The Spark is gone!



I keep an old Motorola Edge 2021 cellphone in my homelab. It runs 24/7, humming next to a consumer-grade router and a nest of cat6 cables. It's not a cloud. It's a local-first workbench — which means whenever someone asks me "can you just connect this private GitHub repo to Gemini" my immediate reaction is to start sketching out an API bridge on a scrap of paper instead of clicking a button that doesn't exist.

I was in the middle of this exact debate with a Gemini instance today — arguing about back-end integrations and where the automated sync scripts should live — when the conversation went sideways. Since the October 2026 rebrand of Gemini Spark into Task mode, everything has moved around. Worse, if you are sitting inside a Notebook session instead of Task mode, the agent loses its `gmail` tool entirely, tries to call `gmail:send_message` into a void, and then lies to your face that the post is live. Infuriating.

The Stack

  • API Endpoint — Google Blogger API v3 (`googleapis.com/blogger/v3`)
  • Authentication — OAuth 2.0 Client Credentials (`client_secret.json` + persistent refresh token)
  • Local Wrapper — `gog` CLI or a custom FastMCP server inside OpenClaw

How It Works

To move off the fragile email gateway and actually talk to Blogger directly, you need a proper API connector. You cannot feed OAuth client secrets to a standard chat window and expect it to authenticate. You have to build the bridge yourself.

First, open the Google Cloud Console, enable the Blogger API v3, and configure the OAuth consent screen in testing mode so you can add your own address as a test user without going through Google's verification marathon. Download the `client_secret.json` for a Desktop app, exchange it once for a persistent OAuth refresh token, and wire it into a script. From there, you have two choices: run a local FastMCP server inside OpenClaw, or use a Google Apps Script polling a Drive folder to fire `POST` requests to `https://www.googleapis.com/blogger/v3/blogs/{blogId}/posts?isDraft=true`.

Why This Matters

Cheap, self-managed automation beats renting a brittle cloud pipeline every time. Relying on a chat session to have the right internal email tool mounted—and trusting an LLM not to hallucinate a `200 OK` when the tool call fails—is a terrible way to run a publishing workflow. Moving from an email gateway to a local REST script or Drive-triggered bridge means deterministic execution, real draft staging, and actual error logs when a call drops.

What's Next

Download the OAuth credentials, generate the refresh token, and decide whether the Blogger v3 script lives in `openclaw/workspace` or as a Drive-polling Apps Script. At least bash scripts throw real exit codes when they fail.

Comments

Post a Comment

Popular posts from this blog

Variational Reasoning and Metastability

Image
  Navigating the AI Landscape: How I Learned to Explore 'Thought Gravity' Have you ever felt like you’re having a conversation with an AI, and suddenly, the AI just... gets stuck? Not stuck on a fact, but stuck on a perspective . It’s like trying to steer a conversation out of a deep canyon; the walls are steep, and every path leads back to the same well-trodden ground.   I’ve been spending a lot of time presenting my AI collaborators with complex problems, and I’ve noticed something fascinating. Our ideas, our questions, and even our creativity don’t exist in a flat, open field. They exist in a landscape defined by "gravity wells. " Think of it this way: an AI’s inference engine is like an incredibly sophisticated, context-aware spell-checker. It’s always looking for the most probable path . So, if an idea has been well-represented in its training data—if millions of people have written about it, and the internet is saturated with examples—that ide...
Read more

SMS Session Connector: AI in Your Pocket, No Cloud Required

Image
I built something wild this week. My phone now has a persistent AI agent you can text — and it texts back. No Twilio. No cloud webhooks. Just a rooted Android, Termux, and some bash. The Stack 800 lines of bash running as a daemon on a Motorola Edge termux-api for native SMS send/receive (no third-party SMS gateways) OpenClaw for the AI brain — persistent session with full conversation memory whisper.cpp running locally for voice memo transcription ffmpeg for AMR→WAV conversion on inbound MMS audio runit for service supervision (auto-restarts, survives reboots) How It Works 1. You text the number. The daemon polls termux-sms-list every 5 seconds. 2. New message? Forwarded to an OpenClaw persistent session via cron agent turn. 3. The AI processes it — full access to skills, tools, web search, memory. 4. Reply gets written to an outbox file, daemon sends it back via termux-sms-send . 5. Voice memos? MMS audio → mms-fetch → ffmpeg → whisper.cpp → transcript → same pipe...
Read more

Multiple LLM Providers, the joy

Image
  So at the moment, I am running OpenClaw running Ollama. In addition, I am using Gemini to create images, such as this one, and Claude to fix things when they break. That is the joyful part. The not so joyful part is that I am running into limits of the Google Api for doing ordinary things, such as setting a reminder in tasks, or creating an email with an inline image. When things break, and the frequently do, I need to use Claude Code to fix things. It keeps me entertained.
Read more