skip to content- 2026-10-15
|
ZCode’s workspace uploads: what was observed and what changed
The reported ZCode workspace uploads, dated fixes, source and binary limits, and six questions to ask before giving an AI coding tool repository access.
- 2026-07-26
|
Prompt Caching: Cut AI Agent Token Costs
See how subagent caches, approval pauses and resumed sessions change API costs, with an eight-minute timeline and a 100K-token cost comparison.
- 2026-07-02
|
Pi Coding Agent: Minimal, Programmable Terminal Harness
Set up Pi as a minimal coding harness with GLM-5.2, persistent sessions, compaction, custom tools, extensions, and clear Z.AI policy caveats.
- 2026-07-02
|
Pi vs ZCode vs OpenCode: Which Harness Fits GLM-5.2?
Compare Pi, ZCode, and OpenCode as coding harnesses for GLM-5.2: workflow, permissions, context, setup, quota paths, and a fair same-model test.
- 2026-07-02
|
ZCode: GLM-5.2-Native Coding Harness Guide
Use ZCode as Z.AI's integrated GLM-5.2 coding harness: desktop setup, Goal Mode, subagents, safety confirmations, quota, and workflow trade-offs.
- 2026-02-03
|
Verify Codex Token-Usage and Caching Claims
A dated verification ledger for Codex token usage, prompt caching, compaction rereads, OpenCode comparisons, usage incidents, and reset claims.
- 2026-02-01
|
OpenCode: Providers, Zen, Permissions, and GLM-5.2
OpenCode setup, public free-model access, the temporary DeepSeek V4.1 Flash Free offer, paid Console and Go routes, permissions, sharing and provider privacy.