Files
PaperClipAI/tests/runner-e2e/journey-features.ts
T
DottaandPaperclip 8c9dd1e444 test(runner): qualify Kimi Code lifecycle and recovery (#18029)
Add the Kimi lifecycle and recovery qualification harness. Preserve original grades and cleanup evidence, strict native ownership audits, bounded startup and cleanup, and early rejection of unsupported local fault execution before credentials or resources.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-30 22:54:37 -05:00

135 lines
7.9 KiB
TypeScript

import { fileURLToPath } from "node:url";
import { featureIndex } from "../../scripts/feature-map.mjs";
import type { ReportExecution } from "./report-catalog.js";
export const journeyFeatureMap = featureIndex(fileURLToPath(new URL("../../", import.meta.url)));
export const journeyFeatures = journeyFeatureMap.sections.flatMap((section) =>
section.features.map((feature) => ({ ...feature, section: section.title })),
);
const capabilities = new Map(journeyFeatures.flatMap((feature) =>
feature.capabilities.map((capability) => [capability.id, { ...capability, feature }] as const),
));
const associations = new Map<string, readonly string[]>();
function associate(suites: readonly string[], cases: Record<string, readonly string[]>) {
for (const [caseId, ids] of Object.entries(cases)) {
for (const id of ids) if (!capabilities.has(id)) throw new Error(`Unknown journey capability: ${id}`);
for (const suite of suites) associations.set(`${suite}/${caseId}`, ids);
}
}
associate(["product-journeys"], { "task-create": ["tasks/create"], "ask-question": ["questions-and-approvals/questions"],
"question-answer-resume": ["questions-and-approvals/questions", "questions-and-approvals/continuation"],
"followup-while-running": ["steering/queue"],
"project-task-context": ["projects/lifecycle", "projects/task-context", "tasks/create"],
"task-properties": ["tasks/properties"], "task-search-filter": ["tasks/organize"], "cloud-onboarding": ["onboarding/first-task"] });
associate(["antigravity-agent-journey"], {
"saved-subscription-two-turn": ["agents/hire", "agents/instructions", "runs-adapters/validation", "runs-adapters/session",
"tasks/create", "tasks/completion", "documents-artifacts/attachments", "documents-artifacts/work-products"],
});
associate(["core-compatibility", "openrouter-model-breadth", "extended-harnesses", "grok-qualification", "grok-subscription-qualification", "kimi-qualification"], {
"message-marker": ["runs-adapters/runs"],
"hello-complete": ["runs-adapters/runs"],
"plan-revise-accept": ["questions-and-approvals/plan-review"],
"plan-approve-complete": ["questions-and-approvals/plan-review"],
"ask-question": ["questions-and-approvals/questions"],
"question-resume-complete": ["questions-and-approvals/questions", "questions-and-approvals/continuation"],
});
associate(["local-session-integrity", "extended-harnesses", "grok-qualification", "grok-subscription-qualification", "kimi-qualification"], {
"structured-question-resume": ["questions-and-approvals/continuation", "runs-adapters/session"],
"structured-question-restart-resume": ["questions-and-approvals/continuation", "runs-adapters/session"],
});
associate(["question-resume"], {
"question-answer-resume": ["questions-and-approvals/questions", "questions-and-approvals/continuation"],
});
associate(["feedback-persistence"], {
"complaint-and-suggestion": ["activity/agent-commentary"],
});
associate(["continuation"], {
"answer-updates-scope": ["questions-and-approvals/questions", "questions-and-approvals/continuation"],
"clarification-not-approval": ["questions-and-approvals/questions", "questions-and-approvals/confirmations"],
"revision-preserves-approval": ["questions-and-approvals/plan-review"],
"completed-action-resume": ["questions-and-approvals/continuation"],
"question-tool-documentation": ["questions-and-approvals/questions"],
"provider-question-bridge": ["questions-and-approvals/questions", "questions-and-approvals/continuation"],
});
associate(["first-task", "confirmation-replies", "completion-updates"], Object.fromEntries([
"interview-first-response", "clear-task-first-response", "ambiguous-task-first-response",
"plain-message-first-response", "plan-first-response", "interview-plan-accept",
"task-card-accept", "accept-while-running", "task-reply-accept", "clarify-propose-accept",
"revise-accept", "reject-no-execution",
].map((id) => [id, ["onboarding/first-task"]])));
associate(["first-task"], { "ordinary-task-control": ["tasks/completion"] });
associate(["confirmation-replies"], {
"confirmation-ambiguous": ["questions-and-approvals/confirmations", "questions-and-approvals/audience"],
"unanswered-question-return": ["questions-and-approvals/dismiss-and-reopen", "questions-and-approvals/continuation"],
});
associate(["agent-chat", "agent-chat-hardening", "grok-qualification", "grok-subscription-qualification", "kimi-qualification", "stock-harness"], {
"create-backlog": ["tasks/create"],
"reassign-task": ["tasks/properties"],
"continuity-restart": ["agent-chat/history", "runs-adapters/session"],
"new-session": ["agent-chat/history", "runs-adapters/session"],
"stop-new-resume": ["steering/stop-and-pause", "runs-adapters/session"],
"stop-startup-new-resume": ["steering/stop-and-pause", "runs-adapters/session"],
"plan-handoff": ["agent-chat/handoff", "questions-and-approvals/plan-review"],
"clarify-reuse": ["projects/task-context"],
"multi-repository": ["projects/repositories"],
"hire-delegate-reuse": ["agents/hire", "task-coordination/delegation"],
"committed-send-retry": ["recovery/unknown-outcome"],
});
associate(["agent-chat-qualification"], {
"active-reassignment": ["tasks/properties"],
"worker-crash-retry": ["recovery/source-action"],
});
associate(["agent-chat-stories"], {
"enable-disable-resume": ["agent-chat/history"],
"followup-while-running": ["steering/queue"],
"revise-while-running": ["steering/steer"],
});
associate(["completion-updates"], Object.fromEntries([
"handoff-completion-idle", "handoff-completion-busy", "handoff-completion-multiple", "handoff-completion-restart",
].map((id) => [id, ["agent-chat/handoff", "tasks/completion"]])));
associate(["everyday-workflows", "native-connection-guidance", "grok-qualification", "grok-subscription-qualification"], {
"build-revise": ["documents-artifacts/work-products"],
"delegate-feedback": ["task-coordination/delegation", "steering/steer"],
"agent-review-handoff": ["task-coordination/signoff"],
"hire-reuse": ["agents/hire", "task-coordination/delegation"],
"service-approve": ["questions-and-approvals/tool-review", "app-permissions/action-policy"],
"service-decline": ["questions-and-approvals/tool-review", "app-permissions/action-policy"],
"connection-decline": ["connection-setup/task-request"],
"provider-decline": ["connection-setup/task-request"],
"provider-second": ["connection-setup/task-request"],
"provider-native": ["connection-setup/task-request"],
"agentmail-setup": ["connection-setup/task-request"],
"recover-controller": ["recovery/user-continuation", "documents-artifacts/work-products"],
"stop-redirect": ["steering/stop-and-pause"],
"create-skill-studio": ["skills/authoring"],
});
associate(["hiring-templates"], { "hire-coder-template-reuse": ["agents/hire", "task-coordination/delegation"] });
associate(["kimi-qualification"], {
"file-edit-validate": ["documents-artifacts/work-products"],
"native-write-permission-stop": ["steering/stop-and-pause", "questions-and-approvals/tool-review"],
"native-write-provider-loss": ["recovery/diagnosis", "questions-and-approvals/tool-review"],
});
associate(["task-workspaces"], {
"task-directory-repository-resume": ["workspaces/binding", "workspaces/provisioning", "projects/repositories"],
});
associate(["task-titles"], {
"prompt-title-standard": ["tasks/create"],
"prompt-title-ask": ["tasks/create"],
"preserve-explicit-title": ["tasks/create"],
});
associate(["pi-controls", "native-active-stop"], {
"pending-permission-stop": ["steering/stop-and-pause"],
"same-turn-steering": ["steering/steer"],
});
export function journeyCapabilities(execution: Pick<ReportExecution, "suite" | "task">) {
return (associations.get(`${execution.suite.id}/${execution.task.id}`) ?? [])
.map((id) => capabilities.get(id)!);
}
export function journeyFeatureIds(execution: Pick<ReportExecution, "suite" | "task">) {
return [...new Set(journeyCapabilities(execution).map((capability) => capability.feature.id))];
}