feat: use OpenClaw sub-agent for slow detect commands, fix keyword generation

- SKILL.md: detect/detect-and-search now spawned via sessions_spawn (non-blocking); search/session run inline
- product-detector.ts: replace sequential chunk loop with worker-pool concurrency (withConcurrency) so all frames dispatch immediately up to the limit
- index.ts: fix generateChineseKeyword prompt to name the container/organizer object, not the items it holds (e.g. 鞋架 not 鞋)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

SKILL.md

@@ -86,9 +86,29 @@ VISION_API_BASE=http://localhost:11434/v1
 VISION_MODEL=llava:13b
 ```
 
-## Rules — MUST follow
+## Execution rules
 
-1. **Execute only, do not reason about internals.** Run the CLI and return the output.
-2. **No fallback strategies.** Report errors as-is; do NOT try alternative approaches.
-3. **No retry loops.** If detection or search fails, report the failure.
-4. **Trust the tool's output.** The CLI handles session management and error formatting internally.
+### For `detect` and `detect-and-search` (slow — use sub-agent)
+
+Spawn a sub-agent via `sessions_spawn`. Do **not** run the command directly.
+
+```
+sessions_spawn(
+  task: "Run this command and return the raw JSON output:\n\nbun dist/run.js <full command here>\n\nCopy the entire JSON output as your reply.",
+  label: "video-product-snapshot",
+  runTimeoutSeconds: 300,
+)
+```
+
+- Announce immediately that processing has started and share the `runId`.
+- Wait for the sub-agent announcement, then parse and format the result for the user.
+
+### For `search` and `session` (fast — run directly)
+
+Run the CLI command inline, no sub-agent needed.
+
+### General rules
+
+1. **No fallback strategies.** Report errors as-is; do NOT try alternative approaches.
+2. **No retry loops.** If detection or search fails, report the failure.
+3. **Trust the tool's output.** The CLI handles session management and error formatting internally.

src/index.ts

@@ -198,10 +198,12 @@ async function generateChineseKeyword(description: string, visionConfig: VisionC
     model,
     prompt: `You are generating a 1688.com (Chinese B2B wholesale) product search keyword.
 Rules:
-- Output ONLY 2-4 Chinese words — the product category + 1-2 key material/feature words
+- Output ONLY 2-4 Chinese words — the product OBJECT TYPE + 1-2 key material/feature words
+- CRITICAL: If the product is a container, organizer, rack, shelf, bag, box, or holder, the keyword MUST name THAT object — NOT the items it holds.
+  Examples: shoe rack → "金属鞋架", cable organizer → "理线器", storage shelf → "收纳架", toolbox → "工具箱"
 - Use common Chinese commerce terms, NOT a literal translation
 - No English, no punctuation, no explanation
-- Short broad terms work better than long specific phrases (e.g. "金属鞋架" not "黑色Z型金属网格鞋架")
+- Short broad terms work better than long specific phrases
 
 Product description: ${description}
 

src/product-detector.ts

@@ -135,23 +135,35 @@ export async function cropProduct(
   return outputPath;
 }
 
+async function withConcurrency<T>(
+  tasks: (() => Promise<T>)[],
+  limit: number,
+): Promise<T[]> {
+  const results: T[] = new Array(tasks.length);
+  let next = 0;
+  async function worker() {
+    while (next < tasks.length) {
+      const i = next++;
+      results[i] = await tasks[i]();
+    }
+  }
+  await Promise.all(Array.from({ length: Math.min(limit, tasks.length) }, worker));
+  return results;
+}
+
 export async function detectProductFrames(
   frames: ExtractedFrame[],
   minConfidence: number,
-  concurrency: number = 5,
+  concurrency: number = 10,
   visionConfig: VisionConfig,
 ): Promise<ProductFrame[]> {
   const model = createVisionModel(visionConfig);
 
-  // Pass 1: parallel filter — discard junk frames
-  const keepFlags: boolean[] = [];
-  for (let i = 0; i < frames.length; i += concurrency) {
-    const chunk = frames.slice(i, i + concurrency);
-    const flags = await Promise.all(
-      chunk.map((f) => filterFrame(f, model).catch(() => false))
+  // Pass 1: all frames in parallel, bounded by concurrency
+  const keepFlags = await withConcurrency(
+    frames.map((f) => () => filterFrame(f, model).catch(() => false)),
+    concurrency,
   );
-    keepFlags.push(...flags);
-  }
 
   const candidates = frames.filter((_, i) => keepFlags[i]);
   if (candidates.length === 0) return [];