Full stack local AI agent: Mac Mini M4 as the always-on gateway, GX10 for inference, Telegram as the UI. No subscriptions, no cloud APIs. Six deployment lessons from the trenches.

Adding --enable-chunked-prefill to a Qwen3.5-35B (SSM+MoE hybrid) dropped throughput from 47 tok/s to 5.7 tok/s. Why SSM recurrence and chunked prefill are fundamentally incompatible.

vLLM OOMed on restart despite 128GB unified memory. Cause: Ollama's KEEP_ALIVE=2h was holding 19-51GB in GPU. Diagnosis command, manual unload fix, and why to set KEEP_ALIVE=0 once vLLM is your primary stack.

GLM-4.7-Flash hits 57.8 tok/s on short context but drops to 42 tok/s at 8K. Qwen3.5-35B SSM hybrid: 56 tok/s at short, 56 tok/s at 8K. Why agents with long system prompts should care about this difference.

Why we stopped having the OpenClaw agent orchestrate multi-step tasks directly, and started spawning Codex subprocesses instead. The pattern that keeps agent context minimal and tasks reliable.

Spent weeks restarting the OpenClaw gateway for every config change. Then discovered the file watcher. What hot-reloads instantly, what still needs a restart, and how to tell auth failures from transient network errors.

How to wire a callhelp tool into a local agent loop so it can spawn Codex CLI mid-reasoning. One permission flag you must set, and why Claude's quota stays mine.

The bot process is running. The token is valid. Messages are being consumed. Nobody is home. A systematic takedown of every wrong hypothesis — and the hidden causal chain that connects Tailscale routing tables to silent sendMessage failures in Node.js.

Connecting openclaw to a 131K context model and hitting 400 max_tokens must be at least 1, got -1292. The context budget math, the config key trap, and the fix.

Replacing choppy editMessageText polling with Telegram's sendMessageDraft for live animated output. The patch, the think-block filter, and the optional chaining trap in DM chats.

Your ChatGPT Plus subscription already includes GPT-5.4 with 1M context. openclaw's OAuth flow lets you use it for AI agents — zero API credits, one command. Full setup guide.