WeChat on Margrop Blog

Why HermesAgent Would Not Reply in WeChat or WeCom: The Real Culprit Was a Local Relay With a 3-Second Timeout

Sun, 31 May 2026 08:00:00 +0800

The short version This incident looked like a model problem or a broken messaging channel, but the real failure happened one layer lower: my local relay cut the upstream request off after 3 seconds. That was fine for quick health checks, but it was wrong for real WeChat and WeCom turns, which often take longer to produce a complete answer from the NewAPI gateway. Once the relay disconnected too early, HermesAgent could only see Connection error, RemoteProtocolError, and then exhausted fallback attempts.

Why My AI Assistant Repeated One Reply Four Times: Debugging an OpenClaw WeChat Channel Issue

Fri, 29 May 2026 11:24:29 +0800

Short version

The symptom looked like a messaging-channel bug: an AI assistant connected to a personal chat channel appeared to repeat the same reply multiple times. The real bug was earlier in the chain. Before the reply ever reached the message-sending layer, the OpenClaw agent had already produced duplicated visible text. The useful fix was not to patch the chat sender blindly, but to split the path into transport, session, model-routing, and provider layers, then compare the OpenAI-compatible gateway path with the native provider path. Once the faulty compatible provider candidate was removed from the visible model set and the personal IM channel was pinned to the native provider, the same minimal prompt returned exactly once.

This post is deliberately privacy-safe. It contains no real internal addresses, account IDs, tokens, session IDs, personal chat identifiers, or private file paths. Configuration examples use placeholders. The value is the debugging method, not the private environment.

How to Prompt OpenClaw, HermesAgent, Codex, Claude, Gemini, OpenCode, and Droid to Write Articles and Publish WeChat Drafts

Tue, 05 May 2026 16:00:00 +0800

Short version

If you want an agent such as OpenClaw, HermesAgent, Codex, Claude, Gemini, OpenCode, or Droid to write an article, prepare a Hugo blog post, convert the Chinese version into WeChat-compatible HTML, preview it, fix layout issues, and create a WeChat Official Account draft, the prompt cannot simply say “write and publish an article.” A useful prompt must define the goal, source material, paths, account constraints, fixed-IP requirements, conversion steps, preview checks, failure recovery, privacy boundaries, and final verification evidence.

This post describes a reusable prompting pattern for article automation. It explains how to prepare the WeChat draft API, why a Linux machine with a fixed public IP is often required, how to tell an agent to try local API access first and then fall back to a fixed-egress host, how to use a Markdown-to-WeChat-HTML converter, and how to make the agent check for invisible white text, strange indentation, broken images, and accidental leaks before declaring the job done.

All examples are privacy-safe. They use placeholders rather than real secrets, private IP addresses, hostnames, repository URLs, tokens, cookies, or personal paths. Replace placeholders with your own values only in a protected runtime environment, never in a public article, public repository, or screenshot.

[Repost] Google Cloud Free VM, 2-core 1 GB RAM, 30 GB disk, 200 GB traffic/month

Mon, 20 Apr 2026 08:28:00 +0800

[Repost] Google Cloud Free VM, 2-core 1 GB RAM, 30 GB disk, 200 GB traffic/month

I have introduced several free cloud servers before. In fact, the three major overseas cloud providers (Google, Amazon, and Microsoft) all have free tiers. The latter two are time-limited and not very interesting. In addition to a three-month trial of regular-priced machines, Google also offers a permanent free server.It comes with 2 cores, 1 GB of memory, 30 GB of disk, and 200 GB of traffic per month. That is still enough to play around with.

I. Google Cloud Trial & Free

Google Cloud, as the name suggests, is a cloud server made by Google. The current Google Cloud trial is only three months, and the quota seems to be 300 US dollars. If you buy a regular-price machine, it will be used up all at once, so it is better to use a free server.

This article does not involve Google Cloud registration and trial use. Anyone with a Google account can register for this thing. It is not difficult. Moreover, I registered it several years ago. I don’t remember the specific details. If you don’t know, you can Google it yourself. Even if the new account is still on trial, it will not affect the trial of the free instance in this article.

Mainly Google Cloud’s free servers. Google Cloud has given free quotas to corresponding regions.Oregon, Iowa, South Carolinae2-micro instance, 2-core CPU + 1g memory + 30g hard disk, with public network IPv4, 200g traffic per month. This traffic is not limited to regions. Some people will say that the picture does not say "1 per month" GB outbound traffic?" Yes, first of all, Google Cloud only counts outbound traffic, not two-way traffic. Secondly, the free 1g traffic in the picture is "advanced tier", not "standard tier" traffic. The advanced tier is a little better than the standard tier network quality, of course, it is only a little better (although it was not before), and the standard tier is global 200g traffic.

WeChat Old Version Installation Method - Version Too Low, Please Upgrade to the Latest Version

Fri, 05 Mar 2021 11:22:11 +0800

First install the latest version of WeChat and log in.

Uninstall the app using the cmd command while preserving user data:

adb shell pm uninstall -k com.tencent.mm

Restart your phone

adb root

This step is very important, otherwise you will get an error message adb: failed to install xxxxxx Failure [INSTALL_FAILED_VERSION_DOWNGRADE]

Install the old version APK using the cmd command (followed by the installation package path):

adb install -r -d

Log into your WeChat account on the old version.