Commit Graph
2 Commits
Author SHA1 Message Date
Xuanru LiandClaude Opus 5.5 150e1c94d0 fix(cli): report spend usage for Claude plans without rate windows (#5629)
* fix(cli): report spend usage for Claude plans without rate windows

Spend-metered Claude plans (for example Enterprise) return null five_hour
and seven_day windows from the OAuth usage endpoint and put their allowance
in spend / extra_usage instead. The parser rejected every such response as
invalid_usage_response, so `hyperframes usage` always reported unknown.

- Read spend.percent (falling back to extra_usage.utilization) into a new
  `spend` window on known results; over-limit spend caps at fully used.
- Report `no_usage_windows` instead of `invalid_usage_response` when a
  well-formed response simply has no window.
- Document the `spend` field in the hyperframes-cli skill.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(cli): satisfy usage budget comment ratchet

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 02:04:55 +00:00
Miguel Ángel 7348933111 feat(cli): expose harness subscription usage to agents (#4919)
* feat(cli): plan video creation around remaining harness usage

* feat(cli): read Codex and Grok subscription allowances

* test(cli): load usage fixtures through portable file URLs

* test(cli): keep fixture writes on filesystem paths

* refactor(cli): separate usage window and login decisions

* fix(cli): guard parsed credential array entries

* refactor(cli): report harness usage without workflow policy

* fix(cli): preserve usage when subscription tier is null

* test(cli): separate usage fixture code from inputs

* style(cli): format usage transport fixture

* refactor(cli): isolate usage fixture credential checks
2026-10-03 00:25:43 +00:00