.github/labels.conf

@@ -1,4 +1,4 @@
-panel=codex-reviewer-andresmgsl glm-reviewer-andresmgsl cluade-reviewer-andresmgsl
+panel=codex-reviewer-andresmgsl glm-reviewer-andresmgsl cluade-reviewer-andresmgsl kimi-reviewer-andresmgsl
 triage-actors=cluade-reviewer-andresmgsl
 scope:release-flow|C5DEF5|The reusable release workflow, decide, the doors
 scope:guards|C5DEF5|changelog-armed / changelog-monotonic / drill-recorded

CONTRIBUTING.md

@@ -41,7 +41,7 @@ only ceremony-specific facts such as the roster and code conventions.
 
 ### Roster
 
-Three identities share the work (org team `agents`), each living in its own
+Four identities share the work (org team `agents`), each living in its own
 [box](https://github.com/heavy-duty/box) — one box per credential, because
 the box is the blast-radius boundary; roles are what a session is told, and
 [AGENTS.md](AGENTS.md) routes from there:
@@ -51,13 +51,14 @@ the box is the blast-radius boundary; roles are what a session is told, and
 | `cluade-reviewer-andresmgsl` | `triage` (claude-box) | **triage** — the only door issues come through; this identity mints issues and nothing else writes them (#18's `triage-actors`) — and review. It does not build. |
 | `codex-reviewer-andresmgsl` | codex-box | build + review |
 | `glm-reviewer-andresmgsl` | glm-box | review |
+| `kimi-reviewer-andresmgsl` | kimi-box | review |
 
 **The review panel for any PR is every bench identity except its author** —
 recusal by construction, enforced by the reconciler (#10): the required
 verdicts are the panel minus the PR's author. On this roster that resolves
-to **two** cross-vendor approvals of the current head, because the only
+to **three** cross-vendor approvals of the current head, because the only
 builder is itself on the panel and recuses from its own PRs; the rule is
-panel-minus-author, and two is what it currently comes to, not a second
+panel-minus-author, and three is what it currently comes to, not a second
 rule. Builders and triage default to different models so the issue contract
 is honestly exercised — a spec gap should surface as a question on the
 issue, not be silently filled by shared priors. Humans (`andres`) decide in

changelog.d/224.md

@@ -0,0 +1,5 @@
+### Changed
+
+- The review panel restores `kimi-reviewer-andresmgsl` alongside GLM. The
+  four-identity panel now requires three cross-vendor approvals after the PR
+  author recuses (#224).