Files
PaperClipAI/tests/runner-e2e/chat-campaign.ts
T

197 lines
16 KiB
TypeScript

import { createHash } from "node:crypto";
import { readFileSync, readdirSync, writeFileSync } from "node:fs";
import path from "node:path";
import { pathToFileURL } from "node:url";
import { parseDocument } from "yaml";
export const CHAT_CAMPAIGN_MANIFEST = "tests/runner-e2e/chat-campaign-manifest.json";
export type CampaignOutcome = "passed" | "failed" | "blocked";
export type CampaignProductLane = "source-build" | "published-global-npm" | "empty-installed-boundary";
export interface CampaignPublishedIdentity {
version: string; treeSha256: string;
artifacts: Array<{ package: "paperclipai" | "@paperclipai/server"; version: string; integrity: string; entrySha256: string }>;
}
export type CampaignProductIdentity =
| { kind: "unknown"; reason: string }
| { kind: "source-build" | "source-built-installed"; productionSourceRevision: string; snapshotSourceRevision: string;
nativeBinarySha256: string; workspaceBuildDigest: string; receiptPaths: string[]; coreCandidate: boolean;
cliSha256?: string; serverSha256?: string; artifactTreeSha256?: string }
| { kind: "published-release"; declaredLane: "published-global-npm" | "empty-installed-boundary";
source: CampaignPublishedIdentity; target?: CampaignPublishedIdentity; observed: CampaignPublishedIdentity;
receiptPaths: string[]; coreCandidate: boolean };
const identityHash = (s: unknown): s is string => typeof s === "string" && /^[a-f0-9]{64}$/.test(s);
const identityRevision = (s: unknown): s is string => typeof s === "string" && /^[a-f0-9]{40}$/.test(s);
const retainedIdentityPaths = (paths: string[]) => Array.isArray(paths) && paths.length > 0 && paths.every(p => typeof p === "string" && p.startsWith("tests/runner-e2e/results/") && !p.split("/").includes(".."));
export function scenarioProductPolicy(id: string, baselineRevision: string) {
const lane: CampaignProductLane = ["instance-operations.update-instance", "instance-operations.provision-runtime"].includes(id)
? "published-global-npm" : id === "onboarding.new-instance" ? "empty-installed-boundary" : "source-build";
return { lane, sourceBaselineRevision: baselineRevision };
}
function publishedIdentityValid(value: CampaignPublishedIdentity) {
return !!value && /^\d+\.\d+\.\d+(?:[-+][A-Za-z0-9.-]+)?$/.test(value.version) && identityHash(value.treeSha256)
&& Array.isArray(value.artifacts) && value.artifacts.length === 2
&& ["paperclipai", "@paperclipai/server"].every(name => value.artifacts.filter(a => a && a.package === name).length === 1)
&& value.artifacts.every(a => a.version === value.version && /^sha512-[A-Za-z0-9+/]+=*$/.test(a.integrity) && identityHash(a.entrySha256));
}
function samePublishedIdentity(a: CampaignPublishedIdentity, b: CampaignPublishedIdentity) {
return publishedIdentityValid(a) && publishedIdentityValid(b) && a.version === b.version && a.treeSha256 === b.treeSha256
&& a.artifacts.every(x => b.artifacts.some(y => x.package === y.package && x.version === y.version && x.integrity === y.integrity && x.entrySha256 === y.entrySha256));
}
/** Identity gates eligibility independently of a model's outcome or test-source SHA. */
export function campaignProductIdentityEligible(scenario: CampaignScenario, attempt: CampaignAttempt, baselineRevision = scenario.productPolicy?.sourceBaselineRevision): boolean {
const policy = scenario.productPolicy, product = attempt.productIdentity;
if (!policy || policy.sourceBaselineRevision !== baselineRevision || !identityRevision(baselineRevision)
|| policy.lane !== scenarioProductPolicy(scenario.id, baselineRevision).lane || !product || product.kind === "unknown"
|| product.coreCandidate !== false || attempt.corePrDependencies.length || !retainedIdentityPaths(product.receiptPaths)) return false;
if (product.kind === "source-build" || product.kind === "source-built-installed") {
return product.productionSourceRevision === baselineRevision && product.snapshotSourceRevision === attempt.sourceRevision
&& identityRevision(product.snapshotSourceRevision) && identityHash(product.nativeBinarySha256) && identityHash(product.workspaceBuildDigest)
&& (product.kind === "source-build" ? policy.lane === "source-build" : policy.lane === "empty-installed-boundary"
&& identityHash(product.cliSha256) && identityHash(product.serverSha256) && identityHash(product.artifactTreeSha256));
}
if (product.kind !== "published-release") return false;
if (policy.lane === "source-build" || product.declaredLane !== policy.lane || !publishedIdentityValid(product.source)) return false;
if (scenario.id === "instance-operations.update-instance") return !!product.target && product.target.version !== product.source.version && samePublishedIdentity(product.target, product.observed);
return !product.target && samePublishedIdentity(product.source, product.observed);
}
export interface CampaignAttempt {
productIdentity?: CampaignProductIdentity;
ordinal: 1 | 2;
outcome: CampaignOutcome | "running";
executionId: string;
startedAt: string;
finishedAt: string | null;
sourceRevision: string;
workingTreeDigest: string;
definitionDigest: string;
suiteDefinitionDigest: string;
graderDigest: string;
model: string;
profile: string;
environment: string;
automaticRetries: 0;
correction: string | null;
classification: string | null;
diagnosisHistory?: Array<{ at: string; classification: string | null; detail: string | null; supersededBy: string }>;
observedFailure: string | null;
evidencePaths: string[];
usage: { costUsd: number | null; coverage: string; tokens: number | null };
cleanup: "pending" | "passed" | "failed" | "not_started";
corePrDependencies: string[];
}
export interface CampaignScenario {
id: string; feature: string; sourceFile: string; sourceSha256: string;
capabilities: string[]; context: string; query: string; expected_outcome: string;
scenarioSha256: string;
qualifyingDefinitionDigest: string | null;
qualifyingGraderDigest: string | null;
owner: string;
readiness: "unimplemented" | "partial" | "implemented" | "blocked";
executionId: string | null;
blocker: string | null;
productPolicy?: { lane: CampaignProductLane; sourceBaselineRevision: string };
attempts: CampaignAttempt[];
}
export interface ChatCampaign {
version: 1; campaignId: string; frozenAt: string; baselineRevision: string;
inventoryDigest: string; defaultsSha256: string;
denominator: number; areas: number; capabilities: number;
requiredPasses: number;
corePrs: string[]; evalPr: string | null;
/** Authored metadata only; never passing execution evidence. */
implementationCheckpoint?: { sourceRevision: string; descriptorSha256: string; authored: number; complete: number; partial: number; unimplemented: number };
scenarios: CampaignScenario[];
}
const digest = (value: string) => createHash("sha256").update(value).digest("hex");
export function freezeChatCampaign(root: string, baselineRevision: string): ChatCampaign {
const directory = path.join(root, "tests/runner-e2e/chat-scenarios");
const scenarios: CampaignScenario[] = [];
const files = readdirSync(directory).filter(name => name.endsWith(".yaml") && name !== "defaults.yaml").sort();
for (const file of files) {
const text = readFileSync(path.join(directory, file), "utf8");
const document = parseDocument(text, { uniqueKeys: true });
if (document.errors.length) throw new Error(`Invalid catalog ${file}`);
const value = document.toJS();
for (const scenario of value.scenarios) {
const canonical = { id: scenario.id, capabilities: scenario.capabilities, context: scenario.context, query: scenario.query, expected_outcome: scenario.expected_outcome };
if (scenarios.some(entry => entry.id === scenario.id)) throw new Error(`Duplicate scenario ${scenario.id}`);
const legacy = ["tasks.create-backlog", "tasks.delegate-announcement"].includes(scenario.id);
scenarios.push({ ...canonical, feature: value.feature, sourceFile: `tests/runner-e2e/chat-scenarios/${file}`,
sourceSha256: digest(text), scenarioSha256: digest(JSON.stringify(canonical)),
qualifyingDefinitionDigest: null, qualifyingGraderDigest: null,
owner: legacy ? "eval_integrator" : "unassigned", readiness: legacy ? "implemented" : "unimplemented",
executionId: legacy ? `chat-features.runner-codex-subscription.local.${scenario.id.slice(6)}` : null,
blocker: null, productPolicy: scenarioProductPolicy(scenario.id, baselineRevision), attempts: [] });
}
}
scenarios.sort((a, b) => a.id.localeCompare(b.id));
const capabilities = new Set(scenarios.flatMap(scenario => scenario.capabilities)).size;
if (scenarios.length !== 244 || files.length !== 35 || capabilities !== 191) throw new Error("Frozen denominator changed; reconcile explicitly");
const defaultsSha256 = digest(readFileSync(path.join(directory, "defaults.yaml"), "utf8"));
return { version: 1, campaignId: "chat-catalog-2026-10-26", frozenAt: new Date().toISOString(), baselineRevision,
inventoryDigest: digest(JSON.stringify({ defaultsSha256, scenarios: scenarios.map(({ id, scenarioSha256, sourceSha256 }) => ({ id, scenarioSha256, sourceSha256 })) })),
defaultsSha256, denominator: scenarios.length, areas: files.length, capabilities, requiredPasses: Math.ceil(scenarios.length * 0.8), corePrs: [], evalPr: null, scenarios };
}
export function validateFrozenCampaign(campaign: ChatCampaign, root: string): void {
const fresh = freezeChatCampaign(root, campaign.baselineRevision);
if (campaign.version !== 1 || campaign.denominator !== 244 || campaign.areas !== 35 || campaign.capabilities !== 191
|| campaign.requiredPasses !== 196 || campaign.scenarios.length !== 244 || campaign.defaultsSha256 !== fresh.defaultsSha256
|| campaign.inventoryDigest !== fresh.inventoryDigest) throw new Error("Frozen campaign inventory metadata changed");
for (let index = 0; index < campaign.scenarios.length; index++) {
const actual = campaign.scenarios[index]!; const expected = fresh.scenarios[index]!;
for (const field of ["id", "feature", "sourceFile", "sourceSha256", "scenarioSha256", "capabilities", "context", "query", "expected_outcome", "productPolicy"] as const) {
if (JSON.stringify(actual[field]) !== JSON.stringify(expected[field])) throw new Error(`Frozen scenario content changed: ${expected.id}`);
}
if (actual.attempts.length > 2 || actual.attempts.some((attempt, attemptIndex) => attempt.ordinal !== attemptIndex + 1 || attempt.automaticRetries !== 0)) throw new Error(`Invalid attempt history: ${actual.id}`);
}
}
export function reserveCampaignAttempt(scenario: CampaignScenario, attempt: CampaignAttempt): void {
if (!scenario.productPolicy || !identityRevision(scenario.productPolicy.sourceBaselineRevision) || scenario.productPolicy.lane !== scenarioProductPolicy(scenario.id, scenario.productPolicy.sourceBaselineRevision).lane) throw new Error("Attempt requires a declared product lane");
if (scenario.readiness !== "implemented" || !scenario.executionId) throw new Error("Scenario has no executable implementation");
if (scenario.attempts.some(entry => entry.outcome === "running")) throw new Error("Previous attempt still running");
if (scenario.attempts.length >= 2 || attempt.ordinal !== scenario.attempts.length + 1) throw new Error("Attempt budget exhausted or incorrect ordinal");
if (scenario.attempts[0]?.outcome === "passed") throw new Error("Passing scenario cannot be rerun");
if (attempt.ordinal === 2 && !attempt.correction?.trim()) throw new Error("Fix cycle requires a recorded correction");
if (attempt.automaticRetries !== 0 || attempt.executionId !== scenario.executionId || attempt.outcome !== "running") throw new Error("Invalid attempt reservation");
if ([attempt.sourceRevision, attempt.workingTreeDigest, attempt.definitionDigest, attempt.suiteDefinitionDigest, attempt.graderDigest, attempt.model, attempt.profile, attempt.environment].some(value => !value.trim())) throw new Error("Missing attempt provenance");
scenario.attempts.push(attempt);
}
export function completeCampaignAttempt(scenario: CampaignScenario, completion: {
outcome: CampaignOutcome; productIdentity?: CampaignProductIdentity; finishedAt: string; definitionDigest: string; graderDigest: string;
evidencePaths: string[]; cleanup: CampaignAttempt["cleanup"]; usage: CampaignAttempt["usage"];
classification: string | null;
diagnosisHistory?: Array<{ at: string; classification: string | null; detail: string | null; supersededBy: string }>; observedFailure: string | null; corePrDependencies: string[];
}): void {
const attempt = scenario.attempts.at(-1);
if (!attempt || attempt.outcome !== "running") throw new Error("No running reserved attempt");
if (completion.definitionDigest !== attempt.definitionDigest || completion.graderDigest !== attempt.graderDigest) throw new Error("Definition or grader changed during attempt");
if (completion.evidencePaths.some(value => !value.startsWith("tests/runner-e2e/results/") || value.split("/").includes(".."))) throw new Error("Evidence must use retained sanitized result paths");
if (completion.outcome === "passed" && (!completion.evidencePaths.length || completion.cleanup !== "passed")) throw new Error("Pass requires evidence and successful cleanup");
if (completion.outcome === "passed" && !campaignProductIdentityEligible(scenario, { ...attempt, ...completion })) throw new Error("Pass requires eligible product identity");
if (Date.parse(completion.finishedAt) < Date.parse(attempt.startedAt) || !Number.isFinite(Date.parse(completion.finishedAt))) throw new Error("Invalid completion timing");
Object.assign(attempt, completion);
}
export function campaignSummary(campaign: ChatCampaign) {
const initialPassed = campaign.scenarios.filter(scenario => { const first = scenario.attempts[0]; return first?.outcome === "passed" && first.cleanup === "passed" && first.corePrDependencies.length === 0 && campaignProductIdentityEligible(scenario, first, campaign.baselineRevision); }).length;
const passed = campaign.scenarios.filter(scenario => { const final = scenario.attempts.at(-1); return final?.outcome === "passed" && final.corePrDependencies.length === 0 && final.cleanup === "passed" && final.definitionDigest === scenario.qualifyingDefinitionDigest && final.graderDigest === scenario.qualifyingGraderDigest && campaignProductIdentityEligible(scenario, final, campaign.baselineRevision); }).length;
const attempted = campaign.scenarios.filter(scenario => scenario.attempts.length).length;
const implemented = campaign.scenarios.filter(scenario => scenario.readiness === "implemented").length;
const measured = campaign.scenarios.flatMap(scenario => scenario.attempts.map(attempt => ({ scenario, attempt })));
const productEvidence = { sourceBaselineRevision: campaign.baselineRevision,
measurementsByIdentity: Object.fromEntries(["source-build", "published-release", "source-built-installed", "unknown"].map(kind => [kind, measured.filter(row => (row.attempt.productIdentity?.kind ?? "unknown") === kind).length])),
identityIneligibleMeasurements: measured.filter(row => !campaignProductIdentityEligible(row.scenario, row.attempt, campaign.baselineRevision)).length };
return { productEvidence, denominator: campaign.denominator, implemented, attempted, unrun: campaign.denominator - attempted,
initialPassed, finalPassed: passed, firstAttemptRate: initialPassed / campaign.denominator,
finalRate: passed / campaign.denominator, requiredPasses: campaign.requiredPasses,
mergeEligible: implemented === campaign.denominator && attempted === campaign.denominator && passed >= campaign.requiredPasses && !campaign.scenarios.some(scenario => scenario.attempts.some(attempt => attempt.outcome === "running")) };
}
if (process.argv[1] && import.meta.url === pathToFileURL(path.resolve(process.argv[1])).href) {
const [command, baseline] = process.argv.slice(2);
if (command === "freeze" && baseline) {
writeFileSync(CHAT_CAMPAIGN_MANIFEST, `${JSON.stringify(freezeChatCampaign(process.cwd(), baseline), null, 2)}\n`, { flag: "wx" });
} else if (command !== "summary") throw new Error("Usage: chat-campaign.ts freeze <baseline> | summary");
const campaign = JSON.parse(readFileSync(CHAT_CAMPAIGN_MANIFEST, "utf8")) as ChatCampaign;
validateFrozenCampaign(campaign, process.cwd());
process.stdout.write(`${JSON.stringify({ inventoryDigest: campaign.inventoryDigest, ...campaignSummary(campaign) }, null, 2)}\n`);
}