reviewer-output — Reviewer agent contract

The uniform output contract every reviewer agent dispatched by the xema/review primitive must produce. The review workflow injects this deliverableSpecRef into every agent invocation it dispatches (mandatory or advisory), and the existing harvest path validates against it. A schema violation surfaces as abstain to the gate — never as silent acceptance.

When this spec applies

  • Every recipient of kind agent inside a xema/review reviewer pool. The review workflow appends deliverableSpecRef: reviewer-output to the agent invocation regardless of which agent slug is used. Any agent that can produce this shape can serve as a reviewer.
  • It does not apply to:
    • Direct xema/decision-gate recipients (those use decision-gate-reply reply schemas).
    • Workflow recipients (kind: workflow — they map outputs through verdictMapper, not through this spec).
    • Endpoint recipients (verdict mapping happens in verdictMapper).
  • It does not gate human reviewers — humans submit verdicts through the Tasks UI and never write a deliverable.

Schema

schema.zod.ts (canonical):

ts
1const ReviewerFindingSeveritySchema = z.enum([
2  'critical', 'major', 'minor', 'info',
3]);
4
5const ReviewerFindingSchema = z.object({
6  severity: ReviewerFindingSeveritySchema,
7  area: z.string().min(1),
8  message: z.string().min(1),
9});
10
11const ReviewerVerdictSchema = z.enum(['approve', 'reject', 'abstain']);
12
13const ReviewerAgentOutputSchema = z.object({
14  verdict: ReviewerVerdictSchema,
15  summary: z.string().min(1),
16  findings: z.array(ReviewerFindingSchema),
17  suggestedEdits: z.array(z.string().min(1)).optional(),
18});

Field semantics

FieldRequiredNotes
verdictyesClosed set: approve (vote yes), reject (vote no), abstain (no opinion). Subject to the recipient's mandatory bit on the gate.
summaryyesSingle-paragraph rationale. Surfaces in the human reviewer's findings panel and in the per-iteration trail.
findingsyes (may be empty)Structured issues. area is open-ended (e.g. "security", "naming", "performance") — the contract does not impose a closed taxonomy.
suggestedEditsoptionalConcrete change suggestions surfaced to the next-iteration drafter as priorReviewerFeedback / pastIterations[].reviewerVerdicts.

Verdict semantics under xema/review

  • approve and reject count toward policy resolution iff the recipient is mandatory: true. Advisory recipients still emit them but don't gate.
  • abstain is a non-vote. The review workflow records it but never short-circuits on it.
  • Repeated reject from an agent is what drives the loop's agentMaxIterations demotion; abstain does not count toward that threshold.

Why this is a kernel-tier spec

xema/review is a first-party platform primitive — every install that ever uses review needs this contract. It therefore ships in the kernel runtime biome, alongside the other always-on baseline content. Biomes are free to introduce richer review contracts for their own actions, but those are biome concerns, not platform ones.

The kernel runtime biome

The runtime biome is the baseline every agent workspace extends from. It is mandatory: the biome host refuses to start unless it resolves, so it is present on every installation.

ContentWhat ships
Deliverable specreviewer-output, described on this page.
Workspace manifestsFour base manifests that other manifests inherit from: primary-agent-base (coordinators and leads), agent-session-base (interactive chat sessions), subagent-base (sub-agents) and reviewer-base. Inputs and references mount read-only. Deliverables are read-write for the primary, session and sub-agent bases. For reviewers the whole workspace is read-only, so findings leave through dedicated review activities, never as workspace writes. Sub-agents see no end-user uploads.
Role capabilitiesNine roles: agent-session, generic-agent, coordinator, clarification-coordinator, unit-worker, scope-validator, auditor, document and gate-reviewer. A gate reviewer, for example, may write only its own pages and may never edit repositories or write to the knowledge base.
SkillsThirteen baseline skills: building agents, compositions, skills and tools; deep-research and web-research; browser-navigate-scrape; document-pdf-to-markdown; media-transcribe-audio; chat-widgets; deliverable-contract (how an agent reads its contract); declare-output-surface; and scratch-workspace.
MCP catalogTool entries for the services the base ships: knowledge, artifact, project, rules, catalog, audit and the organization-database explorer. A product biome adds the entries for its own services.

The roster of platform agents that use this baseline is on the Subagents page.