feat: support zcode (智谱 AI coding CLI) as a data source #1382
Description
Activity
This issue was auto-closed. Issues from new contributors are auto-closed by default.
Maintainers review auto-closed issues and reopen worthwhile ones. Issues that do not meet the quality bar in CONTRIBUTING.md may not be reopened or receive a reply.
Keep the issue short, concrete, and written in your own voice.
If a maintainer replies
lgtmi, your future issues will stay open. If a maintainer replieslgtm, your future issues and PRs will stay open.See CONTRIBUTING.md.
+1 — I'd also like zcode support. I use zcode (智谱 AI) alongside Claude Code and Codex, and tracking all three in one report would be very useful.
@lengmodkx git pull #1675
Historical audit: this discussion was auto-closed by the legacy contributor gate. That closure did not assess technical importance.
Audit result: resolved. A later merged change or the current
mainimplementation covers this request. This item is kept for history and does not need to be reopened.
Feature Request
Please add support for zcode (智谱 AI coding CLI) as a data source.
Background
智谱 AI (https://open.bigmodel.cn/) provides a Claude Code-compatible CLI called zcode that uses their own models (GLM-4.6, GLM-4.7, etc.) via the Anthropic-compatible API. zcode generates conversation transcripts and token usage data locally, similar to Claude Code.
Expected Behavior
ccusage should be able to read zcode usage data:
And ideally auto-detect it in combined reports.
Use Case
Users in China increasingly use 智谱 AI models through the zcode CLI. Tracking token usage and costs across both Claude Code and zcode in one tool would be very valuable.
Additional Context