closing '---'.
+  let end = -1
+  for (let i = 1; i < lines.length; i++) {
+    if (lines[i].trim() === '---') { end = i; break }
+  }
+  if (end === -1) return { frontmatter: {}, frontLines: [], bodyStart: 0 }
+
+  const frontLines = lines.slice(1, end)
+  const frontmatter = {}
+  for (const raw of frontLines) {
+    const line = raw.replace(/\r$/, '')
+    const idx = line.indexOf(':')
+    if (idx === -1) continue
+    const key = line.slice(0, idx).trim()
+    let value = line.slice(idx + 1).trim()
+    if (!key) continue
+    // Strip wrapping quotes.
+    value = value.replace(/^["']|["']$/g, '')
+    // Inline list form: [a, b, c]
+    if (value.startsWith('[') && value.endsWith(']')) {
+      const items = value.slice(1, -1).split(',').map((s) => s.trim().replace(/^["']|["']$/g, '')).filter(Boolean)
+      frontmatter[key] = items
+    } else if (value === '') {
+      frontmatter[key] = ''
+    } else {
+      frontmatter[key] = value
+    }
+  }
+  // bodyStart = char offset just past the closing '---' line + its newline.
+  const consumed = lines.slice(0, end + 1).join('\n')
+  const bodyStart = consumed.length + 1
+  return { frontmatter, frontLines: frontLines.map((l) => l.replace(/\r$/, '')), bodyStart }
+}
+
+// title: frontmatter.title → first `# ` heading in body → filename without extension.
+function deriveTitle(frontmatter, body, filePath) {
+  if (typeof frontmatter.title === 'string' && frontmatter.title.trim()) return frontmatter.title.trim()
+  for (const line of body.split('\n')) {
+    const m = line.match(/^#\s+(.+?)\s*$/)
+    if (m) return m[1].trim()
+  }
+  return basename(filePath, extname(filePath))
+}
+
+// summary: first ~800 chars of the BODY (prose). Bounded so the raw full file never leaves the
+// machine. Frontmatter is NOT prepended — it rides structured in payload, and the title is derived
+// separately, so the summary reads as content (what the digest summarizes), not "key: value" noise.
+function deriveSummary(body) {
+  return body.trim().slice(0, 800)
+}
+
+export async function runIngestFolder(argv) {
+  const path = argv[0]
+  if (!path) {
+    process.stderr.write(
+      'usage: cortex-mcp ingest-folder <path>\n' +
+      '  Ingest a local markdown folder as your authored Cortex records.\n',
+    )
+    return
+  }
+
+  const token = process.env.CORTEX_TOKEN
+  if (!token) {
+    process.stderr.write(
+      'cortex: CORTEX_TOKEN not set. Run setup first, or export CORTEX_TOKEN=<your-token>.\n',
+    )
+    return
+  }
+  const base = resolveBase(process.env.CORTEX_URL)
+
+  const files = walkMarkdown(path)
+  process.stdout.write(`Ingesting ${files.length} markdown files from ${path} …\n`)
+  if (files.length === 0) {
+    process.stdout.write('✓ ingested 0, updated 0, failed 0 (no markdown files found)\n')
+    return
+  }
+
+  let inserted = 0
+  let updated = 0
+  let failed = 0
+
+  for (const file of files) {
+    try {
+      const content = readFileSync(file, 'utf8')
+      const { frontmatter, bodyStart } = parseFrontmatter(content)
+      const body = content.slice(bodyStart)
+
+      const relpath = relative(path, file)
+      const title = deriveTitle(frontmatter, body, file)
+      const summary = deriveSummary(body)
+      const occurredAt = statSync(file).mtime.toISOString()
+
+      const res = await fetchCortex(`${base}/api/ingest`, {
+        method: 'POST',
+        headers: { Authorization: `Bearer ${token}`, 'Content-Type': 'application/json' },
+        body: JSON.stringify({
+          source: 'brain',
+          sessionId: relpath,
+          title,
+          summary,
+          privacy: 'scoped',
+          occurredAt,
+          payload: { path: relpath, frontmatter },
+        }),
+      })
+
+      if (res.ok) {
+        const j = await res.json().catch(() => ({}))
+        if (j.inserted === false) updated++
+        else inserted++
+      } else {
+        failed++
+        const d = classify(res.status, res.headers.get('content-type'), await res.text(), res.headers.get('x-vercel-id'))
+        process.stderr.write(`cortex: ${relative(path, file)} failed — ${d.message}\n`)
+      }
+    } catch (e) {
+      failed++
+      process.stderr.write(`cortex: ${relative(path, file)} failed — ${e.message}\n`)
+    }
+    await sleep(60)
+  }
+
+  process.stdout.write(`✓ ingested ${inserted}, updated ${updated}, failed ${failed}\n`)
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@theronap/cortex-mcp",
-  "version": "0.9.7",
+  "version": "0.9.9",
   "description": "Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.",
   "type": "module",
   "bin": {