FN-5902: make mission validation AI-run all criteria

Route every mission feature through validator-backed completion checks.

- lazily restore a managed feature assertion before validation instead of auto-passing zero-assertion features
- thread milestone acceptance criteria into validator prompts and system instructions as enforced requirements
- update MissionManager copy/tests to present criteria as AI-validated runtime gates and remove informational-only/zero-assertion warnings
- document the all-criteria AI-run contract and add a changeset for @runfusion/fusion

Files changed:
 .changeset/fn-5902-mission-validation-ai-run.md    |   5 +
 AGENTS.md                                          |   2 +-
 docs/architecture.md                               |   2 +-
 docs/missions-completion-contract.md               | 198 ++++++---------------
 docs/missions.md                                   |   5 +-
 packages/core/src/__tests__/mission-store.test.ts  |  23 ++-
 packages/core/src/mission-store.ts                 |  10 ++
 packages/dashboard/app/components/MissionManager.css    |  31 ----
 packages/dashboard/app/components/MissionManager.tsx    |  86 +++------
 packages/dashboard/app/components/__tests__/MissionManager.test.tsx   |  60 +++++--
 packages/engine/src/__tests__/mission-execution-loop.test.ts   | 111 +++++++++---
 packages/engine/src/__tests__/reliability-interactions/mission-validation-trigger-gap.test.ts         |  57 +++---
 packages/engine/src/mission-execution-loop.ts      |  78 ++++----
 13 files changed, 318 insertions(+), 350 deletions(-)

Fusion-Task-Id: FN-5902

Fusion-Task-Lineage: 5f25caad-33c9-42ff-822b-1ea092afc29f
This commit is contained in:
gsxdsm
2026-06-02 18:11:26 -07:00
parent abbeaec0a8
commit cc18206bc5
13 changed files with 318 additions and 350 deletions

View File

@@ -204,6 +204,16 @@ function createMockMissionStore() {
return updated;
}),
listAssertionsForFeature: vi.fn((featureId: string) => assertionsByFeature.get(featureId) ?? []),
ensureFeatureAssertionLinked: vi.fn((featureId: string) => {
const feature = features.get(featureId);
if (!feature) {
throw new Error(`Feature ${featureId} not found`);
}
if ((assertionsByFeature.get(featureId) ?? []).length === 0) {
store._addFeatureWithManagedAssertion(feature);
}
return assertionsByFeature.get(featureId) ?? [];
}),
getAssertionsForFeature: vi.fn((featureId: string) => assertionsByFeature.get(featureId) ?? []),
getSlice: vi.fn((id: string) => {
// Return a mock slice with milestoneId for the hierarchy
@@ -764,12 +774,21 @@ describe("MissionExecutionLoop", () => {
expect(missionStore.completeValidatorRun).toHaveBeenCalledWith(expect.any(String), "passed", "Recovered validation passed");
});
it("should auto-pass if feature has no linked assertions", async () => {
const feature = createMockFeature({ loopState: "implementing", taskId: "FN-001" });
it("lazy-ensures a managed assertion and routes zero-assertion features through validation", async () => {
const feature = createMockFeature({
id: "F-001",
loopState: "implementing",
taskId: "FN-001",
title: "Feature from prose",
acceptanceCriteria: "Feature must validate through AI",
});
missionStore._setFeature(feature);
taskStore._setTask({ id: "FN-001", title: "Test", description: "Test task", log: [] });
missionStore.getFeatureByTaskId = vi.fn().mockReturnValue(feature);
missionStore.listAssertionsForFeature = vi.fn().mockReturnValue([]);
missionStore.listAssertionsForFeature = vi
.fn()
.mockReturnValueOnce([])
.mockImplementation((featureId: string) => (missionStore as any).getAssertionsForFeature(featureId));
loop = new MissionExecutionLoop({
taskStore: taskStore as any,
@@ -777,41 +796,39 @@ describe("MissionExecutionLoop", () => {
rootDir: "/tmp",
});
const emitSpy = vi.spyOn(loop, "emit");
vi.spyOn(loop as any, "runValidation").mockResolvedValue({ status: "pass", summary: "ok" });
loop.start();
await loop.processTaskOutcome("FN-001");
// When there are no assertions, we skip starting a validator run
expect(missionStore.startValidatorRun).not.toHaveBeenCalled();
// But the passed event should be emitted
expect(missionStore.ensureFeatureAssertionLinked).toHaveBeenCalledWith("F-001");
expect(missionStore.startValidatorRun).toHaveBeenCalledWith("F-001", "task_completion");
expect(emitSpy).toHaveBeenCalledWith(
"validation:passed",
expect.objectContaining({ featureId: "F-001" }),
);
expect(missionStore.updateFeature).toHaveBeenCalledWith(
"F-001",
expect.objectContaining({ loopState: "passed", lastValidatorStatus: "passed" }),
);
expect(missionStore.logMissionEvent).toHaveBeenCalledWith(
expect.any(String),
"warning",
expect.stringContaining("auto-passed"),
expect.objectContaining({
code: "validation_auto_passed_no_assertions",
featureId: "F-001",
reason: "No assertions linked",
taskId: "FN-001",
}),
const noAssertionEvents = missionStore.logMissionEvent.mock.calls.filter(
([, , , payload]) => payload?.code === "validation_auto_passed_no_assertions",
);
expect(noAssertionEvents).toHaveLength(0);
expectNoValidationBoardTaskMutation(taskStore);
});
it("emits no-assertions auto-pass event exactly once across re-entry", async () => {
const feature = createMockFeature({ loopState: "implementing", taskId: "FN-001" });
it("does not emit auto-pass evidence across re-entry after lazy assertion ensure", async () => {
const feature = createMockFeature({
id: "F-001",
loopState: "implementing",
taskId: "FN-001",
title: "Feature from prose",
acceptanceCriteria: "Feature must validate through AI",
});
missionStore._setFeature(feature);
taskStore._setTask({ id: "FN-001", title: "Test", description: "Test task", log: [] });
missionStore.getFeatureByTaskId = vi.fn().mockReturnValue(feature);
missionStore.listAssertionsForFeature = vi.fn().mockReturnValue([]);
missionStore.listAssertionsForFeature = vi
.fn()
.mockReturnValueOnce([])
.mockImplementation((featureId: string) => (missionStore as any).getAssertionsForFeature(featureId));
loop = new MissionExecutionLoop({
taskStore: taskStore as any,
@@ -823,10 +840,11 @@ describe("MissionExecutionLoop", () => {
await loop.processTaskOutcome("FN-001");
await loop.processTaskOutcome("FN-001");
expect(missionStore.ensureFeatureAssertionLinked).toHaveBeenCalledTimes(1);
const noAssertionEvents = missionStore.logMissionEvent.mock.calls.filter(
([, , , payload]) => payload?.code === "validation_auto_passed_no_assertions",
);
expect(noAssertionEvents).toHaveLength(1);
expect(noAssertionEvents).toHaveLength(0);
});
it("uses validator path for later-added feature with managed assertion", async () => {
@@ -854,6 +872,44 @@ describe("MissionExecutionLoop", () => {
expect(missionStore.startValidatorRun).toHaveBeenCalledWith("F-LATER", "task_completion");
});
it("threads milestone acceptance criteria into validator prompts", () => {
const feature = createMockFeature({
id: "F-MILESTONE",
title: "Feature under milestone",
acceptanceCriteria: "Feature criteria",
});
const milestone = createMockMilestone({
id: "MS-MILESTONE",
acceptanceCriteria: "Milestone pass bar text",
});
const assertions = [
{
id: "CA-1",
milestoneId: milestone.id,
title: "Managed assertion",
assertion: "Feature criteria",
status: "pending" as const,
orderIndex: 0,
createdAt: new Date().toISOString(),
updatedAt: new Date().toISOString(),
},
];
loop = new MissionExecutionLoop({
taskStore: taskStore as any,
missionStore: missionStore as any,
rootDir: "/tmp",
});
const prompt = (loop as any).buildValidationPrompt(feature, assertions, milestone);
const systemPrompt = (loop as any).buildValidationSystemPrompt(feature, assertions, "Task context", milestone);
expect(prompt).toContain("Milestone pass bar text");
expect(prompt).toContain("must also be satisfied for this feature to pass");
expect(systemPrompt).toContain("Milestone pass bar text");
expect(systemPrompt).toContain("validator-executed requirements");
});
it("does NOT create a board task for single-feature validation", async () => {
const feature = createMockFeature({ loopState: "implementing", taskId: "FN-001", sliceId: "SL-001" });
missionStore._setFeature(feature);
@@ -1464,7 +1520,7 @@ describe("MissionExecutionLoop", () => {
});
missionStore._setFeature(feature);
missionStore.getFeatureByTaskId = vi.fn().mockReturnValue(feature);
missionStore.listAssertionsForFeature = vi.fn().mockReturnValue([]); // No assertions = auto-pass
missionStore.listAssertionsForFeature = vi.fn().mockReturnValue([]);
taskStore._setTask({ id: "FN-001", title: "Test", description: "Test", log: [] });
const notifySpy = vi.fn();
@@ -1477,12 +1533,13 @@ describe("MissionExecutionLoop", () => {
},
});
const emitSpy = vi.spyOn(loop, "emit");
vi.spyOn(loop as any, "runValidation").mockResolvedValue({ status: "pass", summary: "ok" });
loop.start();
await loop.processTaskOutcome("FN-001");
// No validator run started (no assertions)
expect(missionStore.startValidatorRun).not.toHaveBeenCalled();
expect(missionStore.ensureFeatureAssertionLinked).toHaveBeenCalledWith("F-001");
expect(missionStore.startValidatorRun).toHaveBeenCalledWith("F-001", "task_completion");
// validation:passed event emitted
expect(emitSpy).toHaveBeenCalledWith(

View File

@@ -186,9 +186,10 @@ describe("FN-5715 reliability: mission validation trigger gap", () => {
loop.stop();
});
it("periodic recovery pass replays implementing done tasks with zero assertions and advances loop state", async () => {
const feature = makeFeature({ status: "done", lastValidatorStatus: undefined, loopState: "implementing" });
it("periodic recovery lazily ensures assertions and AI-validates zero-link legacy features", async () => {
const feature = makeFeature({ status: "done", lastValidatorStatus: undefined, loopState: "implementing", acceptanceCriteria: "must pass" });
const currentFeature = { ...feature };
const linkedAssertions: Array<{ id: string }> = [];
const missionStore = {
listMissions: vi.fn(() => [{ id: "M-001", status: "active" }]),
getMissionWithHierarchy: vi.fn(() => ({
@@ -203,11 +204,21 @@ describe("FN-5715 reliability: mission validation trigger gap", () => {
Object.assign(currentFeature, patch);
return { ...currentFeature };
}),
listAssertionsForFeature: vi.fn(() => []),
listAssertionsForFeature: vi.fn(() => linkedAssertions),
ensureFeatureAssertionLinked: vi.fn(() => {
if (linkedAssertions.length === 0) {
linkedAssertions.push({ id: "CA-ENSURED" });
}
return linkedAssertions;
}),
startValidatorRun: vi.fn(() => ({ id: "VR-001", featureId: "F-001" })),
completeValidatorRun: vi.fn(),
getSlice: vi.fn(() => ({ id: "SL-001", milestoneId: "MS-001", status: "active" })),
getMilestone: vi.fn(() => ({ id: "MS-001", missionId: "M-001" })),
logMissionEvent: vi.fn(),
transitionLoopState: vi.fn(),
setFeatureCurrentTaskRunId: vi.fn(),
getFailuresForRun: vi.fn(() => []),
};
const taskStore = {
getTask: vi.fn(async () => ({ id: "FN-001", column: "done", status: "done" })),
@@ -220,25 +231,23 @@ describe("FN-5715 reliability: mission validation trigger gap", () => {
taskStore: taskStore as any,
rootDir: process.cwd(),
});
vi.spyOn(loop as any, "runValidation").mockResolvedValue({ status: "pass", summary: "ok" });
loop.start();
const periodicMaintenancePass = async () => loop.recoverActiveMissions();
await periodicMaintenancePass();
await periodicMaintenancePass();
expect(missionStore.updateFeature).toHaveBeenCalledTimes(1);
expect(missionStore.updateFeature).toHaveBeenCalledWith(
"F-001",
expect.objectContaining({ loopState: "passed", lastValidatorStatus: "passed" }),
);
expect(missionStore.ensureFeatureAssertionLinked).toHaveBeenCalledWith("F-001");
expect(missionStore.startValidatorRun).toHaveBeenCalledWith("F-001", "task_completion");
const noAssertionEvents = missionStore.logMissionEvent.mock.calls.filter(
([, type, , payload]) => type === "warning" && payload?.code === "validation_auto_passed_no_assertions",
);
expect(noAssertionEvents).toHaveLength(1);
expect(noAssertionEvents).toHaveLength(0);
loop.stop();
});
it("routes through validator after assertion backfill instead of no-assertion auto-pass", async () => {
it("keeps backfill optional because runtime lazy-ensure routes through validator", async () => {
const feature = makeFeature({ status: "done", acceptanceCriteria: "must pass", loopState: "implementing" });
const currentFeature = { ...feature };
const linkedAssertions: Array<{ id: string }> = [];
@@ -258,6 +267,12 @@ describe("FN-5715 reliability: mission validation trigger gap", () => {
return { ...currentFeature };
}),
listAssertionsForFeature: vi.fn(() => linkedAssertions),
ensureFeatureAssertionLinked: vi.fn(() => {
if (linkedAssertions.length === 0) {
linkedAssertions.push({ id: "CA-001" });
}
return linkedAssertions;
}),
startValidatorRun: vi.fn(() => ({ id: "VR-001", featureId: "F-001" })),
completeValidatorRun: vi.fn(),
getSlice: vi.fn(() => ({ id: "SL-001", milestoneId: "MS-001", status: "active" })),
@@ -279,27 +294,13 @@ describe("FN-5715 reliability: mission validation trigger gap", () => {
await loop.recoverActiveMissions();
const noAssertionEventsBefore = missionStore.logMissionEvent.mock.calls.filter(
([, type, , payload]) => type === "warning" && payload?.code === "validation_auto_passed_no_assertions",
);
expect(noAssertionEventsBefore).toHaveLength(1);
expect(missionStore.startValidatorRun).not.toHaveBeenCalled();
linkedAssertions.push({ id: "CA-001" });
currentFeature.loopState = "implementing";
currentFeature.lastValidatorStatus = undefined;
await loop.processTaskOutcome("FN-001");
expect(missionStore.ensureFeatureAssertionLinked).toHaveBeenCalledWith("F-001");
expect(missionStore.startValidatorRun).toHaveBeenCalledWith("F-001", "task_completion");
const noAssertionEventsAfter = missionStore.logMissionEvent.mock.calls.filter(
const noAssertionEvents = missionStore.logMissionEvent.mock.calls.filter(
([, type, , payload]) => type === "warning" && payload?.code === "validation_auto_passed_no_assertions",
);
expect(noAssertionEventsAfter).toHaveLength(1);
expect(missionStore.updateFeature).toHaveBeenCalledWith(
"F-001",
expect.objectContaining({ loopState: "passed", lastValidatorStatus: "passed" }),
);
expect(noAssertionEvents).toHaveLength(0);
expect(missionStore.completeValidatorRun).toHaveBeenCalledWith("VR-001", "passed", "ok");
loop.stop();
});