Merge pull request #2028 from heygen-com/worktree-fix-media-use-issues

fix(media-use): forgiving prompt matching + precise assets/ scan

skills-manifest.json

@@ -46,8 +46,8 @@
       "files": 10
     },
     "media-use": {
-      "hash": "db5787c5ff2bd852",
-      "files": 97
+      "hash": "caf64c363a39ad9b",
+      "files": 98
     },
     "motion-graphics": {
       "hash": "f5a432862116b39a",

skills/media-use/SKILL.md

@@ -111,8 +111,8 @@ leaving the project + global cache and any local provider.
 
 ## How it works
 
-1. Check project `.media/manifest.jsonl` for exact-prompt match
-2. Scan existing `assets/` directory for unregistered files matching the need
+1. Check project `.media/manifest.jsonl` for a prompt match (case- and whitespace-insensitive)
+2. Scan existing `assets/` directory for unregistered files that share a word with the need
 3. Check global cache `~/.media/` for reusable asset
 4. Search via provider (HeyGen audio catalog, HeyGen asset search)
 5. Freeze file to `.media/<type>/`, register in manifest, regenerate `index.md`
@@ -148,7 +148,7 @@ icon_001   icon   -     200×200    .media/images/icon_001.png    rocket
 
 ## Cross-project reuse
 
-Assets are cached automatically on resolve. Every resolved/ingested asset is auto-promoted to the global cache at `~/.media/`, so subsequent resolves for the same prompt, in any project, hit the cache with no re-download and no provider call.
+Assets are cached automatically on resolve. Every resolved/ingested asset is auto-promoted to the global cache at `~/.media/`, so subsequent resolves for the same (or near-identical) prompt, in any project, hit the cache with no re-download and no provider call.
 
 ## Files
 

skills/media-use/scripts/lib/adopt.mjs

@@ -96,16 +96,49 @@ export function adoptExistingAssets(projectDir) {
   return adopted;
 }
 
+// Common filler words that should never, on their own, make a filename match an
+// intent (e.g. intent "the rocket" must not adopt "the-video.mp4").
+const MATCH_STOPWORDS = new Set([
+  "the",
+  "and",
+  "for",
+  "with",
+  "from",
+  "this",
+  "that",
+  "your",
+  "our",
+]);
+
+// Split into lowercased word tokens of length >= 3, minus stopwords.
+function matchTokens(text) {
+  return new Set(
+    String(text)
+      .toLowerCase()
+      .split(/[^a-z0-9]+/)
+      .filter((t) => t.length >= 3 && !MATCH_STOPWORDS.has(t)),
+  );
+}
+
+// Adopt a pre-existing assets/ file only when it shares a meaningful word with
+// the intent. The old test — `name.includes(intent) || intent.includes(name)` —
+// silently returned the WRONG file: "whoosh" grabbed a stray who.mp3, and a
+// one-letter filename matched every intent. A false negative just falls through
+// to a catalog search (safe); a false positive ships the wrong asset. So bias to
+// precision: require a shared token, don't guess from substrings.
 export function findExistingAsset(projectDir, intent, type) {
   const assetsDir = join(projectDir, "assets");
   if (!existsSync(assetsDir)) return null;
-  const lower = intent.toLowerCase();
+  const intentTokens = matchTokens(intent);
+  if (intentTokens.size === 0) return null;
   for (const rel of walkDir(assetsDir)) {
     const t = inferType(rel);
     if (!t || (type && t !== type)) continue;
-    const name = basename(rel, extname(rel)).toLowerCase().replace(/[-_]/g, " ");
-    if (name.includes(lower) || lower.includes(name)) {
-      return { relativePath: `assets/${rel}`, type: t, name: basename(rel, extname(rel)) };
+    const stem = basename(rel, extname(rel));
+    for (const tok of matchTokens(stem)) {
+      if (intentTokens.has(tok)) {
+        return { relativePath: `assets/${rel}`, type: t, name: stem };
+      }
     }
   }
   return null;

skills/media-use/scripts/lib/adopt.test.mjs

@@ -0,0 +1,95 @@
+import { strict as assert } from "node:assert";
+import { mkdtempSync, rmSync, mkdirSync, writeFileSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import { findExistingAsset, adoptExistingAssets } from "./adopt.mjs";
+
+let tmp;
+function setup() {
+  tmp = mkdtempSync(join(tmpdir(), "mu-adopt-test-"));
+}
+function cleanup() {
+  if (tmp) rmSync(tmp, { recursive: true, force: true });
+}
+function drop(rel) {
+  const full = join(tmp, "assets", rel);
+  mkdirSync(join(full, ".."), { recursive: true });
+  writeFileSync(full, "x");
+}
+
+function runTests() {
+  const tests = [];
+  const test = (name, fn) => tests.push({ name, fn });
+
+  test("does NOT false-match a short filename stem (who.mp3 vs 'whoosh')", () => {
+    setup();
+    drop("sfx/who.mp3");
+    assert.equal(findExistingAsset(tmp, "whoosh", "sfx"), null);
+    cleanup();
+  });
+
+  test("does NOT match a one-letter filename against any intent", () => {
+    setup();
+    drop("images/a.jpg");
+    assert.equal(findExistingAsset(tmp, "gradient tech background", "image"), null);
+    cleanup();
+  });
+
+  test("matches on a shared meaningful word", () => {
+    setup();
+    drop("images/hero-shot.jpg");
+    const hit = findExistingAsset(tmp, "hero image", "image");
+    assert.ok(hit);
+    assert.equal(hit.relativePath, "assets/images/hero-shot.jpg");
+    cleanup();
+  });
+
+  test("matches multi-word overlap", () => {
+    setup();
+    drop("images/gradient-tech-bg.jpg");
+    assert.ok(findExistingAsset(tmp, "gradient tech background", "image"));
+    cleanup();
+  });
+
+  test("a shared stopword alone does not match", () => {
+    setup();
+    drop("video/the-video.mp4");
+    assert.equal(findExistingAsset(tmp, "the rocket", null), null);
+    cleanup();
+  });
+
+  test("respects the type filter", () => {
+    setup();
+    drop("sfx/rocket.mp3");
+    assert.equal(findExistingAsset(tmp, "rocket", "image"), null, "wrong type is skipped");
+    assert.ok(findExistingAsset(tmp, "rocket", "sfx"), "right type matches");
+    cleanup();
+  });
+
+  test("adoptExistingAssets still imports every typed file (unaffected by match rule)", () => {
+    setup();
+    drop("sfx/who.mp3");
+    drop("images/a.jpg");
+    assert.equal(adoptExistingAssets(tmp).length, 2);
+    cleanup();
+  });
+
+  let passed = 0;
+  let failed = 0;
+  for (const { name, fn } of tests) {
+    try {
+      fn();
+      passed++;
+      console.log(`  \x1b[32m✓\x1b[0m ${name}`);
+    } catch (err) {
+      failed++;
+      console.log(`  \x1b[31m✗\x1b[0m ${name}`);
+      console.log(`    ${err.message}`);
+    }
+  }
+  console.log(`\n${passed} passed, ${failed} failed`);
+  if (failed > 0) process.exit(1);
+}
+
+console.log("media-use · adopt / findExistingAsset tests\n");
+runTests();

skills/media-use/scripts/lib/cache.mjs

@@ -2,7 +2,7 @@ import { readFileSync, writeFileSync, mkdirSync, existsSync, copyFileSync } from
 import { join, basename } from "node:path";
 import { createHash } from "node:crypto";
 import { homedir } from "node:os";
-import { readManifest, appendRecord } from "./manifest.mjs";
+import { readManifest, appendRecord, normalizePrompt } from "./manifest.mjs";
 
 const SCHEMA_PREFIX = "mu-v1-";
 const KEY_HEX_CHARS = 16;
@@ -43,9 +43,14 @@ function validateCacheHit(match) {
 }
 
 export function cacheGet(prompt, type) {
+  const key = normalizePrompt(prompt);
+  if (!key) return null;
   return validateCacheHit(
     readGlobalManifest().find(
-      (r) => r.reusable && r.provenance?.prompt === prompt && (type == null || r.type === type),
+      (r) =>
+        r.reusable &&
+        normalizePrompt(r.provenance?.prompt) === key &&
+        (type == null || r.type === type),
     ),
   );
 }

skills/media-use/scripts/lib/manifest.mjs

@@ -64,11 +64,25 @@ export function appendRecord(projectDir, record) {
   appendFileSync(p, line);
 }
 
+// Match prompts forgivingly. Agents rarely re-emit a byte-identical intent, so
+// keying cache lookups on exact equality meant "Calm piano" and "calm  piano"
+// re-searched and re-downloaded. Normalize (trim, lowercase, collapse internal
+// whitespace) on both sides; the raw prompt is still stored for audit.
+export function normalizePrompt(prompt) {
+  return String(prompt ?? "")
+    .trim()
+    .toLowerCase()
+    .replace(/\s+/g, " ");
+}
+
 export function findByPrompt(projectDir, prompt, type) {
+  const key = normalizePrompt(prompt);
+  if (!key) return null;
   const records = readManifest(projectDir);
   return (
-    records.find((r) => r.provenance?.prompt === prompt && (type == null || r.type === type)) ||
-    null
+    records.find(
+      (r) => normalizePrompt(r.provenance?.prompt) === key && (type == null || r.type === type),
+    ) || null
   );
 }
 

skills/media-use/scripts/lib/manifest.test.mjs

@@ -8,6 +8,7 @@ import {
   findByPrompt,
   findByEntity,
   nextId,
+  normalizePrompt,
   manifestPath,
   mediaDir,
   typeDirPath,
@@ -114,6 +115,20 @@ function runTests() {
     cleanup();
   });
 
+  test("findByPrompt matches across case and whitespace variants", () => {
+    setup();
+    appendRecord(tmp, makeRecord({ provenance: { provider: "x", prompt: "calm ambient piano" } }));
+    assert.ok(findByPrompt(tmp, "Calm Ambient Piano", "bgm"), "case-insensitive");
+    assert.ok(findByPrompt(tmp, "  calm   ambient  piano ", "bgm"), "whitespace-insensitive");
+    assert.equal(findByPrompt(tmp, "calm ambient guitar", "bgm"), null, "still a real miss");
+    cleanup();
+  });
+
+  test("normalizePrompt trims, lowercases, collapses whitespace", () => {
+    assert.equal(normalizePrompt("  Upbeat   Tech  Launch "), "upbeat tech launch");
+    assert.equal(normalizePrompt(null), "");
+  });
+
   test("findByEntity matches case-insensitively", () => {
     setup();
     appendRecord(tmp, makeRecord({ entity: "GitHub", type: "icon" }));
@@ -203,6 +218,10 @@ function runTests() {
     assert.ok(found);
     assert.equal(found.reusable, true);
     assert.equal(found.sha, sha);
+
+    // cross-project reuse must survive trivial prompt variation, not just
+    // byte-identical intents (the whole point of normalizePrompt).
+    assert.ok(cacheGet("  Cache   Test ", "bgm"), "cacheGet is case/whitespace-insensitive");
     cleanup();
   });