What's Changed
- Redesigned the
capacitycommand output into a single per-quota table with usage bars, threshold colors, humanized reset times (in 4h 40m · 20:25), andused/totalamounts instead of duplicated window summaries with truncated ISO timestamps. (3c65af7) - Split capacity identity into harness and provider (
codex | OpenAI,pi | z.ai) via a newharnessfield onCapacityReport; the Codex probe now reportsprovider: "openai". (3c65af7) ai-devkit capacitywithout arguments now probes every supported provider and renders one Harness/Provider/Status table;--jsonemits a single object for one provider and an array for many, and per-provider probe failures warn instead of aborting the whole listing. (3c65af7)- Added global z.ai usage limits to
ai-devkit capacitythrough a newgetZaiCapacityReportprobe in@ai-devkit/agent-manager0.34.0 (pinned in this release). (4ea4868) - Added shared UI formatting utilities (pluralization, status labels, time formatting) reused across CLI commands. (#243)
- Clarified agent list and detail rendering. (#245)
- Polished channel status rendering. (#246)
- Aligned status output with the visible checks. (#244)
- Refreshed lint human output. (#247)
- Aligned skill result rendering. (#248)
- Capitalized memory
--tableheaders and shortened the UUID column. (#242) - Standardized flow success output. (#249)
- Moved the opencode adapter into the agent-manager provider structure with no public API changes via
@ai-devkit/agent-manager0.34.0. (f34a9a3)
Full Changelog: https://github.com/codeaholicguy/ai-devkit/compare/cli@0.61.0...cli@0.63.0