fix: auto-register skill on doctor + add XHS output formatter (#154, #134) (#199)

- Add 'agent-reach skill --install/--uninstall' command for explicit skill management
- Make 'agent-reach doctor' auto-install skill if not present (fixes #154)
- Add format_xhs_result() to strip bloated XHS JSON to essential fields (fixes #134)
- Add 'agent-reach format xhs' CLI command (pipe mcporter output to clean it)
- Update SKILL.md with XHS formatter usage tip
- Add tests for both features (11 new tests, 73/73 total pass)

Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
This commit is contained in:
Pnant
2026-03-23 19:40:57 +08:00
committed by GitHub
parent 470c1288d0
commit 3be2a64120
5 changed files with 421 additions and 0 deletions
+109
View File
@@ -8,6 +8,115 @@ import subprocess
from .base import Channel
def format_xhs_result(data):
"""Clean XHS API response, keeping only useful fields.
Handles both single note objects and lists of notes (search results).
Drastically reduces token usage by stripping structural redundancy (#134).
"""
if isinstance(data, list):
return [_clean_note(item) for item in data]
if isinstance(data, dict):
# Handle search_feeds wrapper: {"items": [...]} or {"data": {"items": [...]}}
items = None
if "items" in data:
items = data["items"]
elif "data" in data and isinstance(data.get("data"), dict):
items = data["data"].get("items") or data["data"].get("notes")
if items and isinstance(items, list):
return [_clean_note(item) for item in items]
# Single note
return _clean_note(data)
return data
def _clean_note(note):
"""Extract useful fields from a single XHS note/feed item."""
if not isinstance(note, dict):
return note
# Some responses nest the note under "note_card" or "note"
inner = note.get("note_card") or note.get("note") or note
result = {}
# Basic info
for key in ("id", "note_id", "xsec_token", "title", "desc", "type", "time"):
if key in inner:
result[key] = inner[key]
# Content (may be in desc or content)
if "content" in inner and "desc" not in result:
result["content"] = inner["content"]
# Author
user = inner.get("user") or inner.get("author")
if isinstance(user, dict):
result["user"] = {
k: user[k] for k in ("nickname", "user_id", "nick_name") if k in user
}
# Engagement metrics
interact = inner.get("interact_info") or inner.get("note_interact_info") or {}
if isinstance(interact, dict):
for key in ("liked_count", "collected_count", "comment_count", "share_count"):
if key in interact:
result[key] = interact[key]
# Also check top-level (some API formats)
for key in ("liked_count", "collected_count", "comment_count", "share_count"):
if key in inner and key not in result:
result[key] = inner[key]
# Images — just URLs
images = inner.get("image_list") or inner.get("images_list") or []
if isinstance(images, list):
urls = []
for img in images:
if isinstance(img, dict):
url = img.get("url") or img.get("url_default") or img.get("original")
if url:
urls.append(url)
elif isinstance(img, str):
urls.append(img)
if urls:
result["images"] = urls
# Tags
tags = inner.get("tag_list") or inner.get("tags") or []
if isinstance(tags, list):
tag_names = []
for t in tags:
if isinstance(t, dict) and "name" in t:
tag_names.append(t["name"])
elif isinstance(t, str):
tag_names.append(t)
if tag_names:
result["tags"] = tag_names
# Comments (if present, e.g. from get_feed_detail with comments)
comments = inner.get("comments") or []
if isinstance(comments, list) and comments:
result["comments"] = [_clean_comment(c) for c in comments]
return result
def _clean_comment(comment):
"""Extract useful fields from a comment."""
if not isinstance(comment, dict):
return comment
result = {}
if "content" in comment:
result["content"] = comment["content"]
user = comment.get("user_info") or comment.get("user")
if isinstance(user, dict):
result["user"] = user.get("nickname") or user.get("nick_name", "")
for key in ("like_count", "sub_comment_count"):
if key in comment:
result[key] = comment[key]
return result
def _is_arm64() -> bool:
"""Detect ARM64 architecture (e.g. Apple Silicon)."""
machine = platform.machine().lower()