docs: sync reader-digest-flow skill with Hermes version (absolute path, extract_failed handling, rerun include_read)

2026-08-03 09:55:19 +08:00
parent 807027976e
commit 8e27cca166
4 changed files with 170 additions and 3 deletions
@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+"""IMA 上传单篇 Markdown 知识笔记到 daily 知识库。
+用法: python3 ima_upload_one.py "<绝对路径/summary.md>" "<完整文章标题>"
+依赖环境变量: IMA_OPENAPI_CLIENTID / IMA_OPENAPI_APIKEY / IMA_DAILY_KNOWLEDGE_BASE_ID
+流程: preflight -> check_repeated_names -> create_media -> cos-upload -> add_knowledge
+说明: 用 Python 而非 bash 编排，避免中文文件名/引号转义问题。
+退出码 2 = 文件名重复（需与用户确认保留双方或取消），非 0 均为失败。
+"""
+import json, os, subprocess, sys
+
+SKILL_DIR = "/root/.hermes/skills/openclaw-imports/ima-skill"
+IMA_API = os.path.join(SKILL_DIR, "ima_api.cjs")
+COS_UPLOAD = os.path.join(SKILL_DIR, "knowledge-base/scripts/cos-upload.cjs")
+PREFLIGHT = os.path.join(SKILL_DIR, "knowledge-base/scripts/preflight-check.cjs")
+
+def run_node(script, args):
+    r = subprocess.run(["node", script] + args, capture_output=True, text=True, timeout=120)
+    if r.returncode != 0:
+        raise RuntimeError(f"{script} exit={r.returncode} stderr={r.stderr[:500]}")
+    return json.loads(r.stdout)
+
+def ima_api(api_path, body):
+    r = subprocess.run(["node", IMA_API, api_path, json.dumps(body, ensure_ascii=False)],
+                       capture_output=True, text=True, timeout=120)
+    if r.returncode != 0:
+        raise RuntimeError(f"ima_api {api_path} exit={r.returncode} stderr={r.stderr[:500]}")
+    resp = json.loads(r.stdout)
+    if resp.get("code") != 0:
+        raise RuntimeError(f"ima_api {api_path} code={resp.get('code')} msg={resp.get('msg')}")
+    return resp.get("data", {})
+
+def main():
+    kb_id = os.environ["IMA_DAILY_KNOWLEDGE_BASE_ID"]
+    file_path = sys.argv[1]
+    title = sys.argv[2]  # 完整文章标题（不含 .md）
+
+    pf = run_node(PREFLIGHT, ["--file", file_path])
+    if not pf.get("pass"):
+        raise RuntimeError(f"preflight failed: {pf}")
+    file_name = pf["file_name"]; media_type = pf["media_type"]
+    content_type = pf["content_type"]; file_size = pf["file_size"]; file_ext = pf["file_ext"]
+    print(f"[preflight] ok file={file_name} ext={file_ext} size={file_size} media_type={media_type}")
+
+    dup = ima_api("openapi/wiki/v1/check_repeated_names", {
+        "params": [{"name": file_name, "media_type": media_type}],
+        "knowledge_base_id": kb_id
+    })
+    is_rep = dup.get("results", [{}])[0].get("is_repeated", False) if dup.get("results") else False
+    if is_rep:
+        print(f"[check_repeated_names] REPEATED: {file_name} — 需要处理")
+        sys.exit(2)
+    print("[check_repeated_names] no duplicate")
+
+    cm = ima_api("openapi/wiki/v1/create_media", {
+        "file_name": file_name,
+        "file_size": file_size,
+        "content_type": content_type,
+        "knowledge_base_id": kb_id,
+        "file_ext": file_ext
+    })
+    media_id = cm["media_id"]
+    cos = cm["cos_credential"]
+    print(f"[create_media] media_id={media_id} cos_bucket={cos.get('bucket_name')} cos_key={cos.get('cos_key','')[:40]}")
+
+    r = subprocess.run(["node", COS_UPLOAD,
+        "--file", file_path,
+        "--secret-id", cos["secret_id"],
+        "--secret-key", cos["secret_key"],
+        "--token", cos["token"],
+        "--bucket", cos["bucket_name"],
+        "--region", cos["region"],
+        "--cos-key", cos["cos_key"],
+        "--content-type", content_type,
+        "--start-time", str(cos.get("start_time", "")),
+        "--expired-time", str(cos.get("expired_time", "")),
+        "--timeout", "300000"
+    ], capture_output=True, text=True, timeout=360)
+    if r.returncode != 0:
+        raise RuntimeError(f"cos-upload exit={r.returncode} stderr={r.stderr[:800]}")
+    print(f"[cos-upload] ok rc=0 stdout={r.stdout.strip()[:200]}")
+
+    ak = ima_api("openapi/wiki/v1/add_knowledge", {
+        "media_type": media_type,
+        "media_id": media_id,
+        "title": title,
+        "knowledge_base_id": kb_id,
+        "file_info": {
+            "cos_key": cos["cos_key"],
+            "file_size": file_size,
+            "file_name": file_name
+        }
+    })
+    print(f"[add_knowledge] ok media_id={ak.get('media_id') or media_id}")
+
+if __name__ == "__main__":
+    main()