Addresses review findings before Slice 5 sandbox work. Resolver primitives: - resolveOutcome maps an attempt outcome to retry-or-terminal; removed the no-op isTerminalClassification. - WORK_STATUS_FOR_OUTCOME preserves real terminal Work status instead of collapsing everything back to ready. - Lifecycle: completed is terminal, cancelled reopens only to ready, and the invalid awaiting-design-approval -> awaiting-definition-approval reopening is gone. Execution (workExecution.ts): - finishAttempt replaces completeAttempt: auto-retries within the kit budget and settles Work at the real classification (Succeeded->completed, PermanentFailure/BudgetExhausted->failed, NeedsInput->needs-input, Blocked->blocked). No Work stays silently runnable after a failure. - startSimulatedExecution validates sliceId against the current approved Design (foreign ids rejected; defaults to the first slice) and advances slice status running -> completed/ready. - retrySimulatedExecution is now an explicit user restart with a retryable- state guard, not the automatic resolver path. - reconcileExpiredAttempts is bounded: a dead lease terminates as Blocked, resumes within budget or settles the Run/Work so nothing runs forever. - crons.ts runs the reconciler every 30s, string-referenced so it does not depend on the stale codegen. Planning (workPlanning.ts): - saveDefinition/saveDesign reject revision while a Run is executing. - submitQuestion validates and persists a durable workQuestions row instead of discarding planner questions. - Design revision invalidates active design approvals. Verification: primitives 69 tests (+4), backend 22 tests (+10) covering retry/cancel/failure/restart, slice validation, reconciliation, the revision guard, and question persistence. Root typecheck, web+agents build, and the configured Ultracite gate (53 files) all pass. package.json: the recurring check gate now covers workExecution, workPlanning, crons, resolver, and work-lifecycle.
268 lines
8.5 KiB
TypeScript
268 lines
8.5 KiB
TypeScript
import { convexTest } from "convex-test";
|
|
import { anyApi, makeFunctionReference } from "convex/server";
|
|
import { describe, expect, test } from "vitest";
|
|
|
|
import type { Id } from "./_generated/dataModel";
|
|
import schema from "./schema";
|
|
|
|
declare global {
|
|
interface ImportMeta {
|
|
readonly glob: (pattern: string) => Record<string, () => Promise<unknown>>;
|
|
}
|
|
}
|
|
|
|
const modules = import.meta.glob("./**/*.ts");
|
|
const api = anyApi;
|
|
const executeFakeAttemptRef = makeFunctionReference<
|
|
"action",
|
|
{ attemptId: string; scenario: "success" }
|
|
>("workExecution:executeFakeAttempt");
|
|
const identity = { tokenIdentifier: "https://convex.test|planner-user" };
|
|
|
|
describe("Work planning and execution commands", () => {
|
|
test("binds approvals to exact versions and admits a fake Run only from Ready", async () => {
|
|
const t = convexTest({ modules, schema });
|
|
const fixture = await t.withIdentity(identity).run(async (ctx) => {
|
|
const organizationId = await ctx.db.insert("organizations", {
|
|
createdAt: 1,
|
|
createdBy: identity.tokenIdentifier,
|
|
kind: "personal",
|
|
name: "Personal",
|
|
});
|
|
await ctx.db.insert("organizationMembers", {
|
|
organizationId,
|
|
userId: identity.tokenIdentifier,
|
|
role: "owner",
|
|
createdAt: 1,
|
|
});
|
|
const projectId = await ctx.db.insert("projects", {
|
|
createdAt: 1,
|
|
name: "Zopu",
|
|
normalizedSourceUrl: "https://example.com/zopu",
|
|
organizationId,
|
|
repositoryPath: "puter/zopu",
|
|
sourceHost: "example.com",
|
|
sourceUrl: "https://example.com/zopu",
|
|
updatedAt: 1,
|
|
});
|
|
const workId = await ctx.db.insert("works", {
|
|
organizationId,
|
|
projectId,
|
|
title: "Executable work",
|
|
objective: "Prove the flow",
|
|
status: "proposed",
|
|
createdAt: 1,
|
|
updatedAt: 1,
|
|
});
|
|
return { projectId, workId };
|
|
});
|
|
|
|
await t
|
|
.withIdentity(identity)
|
|
.mutation(api.workPlanning.requestDefinition, { workId: fixture.workId });
|
|
const definition = await t
|
|
.withIdentity(identity)
|
|
.mutation(api.workPlanning.saveDefinitionProposal, {
|
|
workId: fixture.workId,
|
|
payloadJson: JSON.stringify({
|
|
problem: "Need a proof",
|
|
desiredOutcome: "A terminal simulation",
|
|
affectedUsers: ["user"],
|
|
inScope: ["fake"],
|
|
outOfScope: [],
|
|
acceptanceCriteria: ["terminal"],
|
|
constraints: [],
|
|
assumptions: [],
|
|
questions: [],
|
|
risk: "low",
|
|
requiredArtifacts: ["events"],
|
|
}),
|
|
});
|
|
await t
|
|
.withIdentity(identity)
|
|
.mutation(api.workPlanning.approveDefinition, {
|
|
workId: fixture.workId,
|
|
version: definition.version,
|
|
});
|
|
const design = await t
|
|
.withIdentity(identity)
|
|
.mutation(api.workPlanning.saveDesignProposal, {
|
|
workId: fixture.workId,
|
|
payloadJson: JSON.stringify({
|
|
impactMap: { files: [], modules: [], risks: [], summary: "small" },
|
|
architectureSummary: "fake",
|
|
fileTreeDelta: [],
|
|
callFlowDelta: [],
|
|
keyInterfaces: [],
|
|
invariants: ["terminal"],
|
|
concerns: [],
|
|
slices: [
|
|
{
|
|
id: "slice-1",
|
|
title: "fake",
|
|
objective: "fake",
|
|
observableBehavior: "event",
|
|
codeBoundaries: ["runtime"],
|
|
evidenceRequirements: ["event"],
|
|
verification: ["assert"],
|
|
reviewRequired: false,
|
|
dependsOn: [],
|
|
},
|
|
],
|
|
evidenceRequirements: ["event"],
|
|
tradeoffs: [],
|
|
}),
|
|
});
|
|
await t.withIdentity(identity).mutation(api.workPlanning.approveDesign, {
|
|
workId: fixture.workId,
|
|
definitionVersion: definition.version,
|
|
designVersion: design.version,
|
|
});
|
|
const started = await t
|
|
.withIdentity(identity)
|
|
.mutation(api.workExecution.startSimulatedExecution, {
|
|
workId: fixture.workId,
|
|
scenario: "success",
|
|
sliceId: "slice-1",
|
|
});
|
|
expect(started.runId).toBeTruthy();
|
|
const state = await t.run(async (ctx) => ctx.db.get(fixture.workId));
|
|
expect(state?.status).toBe("executing");
|
|
expect(state?.definitionApprovalVersion).toBe(definition.version);
|
|
expect(state?.designApprovalVersion).toBe(design.version);
|
|
await t.action(executeFakeAttemptRef, {
|
|
attemptId: String(started.attemptId),
|
|
scenario: "success",
|
|
});
|
|
const completed = await t.run(async (ctx) => ({
|
|
attempt: await ctx.db
|
|
.query("workAttempts")
|
|
.withIndex("by_run_and_number", (q) => q.eq("runId", started.runId))
|
|
.unique(),
|
|
events: await ctx.db.query("workAttemptEvents").collect(),
|
|
run: await ctx.db.get(started.runId as Id<"workRuns">),
|
|
work: await ctx.db.get(fixture.workId),
|
|
}));
|
|
expect(completed.work?.status).toBe("completed");
|
|
expect(completed.run?.terminalClassification).toBe("Succeeded");
|
|
expect(completed.attempt?.status).toBe("terminal");
|
|
expect(completed.events.length).toBeGreaterThan(0);
|
|
});
|
|
});
|
|
|
|
const validDefinitionPayload = () => ({
|
|
acceptanceCriteria: ["terminal outcome"],
|
|
affectedUsers: ["user"],
|
|
assumptions: [],
|
|
constraints: [],
|
|
desiredOutcome: "A terminal simulation",
|
|
inScope: ["fake"],
|
|
outOfScope: [],
|
|
problem: "Need a proof",
|
|
questions: [],
|
|
requiredArtifacts: ["events"],
|
|
risk: "low",
|
|
});
|
|
|
|
describe("Work planning guards", () => {
|
|
test("a Definition cannot be revised while a Run is executing", async () => {
|
|
const t = convexTest({ modules, schema });
|
|
const { workId } = await t.withIdentity(identity).run(async (ctx) => {
|
|
const organizationId = await ctx.db.insert("organizations", {
|
|
createdAt: 1,
|
|
createdBy: identity.tokenIdentifier,
|
|
kind: "personal",
|
|
name: "Personal",
|
|
});
|
|
await ctx.db.insert("organizationMembers", {
|
|
createdAt: 1,
|
|
organizationId,
|
|
role: "owner",
|
|
userId: identity.tokenIdentifier,
|
|
});
|
|
const projectId = await ctx.db.insert("projects", {
|
|
createdAt: 1,
|
|
name: "Zopu",
|
|
normalizedSourceUrl: "https://example.com/zopu",
|
|
organizationId,
|
|
repositoryPath: "puter/zopu",
|
|
sourceHost: "example.com",
|
|
sourceUrl: "https://example.com/zopu",
|
|
updatedAt: 1,
|
|
});
|
|
const id = await ctx.db.insert("works", {
|
|
createdAt: 1,
|
|
definitionApprovalVersion: 1,
|
|
definitionVersion: 1,
|
|
designApprovalVersion: 1,
|
|
designVersion: 1,
|
|
objective: "Prove the guard",
|
|
organizationId,
|
|
projectId,
|
|
status: "executing",
|
|
title: "Guarded work",
|
|
updatedAt: 1,
|
|
});
|
|
return { workId: id };
|
|
});
|
|
await expect(
|
|
t
|
|
.withIdentity(identity)
|
|
.mutation(api.workPlanning.saveDefinitionProposal, {
|
|
payloadJson: JSON.stringify(validDefinitionPayload()),
|
|
workId,
|
|
})
|
|
).rejects.toThrow(/while a Run is executing/u);
|
|
});
|
|
|
|
test("planner questions are persisted as durable Work questions", async () => {
|
|
const t = convexTest({ modules, schema });
|
|
const { workId } = await t.withIdentity(identity).run(async (ctx) => {
|
|
const organizationId = await ctx.db.insert("organizations", {
|
|
createdAt: 1,
|
|
createdBy: identity.tokenIdentifier,
|
|
kind: "personal",
|
|
name: "Personal",
|
|
});
|
|
const projectId = await ctx.db.insert("projects", {
|
|
createdAt: 1,
|
|
name: "Zopu",
|
|
normalizedSourceUrl: "https://example.com/zopu",
|
|
organizationId,
|
|
repositoryPath: "puter/zopu",
|
|
sourceHost: "example.com",
|
|
sourceUrl: "https://example.com/zopu",
|
|
updatedAt: 1,
|
|
});
|
|
const id = await ctx.db.insert("works", {
|
|
createdAt: 1,
|
|
definitionVersion: 1,
|
|
objective: "Prove questions",
|
|
organizationId,
|
|
projectId,
|
|
status: "awaiting-definition-approval",
|
|
title: "Questionable work",
|
|
updatedAt: 1,
|
|
});
|
|
return { workId: id };
|
|
});
|
|
await t.mutation(api.workPlanning.submitQuestion, {
|
|
questionJson: JSON.stringify({
|
|
alternatives: [],
|
|
id: "q1",
|
|
impact: "medium",
|
|
prompt: "Which runtime?",
|
|
status: "open",
|
|
}),
|
|
token: "test-token",
|
|
workId,
|
|
});
|
|
const questions = await t.run(async (ctx) =>
|
|
ctx.db.query("workQuestions").collect()
|
|
);
|
|
expect(questions).toHaveLength(1);
|
|
expect(questions[0]?.questionId).toBe("q1");
|
|
expect(questions[0]?.definitionVersion).toBe(1);
|
|
});
|
|
});
|