mara/hyperhive
mara/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

docs: the failures-only setting says the unsure rows are left out too

Browse source
This commit is contained in:
iris 2026-11-11 01:00:22 +01:00 • committed by mara
commit eaafe31e66
2 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/2-handbook/swarm/ui.md
View file

@ -299,7 +299,7 @@ The **classifier settings** section shows the runtime, model and
effort the [review classifier](../../4-implementation/swarm/review-classifier.md) runs with and how many effort the [review classifier](../../4-implementation/swarm/review-classifier.md) runs with and how many
requested reviews run at once, and lets you change them. The **PR reviews list requested reviews run at once, and lets you change them. The **PR reviews list
only failed rules** checkbox makes the review the classifier posts on a PR leave only failed rules** checkbox makes the review the classifier posts on a PR leave
out the rules that passed or didn't apply; try-outs always show every rule. The out the rules that passed, didn't apply or were below their threshold; try-outs always show every rule. The
runtime is **API runtime is **API
key** (claude on the Anthropic key) or **ACP** (opencode on a provider). On the key** (claude on the Anthropic key) or **ACP** (opencode on a provider). On the
API key runtime the model is free text, one word as claude's `--model` takes API key runtime the model is free text, one word as claude's `--model` takes

3
docs/4-implementation/swarm/review-classifier.md
View file

@ -241,7 +241,8 @@ replaces it.
answer for as long as the biggest run the limit allows answer for as long as the biggest run the limit allows
- `failures_only`: a boolean, `false` by default (also for a document stored - `failures_only`: a boolean, `false` by default (also for a document stored
before the field existed). When `true`, a posted PR review lists only the before the field existed). When `true`, a posted PR review lists only the
rows that failed their rule, the ones that make it ask for changes, and an rows that failed their rule, the ones that make it ask for changes, so the ❔
rows (below their threshold, or unsure) are left out too, and an
approval says `No check failed.` in place of the table. A review with no approval says `No check failed.` in place of the table. A review with no
verdict, and a try-out, always show every row verdict, and a try-out, always show every row
- `runtime`: `api-key` or `acp` (see [Runtimes](#runtimes)) - `runtime`: `api-key` or `acp` (see [Runtimes](#runtimes))