mikser-io 9.42.0 → 9.43.0

package/docs/api-reference.md

@@ -483,6 +483,76 @@ Query types throughout: function, lodash match object, or `undefined` for all.
 
 ---
 
+## Writing source files
+
+`updateEntity` is a catalog operation. `writeEntitySource` writes the FILE, with
+the checks that make a whole-file rewrite safe to perform without having watched
+the file the whole time.
+
+### `writeEntitySource(options)`
+
+```js
+import { writeEntitySource } from 'mikser-io'
+
+const preview = await writeEntitySource({
+    id: '/documents/about.md',
+    content: next,
+    dryRun: true,          // writes nothing; reports what it would re-render
+})
+
+const result = await writeEntitySource({
+    id: '/documents/about.md',
+    content: next,
+    ifChecksum: preview.currentChecksum,
+})
+```
+
+| Option | Meaning |
+| --- | --- |
+| `id` | Catalog id of an existing entity. Alternative to the pair below. |
+| `collection` + `relativePath` | Where to write. Required unless `id` is given. |
+| `content` | The COMPLETE file. Anything omitted is deleted — there is no patch mode. |
+| `ifChecksum` | Only write if the file's current DISK checksum equals this. |
+| `dryRun` | Write nothing; return the blast radius and any advisory. |
+| `awaitCycle` | Resolve once the cycle that picks the write up finishes, with its build report attached as `report`. |
+
+**Never throws for an expected outcome.** A bad id, a path that escapes the
+collection, a checksum that no longer matches — each returns
+`{ ok: false, refused }` with the facts needed to retry, because those are
+answers rather than faults. `refused` is one of `unresolvable-id`,
+`collection-mismatch`, `incomplete-target`, `invalid-target`,
+`checksum-mismatch`.
+
+**Containment.** `relativePath` cannot leave the collection folder. This
+matters because the path often comes from a request body or a CMS form, and
+`path.join(folder, '../../x')` resolves outside the folder and writes there. It
+is resolved and then contained rather than rejected on a literal `..`, so
+`blog/../about.md` still works. The refusal happens before anything stats the
+file — reporting a checksum for an out-of-tree path is a disclosure on its own.
+
+**The precondition is not a lock.** A writer landing between the check and the
+write still wins. It closes the window that matters in practice: read, think,
+write back a whole file built from a copy that is now stale.
+
+`ifChecksum` is compared against the DISK. `readEntity`'s `checksum` is the
+catalog's, which lags between builds — pass `diskChecksum`, or the
+`currentChecksum` a refusal hands back.
+
+### Advisories
+
+`contentAdvisories(entity, content)` names files a caller must not edit blind,
+from `meta.specLocked` / `meta.generated` or from a header in the first 40
+lines. Two kinds, kept apart because the instruction differs: `spec-locked`
+means the bytes answer to a document outside the repo, `generated` means
+editing the file is pointless because the next build overwrites it.
+`advisoryWarning(advisories)` renders one line of prose for a response meant to
+be read rather than parsed. Both are reported by `writeEntitySource` — on the
+dry run and again on the way out, since a caller that never read the file is
+exactly the one that needs telling.
+
+`siblingDestinations(folder, relativePath)` reports files differing only by
+extension, which may render to the same destination.
+
 ## Search
 
 `queryEntities` sifts **meta**. `searchEntities` answers the other question —

package/index.js

@@ -12,6 +12,7 @@ export * from './src/database/index.js'
 export * from './src/journal.js'
 export * from './src/catalog.js'
 export * from './src/search.js'
+export * from './src/write.js'
 export * from './src/refs.js'
 export * from './src/manifest.js'
 export * from './src/provenance.js'

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mikser-io",
-  "version": "9.42.0",
+  "version": "9.43.0",
   "description": "<p align=\"center\">   <img src=\"mikser-lockup-stacked.svg\" alt=\"mikser\" width=\"198\" /> </p>",
   "main": "index.js",
   "exports": {

package/src/utils.js

@@ -1077,20 +1077,38 @@ export function useCollection(runtime, name) {
         return folder
     }
 
+    // A path that cannot leave the collection folder.
+    //
+    // `path.join(folder, '../../x')` resolves outside the folder and writes
+    // there, which turns a collection handle into an arbitrary-write
+    // primitive the moment a relative path comes from a request body or a CMS
+    // form. Resolved and then contained rather than rejected on a literal
+    // `..`, so `a/../b.md` — which lands inside — still works.
+    function resolveWithin(relativePath) {
+        const folder = resolveFolder()
+        const uri = path.resolve(folder, relativePath ?? '')
+        const root = path.resolve(folder)
+        if (uri !== root && !uri.startsWith(root + path.sep)) {
+            throw new Error(
+                `Path escapes the ${name} collection: ${JSON.stringify(relativePath)} resolves outside ${root}`)
+        }
+        return uri
+    }
+
     return {
         name,
         get folder() { return resolveFolder() },
+        resolveWithin,
 
         async write(relativePath, content = '') {
-            const uri = path.join(resolveFolder(), relativePath)
+            const uri = resolveWithin(relativePath)
             await mkdir(path.dirname(uri), { recursive: true })
             await writeFile(uri, content, 'utf8')
             return uri
         },
 
         async remove(relativePath) {
-            const uri = path.join(resolveFolder(), relativePath)
-            await unlink(uri)
+            await unlink(resolveWithin(relativePath))
         },
     }
 }

package/src/write.js

@@ -0,0 +1,279 @@
+// Write a source file back, with the checks that make a whole-file rewrite
+// safe to perform without having watched the file the whole time.
+//
+// The only write mode is whole-file: there is no patch. That makes the write
+// itself the easy part and everything around it the point —
+//
+//   - a checksum precondition, so a rewrite built from a stale copy is
+//     refused instead of silently discarding whoever edited in between
+//   - a dry run reporting which destinations the write would re-render
+//   - advisories naming a file that is GENERATED or answers to an external
+//     spec, which a caller must not edit blind
+//   - siblings that could render to the same destination
+//   - containment, so a relative path from a form or a request body cannot
+//     write outside the collection folder
+//
+// An editing agent gets these through mikser-io-mcp. An application driving
+// mikser as a CMS writes its own files and gets none of them, which is the
+// gap this closes: the safety belongs to the write, not to one transport.
+
+import path from 'node:path'
+import { readdir } from 'node:fs/promises'
+
+import runtime from './runtime.js'
+import { readEntity, findEntities } from './catalog.js'
+import { useCollection, checksum, readEntityContent } from './utils.js'
+import { nextCycleId, whenCycleCompletes } from './report.js'
+
+// How far into a file to look for a marker. A header nobody reads is not a
+// header; one buried 200 lines down is not either.
+const HEADER_SCAN_LINES = 40
+
+// Files a caller must not edit blind, read from the bytes themselves.
+//
+// Two kinds, kept apart because the instruction differs. `spec-locked` means
+// the bytes answer to a document outside the repo — change it and the site
+// stops matching something a human signed off. `generated` means editing the
+// file is pointless, because the next build overwrites it.
+const HEADER_PATTERNS = [
+    { kind: 'spec-locked', re: /^\W*spec source:\s*(.+?)\s*$/i },
+    { kind: 'generated',   re: /^\W*(?:generated by|do not edit)\b:?\s*(.*?)\s*$/i },
+]
+
+export function contentAdvisories(entity, content) {
+    const found = []
+    const push = (kind, detail, via, line) => {
+        if (found.some(a => a.kind === kind)) return
+        found.push({ kind, detail: detail || null, via, ...(line ? { line } : {}) })
+    }
+    // Explicit meta wins: someone wrote it down as data, on purpose.
+    if (entity?.meta?.specLocked) {
+        push('spec-locked', typeof entity.meta.specLocked === 'string' ? entity.meta.specLocked : null, 'meta.specLocked')
+    }
+    if (entity?.meta?.generated) {
+        push('generated', typeof entity.meta.generated === 'string' ? entity.meta.generated : null, 'meta.generated')
+    }
+    if (typeof content === 'string') {
+        const lines = content.split('\n', HEADER_SCAN_LINES)
+        for (let i = 0; i < lines.length; i++) {
+            for (const { kind, re } of HEADER_PATTERNS) {
+                const m = re.exec(lines[i])
+                if (m) push(kind, m[1], 'header', i + 1)
+            }
+        }
+    }
+    return found
+}
+
+// One line of prose for a response that has to be read, not parsed.
+export function advisoryWarning(advisories) {
+    if (!advisories?.length) return null
+    return advisories.map(a => a.kind === 'spec-locked'
+        ? `SPEC-LOCKED: ${a.detail ?? 'this file answers to an external specification'}`
+            + ' — changing it may break a signed-off design. Confirm against the spec before writing.'
+        : `GENERATED: ${a.detail ?? 'this file is produced by the build'}`
+            + ' — edit its source instead; the next build overwrites this.').join(' ')
+}
+
+// Files beside this one that differ only by extension.
+//
+// An empty `index.md` sitting next to a real `index.yml` renders to the same
+// destination; whichever renders last wins and the other output is discarded.
+// The destination is not known until the cycle runs, but the COLLIDING SHAPE
+// is visible at write time, and the write is the cheapest moment to say so.
+export async function siblingDestinations(folder, relativePath) {
+    const dir = path.dirname(path.join(folder, relativePath))
+    const base = path.basename(relativePath, path.extname(relativePath))
+    try {
+        const entries = await readdir(dir, { withFileTypes: true })
+        return entries
+            .filter(e => e.isFile()
+                && path.basename(e.name, path.extname(e.name)) === base
+                && e.name !== path.basename(relativePath))
+            .map(e => ({
+                path: path.join(path.dirname(relativePath), e.name),
+                note: 'same name, different extension — may render to the same destination',
+            }))
+    } catch {
+        return []
+    }
+}
+
+// The checksum of a file, or null when there is nothing there. Not an error
+// path: "does not exist yet" is the normal case for a create.
+async function fileChecksum(uri) {
+    try {
+        return await checksum(uri)
+    } catch {
+        return null
+    }
+}
+
+// The catalog entity written from this file, when there is one.
+async function findEntityAtUri(uri) {
+    if (!uri) return null
+    const matches = await findEntities({ uri })
+    return matches?.[0] ?? null
+}
+
+// Resolve a catalog id to the (collection, relativePath) pair a write needs.
+//
+// Taken from the entity rather than by splitting the id: the id prefix is
+// `idPrefix ?? '/' + collection` and the extension may have been stripped, so
+// splitting on the first segment is a guess that is usually right and
+// silently wrong for any source configured either way.
+export async function locateEntityFile(id) {
+    const entity = await readEntity({ id })
+    if (!entity) return { error: `No entity with id ${id}.` }
+    if (!entity.collection) {
+        return { error: `Entity ${id} has no collection, so its file location cannot be derived.` }
+    }
+    let folder
+    try {
+        folder = useCollection(runtime, entity.collection).folder
+    } catch (err) {
+        return { error: `Entity ${id} is in collection ${entity.collection}, which has no folder: ${err.message}` }
+    }
+    if (!entity.uri) {
+        return { error: `Entity ${id} has no uri — it is synthetic (emitted by a plugin, not read from a file) `
+            + 'and has no file to rewrite.' }
+    }
+    const relativePath = path.relative(folder, entity.uri)
+    if (!relativePath || relativePath.startsWith('..') || path.isAbsolute(relativePath)) {
+        return { error: `Entity ${id} lives at ${entity.uri}, outside its collection folder ${folder}.` }
+    }
+    return { collection: entity.collection, relativePath }
+}
+
+// Create or overwrite a source file inside a collection.
+//
+// Takes either `id` (an existing entity) or `collection` + `relativePath`.
+// `content` is the COMPLETE file: anything omitted is deleted.
+//
+// Never throws for an expected outcome. A refusal — a bad id, a path that
+// escapes the collection, a checksum that no longer matches — comes back as
+// `{ ok: false, refused }` with the facts needed to retry, because those are
+// answers rather than faults.
+//
+//   dryRun      write nothing; report what the write would touch
+//   ifChecksum  only write if the file's current DISK checksum equals this
+//   awaitCycle  resolve once the cycle that picks the write up has finished,
+//               with its build report attached
+export async function writeEntitySource({
+    id,
+    collection,
+    relativePath,
+    content = '',
+    ifChecksum,
+    dryRun = false,
+    awaitCycle = false,
+} = {}) {
+    if (id) {
+        const located = await locateEntityFile(id)
+        if (located.error) return { ok: false, refused: 'unresolvable-id', error: located.error }
+        // An explicit pair still wins if a caller passes both, but disagreeing
+        // with the id is a mistake worth refusing rather than silently
+        // resolving one way.
+        if (collection && collection !== located.collection) {
+            return {
+                ok: false,
+                refused: 'collection-mismatch',
+                error: `id ${id} is in collection ${located.collection}, not ${collection}. Pass one or the other.`,
+            }
+        }
+        collection ??= located.collection
+        relativePath ??= located.relativePath
+    }
+    if (!collection || !relativePath) {
+        return {
+            ok: false,
+            refused: 'incomplete-target',
+            error: 'Pass either `id` (for an existing entity) or both `collection` and `relativePath`.',
+        }
+    }
+
+    let handle
+    let uri
+    try {
+        handle = useCollection(runtime, collection)
+        // Containment before anything reads or writes. A relative path that
+        // escapes the collection must not even be STATTED — reporting a
+        // checksum for /etc/passwd is a disclosure on its own.
+        uri = handle.resolveWithin(relativePath)
+    } catch (err) {
+        return { ok: false, refused: 'invalid-target', collection, relativePath, error: err.message }
+    }
+
+    // Everything a caller should know BEFORE the bytes move. Computed for the
+    // dry run and the real write alike, so the preview and the thing it
+    // previews cannot disagree.
+    const existing = id ? await readEntity({ id }) : await findEntityAtUri(uri)
+    const onDisk = await readEntityContent({ uri }, { reload: true })
+    const advisories = contentAdvisories(existing, typeof onDisk.content === 'string' ? onDisk.content : null)
+
+    if (dryRun) {
+        const wouldAffect = existing?.id ? (runtime.manifest?.affectedBy?.(existing) ?? []) : []
+        const touched = new Set(wouldAffect.map(a => a.destination))
+        return {
+            ok: true, dryRun: true, collection, relativePath,
+            id: existing?.id ?? null,
+            exists: existing != null,
+            currentChecksum: await fileChecksum(uri),
+            advisories,
+            warning: advisoryWarning(advisories),
+            wouldAffect,
+            wouldAffectCount: wouldAffect.length,
+            siblingDestinations: await siblingDestinations(handle.folder, relativePath),
+            // Collisions ALREADY standing at the outputs this write would
+            // touch. A write cannot be blamed for them, but re-rendering into
+            // one is how the wrong half of a contested destination wins.
+            collisionsAtAffected: (runtime.manifest?.collisions?.() ?? [])
+                .filter(c => touched.has(c.destination)),
+            note: existing?.id
+                ? 'Destinations are computed with the engine\'s own skip rule, so they match what a real cycle '
+                    + 'would do — EXCEPT for changes to the entity\'s own frontmatter, which is parsed during '
+                    + 'import and can move its destination.'
+                : 'This file is not in the catalog yet, so nothing depends on it and there is no blast radius '
+                    + 'to report.',
+        }
+    }
+
+    // Checked immediately before the write. Not a lock — a writer that lands
+    // between the check and the write still wins — but it closes the window
+    // that matters in practice: read, think, write back a whole file built
+    // from a copy that is now stale.
+    const before = await fileChecksum(uri)
+    if (ifChecksum !== undefined && ifChecksum !== before) {
+        return {
+            ok: false,
+            refused: 'checksum-mismatch',
+            collection, relativePath,
+            expectedChecksum: ifChecksum,
+            currentChecksum: before,
+            hint: before === null
+                ? 'The file does not exist. Omit ifChecksum to create it.'
+                : 'The file on disk changed since you read it. Re-read it for the CONTENT, re-apply your change, '
+                    + 'and retry with `currentChecksum` from THIS response.',
+        }
+    }
+
+    const cycleId = nextCycleId()
+    await handle.write(relativePath, content)
+
+    const result = {
+        ok: true, collection, relativePath,
+        checksum: await fileChecksum(uri),
+        bytes: Buffer.byteLength(content),
+        cycleId,
+        siblingDestinations: await siblingDestinations(handle.folder, relativePath),
+    }
+    // Echoed on the way out, not only on read. A caller that never read the
+    // file — or read past the header — is exactly the one that needs telling,
+    // and telling it after the write still names what to check before deploy.
+    if (advisories.length) {
+        result.advisories = advisories
+        result.warning = advisoryWarning(advisories)
+    }
+    if (awaitCycle) result.report = await whenCycleCompletes(cycleId)
+    return result
+}