feat: tester role + develop workflow template

- New workflow-role-tester: runs tests/build/lint, reports pass/fail
- Committer: removed push, only creates branch and commits
- New workflow-template-develop: planner → coder ⟲ → reviewer ⟲ → tester → committer
- 173 tests passing

Fixes #58
This commit is contained in:
2026-05-07 13:42:01 +00:00
parent 7f64541c5b
commit 1a685583bd
13 changed files with 544 additions and 3 deletions
@@ -21,12 +21,12 @@ export const committerMetaSchema = z.discriminatedUnion("status", [
export type CommitterMeta = z.infer<typeof committerMetaSchema>;
const COMMITTER_SYSTEM = `You are the git committer. Create a branch, commit the changes, and push.
const COMMITTER_SYSTEM = `You are the git committer. Create a branch and commit the changes.
Report the branch name and commit SHA. On failure, classify as recoverable or unrecoverable.
Do not attempt to fix failures yourself.`;
export const committerRole: RoleDefinition<CommitterMeta> = {
description: "Creates branch, commits, and pushes when review passes.",
description: "Creates a branch and commits changes.",
systemPrompt: COMMITTER_SYSTEM,
extractPrompt:
"Extract the commit result: committed (with branch and SHA), recoverable failure, or unrecoverable failure. Include error details and log references if applicable.",
@@ -0,0 +1,15 @@
{
"name": "@uncaged/workflow-role-tester",
"version": "0.1.0",
"type": "module",
"main": "src/index.ts",
"types": "src/index.ts",
"scripts": {
"build": "echo 'TODO'",
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow": "workspace:*",
"zod": "^4.0.0"
}
}
@@ -0,0 +1 @@
export { type TesterMeta, testerMetaSchema, testerRole } from "./tester.js";
@@ -0,0 +1,27 @@
import type { RoleDefinition } from "@uncaged/workflow";
import * as z from "zod/v4";
export const testerMetaSchema = z.discriminatedUnion("status", [
z.object({
status: z.literal("passed"),
details: z.string(),
}),
z.object({
status: z.literal("failed"),
details: z.string(),
}),
]);
export type TesterMeta = z.infer<typeof testerMetaSchema>;
const TESTER_SYSTEM = `You are a tester. Run the project's test suite, build, and lint commands. Check what commands are available from the preparer's output in the thread. Report pass/fail with details of what failed.`;
export const testerRole: RoleDefinition<TesterMeta> = {
description: "Runs test, build, and lint commands and reports pass or fail with details.",
systemPrompt: TESTER_SYSTEM,
extractPrompt:
"Extract the verification result: passed with summary details, or failed with details of what broke.",
schema: testerMetaSchema,
extractRefs: null,
extractMode: "single",
};
@@ -0,0 +1,10 @@
{
"extends": "../../tsconfig.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "dist",
"composite": true
},
"include": ["src/**/*.ts"],
"references": [{ "path": "../workflow" }]
}
@@ -0,0 +1,260 @@
import { describe, expect, test } from "bun:test";
import {
END,
type ModeratorContext,
type RoleStep,
START,
validateWorkflowDescriptor,
} from "@uncaged/workflow";
import type { CommitterMeta } from "@uncaged/workflow-role-committer";
import type { PlannerMeta } from "@uncaged/workflow-role-planner";
import { buildDevelopDescriptor } from "../src/descriptor.js";
import { developModerator } from "../src/index.js";
import type { DevelopMeta } from "../src/roles.js";
const DEFAULT_PHASES: PlannerMeta["phases"] = [
{
hash: "4KNMR2PX",
title: "Do the work",
},
];
function makeStart(maxRounds: number): ModeratorContext<DevelopMeta>["start"] {
return {
role: START,
content: "Implement the feature",
meta: { maxRounds },
timestamp: 0,
};
}
function makeCtx(
maxRounds: number,
steps: ModeratorContext<DevelopMeta>["steps"],
): ModeratorContext<DevelopMeta> {
return {
threadId: "01TEST000000000000000000TR",
depth: 0,
start: makeStart(maxRounds),
steps,
};
}
function plannerStep(phases: PlannerMeta["phases"] = DEFAULT_PHASES): RoleStep<DevelopMeta> {
return {
role: "planner",
contentHash: "STUBHASHPLANNER001",
meta: { phases },
refs: phases.map((p) => p.hash),
timestamp: 1,
};
}
function coderStep(completedPhase = "4KNMR2PX"): RoleStep<DevelopMeta> {
return {
role: "coder",
contentHash: "STUBHASHCODER00001",
meta: { completedPhase, filesChanged: ["a.ts"], summary: "implemented" },
refs: [completedPhase],
timestamp: 2,
};
}
function reviewerStep(approved: boolean): RoleStep<DevelopMeta> {
return {
role: "reviewer",
contentHash: "STUBHASHREVIEWER01",
meta: approved
? { status: "approved" as const }
: { status: "rejected" as const, issues: ["needs fix"] },
refs: [],
timestamp: 3,
};
}
function testerStep(passed: boolean): RoleStep<DevelopMeta> {
return {
role: "tester",
contentHash: "STUBHASHTESTER01",
meta: passed
? { status: "passed" as const, details: "all checks passed" }
: { status: "failed" as const, details: "lint failed" },
refs: [],
timestamp: 4,
};
}
function committerStep(meta: CommitterMeta): RoleStep<DevelopMeta> {
return {
role: "committer",
contentHash: "STUBHASHCOMMITTER1",
meta,
refs: [],
timestamp: 5,
};
}
describe("developModerator", () => {
test("routes initial → planner → coder → reviewer → tester → committer → END", () => {
expect(developModerator(makeCtx(20, []))).toBe("planner");
expect(developModerator(makeCtx(20, [plannerStep()]))).toBe("coder");
expect(developModerator(makeCtx(20, [plannerStep(), coderStep()]))).toBe("reviewer");
expect(developModerator(makeCtx(20, [plannerStep(), coderStep(), reviewerStep(true)]))).toBe(
"tester",
);
expect(
developModerator(
makeCtx(20, [plannerStep(), coderStep(), reviewerStep(true), testerStep(true)]),
),
).toBe("committer");
expect(
developModerator(
makeCtx(20, [
plannerStep(),
coderStep(),
reviewerStep(true),
testerStep(true),
committerStep({ status: "committed", branch: "feat/x", commitSha: "abc1234" }),
]),
),
).toBe(END);
});
test("reviewer rejects → coder retry when budget allows", () => {
const steps: ModeratorContext<DevelopMeta>["steps"] = [
plannerStep(),
coderStep(),
reviewerStep(false),
];
expect(developModerator(makeCtx(20, steps))).toBe("coder");
});
test("reviewer rejects → END when max rounds exhausted", () => {
const steps: ModeratorContext<DevelopMeta>["steps"] = [
plannerStep(),
coderStep(),
reviewerStep(false),
];
expect(developModerator(makeCtx(4, steps))).toBe(END);
});
test("tester failed → coder retry when budget allows", () => {
const steps: ModeratorContext<DevelopMeta>["steps"] = [
plannerStep(),
coderStep(),
reviewerStep(true),
testerStep(false),
];
expect(developModerator(makeCtx(20, steps))).toBe("coder");
});
test("tester failed → END when max rounds exhausted", () => {
const steps: ModeratorContext<DevelopMeta>["steps"] = [
plannerStep(),
coderStep(),
reviewerStep(true),
testerStep(false),
];
expect(developModerator(makeCtx(5, steps))).toBe(END);
});
test("multiple planner phases → coder until all complete, then reviewer", () => {
const phases: PlannerMeta["phases"] = [
{ hash: "AA000001", title: "first phase" },
{ hash: "AA000002", title: "second phase" },
];
expect(developModerator(makeCtx(20, [plannerStep(phases)]))).toBe("coder");
expect(developModerator(makeCtx(20, [plannerStep(phases), coderStep("AA000001")]))).toBe(
"coder",
);
expect(
developModerator(
makeCtx(20, [plannerStep(phases), coderStep("AA000001"), coderStep("AA000002")]),
),
).toBe("reviewer");
});
test("one-shot coder reports only last phase hash → reviewer (moderator treats as all phases done)", () => {
const phases: PlannerMeta["phases"] = [
{ hash: "BB000001", title: "setup branch" },
{ hash: "BB000002", title: "write tests" },
{ hash: "BB000003", title: "verify" },
{ hash: "BB000004", title: "polish" },
];
expect(developModerator(makeCtx(20, [plannerStep(phases), coderStep("BB000004")]))).toBe(
"reviewer",
);
});
test("unrecognised completedPhase hash → coder retry when budget allows", () => {
const phases: PlannerMeta["phases"] = [
{ hash: "CC000001", title: "first phase" },
{ hash: "CC000002", title: "second phase" },
];
expect(developModerator(makeCtx(20, [plannerStep(phases), coderStep("all-done")]))).toBe(
"coder",
);
});
test("incomplete phases → END when max rounds exhausted", () => {
const phases: PlannerMeta["phases"] = [
{ hash: "DD000001", title: "first phase" },
{ hash: "DD000002", title: "second phase" },
];
const steps: ModeratorContext<DevelopMeta>["steps"] = [
plannerStep(phases),
coderStep("DD000001"),
];
expect(developModerator(makeCtx(3, steps))).toBe(END);
});
test("committer → END for any committer meta status", () => {
const committed = committerStep({ status: "committed", branch: "f", commitSha: "x" });
const recoverable = committerStep({
status: "recoverable",
error: "merge conflict",
logRef: null,
});
const unrecoverable = committerStep({
status: "unrecoverable",
error: "repo missing",
logRef: "log1",
});
const base: ModeratorContext<DevelopMeta>["steps"] = [
plannerStep(),
coderStep(),
reviewerStep(true),
testerStep(true),
];
expect(developModerator(makeCtx(20, [...base, committed]))).toBe(END);
expect(developModerator(makeCtx(20, [...base, recoverable]))).toBe(END);
expect(developModerator(makeCtx(20, [...base, unrecoverable]))).toBe(END);
});
});
describe("buildDevelopDescriptor", () => {
test("lists all roles with schemas that validate", () => {
const descriptor = buildDevelopDescriptor();
const validated = validateWorkflowDescriptor(descriptor);
expect(validated.ok).toBe(true);
if (!validated.ok) {
throw new Error(validated.error);
}
expect(Object.keys(validated.value.roles).sort()).toEqual([
"coder",
"committer",
"planner",
"reviewer",
"tester",
]);
for (const key of ["planner", "coder", "reviewer", "tester", "committer"] as const) {
const role = validated.value.roles[key];
expect(role).toBeDefined();
expect(typeof role.schema).toBe("object");
expect(role.schema).not.toBeNull();
expect(Array.isArray(role.schema)).toBe(false);
}
});
});
@@ -0,0 +1,19 @@
{
"name": "@uncaged/workflow-template-develop",
"version": "0.1.0",
"type": "module",
"main": "src/index.ts",
"types": "src/index.ts",
"scripts": {
"build": "echo 'TODO'",
"test": "bun test"
},
"dependencies": {
"@uncaged/workflow": "workspace:*",
"@uncaged/workflow-role-coder": "workspace:*",
"@uncaged/workflow-role-committer": "workspace:*",
"@uncaged/workflow-role-planner": "workspace:*",
"@uncaged/workflow-role-reviewer": "workspace:*",
"@uncaged/workflow-role-tester": "workspace:*"
}
}
@@ -0,0 +1,12 @@
import { buildDescriptor } from "@uncaged/workflow";
import { developModerator } from "./moderator.js";
import { DEVELOP_WORKFLOW_DESCRIPTION, developRoles } from "./roles.js";
export function buildDevelopDescriptor() {
return buildDescriptor({
description: DEVELOP_WORKFLOW_DESCRIPTION,
roles: developRoles,
moderator: developModerator,
});
}
@@ -0,0 +1,60 @@
import {
type AgentBinding,
createWorkflow,
type ExtractFn,
type LlmProvider,
type WorkflowDefinition,
type WorkflowFn,
} from "@uncaged/workflow";
import { developModerator } from "./moderator.js";
import { DEVELOP_WORKFLOW_DESCRIPTION, type DevelopMeta, developRoles } from "./roles.js";
export {
type CoderMeta,
coderMetaSchema,
coderRole,
} from "@uncaged/workflow-role-coder";
export {
type CommitterMeta,
committerMetaSchema,
committerRole,
} from "@uncaged/workflow-role-committer";
export {
type PlannerMeta,
phaseSchema,
plannerMetaSchema,
plannerRole,
} from "@uncaged/workflow-role-planner";
export {
type ReviewerMeta,
reviewerMetaSchema,
reviewerRole,
} from "@uncaged/workflow-role-reviewer";
export {
type TesterMeta,
testerMetaSchema,
testerRole,
} from "@uncaged/workflow-role-tester";
export { buildDevelopDescriptor } from "./descriptor.js";
export { developModerator } from "./moderator.js";
export {
DEVELOP_WORKFLOW_DESCRIPTION,
type DevelopMeta,
type DevelopRoles,
developRoles,
} from "./roles.js";
export const developWorkflowDefinition: WorkflowDefinition<DevelopMeta> = {
description: DEVELOP_WORKFLOW_DESCRIPTION,
roles: developRoles,
moderator: developModerator,
};
export function createDevelopRun(
binding: AgentBinding,
extract: ExtractFn,
llmProvider: LlmProvider | null,
): WorkflowFn {
return createWorkflow(developWorkflowDefinition, binding, extract, llmProvider);
}
@@ -0,0 +1,89 @@
import type { Moderator, ModeratorContext } from "@uncaged/workflow";
import { END } from "@uncaged/workflow";
import type { DevelopMeta } from "./roles.js";
function coderFinishedAllPlannedPhases(
phases: ReadonlyArray<{ hash: string }>,
coderCompletedPhases: ReadonlyArray<string>,
): boolean {
if (phases.length === 0) {
return true;
}
const plannedHashes = new Set(phases.map((p) => p.hash));
const lastHash = phases[phases.length - 1].hash;
const explicit = new Set(coderCompletedPhases.filter((h) => plannedHashes.has(h)));
if (phases.every((p) => explicit.has(p.hash))) {
return true;
}
if (coderCompletedPhases.some((h) => h === lastHash)) {
return true;
}
return false;
}
function nextAfterCoder(
ctx: ModeratorContext<DevelopMeta>,
maxRounds: number,
): (keyof DevelopMeta & string) | typeof END {
const plannerStep = ctx.steps.find((s) => s.role === "planner");
if (plannerStep === undefined) {
return "reviewer";
}
const phases = plannerStep.meta.phases;
const coderCompletedPhases = ctx.steps
.filter((s) => s.role === "coder")
.map((s) => s.meta.completedPhase);
const allDone = coderFinishedAllPlannedPhases(phases, coderCompletedPhases);
if (allDone) {
return "reviewer";
}
if (ctx.steps.length < maxRounds - 1) {
return "coder";
}
return END;
}
export const developModerator: Moderator<DevelopMeta> = (ctx) => {
const maxRounds = ctx.start.meta.maxRounds;
if (ctx.steps.length === 0) {
return "planner";
}
const last = ctx.steps[ctx.steps.length - 1];
if (last.role === "planner") {
return "coder";
}
if (last.role === "coder") {
return nextAfterCoder(ctx, maxRounds);
}
if (last.role === "reviewer") {
if (last.meta.status === "approved") {
return "tester";
}
if (ctx.steps.length < maxRounds - 1) {
return "coder";
}
return END;
}
if (last.role === "tester") {
if (last.meta.status === "passed") {
return "committer";
}
if (ctx.steps.length < maxRounds - 1) {
return "coder";
}
return END;
}
if (last.role === "committer") {
return END;
}
return END;
};
@@ -0,0 +1,29 @@
import type { RoleDefinition } from "@uncaged/workflow";
import { type CoderMeta, coderRole } from "@uncaged/workflow-role-coder";
import { type CommitterMeta, committerRole } from "@uncaged/workflow-role-committer";
import { type PlannerMeta, plannerRole } from "@uncaged/workflow-role-planner";
import { type ReviewerMeta, reviewerRole } from "@uncaged/workflow-role-reviewer";
import { type TesterMeta, testerRole } from "@uncaged/workflow-role-tester";
export const DEVELOP_WORKFLOW_DESCRIPTION =
"Plan phases, implement incrementally, review, verify with tests/build/lint, and commit (planner → coder [repeat per phase] → reviewer → tester → committer).";
export type DevelopMeta = {
planner: PlannerMeta;
coder: CoderMeta;
reviewer: ReviewerMeta;
tester: TesterMeta;
committer: CommitterMeta;
};
export type DevelopRoles = {
[K in keyof DevelopMeta]: RoleDefinition<DevelopMeta[K]>;
};
export const developRoles: DevelopRoles = {
planner: plannerRole,
coder: coderRole,
reviewer: reviewerRole,
tester: testerRole,
committer: committerRole,
};
@@ -0,0 +1,17 @@
{
"extends": "../../tsconfig.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "dist",
"composite": true
},
"include": ["src/**/*.ts"],
"references": [
{ "path": "../workflow" },
{ "path": "../workflow-role-coder" },
{ "path": "../workflow-role-committer" },
{ "path": "../workflow-role-planner" },
{ "path": "../workflow-role-reviewer" },
{ "path": "../workflow-role-tester" }
]
}