Fixes#110 and #115. Since OpenClaw 2026-01 disabled the exec tool by
default, users on OpenClaw can't run any agent-reach commands unless
exec is explicitly enabled.
Added:
- Warning callout before '快速上手' explaining exec requirement for
OpenClaw users with the exact config command to use
- Note in the FAQ 'Compatible with Claude Code / OpenClaw...' entry
with the same fix instructions
Closes#110Closes#115
Co-authored-by: neo-minion1 <bot@openclaw.ai>
- Weibo now auto-installs during 'agent-reach install' (no login needed)
- Uses Panniantong/mcp-server-weibo fork with visitor passport auth fix
- Works from overseas servers without proxy or cookies
- Updated README (CN/EN), install.md, and channel check to point to fork
- 10 tools: trending, search content/users/topics, profile, feeds, comments
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
The m.weibo.cn API works from overseas IPs (browsers handle the
visitor passport flow automatically). The issue is that
mcp-server-weibo doesn't handle the visitor auth flow, so it
needs a valid Cookie to work.
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
Adds install steps for mcp-server-weibo and documents that the
Weibo mobile API (m.weibo.cn) only works from mainland China IPs.
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- YouTube: warn when only Node.js is installed but yt-dlp config file
is missing (previously returned "ok" incorrectly)
- Douyin: use `mcporter list` instead of calling with a hardcoded
invalid share URL that always fails
- cli: replace bare `except:` with `except Exception:` in
`_detect_environment` to avoid catching KeyboardInterrupt/SystemExit
- cli: fix unclosed file handle for cloud VM detection
- config: use `os.open()` with 0o600 mode to eliminate permission
race window when saving credentials
Adds a proper way for AI agents to import XiaoHongShu cookies into
the xiaohongshu-mcp Docker container. Previously agents had no clear
command to use, leading to confusion loops (issue #108).
Supports two input formats:
- Cookie-Editor JSON export (array of cookie objects)
- Header String format (key1=val1; key2=val2; ...)
The command:
1. Parses and validates the cookie input
2. Finds the running xiaohongshu-mcp container
3. Reads COOKIES_PATH from container env
4. Writes cookies via docker cp
5. Verifies login status via mcporter
Also updates install.md with the new command.
Closes#108
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
Previously, Extracting cookies from chrome...
✅ Twitter/X: auth_token + ct0
✅ Cookies configured! Run `agent-reach doctor` to see updated status. stored Twitter
cookies in ~/.agent-reach/config.yaml but did NOT write them to
~/.config/xfetch/session.json. This caused xreach CLI to report
'Not authenticated' even after a successful configure.
The xfetch bridge existed only in the manual
code path (cli.py:829). This commit extracts it into a shared helper
_sync_xfetch_session() in cookie_extract.py and calls it from
configure_from_browser() too, so both paths behave consistently.
Fix is non-fatal: if the xfetch dir/file cannot be written, the error
is swallowed silently (agent-reach config.yaml remains the source of truth).
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
The isatty() check skipped UTF-8 wrapping when agent-reach was called
as a subprocess by AI agents (non-TTY). On Windows with GBK encoding,
any remaining non-ASCII chars would crash with UnicodeEncodeError.
Now UTF-8 wrapping applies in all environments on Windows.
Closes#95
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- Remove all decorative emoji (👁️🔍📦🍪💡🔧📥🧩🛡️📡💻🤖⭐🙏🆕ℹ️) from cli.py and doctor.py
- Replace ⚠️ with [!] and ❌ with [X] (ASCII-safe status markers)
- Replace ⬜ with -- (ASCII-safe)
- Keep ✅ only for final success confirmations
- Fixes Windows GBK encoding crash during 'agent-reach install' (issue #95)
Closes#95
A friendly, non-intrusive message after successful installation
asking users to star the repo.
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
* feat: auto-install WeChat article tools during agent-reach install
WeChat (微信公众号) deps are now auto-installed during 'agent-reach install':
- Python packages: camoufox[geoip], markdownify, beautifulsoup4, httpx, miku_ai
- Tool repo: wechat-article-for-ai cloned to ~/.agent-reach/tools/
No login or configuration needed — works out of the box like YouTube/RSS.
Updated README tables to reflect zero-config status.
Also covers safe mode and dry-run.
* feat: auto-install WeChat + add channel-setup reference to SKILL.md
1. WeChat auto-install during 'agent-reach install':
- pip install camoufox[geoip], markdownify, bs4, httpx, miku_ai
- clone wechat-article-for-ai to ~/.agent-reach/tools/
- covers safe mode and dry-run
- README tables: WeChat → zero-config
2. SKILL.md improvements:
- Added 'configure' triggers to description
- Added references/channel-setup.md with install steps for all
login-required platforms (Twitter, XHS, Douyin, LinkedIn, Boss)
- Principle: user only provides cookies, agent does everything else
* simplify: point to install.md URL instead of bundled reference
No need to maintain a separate channel-setup.md. Just tell agents
to fetch install.md when they need setup instructions.
---------
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
Changed '怎么配' column from raw pip command to '告诉 Agent「帮我配微信公众号」',
matching the pattern of all other channels. Updated both Chinese and English READMEs.
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
SKILL.md was mixing installation/configuration with usage commands.
Now it's a pure usage guide per skill-creator conventions:
- Description includes ALL platform trigger words (search, read,
browse for each of 13 channels) so agents load it when users
ask to search/read any platform
- Body is concise command reference only — no install/config
instructions (those belong in install.md)
- Removed duplicate workspace rules explanation
- Removed cookie setup, proxy config, and channel setup sections
- 324 → 160 lines (51% reduction in context tokens)
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- English README: added update one-liner in hero section and Quick Start
- update.md: added English version of the one-liner for humans
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
Two subprocess.run(["npm", ...]) calls in undici installation were
using bare command name, which fails on Windows where npm is
installed as npm.cmd. Now resolves full path via shutil.which()
first, consistent with all other subprocess calls.
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
Problem: After installing Agent Reach, agents may clone repos, create
files, or write output into the workspace directory, gradually polluting
the user's project. Over time this degrades the agent experience.
Fix:
- SKILL.md: add Workspace Rules section — never create files in workspace
- install.md: add Directory Rules table, explicit boundary about workspace
- install.md: all git clone commands now target ~/.agent-reach/tools/
- update.md: add workspace warning
- cli.py: install creates ~/.agent-reach/tools/ directory
All agent-facing docs now enforce: /tmp for temp, ~/.agent-reach/ for
persistent data, workspace stays untouched.
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- New docs/update.md for AI agents to follow
- README: add update one-liner next to install one-liner
- Same pattern: copy one line to your agent, it handles the rest
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- wechat channel now supports both search and read
- Search: miku_ai (sogou weixin search) → article list with URLs
- Read: camoufox (stealth Firefox) → full Markdown content
- Doctor shows granular status (search only / read only / both)
- SKILL.md updated with search + read workflow examples
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- Replace text=True with encoding='utf-8', errors='replace' in all
subprocess.run calls (channels + cli.py) to fix GBK decode errors
on Chinese Windows systems
- Use shutil.which() resolved paths in channel subprocess calls to
handle Windows .cmd wrappers (npm global installs)
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
- Remove dead '# ── read ──' placeholder comment in cli.py
- Reword SKILL.md to make it explicit that agent-reach is an
installer/config tool, not a content fetcher
- Addresses confusion from issue #58
Co-authored-by: Panniantong <panniantong@users.noreply.github.com>
When running 'agent-reach configure twitter-cookies', credentials are now
automatically written to ~/.config/xfetch/session.json so that 'xreach auth
check' works without manual intervention.
Preserves existing session.json fields if the file already exists.
Falls back gracefully if the sync fails (still saves to agent-reach config).
Fixes#50
yt-dlp now requires an external JS runtime (deno or Node.js) for YouTube.
Since agent-reach already installs Node.js, we configure yt-dlp to use it:
1. cli.py: install writes '--js-runtimes node' to ~/.config/yt-dlp/config
2. youtube.py: doctor checks JS runtime availability and config
3. SKILL.md: updated YouTube section with accurate troubleshooting
Bilibili note: 412 errors are IP-based (needs proxy), not cookie-related.
Fixes#47
YouTube may trigger 'Sign in to confirm you're not a bot' on server IPs.
Bilibili may return 412 on non-residential IPs.
Added --cookies-from-browser fallback examples for both channels.
Fixes#47
- Detect ARM64 architecture and auto-add --platform linux/amd64 to
docker run hints in doctor/check output
- Add ARM64 FAQ section to setup guide with two options:
Rosetta emulation (--platform linux/amd64) or build from source
- Closes#44
mcporter list probes all configured servers sequentially, which can hang
indefinitely when servers are slow/offline. mcporter config list reads
config without probing — sufficient for checking if a server is configured.
Affected: doctor checks (4 channels) and install command (2 calls).
Fixes#34
Pnant