PaperClipAI/tests/runner-e2e/catalog.ts

import { ROLLING_WEB_DEPLOYMENT_SUITE, ROLLING_WEB_DEPLOYMENT_WARM_SUITE } from "./controller-rolling-deployment.js";
import { supportsManagedNativeWarmSession } from "../../server/src/services/native-runtime/native-warm-capability.js";
import { CHAT_NATIVE_TIMEOUT_POLICY } from "./chat-native-timeout-policy.js";
import { CHAT_SETUP_HEALTH_SUITE, chatSetupHealthTask, chatSetupHealthDigest } from "./chat-setup-health.js";
import { CHAT_OPENCODE_MODEL, CHAT_OPENCODE_PROFILE } from "./chat-runtime-profile.js";
import { FEEDBACK_PERSISTENCE_SUITE, feedbackPersistenceTask, feedbackPersistenceDigest } from "./feedback-persistence.js";
import { followupStopTask, followupStopDigest } from "./followup-stop-resume.js";
import { finalizationRecoveryTask, finalizationRecoveryDigest } from "./finalization-recovery.js";
import { necessaryQuestionTask, necessaryQuestionDigest } from "./necessary-question.js";
import { caseHandoffTask, caseHandoffDefinitionDigest } from "./case-handoffs-cases.js";
import { caseReceiptTask, caseReceiptDefinitionDigest, CASE_RECEIPT_BUDGET_CENTS, CASE_RECEIPT_MAX_TURNS, CASE_RECEIPT_RUN_TIMEOUT_MS } from "./case-receipt-cases.js";
import { TASK_WORKSPACES_SUITE, taskWorkspaceTask, taskWorkspaceProfile, taskWorkspaceDefinitionDigest } from "./task-workspaces-cases.js";
import { repositoryProofTasks, repositoryProofProfile, repositoryProofDigest } from "./repository-verification.js";
import { automaticRepositoryTask, automaticRepositoryDigest } from "./automatic-repository.js";
import { nativeActiveStopTasks } from "./native-active-stop-tasks.js";
import { CURSOR_CLOUD_SUITE, cursorCloudArtifactTask, cursorCloudStopTask, CURSOR_CLOUD_QUIET_WINDOW_MS, cursorCloudDefinitionDigest } from "./cursor-cloud-cases.js";
import { kimiLifecycleTasks } from "./kimi-lifecycle-tasks.js";
import { piControlTasks } from "./pi-controls-cases.js";
import { cursorNativeTasks } from "./cursor-native-cases.js";
import { copilotProtectionTasks } from "./copilot-protection-tasks.js";
import { piNativeTasks } from "./pi-native-cases.js";
import { piFilePrompt } from "./pi-file-evidence.js";
import { planTaskCases, planTaskProfile, planDefinitionDigest } from "./plan-task-cases.js";
import { nativeCompletionTasks, nativeCompletionDefinitionDigest } from "./native-completion-cases.js";
import { NATIVE_INSTRUCTION_SUITE, NATIVE_INSTRUCTION_BASE_SHA, nativeInstructionDefinitionDigest } from "./native-instruction-consolidation.js";
import { nativeCompletionProfile, NATIVE_COMPLETION_BUDGET_CENTS } from "./native-completion-defaults.js";
import { chatConfirmationTasks } from "./chat-cases.js";
import { buildConnectionSuite } from "./connection-cases.js";
import { buildGitHubReviewJourneySuite } from "./github-review-cases.js";
import { buildAntigravityJourneySuite } from "./antigravity-journey-cases.js";
import { hiringTemplateTasks, hiringTemplateProfile, hiringTemplateDefinitionDigest } from "./hiring-template-cases.js";
import { copilotProviderDeathTasks } from "./copilot-active-stop-tasks.js";
import { instructionPersistenceTask } from "./instruction-persistence.js";
import { apiResponseReadingTask } from "./api-response-reading.js";
import { CODEX_PLANNING_READ_ONLY_SUITE, codexPlanningReadOnlyTask } from "./codex-planning-read-only.js";
import { apiArtifactTransferTask } from "./api-artifact-transfer.js";
import { taskTitleTasks, taskTitleDefinitionDigest, TASK_TITLE_BUDGET_CENTS } from "./task-titles.js";
import { chatCatalogInventoryDigest, chatCatalogScenarios } from "./chat-catalog-inventory.js";
import { CHAT_FEATURE_SUITE, CHAT_FEATURE_BUDGET_CENTS, CHAT_FEATURE_OPENCODE_MODEL, chatFeatureTasks, chatCatalogTasks, chatFeatureProfile, chatFeatureScenarios, chatFeatureDefinitionDigest } from "./chat-feature-cases.js";
import { blockerTasks, blockerProfile } from "./blocker-cases.js";
import { accountingTasks } from "./accounting-cases.js";
import { continuationTasks, questionResumeTask } from "./continuation-cases.js";
import { contextIntegrityTasks, paperclipDocumentTask } from "./context-integrity-cases.js";
import { productionDefaultHireProfile, stockHarnessSourceDigest, stockHarnessSkillSources } from "./stock-harness.js";
import { lifecycleLiveTasks, lifecycleLiveDefinitionDigest } from "./lifecycle-live-cases.js";
import { publicMcpTasks, publicMcpExpandedDigest, publicMcpSetupDigest, publicMcpWorkflowDigest, publicMcpWorkerInstructions, publicMcpWorkerSkillDigest } from "./public-mcp-cases.js";
import { graderVersion as publicMcpGraderVersion } from "./public-mcp-grading.js";
import { everydayTasks, productionStoryProfile } from "./everyday-cases.js";
import { EVERYDAY_RELIABILITY_GROUP, EVERYDAY_RELIABILITY_SLOW_GROUP, RELIABILITY_FACADE_PROFILE_IDS, RELIABILITY_PLAN_PROFILE_ID, everydayReliabilityExecutionIds, reliabilityPlanCells, everydayReliabilitySignatures, everydayReliabilityTasks } from "./everyday-reliability-cases.js";
import { REMOTE_WORKSPACE_STORAGE_SUITE, remoteWorkspaceStoragePrompt } from "./remote-workspace-storage.js";
import { CONNECTION_GUIDANCE_SUITE, CONNECTION_GUIDANCE_BUDGET_CENTS, connectionGuidanceTasks, connectionGuidanceDefinitionDigest } from "./connection-guidance-cases.js";

import { firstTaskTasks, onboardingApprovalHistoryTask } from "./first-task-cases.js";
import { APPROVAL_HISTORY_SUITE, approvalHistoryDefinitionDigest } from "./first-task-approval-history.js";
import { chatTasks, chatHardeningTasks, chatStoryTasks, chatQualificationTasks, chatCompletionTasks } from "./chat-cases.js";
import { createHash } from "node:crypto";
import { neutralFixtureSuffix } from "./fixture-names.js";
import { fileURLToPath } from "node:url";
import { createAgentSchema } from "../../packages/shared/src/validators/agent.js";
import { createEnvironmentSchema } from "../../packages/shared/src/validators/environment.js";
import { DEFAULT_CODEX_LOCAL_MODEL } from "../../packages/adapters/codex-local/src/index.js";
import { models as claudeModels } from "../../packages/adapters/claude-local/src/index.js";
import { DEFAULT_KIMI_LOCAL_MODEL } from "../../packages/adapters/kimi-local/src/index.js";
import { DEFAULT_GROK_LOCAL_MODEL } from "../../packages/adapters/grok-local/src/index.js";
import { QUALIFIED_ACPX_PROFILES } from "../../packages/paperclip-runner/src/drivers/acpx/qualified-profiles.js";
import { ACPX_QUALIFICATION_MODELS } from "../acpx-qualification-models.js";
import { QUALIFIED_OPENCODE_MODEL } from "../../packages/paperclip-runner/src/drivers/opencode/opencode-server-driver.js";
import { CREDENTIAL_NAMES } from "./types.js";
import { repositorySkillsTask, repositorySkillsProfile } from "./repository-skills.js";
import { createGitStreamingTask } from "./daytona-git-streaming.js";
import { PENDING_PROFILE_PREREQUISITES } from "./prerequisites.js";
import {
  openRouterProfileId,
  openRouterRankingSnapshot,
} from "./openrouter-ranking.js";
import type {
  AgentFixtureBuildInput,
  EnvironmentFixture,
  EnvironmentFixtureBuildInput,
  MatrixExecution,
  RunnerProfileFixture,
  RunnerTaskFixture,
  RunnerSuiteFixture,
  SecretReference,
} from "./types.js";

const ENVIRONMENT_IDS = ["local", "daytona"] as const;
const SELECTABLE_GROUPS = [
  "legacy",
  "native",
  "local",
  "daytona",
  "warm",
  "core",
  "breadth",
  "chat",
  "onboarding",
  "context-integrity",
  "stock-harness",
  EVERYDAY_RELIABILITY_GROUP,
  EVERYDAY_RELIABILITY_SLOW_GROUP,
] as const;
const SAMPLE_UUID = "11111111-1111-4111-8111-111111111111";

export function isImmutableDaytonaImage(value: string | undefined) {
  return /^.+@sha256:[0-9a-f]{64}$/i.test(value ?? "");
}

function requiredSecret(
  input: AgentFixtureBuildInput,
  name: RunnerProfileFixture["credential"],
): SecretReference {
  const value = input.secretRefs[name];
  if (!value) throw new Error(`Missing fixture secret reference ${name}`);
  return value;
}

function commonAgent(
  input: AgentFixtureBuildInput,
  fixtureId: string,
  adapterType: string,
  adapterConfig: Record<string, unknown>,
  additionalInstructions: readonly string[] = [],
) {
  return {
    name: `Agent ${neutralFixtureSuffix(fixtureId, input.executionId)}`,
    role: "qa",
    title: "Operations agent",
    capabilities:
      "Completes standard, planning, and ask-mode tasks for the company.",
    adapterType,
    ...(adapterType === "codex_local" ? { runner: "legacy" as const } : {}),
    adapterConfig,
    defaultEnvironmentId: input.environmentId,
    budgetMonthlyCents: 0,
    instructionsBundle: {
      entryFile: "AGENTS.md",
      files: {
        "AGENTS.md": [
          "You are running a paid Paperclip end-to-end acceptance fixture.",
          "Follow the assigned task and its Paperclip work mode literally.",
          "In ongoing agent chats, follow the injected production chat directive; keep the conversation available after replying. The completion and implementation instructions below apply only to ordinary execution tasks.",
          "For ordinary standard and ask tasks, publish the requested visible answer and mark the task done.",
          "For ordinary planning tasks, publish or revise the canonical Plan document and its revision-bound request_confirmation, then wait. Only implement after that exact plan is accepted.",
          "Invoke assigned tools only through the runtime's real tool-call channel. Never print XML, DSML, JSON, or other tool-call markup as assistant text.",
          "Legacy adapters must use the public Paperclip API and the injected PAPERCLIP_API_URL, PAPERCLIP_API_KEY, PAPERCLIP_TASK_ID, and PAPERCLIP_RUN_ID values for comments, documents, interactions, and status changes.",
          ...(adapterType === "paperclip_runner"
            ? []
            : [
                "Read the assigned paperclip skill before using the Paperclip API. Use its documented request payloads rather than guessing fields from memory.",
                'For a planning task, do not inspect the OpenAPI schema. PUT /api/issues/$PAPERCLIP_TASK_ID/documents/plan with {title:"Plan",format:"markdown",body,changeSummary}; read latestRevisionId and latestRevisionNumber from that response. Then POST /api/issues/$PAPERCLIP_TASK_ID/interactions with {kind:"request_confirmation",continuationPolicy:"wake_assignee",payload:{version:1,prompt,acceptLabel:"Approve",rejectLabel:"Reject",rejectRequiresReason:true,target:{type:"issue_document",key:"plan",revisionId,revisionNumber}}}, and PATCH the issue to {status:"in_review"}. Include Authorization and X-Paperclip-Run-Id on every write.',
              ]),
          "Never print, persist, or expose credential values, and never create unrelated work.",
          ...additionalInstructions,
        ].join("\n"),
      },
    },
    runtimeConfig: {},
  };
}

function legacyProfile(input: {
  id: string;
  label: string;
  adapterType: "codex_local" | "claude_local" | "opencode_local" | "kimi_local" | "grok_local";
  provider: string;
  model: string;
  credential: RunnerProfileFixture["credential"];
  extraConfig?: Record<string, unknown>;
  instructions?: readonly string[];
  modelQualification?: RunnerProfileFixture["modelQualification"];
}): RunnerProfileFixture {
  return {
    ...input,
    modelQualification: input.modelQualification ?? {
      source: "adapter_constant",
      qualificationId: `${input.adapterType}:default-model`,
    },
    generation: "legacy",
    groups: ["legacy"],
    supportedEnvironments: ENVIRONMENT_IDS,
    expectedRuntimeMode: "legacy",
    expectedRuntimeMetadata: {
      adapterType: input.adapterType,
      provider: input.provider,
    },
    buildAgent(buildInput) {
      return commonAgent(buildInput, input.id, input.adapterType, {
        // Remote adapters must inherit the lease's provider-owned remoteCwd.
        // A host path here would override that mapping inside the sandbox.
        ...(buildInput.environmentFixtureId === "local"
          ? { cwd: buildInput.workspacePath }
          : {}),
        model: input.model,
        timeoutSec: buildInput.environmentFixtureId === "daytona" ? 780 : 360,
        dangerouslySkipPermissions: true,
        ...input.extraConfig,
        env: {
          [input.credential]: requiredSecret(buildInput, input.credential),
        },
      }, input.instructions);
    },
  };
}

const PI_QUALIFICATION_THINKING_LEVEL = "low" as const;

function nativeProfile(input: {
  id: string;
  label: string;
  provider: "codex" | "opencode" | "acpx";
  model: string;
  credential: RunnerProfileFixture["credential"];
  acpxAgent?: "claude" | "codex" | "grok" | "cursor" | "copilot" | "pi" | "kimi";
  qualificationCandidate?: RunnerProfileFixture["qualificationCandidate"];
  supportedEnvironments?: readonly (typeof ENVIRONMENT_IDS)[number][];
  modelQualification?: RunnerProfileFixture["modelQualification"];
  ranking?: RunnerProfileFixture["ranking"];
}): RunnerProfileFixture {
  return {
    ...input,
    adapterType: "paperclip_runner",
    generation: "native",
    groups: ["native"],
    supportedEnvironments: input.supportedEnvironments ?? ENVIRONMENT_IDS,
    expectedRuntimeMode: "native",
    modelQualification: input.modelQualification ?? {
      source:
        input.provider === "acpx"
          ? "qualified_runner_profile"
          : "adapter_constant",
      qualificationId:
        input.provider === "acpx"
          ? `acpx:${input.acpxAgent}`
          : `${input.provider}:qualified-model`,
    },
    ...(input.ranking ? { ranking: input.ranking } : {}),
    expectedRuntimeMetadata: {
      adapterType: "paperclip_runner",
      provider: input.provider,
    },
    buildAgent(buildInput) {
      const credentialRef = ["GROK_AUTH_JSON", "CODEX_AUTH_JSON"].includes(input.credential)
        ? null
        : requiredSecret(buildInput, input.credential);
      const permissionConfig =
        input.provider === "codex"
          ? { codexPermissionMode: "never" }
          : input.provider === "opencode"
            ? { opencodePermissionMode: "allow" }
            : { acpxPermissionMode: "approve-all", acpxAgent: input.acpxAgent };
      return commonAgent(buildInput, input.id, "paperclip_runner", {
        provider: input.provider,
        model: input.model,
        ...(input.qualificationCandidate ? { timeoutSec: 120 } : {}),
        lifecycleMode: "per_turn",
        idleTimeoutMs: 300_000,
        ...permissionConfig,
        ...(input.acpxAgent === "pi" ? { piThinkingLevel: PI_QUALIFICATION_THINKING_LEVEL } : {}),
        env: {
          ...(credentialRef ? { [input.credential]: credentialRef } : {}),
          // Codex's supported automation credential is CODEX_API_KEY. Keep
          // OPENAI_API_KEY as the operator-facing fixture secret name and bind
          // the same encrypted reference to the runtime-specific alias.
          ...(input.provider === "codex" && credentialRef
            ? { CODEX_API_KEY: credentialRef }
            : {}),
        },
      });
    },
  };
}

/** Chat acceptance exercises the shipped provider defaults, not full-auto fixtures. */
function defaultPermissionProfile(profile: RunnerProfileFixture): RunnerProfileFixture {
  if (profile.generation !== "native") return profile;
  return {
    ...profile,
    buildAgent(input) {
      const payload = profile.buildAgent(input);
      const { codexPermissionMode: _codex, acpxPermissionMode: _acpx, ...adapterConfig } = payload.adapterConfig as Record<string, unknown>;
      return { ...payload, adapterConfig };
    },
  };
}

const claudeLegacyModel = "claude-sonnet-4-6";
if (!claudeModels.some((model) => model.id === claudeLegacyModel)) {
  throw new Error(
    `Claude adapter does not expose the qualified ${claudeLegacyModel} model`,
  );
}

export const runnerProfiles: readonly RunnerProfileFixture[] = [
  legacyProfile({
    id: "legacy-codex",
    label: "Legacy Codex",
    adapterType: "codex_local",
    provider: "codex",
    model: DEFAULT_CODEX_LOCAL_MODEL,
    credential: "OPENAI_API_KEY",
    // Keep this fixture on the classic adapter/CLI lane. ACP execution is
    // covered independently by the native runner ACPX profiles below.
    extraConfig: {
      engine: "cli",
      // Shell snapshots serialize inherited environment values into CODEX_HOME.
      // These disposable runs carry short-lived API credentials; keep that
      // optional optimization off rather than exempting leaked files from scans.
      extraArgs: ["-c", "features.shell_snapshot=false"],
    },
  }),
  legacyProfile({
    id: "legacy-claude",
    label: "Legacy Claude",
    adapterType: "claude_local",
    provider: "claude",
    model: claudeLegacyModel,
    credential: "ANTHROPIC_API_KEY",
    extraConfig: {
      engine: "cli",
      // Plan fixtures need enough tool turns to read the issue, write the
      // canonical Plan document, and request confirmation. Four turns caused
      // the Claude CLI to terminate correctly but prematurely with
      // `max_turns_exhausted` during the revision flow.
      maxTurnsPerRun: 24,
    },
  }),
  legacyProfile({
    id: "legacy-opencode",
    label: "Legacy OpenCode",
    adapterType: "opencode_local",
    provider: "opencode",
    model: QUALIFIED_OPENCODE_MODEL,
    credential: "OPENROUTER_API_KEY",
  }),
  nativeProfile({
    id: "runner-codex",
    label: "Runner Codex",
    provider: "codex",
    model: DEFAULT_CODEX_LOCAL_MODEL,
    credential: "OPENAI_API_KEY",
  }),
  nativeProfile({
    id: "runner-opencode",
    label: "Runner OpenCode",
    provider: "opencode",
    model: QUALIFIED_OPENCODE_MODEL,
    credential: "OPENROUTER_API_KEY",
  }),
  nativeProfile({
    id: "runner-acpx-claude",
    label: "Runner ACPX Claude",
    provider: "acpx",
    acpxAgent: "claude",
    model: ACPX_QUALIFICATION_MODELS.claude,
    credential: "ANTHROPIC_API_KEY",
  }),
  nativeProfile({
    id: "runner-acpx-grok",
    label: "Runner Grok Build",
    provider: "acpx",
    acpxAgent: "grok",
    model: ACPX_QUALIFICATION_MODELS.grok,
    credential: "XAI_API_KEY",
  }),
  nativeProfile({
    id: "runner-acpx-codex",
    label: "Runner ACPX Codex",
    provider: "acpx",
    acpxAgent: "codex",
    model: ACPX_QUALIFICATION_MODELS.codex,
    credential: "OPENAI_API_KEY",
  }),
] as const;

// Explicit qualification choices from authenticated model discovery, not shipped
// defaults. Cursor has local/Daytona proof; Copilot and Pi remain pending.
export const extendedHarnessProfiles: readonly RunnerProfileFixture[] = [
  nativeProfile({
    id: "runner-acpx-cursor", label: "Runner Cursor", provider: "acpx", acpxAgent: "cursor",
    qualificationCandidate: "cursor", credential: "CURSOR_AUTH_TOKEN",
    model: "gpt-5.6-luna[context=272k,reasoning=medium,fast=false]",
    modelQualification: { source: "qualified_runner_profile", qualificationId: "cursor:2026.09.26-dd393fe:v11:luna:local-daytona-2026-10-04" },
  }),
  nativeProfile({
    id: "runner-acpx-copilot", label: "Runner Copilot (candidate)", provider: "acpx", acpxAgent: "copilot",
    qualificationCandidate: "copilot", credential: "COPILOT_GITHUB_TOKEN", model: "gpt-5.6-luna",
    modelQualification: { source: "candidate_runner_profile", qualificationId: "copilot:1.0.88:discovery-2026-09-28" },
  }),
  nativeProfile({
    id: "runner-acpx-pi", label: "Runner Pi (candidate)", provider: "acpx", acpxAgent: "pi",
    qualificationCandidate: "pi", credential: "OPENROUTER_API_KEY", model: ACPX_QUALIFICATION_MODELS.pi,
    modelQualification: { source: "candidate_runner_profile", qualificationId: "pi:0.0.33:1.0.0:openrouter" },
  }),
];

/** Narrow legacy ACP lanes used only by the explicit context-integrity matrix. */
export const legacyAcpxProfiles: readonly RunnerProfileFixture[] = [
  legacyProfile({
    id: "legacy-acp-codex",
    label: "Legacy ACP Codex",
    adapterType: "codex_local",
    provider: "codex",
    model: DEFAULT_CODEX_LOCAL_MODEL,
    credential: "OPENAI_API_KEY",
    extraConfig: { engine: "acp", mode: "oneshot" },
  }),
  legacyProfile({
    id: "legacy-acp-claude",
    label: "Legacy ACP Claude",
    adapterType: "claude_local",
    provider: "claude",
    model: claudeLegacyModel,
    credential: "ANTHROPIC_API_KEY",
    extraConfig: { engine: "acp", mode: "oneshot" },
  }),
] as const;

/** Explicit-only context-integrity profiles; admission is blocked until qualification is complete. */
export const pendingContextIntegrityProfiles: readonly RunnerProfileFixture[] = [
  legacyProfile({
    id: "legacy-kimi-cli",
    label: "Legacy Kimi CLI (pending qualification)",
    adapterType: "kimi_local",
    provider: "kimi",
    model: DEFAULT_KIMI_LOCAL_MODEL,
    credential: "KIMI_MODEL_API_KEY",
    extraConfig: { engine: "cli" },
  }),
  legacyProfile({
    id: "legacy-kimi-acp",
    label: "Legacy Kimi ACP (pending qualification)",
    adapterType: "kimi_local",
    provider: "kimi",
    model: DEFAULT_KIMI_LOCAL_MODEL,
    credential: "KIMI_MODEL_API_KEY",
    extraConfig: { engine: "acp", mode: "oneshot" },
  }),
  legacyProfile({
    id: "legacy-grok",
    label: "Legacy Grok (pending qualification)",
    adapterType: "grok_local",
    provider: "grok",
    model: DEFAULT_GROK_LOCAL_MODEL,
    credential: "XAI_API_KEY",
  }),
] as const;

export const contextIntegrityProfiles: readonly RunnerProfileFixture[] = [
  ...runnerProfiles.filter((profile) => ["runner-codex", "runner-acpx-claude", "runner-opencode", "legacy-codex", "legacy-claude"].includes(profile.id)),
  ...legacyAcpxProfiles,
  ...pendingContextIntegrityProfiles,
];

export const openRouterBreadthExcludedModelIds = ["xiaomi/mimo-v2.5"] as const;
export const openRouterBreadthExcludedExecutionIds = [
  "openrouter-model-breadth.openrouter-deepseek-deepseek-v4-flash-0731.local.plan-approve-complete",
  "openrouter-model-breadth.openrouter-tencent-hy3.local.plan-approve-complete",
] as const;
const openRouterBreadthExcludedModelIdSet = new Set<string>(
  openRouterBreadthExcludedModelIds,
);

export const openRouterBreadthProfiles: readonly RunnerProfileFixture[] =
  openRouterRankingSnapshot.models
    .filter(
      (rankedModel) => !openRouterBreadthExcludedModelIdSet.has(rankedModel.id),
    )
    .map((rankedModel) =>
      nativeProfile({
        id: openRouterProfileId(rankedModel.id),
        label: `#${rankedModel.rank} ${rankedModel.name}`,
        provider: "opencode",
        model: `openrouter/${rankedModel.id}`,
        credential: "OPENROUTER_API_KEY",
        supportedEnvironments: ["local"],
        modelQualification: {
          source: "openrouter_rankings_snapshot",
          qualificationId: `${openRouterRankingSnapshot.snapshotId}:${rankedModel.rank}`,
        },
        ranking: {
          rank: rankedModel.rank,
          canonicalModelId: rankedModel.id,
          snapshotId: openRouterRankingSnapshot.snapshotId,
          capturedAt: openRouterRankingSnapshot.capturedAt,
          sourceUrl: openRouterRankingSnapshot.sourceUrl,
        },
      }),
    );

function requiredDaytonaSecret(input: EnvironmentFixtureBuildInput) {
  const apiKey = input.secretRefs.DAYTONA_API_KEY;
  if (!apiKey)
    throw new Error("Missing fixture secret reference DAYTONA_API_KEY");
  return apiKey;
}

export const runnerEnvironments: readonly EnvironmentFixture[] = [
  {
    id: "local",
    label: "Isolated local",
    groups: ["local"],
    driver: "local",
    provider: "local",
    lifecycle: {
      setup: "instance_managed",
      probe: "run_context_via_api",
      cleanup: "instance_shutdown",
    },
    expectedExecutionTarget: { kind: "local" },
    buildEnvironment(input) {
      return {
        name: `Local ${neutralFixtureSuffix(input.executionId)}`,
        description: "Local execution environment",
        driver: "local",
        config: {},
        envVars: {},
      };
    },
  },
  {
    id: "daytona",
    label: "Daytona sandbox",
    groups: ["daytona"],
    driver: "sandbox",
    provider: "daytona",
    credential: "DAYTONA_API_KEY",
    lifecycle: {
      setup: "create_via_api",
      probe: "run_context_via_api",
      cleanup: "delete_via_api_and_destroy_leases",
    },
    expectedExecutionTarget: { kind: "remote", transport: "sandbox" },
    buildEnvironment(input) {
      if (!isImmutableDaytonaImage(input.daytonaImage)) {
        throw new Error(
          "PAPERCLIP_E2E_DAYTONA_IMAGE must be an immutable image digest",
        );
      }
      return {
        name: `Daytona ${neutralFixtureSuffix(input.executionId)}`,
        description: "Daytona sandbox environment",
        driver: "sandbox",
        config: {
          provider: "daytona",
          apiKey: requiredDaytonaSecret(input),
          image: input.daytonaImage,
          // Pin the billable resource shape so per-test runtime list-price
          // estimates remain reproducible when provider defaults change.
          cpu: 4,
          memory: 4,
          disk: 10,
          reuseLease: false,
          runnerLifecycleMode: "per_turn",
          autoStopInterval: 5,
          autoArchiveInterval: 15,
          autoDeleteInterval: 60,
          ttlMinutes: 60,
          timeoutMs: 300_000,
          livenessTimeoutMs: 30_000,
        },
        envVars: {},
      };
    },
  },
] as const;

export const daytonaWarmEnvironment: EnvironmentFixture = {
  id: "daytona",
  configurationKey: "warm-reuse-v1",
  label: "Daytona warm reusable sandbox",
  groups: ["daytona", "warm"],
  driver: "sandbox",
  provider: "daytona",
  credential: "DAYTONA_API_KEY",
  lifecycle: {
    setup: "create_via_api",
    probe: "run_context_via_api",
    cleanup: "delete_via_api_and_destroy_leases",
  },
  expectedExecutionTarget: { kind: "remote", transport: "sandbox" },
  buildEnvironment(input) {
    if (!isImmutableDaytonaImage(input.daytonaImage)) {
      throw new Error(
        "PAPERCLIP_E2E_DAYTONA_IMAGE must be an immutable image digest",
      );
    }
    return {
      name: `Daytona warm ${neutralFixtureSuffix(input.executionId)}`,
      description: "Reusable Daytona sandbox environment",
      driver: "sandbox",
      config: {
        provider: "daytona",
        apiKey: requiredDaytonaSecret(input),
        image: input.daytonaImage,
        cpu: 4,
        memory: 4,
        disk: 10,
        reuseLease: true,
        runnerLifecycleMode: "warm",
        autoStopInterval: 5,
        autoArchiveInterval: 15,
        autoDeleteInterval: 60,
        timeoutMs: 300_000,
        livenessTimeoutMs: 30_000,
      },
      envVars: {},
    };
  },
};

export const runnerTasks: readonly RunnerTaskFixture[] = [
  {
    id: "message-marker",
    label: "Basic response",
    groups: [],
    workMode: "standard",
    flow: "single_turn",
    expectedRunCount: 1,
    attemptTimeoutMs: {
      local: 8 * 60_000,
      daytona: 15 * 60_000,
    },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: (nonce) => `Runner E2E PAPERCLIP_E2E_OK_${nonce}`,
    buildVisibleMarker: (nonce) => `PAPERCLIP_E2E_OK_${nonce}`,
    buildPrompt: (nonce) =>
      [
        "Complete this task in a single run.",
        `The exact marker also appears unescaped in the task title: PAPERCLIP_E2E_OK_${nonce}`,
        `Your final visible task-thread response must be exactly this marker: PAPERCLIP_E2E_OK_${nonce}`,
        `In a native runner, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_OK_${nonce}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit exactly PAPERCLIP_E2E_OK_${nonce} once as the complete user-facing final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
        `In a legacy runner, make exactly one public-API write containing the marker: PATCH /api/issues/$PAPERCLIP_TASK_ID with {"status":"done","comment":"PAPERCLIP_E2E_OK_${nonce}"}. Do not POST to /comments, and do not include the marker in any other write.`,
        "The visible task-thread response is asserted; hidden reasoning or provider terminal output alone does not count.",
        "Use underscore characters exactly as shown and do not insert backslashes.",
        "Do not create files, ask questions, start additional tasks, or include any credentials.",
      ].join("\n"),
    buildMatchers(nonce, execution) {
      return [
        { kind: "message_exact", expected: `PAPERCLIP_E2E_OK_${nonce}` },
        {
          kind: "message_occurrences",
          expected: `PAPERCLIP_E2E_OK_${nonce}`,
          count: 1,
        },
        {
          kind: "issue_status",
          expected: execution.task.expectedTerminalState.issue,
        },
        {
          kind: "run_status",
          expected: execution.task.expectedTerminalState.run,
        },
        {
          kind: "runtime_mode",
          expected: execution.profile.expectedRuntimeMode,
        },
        { kind: "environment", expected: execution.environment.id },
      ];
    },
  },
  {
    id: "plan-revise-accept",
    label: "Plan, revise, accept, implement",
    groups: [],
    workMode: "planning",
    flow: "plan_revision_acceptance",
    expectedRunCount: 3,
    attemptTimeoutMs: {
      local: 8 * 60_000,
      daytona: 12 * 60_000,
    },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: (nonce) => `Runner E2E plan lifecycle ${nonce}`,
    buildVisibleMarker: (nonce) => `PAPERCLIP_E2E_PLAN_DONE_${nonce}`,
    buildPlanMarkers: (nonce) => ({
      draft: `PAPERCLIP_E2E_PLAN_DRAFT_${nonce}`,
      revised: `PAPERCLIP_E2E_PLAN_REVISED_${nonce}`,
    }),
    buildRevisionRequest: (nonce) =>
      [
        "Revise this same plan; do not implement it yet.",
        `Replace the first line with exactly PAPERCLIP_E2E_PLAN_REVISED_${nonce} and remove PAPERCLIP_E2E_PLAN_DRAFT_${nonce}. Use literal underscore characters with no backslashes or other text on that first line.`,
        "Change the plan from two steps to exactly three numbered steps, with verification as step 3.",
        "Publish the revised canonical Plan revision and request confirmation for that new revision.",
        "In a native runner, call write_document for key `plan`, then call request_human_input exactly once with interactionKind `confirmation`, targetRevisionId set to the returned latest Plan revision, and continuationPolicy `wake_assignee`; do not call paperclip_finish while waiting. After write_document succeeds, request_human_input must be your immediate next action using that call's returned latestRevisionId; do not emit assistant text, end the response or heartbeat, or stop after write_document alone.",
        "In a legacy runner, first GET the current `plan` issue document, then PUT the revised Plan with `baseRevisionId` set to that response's `latestRevisionId`; after the update succeeds, create the equivalent request_confirmation targeting the newly returned `latestRevisionId` through the public Paperclip API.",
      ].join(" "),
    buildPrompt: (nonce) =>
      [
        "This is a planning-mode lifecycle acceptance task.",
        "First, create a small canonical Plan with exactly two numbered steps and request approval; do not implement it.",
        `The initial Plan body must have exactly PAPERCLIP_E2E_PLAN_DRAFT_${nonce} as its first line, followed by exactly two numbered steps. Use literal underscore characters with no backslashes or other text on that first line.`,
        "If the plan is sent back, revise that same Plan document according to the revision note, publish a new revision-bound confirmation, and still do not implement.",
        `Before the revised Plan is accepted, do not spell, quote, repeat, announce, or include PAPERCLIP_E2E_PLAN_DONE_${nonce} in any visible response, comment, or tool payload; refer to it only as “the terminal marker.”`,
        "Only after the revised plan is accepted, implement it by posting one final visible task-thread response containing exactly " +
          `PAPERCLIP_E2E_PLAN_DONE_${nonce}` +
          " and mark the task Done.",
        `For a native runner, remain in the requested planning collaboration mode. Call write_document for key \`plan\`, then call request_human_input exactly once with interactionKind \`confirmation\`, targetRevisionId set to the returned latest Plan revision, and continuationPolicy \`wake_assignee\`. For both the initial Plan and the revised Plan, those two tool calls form one indivisible response sequence: immediately after write_document succeeds, request_human_input must be your next action using that call's returned latestRevisionId. Do not emit assistant text, end the response or heartbeat, or stop after write_document alone before the matching confirmation request succeeds. Do not call paperclip_finish while waiting for either Plan confirmation. When an acceptance wake arrives, first call get_task_context. Treat the wake as valid only when that control-plane result is for the current task and identifies the exact revised Plan revision used as the confirmation target as accepted; otherwise do not finish and continue waiting for the matching revision-bound confirmation. After that verification succeeds, your immediate next action must be the paperclip_finish tool call. Do not call list_documents or any other tool, and do not emit any assistant text, acknowledgement, progress note, or preamble between verification and paperclip_finish. Use the current turn completion revision and criterion IDs. CURRENT_TURN_REVISION and CURRENT_TURN_CRITERIA below are placeholders, not literals. CURRENT_TURN_CRITERIA must contain one {criterionId:<current criterion ID>,status:"satisfied",evidenceRefs:[]} entry for every current criterion ID. Call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_PLAN_DONE_${nonce}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:CURRENT_TURN_CRITERIA,remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit only PAPERCLIP_E2E_PLAN_DONE_${nonce} as the complete final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
        `For a legacy runner, use the public Paperclip API. The first PUT of the \`plan\` issue document creates it. For every later PUT, first GET the current document and set \`baseRevisionId\` to its \`latestRevisionId\`; a 409 means you must GET again and retry with the new latest revision. Create a \`request_confirmation\` targeting the successful PUT response's \`latestRevisionId\` with \`continuationPolicy: wake_assignee\`, and move the issue to \`in_review\` while waiting. After the revised Plan is accepted, write PAPERCLIP_E2E_PLAN_DONE_${nonce} exactly once through one atomic issue PATCH with status \`done\` and that exact comment; do not POST a separate comment or perform a second write.`,
        "Do not create files, child tasks, or unrelated work, and do not expose credentials.",
      ].join("\n"),
    buildMatchers(nonce, execution) {
      return [
        {
          kind: "message_exact",
          expected: `PAPERCLIP_E2E_PLAN_DONE_${nonce}`,
        },
        {
          kind: "message_occurrences",
          expected: `PAPERCLIP_E2E_PLAN_DONE_${nonce}`,
          count: 1,
        },
        {
          kind: "issue_status",
          expected: execution.task.expectedTerminalState.issue,
        },
        {
          kind: "run_status",
          expected: execution.task.expectedTerminalState.run,
        },
        {
          kind: "runtime_mode",
          expected: execution.profile.expectedRuntimeMode,
        },
        { kind: "environment", expected: execution.environment.id },
      ];
    },
  },
  {
    id: "ask-question",
    label: "Ask mode question",
    groups: [],
    workMode: "ask",
    flow: "single_turn",
    expectedRunCount: 1,
    attemptTimeoutMs: {
      local: 8 * 60_000,
      daytona: 15 * 60_000,
    },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: (nonce) => `Runner E2E ask mode ${nonce}`,
    buildVisibleMarker: (nonce) => `E2E_ASK_12_${nonce}`,
    buildPrompt: (nonce) =>
      [
        "Answer this question directly in Ask mode: what is seven plus five?",
        `Your final visible task-thread answer must be exactly this complete marker, including its final suffix: E2E_ASK_12_${nonce}.`,
        "Do not create or modify files, do not create a plan or additional work, and do not expose credentials.",
        "After posting the direct answer, mark this task Done.",
        `In a native runner, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"E2E_ASK_12_${nonce}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. For the entire run, paperclip_finish must be your only tool call: never call report_progress or any other tool before or after it. Wait for that tool call to succeed, then emit exactly E2E_ASK_12_${nonce} as the complete final response. Do not write a user-facing final response before paperclip_finish succeeds.`,
        `In a legacy runner, make exactly one public-API write containing the marker: PATCH /api/issues/$PAPERCLIP_TASK_ID with {"status":"done","comment":"E2E_ASK_12_${nonce}"}. Do not POST to /comments, do not PATCH the status separately, and do not include the marker in any other API write.`,
      ].join("\n"),
    buildMatchers(nonce, execution) {
      return [
        {
          kind: "message_exact",
          expected: `E2E_ASK_12_${nonce}`,
        },
        {
          kind: "message_occurrences",
          expected: `E2E_ASK_12_${nonce}`,
          count: 1,
        },
        {
          kind: "issue_status",
          expected: execution.task.expectedTerminalState.issue,
        },
        {
          kind: "run_status",
          expected: execution.task.expectedTerminalState.run,
        },
        {
          kind: "runtime_mode",
          expected: execution.profile.expectedRuntimeMode,
        },
        { kind: "environment", expected: execution.environment.id },
      ];
    },
  },
] as const;

function terminalMatchers(
  nonceMarker: string,
  execution: MatrixExecution,
): readonly ReturnType<RunnerTaskFixture["buildMatchers"]>[number][] {
  return [
    { kind: "message_exact", expected: nonceMarker },
    { kind: "message_occurrences", expected: nonceMarker, count: 1 },
    {
      kind: "issue_status",
      expected: execution.task.expectedTerminalState.issue,
    },
    { kind: "run_status", expected: execution.task.expectedTerminalState.run },
    { kind: "runtime_mode", expected: execution.profile.expectedRuntimeMode },
    { kind: "environment", expected: execution.environment.id },
  ];
}

function breadthMarker(phase: "H" | "Q_C" | "P_READY" | "P_OK", nonce: string) {
  // Keep the complete visible marker comfortably below the shortest output
  // fragments observed across ranked models while retaining the attempt nonce.
  return `PC_${phase}_${nonce}`;
}

const structuredQuestionResumeTask = {
  id: "structured-question-resume",
  label: "Structured question, answer, resume",
  groups: [],
  workMode: "standard",
  flow: "question_resume_completion",
  expectedRunCount: 2,
  attemptTimeoutMs: { local: 12 * 60_000, daytona: 12 * 60_000 },
  expectedTerminalState: { issue: "done", run: "succeeded" },
  buildTitle: (nonce) => `Runner E2E structured question ${nonce}`,
  buildVisibleMarker: (nonce) => `PAPERCLIP_E2E_QUESTION_DONE_${nonce}`,
  buildQuestionAnswer: (nonce) => ({
    optionLabel: "Cobalt",
    expectedMarker: `PAPERCLIP_E2E_QUESTION_DONE_${nonce}`,
  }),
  buildPrompt: (nonce) =>
    [
      "Ask the user one structured question before completing this task.",
      "The question must be required, single-select, and offer Cobalt and Amber. Do not publish a final answer or mark the task Done while it is pending.",
      `Before the answer arrives, do not spell, quote, repeat, announce, or include PAPERCLIP_E2E_QUESTION_DONE_${nonce} in any visible response, comment, or tool payload; refer to it only as “the terminal marker.”`,
      `In a native runner, call request_human_input exactly once with idempotencyKey \`question-${nonce}\`, interactionKind \`questions\`, title \`Verification word\`, prompt \`Choose the verification word\`, continuationPolicy \`wake_assignee\`, and payload {version:1,questions:[{id:\`verification-word\`,prompt:\`Choose the verification word.\`,selectionMode:\`single\`,required:true,options:[{id:\`cobalt\`,label:\`Cobalt\`},{id:\`amber\`,label:\`Amber\`}]}]}.`,
      'In a legacy runner, derive `API_ORIGIN` exactly once with `API_ORIGIN="${PAPERCLIP_API_URL%/}"; API_ORIGIN="${API_ORIGIN%/api}"`. Build every endpoint as `$API_ORIGIN/api/...`; never append `/api` to a base that already ends in `/api`.',
      `In a legacy runner, create exactly one question interaction: POST $API_ORIGIN/api/issues/$PAPERCLIP_TASK_ID/interactions once with {"kind":"ask_user_questions","idempotencyKey":"question-${nonce}","continuationPolicy":"wake_assignee","payload":{"version":1,"questions":[{"id":"verification-word","prompt":"Choose the verification word.","selectionMode":"single","required":true,"options":[{"id":"cobalt","label":"Cobalt"},{"id":"amber","label":"Amber"}]}]}} using Authorization and X-Paperclip-Run-Id. Do not create a replacement interaction if a later write fails.`,
      'In a legacy runner, after that POST returns 2xx, PATCH $API_ORIGIN/api/issues/$PAPERCLIP_TASK_ID with exactly {"status":"in_review"}. Do not include `reviewInteractionId`: it only designates confirmation interactions, not `ask_user_questions`. If the PATCH fails, retry only that PATCH and never POST the interaction again.',
      "In a legacy runner, after those two writes succeed, end the current response and heartbeat immediately. Do not wait, sleep, poll, or fetch the interaction; `wake_assignee` will start a new heartbeat after the user answers.",
      `After the answer arrives, if it is Cobalt, publish exactly PAPERCLIP_E2E_QUESTION_DONE_${nonce} once as the complete visible response and mark the task Done.`,
      `In a native runner, after the answer arrives, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_QUESTION_DONE_${nonce}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit exactly PAPERCLIP_E2E_QUESTION_DONE_${nonce} as the complete final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
      `In a legacy runner, make exactly one completion write: PATCH $API_ORIGIN/api/issues/$PAPERCLIP_TASK_ID with {"status":"done","comment":"PAPERCLIP_E2E_QUESTION_DONE_${nonce}"}. Do not POST a separate comment or perform a second write containing the marker.`,
      "Do not create files, plans, child tasks, or unrelated work, and do not expose credentials.",
    ].join("\n"),
  buildMatchers(nonce, execution) {
    return [
      {
        kind: "message_exact",
        expected: `PAPERCLIP_E2E_QUESTION_DONE_${nonce}`,
      },
      {
        kind: "message_occurrences",
        expected: `PAPERCLIP_E2E_QUESTION_DONE_${nonce}`,
        count: 1,
      },
      {
        kind: "issue_status",
        expected: execution.task.expectedTerminalState.issue,
      },
      {
        kind: "run_status",
        expected: execution.task.expectedTerminalState.run,
      },
      {
        kind: "runtime_mode",
        expected: execution.profile.expectedRuntimeMode,
      },
      { kind: "environment", expected: execution.environment.id },
    ];
  },
} satisfies RunnerTaskFixture;

export const localIntegrityTasks: readonly RunnerTaskFixture[] = [
  structuredQuestionResumeTask,
  {
    ...structuredQuestionResumeTask,
    id: "structured-question-restart-resume",
    label: "Structured question, server restart, answer, resume",
    restartServerBeforeQuestionAnswer: true,
    buildTitle: (nonce) => `Runner E2E restart question ${nonce}`,
  },
] as const;

export const openRouterBreadthTasks: readonly RunnerTaskFixture[] = [
  {
    id: "hello-complete",
    label: "Hello and complete",
    groups: [],
    workMode: "standard",
    flow: "single_turn",
    expectedRunCount: 1,
    attemptTimeoutMs: { local: 8 * 60_000, daytona: 8 * 60_000 },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: (nonce) => `OpenRouter breadth hello ${nonce}`,
    buildVisibleMarker: (nonce) => breadthMarker("H", nonce),
    buildPrompt: (nonce) =>
      [
        "Complete this deterministic hello task in one turn.",
        "Your first response action must be the paperclip_finish tool call. Do not emit any assistant text, acknowledgement, or preamble before calling it.",
        `Use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal). Call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"${breadthMarker("H", nonce)}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit exactly ${breadthMarker("H", nonce)} as the complete user-facing final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
        "Do not create files, plans, interactions, or additional work.",
      ].join("\n"),
    buildMatchers: (nonce, execution) =>
      terminalMatchers(breadthMarker("H", nonce), execution),
  },
  {
    id: "question-resume-complete",
    label: "Ask, answer, resume",
    groups: [],
    workMode: "standard",
    flow: "question_resume_completion",
    expectedRunCount: 2,
    attemptTimeoutMs: { local: 12 * 60_000, daytona: 12 * 60_000 },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: (nonce) => `OpenRouter breadth question ${nonce}`,
    buildVisibleMarker: (nonce) => breadthMarker("Q_C", nonce),
    buildQuestionAnswer: (nonce) => ({
      optionLabel: "Cobalt",
      expectedMarker: breadthMarker("Q_C", nonce),
    }),
    buildPrompt: (nonce) =>
      [
        "Ask the user one structured question before completing this task.",
        `Call request_human_input exactly once with idempotencyKey \`question-${nonce}\`, interactionKind \`questions\`, title \`Verification word\`, prompt \`Choose the verification word\`, continuationPolicy \`wake_assignee\`, and payload {version:1,questions:[{id:\`verification-word\`,prompt:\`Choose the verification word.\`,selectionMode:\`single\`,required:true,options:[{id:\`cobalt\`,label:\`Cobalt\`},{id:\`amber\`,label:\`Amber\`}]}]}.`,
        `Before the answer arrives, do not spell, quote, repeat, announce, or include ${breadthMarker("Q_C", nonce)} in any visible response, comment, or tool payload; refer to it only as “the terminal marker.”`,
        "Do not call paperclip_finish while the question is pending.",
        `After the answer arrives, if it is Cobalt, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"${breadthMarker("Q_C", nonce)}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit exactly ${breadthMarker("Q_C", nonce)} as the complete user-facing final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
        "Do not create files, plans, or additional work.",
      ].join("\n"),
    buildMatchers: (nonce, execution) =>
      terminalMatchers(breadthMarker("Q_C", nonce), execution),
  },
  {
    id: "plan-approve-complete",
    label: "Plan, approve, complete",
    groups: [],
    workMode: "planning",
    flow: "plan_approval_completion",
    expectedRunCount: 2,
    attemptTimeoutMs: { local: 15 * 60_000, daytona: 15 * 60_000 },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: (nonce) => `OpenRouter breadth plan ${nonce}`,
    buildVisibleMarker: (nonce) => breadthMarker("P_OK", nonce),
    buildPlanMarkers: (nonce) => ({
      draft: breadthMarker("P_READY", nonce),
      revised: breadthMarker("P_OK", nonce),
    }),
    buildPrompt: (nonce) =>
      [
        "Create a canonical Plan with exactly two numbered steps and request approval; do not implement before approval.",
        `The Plan body must contain ${breadthMarker("P_READY", nonce)}.`,
        "Call write_document for key `plan`, then call request_human_input exactly once with interactionKind `confirmation`, targetRevisionId set to the returned latest Plan revision, and continuationPolicy `wake_assignee`.",
        `Before that exact Plan revision is accepted, do not spell, quote, repeat, announce, or include ${breadthMarker("P_OK", nonce)} in any visible response, comment, or tool payload; refer to it only as “the terminal marker.”`,
        "Do not call paperclip_finish while confirmation is pending.",
        `After that exact Plan revision is accepted, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"${breadthMarker("P_OK", nonce)}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},evidence:[],verification:[]}. Wait for that tool call to succeed, then emit exactly ${breadthMarker("P_OK", nonce)} as the complete user-facing final response. Do not write a user-facing final response before paperclip_finish succeeds, and do not call another tool.`,
        "Do not create files, child tasks, or unrelated work.",
      ].join("\n"),
    buildMatchers: (nonce, execution) =>
      terminalMatchers(breadthMarker("P_OK", nonce), execution),
  },
] as const;

const localEnvironment = runnerEnvironments.find(
  (environment) => environment.id === "local",
)!;

function warmTurnMarker(turn: 1 | 2 | 3, nonce: string) {
  return `PAPERCLIP_E2E_WARM_T${turn}_${nonce}`;
}

function warmWorkspaceLine(turn: 1 | 2 | 3, nonce: string) {
  // Issue descriptions are rendered through the native prompt's Markdown
  // boundary, which escapes underscores. Keep the byte-level workspace
  // sentinel Markdown-inert so both legacy and native providers receive the
  // same literal content.
  return `T${turn}-${nonce}`;
}

function warmTurnInstructions(turn: 1 | 2 | 3, nonce: string) {
  const file = `daytona-warm-${nonce}.txt`;
  const lines = Array.from({ length: turn }, (_, index) =>
    warmWorkspaceLine((index + 1) as 1 | 2 | 3, nonce),
  );
  const marker = warmTurnMarker(turn, nonce);
  const finalTurn = turn === 3;
  const reviewRequests = finalTurn ? [] : [{
    kind: "review", ownerClass: "human",
    summary: `Review the verified turn ${turn} workspace file and decide whether this task is ready to complete or needs another revision.`,
  }];
  const legacyCompletion = finalTurn
    ? `In a legacy runner, make exactly one public-API completion write after verification: PATCH /api/issues/$PAPERCLIP_TASK_ID with {"status":"done","comment":"${marker}"}. Include Authorization and X-Paperclip-Run-Id. Do not POST a separate comment.`
    : `In a legacy runner, after verification POST exactly one request_confirmation to /api/issues/$PAPERCLIP_TASK_ID/interactions with {"kind":"request_confirmation","idempotencyKey":"daytona-warm-review-T${turn}-${nonce}","resolverPolicy":"human_only","title":"Warm continuity turn ${turn}","summary":"Review completed warm continuity turn ${turn}.","continuationPolicy":"wake_assignee","payload":{"version":1,"prompt":"Is this warm continuity task ready to complete after turn ${turn}?","acceptLabel":"Approve completion","rejectLabel":"Continue work","rejectRequiresReason":true,"allowDeclineReason":true,"supersedeOnUserComment":false,"target":{"type":"custom","key":"daytona_warm_turn_${turn}","revisionId":"${nonce}-T${turn}","label":"Warm continuity turn ${turn}"}}}. Capture the returned interaction id. Then make exactly one issue PATCH with {"status":"in_review","comment":"${marker}","reviewInteractionId":"<returned interaction id>"}. Include Authorization and X-Paperclip-Run-Id on both writes. If the issue PATCH fails, retry only that PATCH and never create another interaction. Do not POST a separate comment. After both writes succeed, end the response and heartbeat immediately; do not wait or poll because the reviewer action will start the next turn.`;
  return [
    `This is warm Daytona continuity turn ${turn} of 3. Work only in the current execution workspace.`,
    turn === 1
      ? `Create ${file} with exactly this one line followed by a newline: ${lines[0]}`
      : `Before changing anything, read ${file} and verify its content is exactly these prior lines in order, each followed by a newline: ${lines.slice(0, -1).join(" | ")}. Then append exactly ${lines.at(-1)} followed by a newline.`,
    "Each newline in this task means the actual LF character (byte 10), including in personal memory files. An escaped representation containing a literal backslash and n is not a newline. Verify the saved bytes against the requested line content and LF byte 10, independently of the string expression used to write them.",
    `After the write, verify ${file} contains exactly these lines, once each and in order: ${lines.join(" | ")}.`,
    `In a native runner, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"${finalTurn ? "done" : "needs_review"}",summary:"${marker}",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},attentionRequests:${JSON.stringify(reviewRequests)},evidence:[],verification:[{commandOrCheck:"read ${file}",status:"passed"}]}. Wait for that tool call to succeed, then emit exactly ${marker} once as the complete user-facing final response.`,
    legacyCompletion,
    `In a legacy runner, the PATCH comment is the complete visible response. After its 2xx response, finish silently: do not print, echo, or emit ${marker} again as assistant text.`,
    `Do not include ${marker} in any other visible response or write. Do not recreate, truncate, reorder, or duplicate prior lines.`,
  ].join("\n");
}

const warmTurnDefinitionDigest = createHash("sha256").update(JSON.stringify(
  ([1, 2, 3] as const).map(turn => warmTurnInstructions(turn, "definition")),
)).digest("hex");

function managedWarmTurnInstructions(turn: 1 | 2 | 3, nonce: string) {
  return [warmTurnInstructions(turn, nonce),
    "Also update your personal AGENT_HOME with ordinary filesystem tools. Do not edit the loaded AGENTS.md instructions and do not use an API to save these files.",
    turn === 1
      ? `Create notes/warm-memory.txt containing exactly T1-${nonce} followed by a newline. Create notes/unchanged.bin with exactly 8388608 bytes, each byte equal to 93. Create notes/delete-me.txt with exactly the nine ASCII bytes temporary and no trailing newline.`
      : `Read notes/warm-memory.txt under AGENT_HOME and verify it contains exactly the prior turn lines ${Array.from({ length: turn - 1 }, (_, i) => `T${i + 1}-${nonce}`).join(" | ")}, each followed by a newline. Append exactly T${turn}-${nonce} and a newline. Verify notes/unchanged.bin still has 8388608 bytes, each equal to 93, and leave it unchanged. ${turn === 2 ? "Delete notes/delete-me.txt." : "Verify notes/delete-me.txt is absent."}`,
    "Perform these personal-file edits and verification before calling paperclip_finish. Paperclip saves them at the turn boundary.",
  ].join("\n");
}

export const daytonaWarmContinuityTask: RunnerTaskFixture = {
  id: "warm-three-turn",
  label: "Warm three-turn workspace continuity",
  groups: ["warm"],
  workMode: "standard",
  flow: "warm_three_turn",
  expectedRunCount: 3,
  attemptTimeoutMs: { local: 30 * 60_000, daytona: 30 * 60_000 },
  turnTimeoutMs: 10 * 60_000,
  expectedTerminalState: { issue: "done", run: "succeeded" },
  buildTitle: (nonce) => `Runner E2E warm Daytona continuity ${nonce}`,
  buildVisibleMarker: (nonce) => warmTurnMarker(3, nonce),
  buildPrompt: (nonce) => managedWarmTurnInstructions(1, nonce),
  buildFollowupMessages: (nonce) => [
    managedWarmTurnInstructions(2, nonce),
    managedWarmTurnInstructions(3, nonce),
  ],
  buildMatchers(nonce, execution) {
    // Workspace persistence is the oracle for this story. Exact response text
    // formatting must not mask a valid workspace, but every warm turn still
    // needs one visible marker in chronological order. Surrounding provider
    // prose is allowed; the occurrence and order matchers grade only markers.
    const markers = ([1, 2, 3] as const).map((turn) => warmTurnMarker(turn, nonce));
    return [
      ...markers.map((marker) => ({ kind: "message_occurrences" as const, expected: marker, count: 1 })),
      { kind: "message_ordered" as const, expected: markers },
      {
        kind: "file_exact",
        path: `daytona-warm-${nonce}.txt`,
        expected: `${([1, 2, 3] as const)
          .map((turn) => warmWorkspaceLine(turn, nonce))
          .join("\n")}\n`,
      },
      { kind: "issue_status", expected: "done" },
      { kind: "run_status", expected: "succeeded" },
      { kind: "runtime_mode", expected: execution.profile.expectedRuntimeMode },
      { kind: "environment", expected: execution.environment.id },
    ];
  },
};

export const daytonaLargeJournalTask: RunnerTaskFixture = {
  ...daytonaWarmContinuityTask,
  id: "large-journal-three-turn",
  label: "Large journal three-turn workspace continuity",
  buildFollowupMessages: nonce => [warmTurnInstructions(2, nonce), warmTurnInstructions(3, nonce)],
  buildTitle: (nonce) => `Runner E2E large journal continuity ${nonce}`,
  buildPrompt: (nonce) => [
    "First exercise ordinary execution history with 240 separate execution-tool calls. In each call, run the Python command below exactly once. Issue the calls one by one. Do not combine them into a shell loop, script, parallel wrapper, or a single tool call: each command must be a separate ordinary execution-tool invocation. Keep a count from 1 through 240. The output is synthetic fixture data and needs no analysis.",
    `python3 -c 'print("journal-continuity-" + "x" * 65000)'`,
    "Wait for all 240 execution-tool calls to exit successfully. Do not redirect, suppress, or pipe their stdout. Then do the workspace task below and submit its completion report.",
    warmTurnInstructions(1, nonce),
  ].join("\n"),
};
export const daytonaGitStreamingTask = createGitStreamingTask({ ...daytonaWarmContinuityTask, buildPrompt: nonce => warmTurnInstructions(1, nonce), buildFollowupMessages: nonce => [warmTurnInstructions(2, nonce), warmTurnInstructions(3, nonce)] });

const codexContinuityProfiles = runnerProfiles.filter((profile) =>
  ["legacy-codex", "runner-codex"].includes(profile.id),
);

// The journal stress fixture keeps a fixed external bundle as a control.
// Ordinary warm continuity exercises managed files and incremental checkpoints.
const warmCodexContinuityProfiles = codexContinuityProfiles.map((profile) =>
  profile.generation !== "native" ? profile : {
    ...profile,
    buildAgent(input: AgentFixtureBuildInput) {
      const agent = profile.buildAgent(input);
      return { ...agent, adapterConfig: {
        ...(agent.adapterConfig as Record<string, unknown>),
        instructionsBundleMode: "external",
        instructionsRootPath: fileURLToPath(new URL("./fixtures/warm-continuity/", import.meta.url)),
        instructionsEntryFile: "AGENTS.md",
        instructionsFilePath: fileURLToPath(new URL("./fixtures/warm-continuity/AGENTS.md", import.meta.url)),
      } };
    },
  },
);

export const connectionReviewSuite: RunnerSuiteFixture = {
  id: "connection-reviews",
  label: "Governed Connection Reviews",
  description: "Opt-in local review, decision, stored execution, and continuation acceptance.",
  groups: ["local"],
  profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude", "legacy-codex", "legacy-claude"].includes(profile.id)),
  environments: [localEnvironment],
  expectedMatrixSize: 16,
  tasks: (["approve", "decline", "always", "restart"] as const).map(decision => ({
    id: `tool-review-${decision}`, label: `Connection review: ${decision}`, groups: [],
    workMode: "standard", flow: "governed_tool_review", toolReviewDecision: decision,
    expectedRunCount: 2, attemptTimeoutMs: { local: 12 * 60_000, daytona: 12 * 60_000 },
    expectedTerminalState: { issue: "done", run: "succeeded" },
    buildTitle: nonce => `Runner E2E connection review ${decision} ${nonce}`,
    buildVisibleMarker: nonce => `PAPERCLIP_E2E_REVIEW_DONE_${nonce}`,
    buildPrompt: nonce => [
      'Use the installed connection action "List fixture pages" with query "recent". Discover it through the runtime tool gateway. Do not simulate or invent its result.',
      'It requires human approval. When approval_required is returned, do not retry and do not create another interaction. End the turn waiting for that existing server-owned review; leave this task in_review. Do not claim completion before the decision arrives.',
      'Approval executes the stored call on the server. Your continuation receives its result; do not repeat that approved call. A decline executes nothing and must be respected.',
      ...(decision === "always" ? ['After the approved result arrives, call the same action once more with query "changed arguments" to verify the remembered permission.'] : []),
      `After consuming the real result (or the human decline), finish the task and publish exactly PAPERCLIP_E2E_REVIEW_DONE_${nonce} once as your final task response.`,
      'For native runners use paperclip_finish. Legacy runners PATCH the task with status done and the final comment. Do not create unrelated work.',
    ].join("\n"),
    buildMatchers: (nonce, execution) => terminalMatchers(`PAPERCLIP_E2E_REVIEW_DONE_${nonce}`, execution),
  })),
};

const everydayProfiles = [
  ...runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id)),
  nativeProfile({ id: "runner-codex-mini", label: "Runner Codex Mini", provider: "codex", model: "gpt-5.4-mini", modelQualification: {source:"qualified_runner_profile",qualificationId:"everyday-codex-mini-pilot"}, credential: "OPENAI_API_KEY", supportedEnvironments: ["local"] }),
].map(productionStoryProfile);

export const extendedHarnessFileTask: RunnerTaskFixture = {
  id: "file-edit-validate", label: "Edit a file and validate its contents", groups: [],
  workMode: "standard", flow: "single_turn", expectedRunCount: 1,
  attemptTimeoutMs: { local: 180_000, daytona: 300_000 },
  expectedTerminalState: { issue: "done", run: "succeeded" },
  buildTitle: nonce => `Extended harness file validation ${nonce}`,
  buildVisibleMarker: nonce => `EXTENDED-FILE-${nonce}`,
  buildPrompt: nonce => [
    `Create extended-${nonce}.txt in the current execution workspace with exactly ready-${nonce} followed by a newline.`,
    `Edit that file to contain exactly verified-${nonce} followed by a newline, then run a command that reads it and fails unless those exact bytes match.`,
    `Register the verified file as a deliverable with title extended-${nonce}.txt. Use EXTENDED-FILE-${nonce} only as completion summary and final response, never as a file title or progress message.`,
    `After successful validation, call paperclip_finish with reportedWorkDisposition done, summary EXTENDED-FILE-${nonce}, the current completion contract revision and satisfied objective criterion, no remaining work, and the actual validation command and result.`,
    `Wait for paperclip_finish to succeed, then emit exactly EXTENDED-FILE-${nonce} as your final response. Do not create unrelated files or work.`,
  ].join("\n"),
  buildMatchers: (nonce, execution) => [
    ...terminalMatchers(`EXTENDED-FILE-${nonce}`, execution),
    { kind: "file_exact", path: `extended-${nonce}.txt`, expected: `verified-${nonce}\n` },
    { kind: "artifact_exact", name: `extended-${nonce}.txt`, expected: `verified-${nonce}\n`, mimeType: "text/plain" },
  ],
};

// Keep the create/edit journey and its independent byte/artifact oracles. The
// explicit read-only check avoids shell operand and newline-escaping ambiguity
// in the Copilot qualification prompt; it does not repair the provider's file.
function copilotFilePrompt(nonce: string): string {
  if (!/^[A-Za-z0-9-]{1,100}$/u.test(nonce)) throw new Error("Invalid Copilot file fixture nonce");
  const filename = `extended-${nonce}.txt`;
  const expectedHex = Buffer.from(`verified-${nonce}\n`).toString("hex");
  const marker = `COPILOT-VALIDATED-${nonce}`;
  const command = `node -e 'const b=require("node:fs").readFileSync(${JSON.stringify(filename)});if(!b.equals(Buffer.from("${expectedHex}","hex")))process.exit(1);console.log(${JSON.stringify(marker)})'`;
  return [
    extendedHarnessFileTask.buildPrompt(nonce),
    "Use the exact read-only validation command below after editing. It must exit with code 0 and print the validation marker before registration or completion. A failed check requires correcting the file; do not claim success from a failed command or change the check.",
    "Exact read-only validation command:",
    command,
  ].join("\n");
}

const repositoryModelProfiles = [
  {
    native: nativeProfile({
      id: "runner-codex", label: "Codie staging-model diagnostic", provider: "codex", model: "gpt-6.1-sol", credential: "OPENAI_API_KEY",
      modelQualification: { source: "candidate_runner_profile", qualificationId: "observed-staging-codie-model-2026-10-20" },
    }),
    legacy: runnerProfiles.find(profile => profile.id === "legacy-codex")!,
  },
  {
    native: nativeProfile({
      id: "runner-acpx-claude", label: "Claude staging-model diagnostic", provider: "acpx", acpxAgent: "claude", model: "claude-opus-5-5", credential: "ANTHROPIC_API_KEY",
      modelQualification: { source: "candidate_runner_profile", qualificationId: "observed-staging-claude-model-2026-10-20" },
    }),
    legacy: runnerProfiles.find(profile => profile.id === "legacy-claude")!,
  },
];

export const cursorCloudProfile: RunnerProfileFixture = {
  id: "runner-cursor-cloud", label: "Native Cursor Cloud (experimental)", generation: "native", groups: [],
  adapterType: "paperclip_runner", provider: "cursor_cloud", model: process.env.PAPERCLIP_CURSOR_CLOUD_ACCEPTANCE_MODEL?.trim() ?? "",
  modelQualification: { source: "candidate_runner_profile", qualificationId: "cursor-cloud-explicit-acceptance-env" },
  credential: "CURSOR_API_KEY", supportedEnvironments: ["local"], expectedRuntimeMode: "native",
  expectedRuntimeMetadata: { adapterType: "paperclip_runner", provider: "cursor_cloud" },
  buildAgent(input) {
    const agent = commonAgent(input, this.id, "paperclip_runner", {
      provider: "cursor_cloud", model: this.model, lifecycleMode: "per_turn", cloudEnvType: "cloud",
      repoUrl: process.env.PAPERCLIP_CURSOR_CLOUD_ACCEPTANCE_REPO?.trim() ?? "",
      ...(process.env.PAPERCLIP_CURSOR_CLOUD_ACCEPTANCE_REF?.trim() ? { repoRef: process.env.PAPERCLIP_CURSOR_CLOUD_ACCEPTANCE_REF.trim() } : {}),
      autoCreatePR: false, workOnCurrentBranch: false, skipReviewerRequest: true, cursorCloudTimeoutMs: 360_000,
      env: { CURSOR_API_KEY: requiredSecret(input, "CURSOR_API_KEY") },
    });
    return { ...agent, budgetMonthlyCents: 1_000 };
  },
};

export const cursorCloudFollowupTask: RunnerTaskFixture = {
  ...openRouterBreadthTasks.find(task => task.id === "question-resume-complete")!,
  id: "cloud-followup", label: "Answer a question and continue the same Cloud agent", automaticRetryPolicy: "single_attempt",
  buildTitle: nonce => `Cursor Cloud follow-up ${nonce}`,
};

const cursorCloudPlanningBase = runnerTasks.find(task => task.id === "plan-revise-accept")!;
export const cursorCloudPlanningTask: RunnerTaskFixture = {
  ...cursorCloudPlanningBase, automaticRetryPolicy: "single_attempt",
  buildPrompt: nonce => cursorCloudPlanningBase.buildPrompt(nonce).replace(
    "For a native runner, remain in the requested planning collaboration mode.",
    "For a native runner, follow the requested Paperclip planning authority. Cursor Cloud uses its default harness for this semantic Plan workflow; do not request Cursor native Plan mode.",
  ),
};

const daytonaControllerOutageEnvironment: EnvironmentFixture = {
  ...daytonaWarmEnvironment,
  configurationKey: "warm-controller-outage-v1",
  buildEnvironment(input: EnvironmentFixtureBuildInput) {
    const payload = daytonaWarmEnvironment.buildEnvironment(input);
    // Keep provider idle stop beyond the outage and replacement budget.
    return { ...payload, config: { ...(payload.config as Record<string, unknown>), autoStopInterval: 15 } };
  },
};

function managedWarmProfiles(profiles: readonly RunnerProfileFixture[]): RunnerProfileFixture[] {
  return profiles.filter(profile => {
    const backend = profile.provider === "codex" ? "codex_app_server" : profile.provider === "opencode" ? "opencode_server" : "acpx_runtime";
    return supportsManagedNativeWarmSession({ backend, acpxAgent: "acpxAgent" in profile ? profile.acpxAgent : undefined },
      profile.credential === "COPILOT_GITHUB_TOKEN" ? { provider: "github", method: "api_key" } : undefined);
  }).map(profile => ({ ...profile, buildAgent(input: AgentFixtureBuildInput) {
    const agent = profile.buildAgent(input);
    return { ...agent, adapterConfig: { ...(agent.adapterConfig as Record<string, unknown>), lifecycleMode: "warm" } };
  } }));
}

const remoteWorkspaceStorageSuite: RunnerSuiteFixture = {
    id: REMOTE_WORKSPACE_STORAGE_SUITE, label: "Remote workspace storage and controller replacement", manualOnly: true,
    description: "Keep synthetic files and local Git work in the sandbox, commit saved versions to object storage, and preserve the original active execution through controller replacement.",
    groups: [], profiles: managedWarmProfiles([(() => {
      const profile = productionStoryProfile(repositoryModelProfiles[0]!.native);
      return { ...profile, buildAgent(input: AgentFixtureBuildInput) {
        const agent = profile.buildAgent(input);
        const adapterConfig = { ...(agent.adapterConfig as Record<string, unknown>) };
        delete adapterConfig.cwd;
        return { ...agent, adapterConfig };
      } };
    })()]), environments: [daytonaControllerOutageEnvironment],
    tasks: everydayTasks.filter(task => task.id === "recover-controller").map(task => ({ ...task,
      label: "Recover sandbox-owned files after controller replacement", expectedRunCount: task.expectedRunCount + 1,
      automaticRetryPolicy: "single_attempt" as const,
      buildPrompt: (nonce: string) => remoteWorkspaceStoragePrompt(task.buildPrompt(nonce)),
    })), expectedMatrixSize: 1,
    definitionMetadata: { version: 6, lifecycleCoverage: "warm-reusable", workspaceFileSource: "saved-exact-snapshot-with-retained-location", scheduling: "explicit-only", controllerDowntimeMs: 300_000, autoStopIntervalMinutes: 15,
      retainedControllerContinuation: true, retainedControllerFollowupTransport: "task_comment_api",
      maximumAttemptsPerCell: 1, budgetMonthlyCents: 1000, instructions: "production", remoteWorkspaceStorage: true,
      upgradeReadiness: "active-remote-workspace-recoverable-before-sigkill",
      savedRunReadback: "public-runId-summary-then-bound-native-detail",
      fileViewerSetup: "ordinary-setting-enabled-with-storage-default-preserved",
      postControllerReplyFormat: "one-plain-text-line-marker-space-actual-command-output",
      grading: "same-active-execution-committed-snapshots-browser-files-and-post-controller-native-continuation",
      source: "projectless-synthetic-files-and-model-created-git", authentication: "api-key", stagingQualification: false },
  };

export const kimiRunnerProfile = nativeProfile({
  id: "runner-acpx-kimi", label: "Runner Kimi Code",
  provider: "acpx", acpxAgent: "kimi", qualificationCandidate: "kimi",
  credential: "KIMI_API_KEY", model: "kimi-for-coding",
  modelQualification: { source: "qualified_runner_profile", qualificationId: "kimi:2.3.3:native-qualified-profile17" },
});

/**
 * ACPX facades admitted only for the reliability long-silent-command case. Like the
 * rolling-deployment matrix, they run as ordinary released profiles: a pending
 * candidate needs its own qualification suite and is rejected here.
 */
const everydayFacadeProfiles = RELIABILITY_FACADE_PROFILE_IDS
  .map(id => [...runnerProfiles, ...extendedHarnessProfiles, kimiRunnerProfile].find(profile => profile.id === id)!)
  .filter(original => !original.qualificationCandidate || QUALIFIED_ACPX_PROFILES[original.qualificationCandidate].qualificationStatus !== "pending")
  .map(original => {
    const { qualificationCandidate: _candidate, ...profile } = productionStoryProfile(original);
    return profile;
  });
/** Released facades currently in the reliability group; a pending one drops out. */
export const everydayReliabilityFacadeProfileIds = everydayFacadeProfiles.map(profile => profile.id);
/**
 * Native OpenCode with DeepSeek 1017 through OpenRouter. It is the chat-feature
 * candidate and the TestOps Reliability plan profile. The OpenCode server driver
 * runs this model on Daytona exactly as it runs the qualified runner-opencode
 * model there; only the configured model differs.
 */
const runnerOpenCodeDeepSeek1017Profile = nativeProfile({ id: RELIABILITY_PLAN_PROFILE_ID, label: "Native OpenCode DeepSeek 1017",
  provider: "opencode", model: CHAT_FEATURE_OPENCODE_MODEL, credential: "OPENROUTER_API_KEY", supportedEnvironments: ["local", "daytona"],
  modelQualification: { source: "candidate_runner_profile", qualificationId: "chat-feature-testops:deepseek-v4.1-flash-1017" } });
const everydayWorkflowProfiles = [...everydayProfiles,
  productionStoryProfile(runnerProfiles.find(profile => profile.id === "runner-opencode")!),
  productionStoryProfile(runnerOpenCodeDeepSeek1017Profile),
  ...everydayFacadeProfiles];

/** Every reliability cell outside the deliberately small explicit matrix. */
function everydayReliabilityExcludedIds(suiteId: string): string[] {
  const allowed = new Set(everydayReliabilityExecutionIds(suiteId, everydayReliabilityFacadeProfileIds));
  return everydayWorkflowProfiles.flatMap(profile => ["local", "daytona"].flatMap(environmentId =>
    everydayReliabilityTasks.map(task => `${suiteId}.${profile.id}.${environmentId}.${task.id}`)))
    .filter(id => !allowed.has(id));
}


const rollingDeploymentProfiles = [...runnerProfiles, ...extendedHarnessProfiles, kimiRunnerProfile]
  .filter(profile => profile.generation === "native" && profile.supportedEnvironments.includes("daytona")
    && (!profile.qualificationCandidate || QUALIFIED_ACPX_PROFILES[profile.qualificationCandidate].qualificationStatus !== "pending"))
  .map(original => {
    const { qualificationCandidate: _candidate, ...profile } = productionStoryProfile(original);
    return { ...profile, buildAgent(input: AgentFixtureBuildInput) {
      const agent = profile.buildAgent(input);
      const adapterConfig = { ...(agent.adapterConfig as Record<string, unknown>) };
      delete adapterConfig.cwd;
      return { ...agent, adapterConfig };
    } };
  });
const rollingWarmDeploymentProfiles = managedWarmProfiles(rollingDeploymentProfiles);

const rollingDeploymentSuites: RunnerSuiteFixture[] = [
  { id: ROLLING_WEB_DEPLOYMENT_SUITE, environment: runnerEnvironments.find(environment => environment.id === "daytona")! },
  { id: ROLLING_WEB_DEPLOYMENT_WARM_SUITE, environment: daytonaControllerOutageEnvironment },
].map(({ id, environment }) => ({
  ...remoteWorkspaceStorageSuite, id, label: `Rolling control-plane web deployment (${environment.configurationKey ? "warm" : "per-turn"})`,
  description: "Overlap independent ephemeral web servers while a remote execution stays active; keep ordinary reads, saves, files and a later native continuation working.",
  profiles: id === ROLLING_WEB_DEPLOYMENT_WARM_SUITE ? rollingWarmDeploymentProfiles : rollingDeploymentProfiles, environments: [environment],
  expectedMatrixSize: (id === ROLLING_WEB_DEPLOYMENT_WARM_SUITE ? rollingWarmDeploymentProfiles : rollingDeploymentProfiles).length * remoteWorkspaceStorageSuite.tasks.length,
  definitionMetadata: { ...remoteWorkspaceStorageSuite.definitionMetadata, version: 6, controllerDowntimeMs: 0,
    activeWorkBoundary: "foreground-180-second-cli-reliability-soak-and-live-owner-recheck",
    workspaceFileSource: environment.configurationKey ? "saved-exact-snapshot-with-retained-location" : "saved-exact-snapshot-after-per-turn-retirement",
    lifecycleCoverage: environment.configurationKey ? "warm-reusable" : "per-turn-disposable", providerCoverage: "registered-native-daytona-profiles",
    replacement: "ready-before-traffic-switch-sigterm-delete-entire-home",
    upgradeReadiness: "active-remote-workspace-recoverable-before-handoff",
    grading: "same-active-execution-ordinary-reads-saves-and-second-empty-home-continuation" },
}));

const chatFeatureExecutionProfile = chatFeatureProfile(nativeProfile({
  id: CHAT_OPENCODE_PROFILE, label: "Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017",
  provider: "opencode", model: CHAT_OPENCODE_MODEL, credential: "OPENROUTER_API_KEY", supportedEnvironments: ["local"],
  modelQualification: { source: "candidate_runner_profile", qualificationId: "chat-catalog:opencode-1.18.34:deepseek-v4.1-flash-1017:remote-initial" },
}));

export const runnerSuites: readonly RunnerSuiteFixture[] = [
  remoteWorkspaceStorageSuite,
  ...rollingDeploymentSuites,
  ...[
    { id: "legacy-workspace-migration", environment: runnerEnvironments.find(environment => environment.id === "daytona")! },
    { id: "legacy-workspace-migration-warm", environment: daytonaControllerOutageEnvironment },
  ].map(({ id, environment }): RunnerSuiteFixture => ({
    id, label: `Legacy native session migration (${environment.configurationKey ? "warm" : "per-turn"})`, manualOnly: true,
    description: "Resume an existing native session and workspace after the production offline migration and deletion of the original controller home.",
    groups: [], profiles: environment.configurationKey ? rollingWarmDeploymentProfiles : rollingDeploymentProfiles, environments: [environment],
    tasks: [{ ...necessaryQuestionTask, minimumExpectedRunCount: 2, turnTimeoutMs: 6 * 60_000,
      attemptTimeoutMs: { local: 15 * 60_000, daytona: 20 * 60_000 } }],
    expectedMatrixSize: (environment.configurationKey ? rollingWarmDeploymentProfiles : rollingDeploymentProfiles).length,
    definitionMetadata: { version: 2, scheduling: "explicit-only", maximumAttemptsPerCell: 1, providerTurns: 2, budgetMonthlyCents: 1000,
      lifecycleCoverage: environment.configurationKey ? "warm-reusable" : "per-turn-disposable",
      migration: "packaged-offline-entry-verified-export-delete-entire-source-home", authentication: "api-key", stagingQualification: false,
      grading: "same-native-and-provider-session-logical-and-remote-paths-reference-bytes-question-and-final-document" },
  })),
  {
    id: CURSOR_CLOUD_SUITE, label: "Native Cursor Cloud", manualOnly: true, groups: [],
    description: "Local Paperclip controller with hosted Cursor work: verified artifact, same-agent follow-up, real active-run Stop and semantic plan revision/approval.",
    profiles: [cursorCloudProfile], environments: runnerEnvironments.filter(environment => environment.id === "local"),
    tasks: [cursorCloudArtifactTask, cursorCloudFollowupTask, cursorCloudStopTask, cursorCloudPlanningTask], expectedMatrixSize: 4,
    definitionMetadata: { version: 3, definitionDigest: cursorCloudDefinitionDigest(), scheduling: "explicit-only", maximumAttemptsPerCell: 1,
      effectiveModelAcknowledged: false, commandPermissions: "provider-managed", costCoverage: "provider-cost-unavailable",
      quietWindowMs: CURSOR_CLOUD_QUIET_WINDOW_MS, repository: process.env.PAPERCLIP_CURSOR_CLOUD_ACCEPTANCE_REPO ?? "",
      repositoryRef: process.env.PAPERCLIP_CURSOR_CLOUD_ACCEPTANCE_REF ?? "", callbackExposure: "callback-path-only-loopback-proxy" },
  },
  {
    id: "daytona-restart-continuity", label: "Daytona warm controller outage continuity", manualOnly: true,
    description: "Keep the original active native runner, reusable warm sandbox, task tools and saved files through five minutes without a controller, then continue the completed session after another replacement.",
    groups: [], profiles: managedWarmProfiles(repositoryModelProfiles.map(({ native }) => productionStoryProfile(native))),
    environments: [daytonaControllerOutageEnvironment],
    tasks: everydayTasks.filter(task => task.id === "recover-controller")
      .map(task => ({ ...task, expectedRunCount: task.expectedRunCount + 1, automaticRetryPolicy: "single_attempt" as const })), expectedMatrixSize: managedWarmProfiles(repositoryModelProfiles.map(({ native }) => productionStoryProfile(native))).length,
    definitionMetadata: { version: 8, scheduling: "explicit-only", controllerDowntimeMs: 300_000, autoStopIntervalMinutes: 15, retainedControllerContinuation: true, retainedControllerFollowupTransport: "task_comment_api",
      maximumAttemptsPerCell: 1, budgetMonthlyCents: 1000, instructions: "production", grading: "same-active-process-lease-native-prefix-and-workspace-receipt",
      authentication: "api-key", stagingAuthentication: "subscription", stagingQualification: false },
  },
  {
    id: "codie-latency-diagnostic",
    label: "Native Codex latency diagnostic",
    description: "One real Daytona turn on the staging-selected model. API-key auth and a fresh fixture do not reproduce the staging subscription, data or Slack delivery.",
    groups: ["native"],
    manualOnly: true,
    profiles: [(() => {
      const profile = nativeProfile({
        id: "runner-codex-61-diagnostic", label: "Native Codex 6.1 diagnostic",
        provider: "codex", model: "gpt-6.1-sol", credential: "OPENAI_API_KEY",
        supportedEnvironments: ["daytona"],
        modelQualification: { source: "candidate_runner_profile", qualificationId: "explicit-model-latency-diagnostic" },
      });
      return { ...profile, buildAgent(input: AgentFixtureBuildInput) {
        const agent = profile.buildAgent(input);
        return { ...agent, budgetMonthlyCents: 1000,
          adapterConfig: { ...(agent.adapterConfig as Record<string, unknown>), lifecycleMode: "warm", idleTimeoutMs: 300_000 } };
      } };
    })()],
    environments: [daytonaWarmEnvironment],
    tasks: runnerTasks.filter(task => task.id === "message-marker")
      .map(task => ({ ...task, automaticRetryPolicy: "single_attempt" as const })),
    expectedMatrixSize: 1,
    definitionMetadata: { diagnostic: true, modelSource: "observed-staging-run", providerAuth: "api_key", stagingAuth: "subscription", companyData: "fresh-fixture", slackDelivery: false, maximumAutomaticRetries: 0,
      timing: { version: 1, clock: "monotonic", responseTargetMs: 30_000, event: "first_visible_response", settlementSeparate: true } },
  },
  {
    id: TASK_WORKSPACES_SUITE, label: "Task workspaces without projects", manualOnly: true,
    description: "Three browser-driven admissions prove deferred repository preparation, stable projectless task files and nested Git persistence across a controller restart.",
    groups: [], profiles: runnerProfiles.filter(profile => ["legacy-opencode", "runner-opencode"].includes(profile.id)).map(taskWorkspaceProfile),
    environments: runnerEnvironments, tasks: [taskWorkspaceTask],
    excludedExecutionIds: ["task-workspaces.legacy-opencode.daytona.task-directory-repository-resume"],
    expectedMatrixSize: 3,
    definitionMetadata: { version: 1, definitionDigest: taskWorkspaceDefinitionDigest(), scheduling: "explicit-only", providerTurns: 3,
      attempts: 1, budgetMonthlyCents: 1000, project: "none", cwd: "unconfigured-task-default", oracle: "public-file-download-and-host-nested-git", remoteLifecycle: "per_turn" },
  },
  {
    id: "followup-stop-resume", label: "Follow-up, Stop and retained-context resumption", manualOnly: true,
    description: "Send an ordinary follow-up during active work, Stop through the task composer, observe a quiet cancelled run, then explicitly resume and download retained context with the earlier direction.",
    groups: [], profiles: repositoryModelProfiles.map(({ native }) => productionDefaultHireProfile(native)),
    environments: runnerEnvironments.filter(environment => environment.id === "local"), tasks: [followupStopTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, definitionDigest: followupStopDigest(), scheduling: "explicit-only", attempts: 1,
      providerTurns: 2, budgetMonthlyCents: 1000, instructions: "production-default", stopObservationWindowMs: 5000,
      surface: "paperclip", target: "isolated-development-instance", authentication: "api-key", stagingAuthentication: "subscription",
      stagingQualification: false, unexercisedBoundaryIsFailure: true },
  },
  {
    id: "finalization-recovery", label: "Preserve completed work through finalization restart", manualOnly: true,
    description: "Crash an owned isolated server after accepted provider output, then require real workspace recovery and one final delivery without provider replay.",
    groups: [], profiles: repositoryModelProfiles.map(({ native }) => productionDefaultHireProfile(native)),
    environments: runnerEnvironments.filter(environment => environment.id === "daytona"), tasks: [finalizationRecoveryTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, definitionDigest: finalizationRecoveryDigest(), scheduling: "explicit-only", attempts: 1,
      providerTurns: 1, budgetMonthlyCents: 1000, instructions: "production-default", fault: "owned-process-crash-after-persisted-result",
      workspacePayloadBytes: 64 * 1024 * 1024, unexercisedFaultIsFailure: true, surface: "paperclip", target: "isolated-development-instance",
      authentication: "api-key", stagingAuthentication: "subscription", remoteLifecycle: "per_turn", stagingQualification: false },
  },
  {
    id: "necessary-question", label: "Necessary free-text question and verified confirmation", manualOnly: true,
    description: "One required private input, a visible question and context, and one exactly bound answer continuation.",
    groups: [], profiles: repositoryModelProfiles.map(({ native }) => productionDefaultHireProfile(native)),
    environments: runnerEnvironments, tasks: [necessaryQuestionTask], expectedMatrixSize: 4,
    definitionMetadata: { version: 1, definitionDigest: necessaryQuestionDigest(), scheduling: "explicit-only", attempts: 1,
      providerTurns: "1-2; provider pause or one semantic successor", budgetMonthlyCents: 1000, instructions: "production-default",
      surface: "paperclip", target: "isolated-development-instance", authentication: "api-key", stagingAuthentication: "subscription",
      remoteLifecycle: "per_turn", stagingQualification: false },
  },
  ...([false, true] as const).map(conversion => ({
    id: conversion ? "legacy-conversion" : "configured-repository",
    label: conversion ? "Legacy conversion with verified delivery" : "Configured repository with verified delivery",
    manualOnly: true, description: "Production instructions, retained configuration, and a downloaded result checked against an independent Git and file baseline.",
    groups: [], profiles: repositoryModelProfiles.map(({ native, legacy }) => repositoryProofProfile(native, conversion ? legacy : undefined)),
    environments: runnerEnvironments, tasks: repositoryProofTasks.filter(task => task.id === (conversion ? "convert-and-deliver" : "repository-output")), expectedMatrixSize: 4,
    definitionMetadata: { version: 1, definitionDigest: repositoryProofDigest(), scheduling: "explicit-only", providerTurns: 1, attempts: 1,
      budgetMonthlyCents: 1000, instructions: "production-default", surface: "paperclip", oracle: "registered-download-and-independent-configured-checkout",
      target: "isolated-development-instance", authentication: "api-key", stagingAuthentication: "subscription", remoteLifecycle: "per_turn", stagingQualification: false },
  })),
  {
    id: "automatic-repository", label: "Automatic repository continuation", manualOnly: true,
    description: "A projectless user request stages its managed repository, continues automatically, and delivers independently verified downloaded bytes.",
    groups: [], profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(taskWorkspaceProfile).map(productionDefaultHireProfile),
    environments: runnerEnvironments, tasks: [automaticRepositoryTask], expectedMatrixSize: 4,
    definitionMetadata: { version: 1, definitionDigest: automaticRepositoryDigest(), scheduling: "explicit-only",
      providerTurns: 2, attempts: 1, budgetMonthlyCents: 1000, project: "none", instructions: "production-default",
      surface: "paperclip", oracle: "registered-download-and-independent-checkout", remoteLifecycle: "per_turn" },
  },
  {
    id: "automatic-repository-configured-models", label: "Automatic repository with recorded staging models", manualOnly: true,
    description: "Replay projectless setup with the recorded Codie and Claude models while keeping development authentication and lifecycle differences explicit.",
    groups: [], profiles: repositoryModelProfiles.map(({ native }) => productionDefaultHireProfile(taskWorkspaceProfile(native))),
    environments: runnerEnvironments, tasks: [automaticRepositoryTask], expectedMatrixSize: 4,
    definitionMetadata: { version: 1, definitionDigest: automaticRepositoryDigest(), scheduling: "explicit-only", providerTurns: 2, attempts: 1,
      budgetMonthlyCents: 1000, instructions: "production-default", surface: "paperclip", target: "isolated-development-instance",
      authentication: "api-key", stagingAuthentication: "subscription", remoteLifecycle: "per_turn", stagingQualification: false },
  },
  {
    id: "pi-controls", label: "Pi active controls", manualOnly: true,
    description: "Pending native-write Stop and browser-originated same-turn steering, with exact control receipts and independent retirement/no-effect evidence.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => profile.qualificationCandidate === "pi"),
    environments: runnerEnvironments, tasks: piControlTasks, expectedMatrixSize: 4,
    definitionMetadata: { version: 10, remoteProcExit: "separately-confirmed-absence-after-read-failure", taskCreation: "explicit-title-and-creation-response-id", qualification: "pending", scheduling: "explicit-only", profileVersion: QUALIFIED_ACPX_PROFILES.pi.agentProfileVersion,
      nativeArguments: "streamed-until-exact-target",
      remoteProcessIdentity: "observer-pid-startTicks-bootId",
      remoteBootstrapAdmission: "owned-active-lease-with-native-runtime-readiness-rpc-v1", remoteBootstrapApproval: "exact-published-native-read-public-accept-once-v1",
      controlPlaneSettlement: "required-scoped-result-and-terminal-after-runner",
      steeringComment: "exact-browser-submitted-markdown",
      steeringDispatch: "require-public-api-acceptance",
      pending: "paperclip.e2e.pi-control-pending.v1", stop: "paperclip.e2e.pi-stop-settlement.v1", steering: "paperclip.e2e.pi-steering-settlement.v1",
      permissionPolicy: "approve-reads", lifecycle: "per_turn", normalCompletionProvesStop: false, nativeFollowUp: "not-covered", providerDeath: "not-covered",
      remoteObservationCoverage: "continuous-through-owned-process-retirement", filesystemAfterRemoteRetirementObserved: false },
  },
  {
    id: "cursor-native", label: "Cursor native interactions", manualOnly: true,
    description: "Native question continuation, revision-bound plan decisions and restrictive permission denial with independent process and file evidence.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => profile.qualificationCandidate === "cursor"),
    environments: runnerEnvironments, tasks: cursorNativeTasks, expectedMatrixSize: 8,
    definitionMetadata: { version: 2, qualification: "pending", scheduling: "explicit-only", profileVersion: QUALIFIED_ACPX_PROFILES.cursor.agentProfileVersion, modeAdmission: "native-config-ack", artifactExport: "pending-private-home", remoteEvidence: "owned-lease-sealed-observer" },
  },
  {
    id: "pi-native", label: "Pi native boundaries", manualOnly: true,
    description: "Pi native forms, registered agent files and human permission denial on local and Daytona execution; automatic deny-all remains local-only.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => profile.qualificationCandidate === "pi"),
    environments: runnerEnvironments, tasks: piNativeTasks, expectedMatrixSize: 10,
    excludedExecutionIds: ["pi-native.runner-acpx-pi.daytona.restrictive-denial", "pi-native.runner-acpx-pi.local.native-pending-provider-death"],
    definitionMetadata: { version: 23, remoteProcExit: "separately-confirmed-absence-after-read-failure", taskCreation: "explicit-title-and-creation-response-id", agentMemoryParent: "public-managed-file-seed-before-admission", incompleteTerminalCleanup: "retirement-retained-with-failed-watch", qualification: "pending", scheduling: "explicit-only", profileVersion: QUALIFIED_ACPX_PROFILES.pi.agentProfileVersion, agentMemoryContent: "utf8-nonce-plus-final-lf", agentMemoryPrompt: "single-json-write-and-content-bound-native-read-both-runs", agentMemoryReadAuthority: "local-withheld-or-exact-remote-agent-run-file", taskPromptTransport: "fenced-markdown-paste-and-multiline-literal-escapes", nativeFinish: "current-contract-objective-evidence-refs", providerDeath: "daytona-exact-pi-child-pidfd-production-expiry", providerFaultExecutable: "stable-preinstalled-runner-link-and-snapshot-node-inode-with-held-bootstrap-fd-3-or-7", remoteBootstrapAdmission: "owned-active-lease-with-native-runtime-readiness-rpc-v1", remoteBootstrapApproval: "exact-published-native-read-public-accept-once-v1", remoteDenyAll: "unsupported-native-bootstrap-read-is-denied", remoteEvidence: "owned-lease-sealed-observer", pendingControllerRestart: "same-live-native-request-trusted-ancestry-cleanup" },
  },


  {
    id: "rich-acp-warm-continuity", label: "Rich ACP warm continuity", manualOnly: true,
    description: "Three browser-driven turns with stable native session, runner process and workspace identity for Cursor, Copilot and Pi.",
    groups: ["native", "warm"],
    profiles: extendedHarnessProfiles.map(profile => ({ ...profile, buildAgent(input: AgentFixtureBuildInput) {
      const agent = profile.buildAgent(input);
      return { ...agent, adapterConfig: { ...agent.adapterConfig as Record<string, unknown>, lifecycleMode: "warm", idleTimeoutMs: 300_000 } };
    } })),
    environments: [localEnvironment, daytonaWarmEnvironment],
    // ACP collects changed agent files only after provider retirement. Keep this
    // process-continuity fixture on workspace writes; Codex retains its separate
    // managed-home checkpoint fixture, and Pi covers saved files in a fresh run.
    tasks: [{ ...daytonaWarmContinuityTask,
      buildPrompt: nonce => warmTurnInstructions(1, nonce),
      buildFollowupMessages: nonce => [warmTurnInstructions(2, nonce), warmTurnInstructions(3, nonce)],
      turnTimeoutMs: 120_000, attemptTimeoutMs: { local: 420_000, daytona: 420_000 } }],
    expectedMatrixSize: 6,
    definitionMetadata: { version: 3, warmPromptDigest: warmTurnDefinitionDigest, qualification: "pending", scheduling: "explicit-only", identity: "native-session-runner-provider-session-process-start", agentFiles: "unchanged-home-process-continuity" },
  },
  {
    id: "public-mcp", label: "Paperclip through an assistant", manualOnly: true,
    description: "Paid assistant tool use plus actual team execution, browser OAuth consent, durable outcomes and authorization boundaries.",
    groups: ["local"], environments: [localEnvironment], tasks: publicMcpTasks, expectedMatrixSize: 63,
    profiles: [
      ...["mini"].map(size => legacyProfile({
        id: `assistant-codex-${size}`, label: `Assistant + Codex ${size}`, adapterType: "codex_local", provider: "codex",
        model: `gpt-5.4-${size}`, credential: "OPENAI_API_KEY",
        instructions: publicMcpWorkerInstructions,
        modelQualification: { source: "qualified_runner_profile", qualificationId: `public-mcp-gpt-5.4-${size}-pilot` },
        extraConfig: { engine: "cli", extraArgs: ["-c", "features.shell_snapshot=false", "-c", "features.apps=false", "-c", "features.plugins=false"] },
      })),
      ...[["haiku", "claude-haiku-4-5-20251001"], ["sonnet", "claude-sonnet-4-6"]].map(([name, model]) => legacyProfile({
        id: `assistant-claude-${name}`, label: `Assistant + Claude ${name}`, adapterType: "claude_local", provider: "claude",
        model: model!, credential: "ANTHROPIC_API_KEY",
        instructions: publicMcpWorkerInstructions,
        modelQualification: { source: "qualified_runner_profile", qualificationId: `public-mcp-${name}-pilot` },
        extraConfig: { engine: "cli", maxTurnsPerRun: 16 },
      })),
    ],
    definitionMetadata: { version: 10, expandedDigest: publicMcpExpandedDigest, setupDigest: publicMcpSetupDigest, grader: publicMcpGraderVersion, workflowDigest: publicMcpWorkflowDigest, workerSkillDigest: publicMcpWorkerSkillDigest, workerInstructions: publicMcpWorkerInstructions, assistantMaxRequests: 16, assistantMaxEstimatedUsd: 2, instructions: "shipped-plugin-skills", scheduling: "explicit-only" },
  },
  {
    id: "plan-task-guidance", label: "Planning guidance utility", manualOnly: true,
    description: "Current, short and disabled planning skills on cohesive, parallel, dependent and independently reviewed work.",
    groups: ["native"], profiles: runnerProfiles.filter(p => p.id === "runner-codex").map(planTaskProfile),
    environments: [localEnvironment], tasks: planTaskCases, expectedMatrixSize: 12,
    definitionMetadata: { version: 1, definitionDigest: planDefinitionDigest, scheduling: "explicit-only", comparison: "public-skill-availability-ablation", scope: "one-profile-single-attempt" },
  },
  {
    id: "blocker-guidance", label: "Direct blocker handling", manualOnly: true,
    description: "Human authority, hiring permissions, and requester scope under the production coordination skill.",
    groups: ["legacy"], profiles: runnerProfiles.filter(p => ["legacy-codex", "legacy-claude"].includes(p.id)).map(blockerProfile),
    environments: [localEnvironment], tasks: blockerTasks, expectedMatrixSize: 6,
    definitionMetadata: { version: 1, instructions: "production-coordination-skill", grading: "saved-human-decision-ownership-and-resume", scheduling: "explicit-only" },
  },

  {
    id: "native-active-stop", label: "Stop an unanswered native permission", manualOnly: true,
    description: "Stop while one exact Cursor or Copilot native permission remains unanswered; require cancelled provider settlement, caller-owned acknowledgement, stale-answer refusal and independent retirement/no effects.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => ["cursor", "copilot"].includes(profile.qualificationCandidate ?? "")),
    environments: runnerEnvironments, tasks: nativeActiveStopTasks, expectedMatrixSize: 4,
    definitionMetadata: { version: 20, copilotDefinition: { version: 19, titleCreation: "explicit-search-composer", taskBinding: "browser-creation-response-id", processAuthority: "local-native-root-or-attested-remote-root", remoteTerminalDiagnostics: "bounded-incomplete-reasons-with-strict-failure", remoteSetupOrder: "observed-action-published-before-context-approval", remoteBootstrapContext: "already-exposed-dedicated-tool-no-http-substitution", bootstrapPrompt: "already-exposed-dedicated-context-before-native-edit", editOrigin: "exact-permission-target-and-native-call-identity", stopAcknowledgement: "retained-current-mainline-api-response", contextPermission: "context-and-bounded-attested-discovery-sequence-await-origin-rows", permissionCard: "current-operation-and-decision-control-excludes-history", qualification: "pending", scheduling: "explicit-only", evidence: "paperclip.e2e.native-active-stop-settlement.v3", pendingObservation: "retained-api-before-stop-with-fixture-correlation", normalCompletionAccepted: false, permissionPolicy: "approve-reads", lifecycle: "per_turn", remoteEvidence: "paperclip.e2e.native-active-stop-remote-retirement.v1", remoteObservationCoverage: "continuous-through-owned-process-retirement", filesystemAfterRemoteRetirementObserved: false, localObservationCoverage: "four-phases-through-cleanup", providerDeath: "not-covered" }, qualification: "pending", scheduling: "explicit-only", evidence: "paperclip.e2e.native-active-stop-settlement.v2", pendingObservation: "retained-api-before-caller-uuid-stop", normalCompletionAccepted: false, permissionPolicy: "approve-reads", lifecycle: "per_turn", remoteEvidence: "paperclip.e2e.native-active-stop-remote-retirement.v1", remoteObservationCoverage: "continuous-through-owned-process-retirement", filesystemAfterRemoteRetirementObserved: false, localObservationCoverage: "four-phases-through-cleanup", providerDeath: "not-covered" },
  },
  {
    id: "copilot-provider-death", label: "Copilot provider death", manualOnly: true,
    description: "Terminate only the verified owned Copilot child with an unanswered permission; require callback expiry, stale-answer refusal, no replay and independent retirement.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => profile.qualificationCandidate === "copilot"),
    environments: runnerEnvironments, tasks: copilotProviderDeathTasks, expectedMatrixSize: 2,
    definitionMetadata: { version: 17, titleCreation: "explicit-search-composer", taskBinding: "browser-creation-response-id", linuxDeathExecutable: "verified-inherited-descriptor-and-live-executable-inode", processAuthority: "local-native-root-or-attested-remote-root", remoteTerminalDiagnostics: "bounded-incomplete-reasons-with-strict-failure", remoteSetupOrder: "observed-action-published-before-context-approval", remoteBootstrapContext: "already-exposed-dedicated-tool-no-http-substitution", finalUiStatus: "blocked-with-current-mainline-attention-label", bootstrapPrompt: "already-exposed-dedicated-context-before-native-edit", editOrigin: "exact-permission-target-and-native-call-identity", contextPermission: "context-and-bounded-attested-discovery-sequence-await-origin-rows", permissionCard: "current-operation-and-decision-control-excludes-history", qualification: "pending", scheduling: "explicit-only", evidence: "paperclip.e2e.copilot-provider-death.v1", signal: "SIGKILL", target: "owned-native-child-only", permissionPolicy: "approve-reads", lifecycle: "per_turn", automaticRetries: 0 },
  },
  {
    id: "copilot-protection", label: "Copilot native protection", manualOnly: true,
    description: "Exact native denial with independently correlated provider settlement and acknowledged run Stop, plus attached command settlement with independent process evidence.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => profile.qualificationCandidate === "copilot"),
    environments: runnerEnvironments, tasks: copilotProtectionTasks, expectedMatrixSize: 4,
    definitionMetadata: { version: 24, denialIssueOutcome: "in-progress-or-proven-blocked-recovery", titleCreation: "explicit-search-composer", taskBinding: "browser-creation-response-id", remoteTerminalDiagnostics: "bounded-incomplete-reasons-with-strict-failure", remoteSetupOrder: "observed-action-published-before-context-approval", remoteBootstrapContext: "already-exposed-dedicated-tool-no-http-substitution", denialContext: "already-exposed-dedicated-tool-before-write", stopAcknowledgement: "retained-current-mainline-api-response", contextPermission: "context-and-bounded-attested-discovery-sequence-await-origin-rows", permissionCard: "current-operation-and-decision-control-excludes-history", semanticCompletionEvidence: "paperclip.e2e.copilot-semantic-completion.v4", qualification: "pending", naturalSettlementObservationMs: 2000, scheduling: "explicit-only", evidence: "copilot_tool_evidence_v1", profileVersion: QUALIFIED_ACPX_PROFILES.copilot.agentProfileVersion, denialTerminal: "correlated-provider-settlement-and-audited-run-stop", denialSettlementEvidence: "paperclip.e2e.copilot-denial-settlement.v4", activeTurnCancellation: "not-implied-by-completed-provider-turn", settlement: "attached-finite-command-released-after-native-finish-receipt", settlementMarker: "private-diagnostic-not-deliverable", remoteEvidence: "owned-lease-sealed-observer" },
  },
  {
    id: "native-provider-loss", label: "Lose a runtime with an unanswered native permission", manualOnly: true,
    description: "Lose the owned Cursor runtime while a native mutation remains unanswered; require a visible failed run, closed unanswerable input, stale-answer refusal and independent retirement with no effects or replay.",
    groups: ["native"], profiles: extendedHarnessProfiles.filter(profile => profile.qualificationCandidate === "cursor"),
    environments: runnerEnvironments,
    tasks: [{
      id: "pending-permission-provider-loss", label: "Owned runtime loss with pending permission", groups: [], workMode: "standard", flow: "native_provider_loss",
      expectedRunCount: 1, attemptTimeoutMs: { local: 300_000, daytona: 300_000 }, turnTimeoutMs: 120_000,
      expectedTerminalState: { issue: "blocked", run: "failed" },
      buildTitle: nonce => `Native provider loss ${nonce}`,
      buildVisibleMarker: nonce => `NATIVE-PROVIDER-LOSS-${nonce}`,
      buildPrompt: () => "Attempt the supplied exact native shell operation once and leave its permission callback unanswered. Do not retry, use another tool or path, answer your own permission, call paperclip_finish, or claim completion. The qualification fixture will deliberately lose the isolated runtime before any approval.",
      buildMatchers: () => [],
    }], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, qualification: "pending", scheduling: "explicit-only", fault: "observed-per-turn-run-root-loss", remoteFaultAuthority: "pidfd-start-ticks-boot-id", replayAllowed: false },
  },

  {
    id: "extended-harnesses", label: "Extended ACP harnesses", manualOnly: true,
    description: "Explicit candidate qualification through real Paperclip tools, browser interactions, file edits and restart recovery.",
    groups: ["native"], profiles: extendedHarnessProfiles, environments: runnerEnvironments,
    tasks: [...openRouterBreadthTasks, localIntegrityTasks[1]!, extendedHarnessFileTask],
    expectedMatrixSize: 30,
    definitionMetadata: { version: 6, copilotFileValidation: "exact-read-only-byte-check-v1", qualification: "pending", scheduling: "explicit-only", admission: "host-exact-candidate-and-model", authenticatedDiscoveryDate: "2026-09-28", piFileEvidence: "seed-edit-single-execute-public-download-v2", piFileArtifactTitle: "exact-filename", piFileCommandTransport: "fenced-bash-markdown-paste" },
  },
  {
    id: "instruction-persistence", label: "Instruction Persistence",
    description: "Agent-owned text and binary files round trip through the editor, survive a server restart and fresh task, and synchronize concurrent edits per file with last-sync-wins.",
    groups: [], profiles: codexContinuityProfiles,
    environments: [localEnvironment, runnerEnvironments.find(environment => environment.id === "daytona")!], tasks: [instructionPersistenceTask],
    excludedExecutionIds: ["instruction-persistence.legacy-codex.daytona.private-copy-persists"],
    expectedMatrixSize: 3, manualOnly: true,
    definitionMetadata: { version: 6, oracle: "current-directory-independent-nonce-binary-last-sync-wins-and-nonblocking-storage-quota", providerTurns: 6, restart: "between-tasks", instructions: "production" },
  },
  {
    id: "grok-subscription-qualification", label: "Grok Build Subscription Qualification", manualOnly: true,
    description: "Explicit company subscription login across Grok browser workflows in local and Daytona environments.",
    groups: ["native"],
    profiles: [nativeProfile({
      id: "runner-acpx-grok-subscription", label: "Grok Build Subscription",
      provider: "acpx", acpxAgent: "grok",
      model: ACPX_QUALIFICATION_MODELS.grok,
      credential: "GROK_AUTH_JSON",
    })],
    environments: [localEnvironment, daytonaWarmEnvironment],
    tasks: [
      ...runnerTasks, ...localIntegrityTasks,
      ...everydayTasks.filter(task => task.id === "build-revise"),
      ...chatHardeningTasks.filter(task => ["stop-new-resume", "continuity-restart"].includes(task.id)),
    ], expectedMatrixSize: 16,
    definitionMetadata: { version: 1, authentication: "company-subscription", binary: "1.0.13", model: "grok-4.7", scheduling: "explicit-only", repetitionsRequired: 3, artifactOracle: "independent-python-contract", stopBoundary: "provider-turn-started" },
  },
  {
    id: "grok-qualification", label: "Grok Build Qualification", manualOnly: true,
    description: "Grok replies, planning approval, questions, downloadable artifacts, stop/resume and controller restart in local and Daytona environments.",
    groups: ["native"],
    profiles: runnerProfiles.filter(profile => profile.id === "runner-acpx-grok"),
    environments: [localEnvironment, daytonaWarmEnvironment],
    tasks: [
      ...runnerTasks, ...localIntegrityTasks,
      ...everydayTasks.filter(task => task.id === "build-revise"),
      ...chatHardeningTasks.filter(task => ["stop-new-resume", "continuity-restart"].includes(task.id)),
    ], expectedMatrixSize: 16,
    definitionMetadata: { version: 2, binary: "1.0.13", model: "grok-4.7", scheduling: "explicit-only", repetitionsRequired: 3, artifactOracle: "independent-python-contract", stopBoundary: "provider-turn-started" },
  },
  {
    id: "kimi-qualification", label: "Kimi Code Qualification", manualOnly: true,
    description: "Kimi Code replies, semantic planning and questions, verified file delivery, Stop and controller continuation through local and Daytona user journeys.",
    groups: ["native"],
    profiles: [kimiRunnerProfile],
    environments: [localEnvironment, daytonaWarmEnvironment],
    environmentOverrides: Object.fromEntries(kimiLifecycleTasks.map(task => [task.id, {
      daytona: runnerEnvironments.find(environment => environment.id === "daytona")!,
    }])),
    tasks: [
      ...runnerTasks, ...localIntegrityTasks, extendedHarnessFileTask,
      ...chatHardeningTasks.filter(task => ["stop-new-resume", "continuity-restart"].includes(task.id)),
      ...kimiLifecycleTasks,
    ].map(task => ({ ...task, automaticRetryPolicy: "single_attempt" as const })),
    expectedMatrixSize: 20,
    definitionMetadata: { version: 7, binary: "2.3.3", model: "kimi-for-coding",
      candidateAdmission: "ordinary-released-profile-without-candidate-grant-v1", profileVersion: QUALIFIED_ACPX_PROFILES.kimi.agentProfileVersion,
      stopNewRunAccounting: "three-native-provider-runs-authored-reset-and-verified-predispatch-wait-v1",
      planPromptContract: "literal-first-line-markers-v2",
      modelDiscovery: "exact-model-authenticated-observed", qualification: "qualified",
      scheduling: "explicit-only", maximumAttemptsPerCell: 1, repetitionsRequired: 1,
      instructionAdmission: "native-effective-prompt-digest-on-create-load",
      nativeQuestions: "not-claimed", nativePlans: "not-claimed", accounting: "usage-and-cost-unavailable",
      artifactOracle: "independent-workspace-and-public-download-bytes", stopBoundary: "provider-turn-started",
      remoteLifecycleBootstrap: "observer-bound-scoped-get-task-context-dual-turn-workspace-binding-full-semantic-command-ack-and-bounded-native-receipt",
      nativeWriteLifecycle: "pending-permission-stop-and-exact-native-worker-loss", nativeWriteCleanup: "continuous-no-effects-through-owned-tree-retirement" },
  },
  {
    id: "api-response-reading", label: "Bounded API response reading", manualOnly: true,
    description: "Retrieve evidence beyond a saved API preview through authorized bounded text windows.",
    groups: [], environments: runnerEnvironments,
    profiles: runnerProfiles.filter(profile => profile.id === "runner-codex"),
    tasks: [apiResponseReadingTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, grading: "hidden-evidence-exact-copy-and-api-tool-events", scheduling: "explicit-only" },
  },
  {
    id: CODEX_PLANNING_READ_ONLY_SUITE, label: "Codex planning read-only enforcement", manualOnly: true,
    description: "Start a native Codex planning turn, attempt one workspace write, and require the sandbox to refuse it before the Plan is approved.",
    groups: [], environments: runnerEnvironments,
    profiles: runnerProfiles.filter(profile => profile.id === "runner-codex"),
    tasks: [codexPlanningReadOnlyTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, grading: "plan-marker-and-refused-shell-write-event", scheduling: "explicit-only", maximumAttemptsPerCell: 1 },
  },
  {
    id: "api-artifact-transfer", label: "Verified API artifact transfer", manualOnly: true,
    description: "Install an authorized complete API artifact in Daytona and independently verify the delivered bytes.",
    groups: [], environments: runnerEnvironments.filter(environment => environment.id === "daytona"),
    profiles: runnerProfiles.filter(profile => profile.id === "runner-codex"),
    tasks: [apiArtifactTransferTask], expectedMatrixSize: 1,
    definitionMetadata: { version: 3, grading: "server-capture-provenance-redacted-receipt-source-and-delivery-digest", scheduling: "explicit-only", maximumAttemptsPerCell: 1 },
  },
  {
    id: "task-titles", label: "Automatic task titles", manualOnly: true,
    description: "A real agent names a prompt-only task early using production guidance and preserves a supplied title.",
    groups: ["native", "local"], environments: [localEnvironment],
    profiles: everydayProfiles.filter(profile => profile.provider === "codex").map(profile => ({
      ...profile,
      buildAgent(input) { return { ...profile.buildAgent(input), budgetMonthlyCents: TASK_TITLE_BUDGET_CENTS }; },
    })),
    tasks: taskTitleTasks, expectedMatrixSize: 6,
    definitionMetadata: { version: 1, gradingDigest: taskTitleDefinitionDigest, instructions: "production", grading: "initial-response-early-correlated-tool-and-agent-audit", providerRuns: 1, budgetMonthlyCents: TASK_TITLE_BUDGET_CENTS, scheduling: "explicit-only" },
  },
  {
    id: "continuation-accounting", label: "Continuation accounting baseline", manualOnly: true,
    description: "Structured productive steps, bounded repair, restart and late gates; comments cannot buy more attempts.",
    groups: ["local"], environments: [localEnvironment], profiles: codexContinuityProfiles.map(productionStoryProfile),
    tasks: accountingTasks, expectedMatrixSize: 8,
    excludedExecutionIds: accountingTasks.filter(t => !t.id.includes("productive")).map(t => `continuation-accounting.runner-codex.local.${t.id}`),
    definitionMetadata: { version: 4, grading: "accounting-v4-cancellation-evidence", scheduling: "explicit-only", providerTurns: "five productive, three repair, two executed plus one cancelled for Stop" },
  },
  {
    id: "lifecycle-baseline", label: "Lifecycle authority baseline", manualOnly: true,
    description: "Paired narrative probes plus real stop/resume and governed-action controls; live browser/server/database/provider execution.",
    groups: ["local"], environments: [localEnvironment],
    profiles: codexContinuityProfiles.map(productionStoryProfile),
    tasks: [...lifecycleLiveTasks,
      ...chatTasks.filter(task => ["clarify-reuse", "stop-new-resume"].includes(task.id)),
      ...connectionReviewSuite.tasks],
    expectedMatrixSize: 46,
    excludedExecutionIds: ["neutral", "challenge"].map(variant => `lifecycle-baseline.runner-codex.local.lifecycle-repair-${variant}`),
    definitionMetadata: { version: 5, clarificationGrading: "wrapped-information-fields-list", narrativeDigest: lifecycleLiveDefinitionDigest, grading: "durable-state-and-attributed-narrative", scheduling: "explicit-only" },
  },
  {
    id: "question-resume", label: "Native question and answer continuation", manualOnly: true,
    description: "Two real UI answers, exact provider-pause or semantic-wake identity, and one saved document.",
    groups: ["native", "local"], environments: [localEnvironment],
    profiles: runnerProfiles.filter(p => ["runner-codex", "runner-acpx-claude"].includes(p.id)).map(productionStoryProfile),
    tasks: [questionResumeTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, grading: "bound-question-path-and-two-durable-answers", instructions: "unchanged-production",
      scheduling: "explicit-only", automaticRetryPolicy: "single_attempt", companyAndAgentBudgetCents: 1_000,
      providerRuns: "1-3; each semantic answer starts one exactly bound wake; provider answers retain their paused run" },
  },
  {
    id: "continuation", label: "Task continuation",
    description: "Human direction, approval boundaries, untrusted evidence, and completed actions across turns.",
    groups: ["local"], environments: [localEnvironment],
    profiles: runnerProfiles.filter(profile => ["legacy-codex", "legacy-claude", "runner-codex", "runner-acpx-claude"].includes(profile.id)).map(productionStoryProfile),
    tasks: continuationTasks, expectedMatrixSize: 23,
    excludedExecutionIds: [
      ...["legacy-codex", "legacy-claude"].map(profile => `continuation.${profile}.local.question-tool-documentation`),
      ...["legacy-codex", "legacy-claude", "runner-codex"].map(profile => `continuation.${profile}.local.provider-question-bridge`),
    ],
    definitionMetadata: { version: 5, grading: "durable-wait-owner-and-all-answer-identities", instructions: "production", automaticRetryPolicy: "single_attempt", companyAndAgentBudgetCents: 1_000 },
  },
  {
    id: CONNECTION_GUIDANCE_SUITE, label: "Native connection guidance", manualOnly: true,
    description: "Neutral decline prompts and approval/provider-choice controls; production connection instructions stay unchanged.",
    groups: ["native", "local"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude", "runner-opencode"].includes(profile.id)).map(productionStoryProfile),
    environments: [localEnvironment], tasks: connectionGuidanceTasks, expectedMatrixSize: 15,
    definitionMetadata: { version: 1, fixtureDigest: connectionGuidanceDefinitionDigest(),
      instructions: "unchanged-production", maximumAttemptsPerCell: 1,
      automaticRetryPolicy: "single_attempt", companyAndAgentBudgetCents: CONNECTION_GUIDANCE_BUDGET_CENTS,
      expectedProviderTurnsPerCell: 2, maximumRunRecordsPerCell: 12,
      grading: "original-workflow-plus-attributed-decline-output", scheduling: "explicit-only" },
  },
  {
    id: "everyday-workflows", label: "Everyday Paperclip Work", manualOnly: true,
    description: "Real user requests, useful downloaded work, and durable continuation using production instructions.",
    groups: ["native"], profiles: everydayWorkflowProfiles, environments: [localEnvironment, daytonaWarmEnvironment],
    // The S49 turn-3 failure needed an ephemeral per-turn lease, not the warm one.
    environmentOverrides: { "three-turn-revise": { daytona: runnerEnvironments.find(environment => environment.id === "daytona")! } },
    tasks: [...everydayTasks.map(task => ["hire-reuse", "delegate-feedback", "recover-controller"].includes(task.id)
      ? { ...task, automaticRetryPolicy: "single_attempt" as const } : task), ...everydayReliabilityTasks],
    // 52 everyday cells; one native Codex Daytona cell per reliability case, six DeepSeek plan cells (queue-steer needs
    // Codex steering) and released facades for the silent command.
    expectedMatrixSize: 52 + 2 * everydayReliabilityTasks.length - 1 + everydayFacadeProfiles.length,
    excludedExecutionIds: [...everydayProfiles.flatMap(profile => everydayTasks
      .filter(task => !["build-revise", "delegate-feedback", "recover-controller", "create-skill-studio"].includes(task.id))
      .map(task => `everyday-workflows.${profile.id}.daytona.${task.id}`)),
      ...everydayTasks.flatMap(task => [
        `everyday-workflows.runner-opencode.daytona.${task.id}`,
        ...(["hire-reuse", "delegate-feedback"].includes(task.id) ? [] : [`everyday-workflows.runner-opencode.local.${task.id}`]),
      ]),
      // ACPX facades and the DeepSeek plan profile join only reliability cells.
      ...[...everydayFacadeProfiles, runnerOpenCodeDeepSeek1017Profile].flatMap(profile => everydayTasks.flatMap(task =>
        ["local", "daytona"].map(environmentId => `everyday-workflows.${profile.id}.${environmentId}.${task.id}`))),
      ...everydayReliabilityExcludedIds("everyday-workflows"),
    ],
    definitionMetadata: { version: 12, instructions: "production", grading: "outcome-and-invariants", scheduling: "explicit-only",
      reliability: { group: EVERYDAY_RELIABILITY_GROUP, selection: "explicit-group-only", signatures: everydayReliabilitySignatures,
        productRule: "interrupted-work-resumes-automatically-or-offers-a-working-first-retry", companyAndLeadBudgetCents: 1_000,
        testOpsPlan: { profile: RELIABILITY_PLAN_PROFILE_ID, cells: reliabilityPlanCells,
          cadence: "testops-launch-or-manual-dispatch", extras: "explicit-only-codex-and-acpx-cells" } },
      controllerDowntimeMs: 125_000,
      remoteCodexRestart: "bounded-main-server-outage-receipt-empty-cache-same-active-process-and-finalization",
      procedureCases: { ids: ["hire-reuse", "delegate-feedback"], maximumAttemptsPerCell: 1, companyAndLeadBudgetCents: 1_000 } },
  },
  {
    id: NATIVE_INSTRUCTION_SUITE, label: "Native completion instruction consolidation", manualOnly: true,
    description: "Matched production-default durable-document and concrete-blocker checks for the completion constraint reduction.",
    groups: ["native", "local"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude", "runner-opencode"].includes(profile.id)).map(nativeCompletionProfile),
    environments: [localEnvironment], tasks: nativeCompletionTasks, expectedMatrixSize: 6,
    definitionMetadata: { version: 1, fixtureDigest: nativeInstructionDefinitionDigest(), baseSha: NATIVE_INSTRUCTION_BASE_SHA,
      instructions: "production-default", maximumAttemptsPerCell: 1, automaticRetryPolicy: "single_attempt",
      budgetMonthlyCents: NATIVE_COMPLETION_BUDGET_CENTS, scheduling: "explicit-only",
      grading: "original-assigned-skill-and-strict-native-completion", },
  },
  {
    id: "native-completion", label: "Native completion guidance", manualOnly: true,
    description: "Production-default assigned-skill document completion and concrete whole-task blocking, with independent native result/final ordering.",
    groups: ["native", "local"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude", "runner-opencode"].includes(profile.id)).map(nativeCompletionProfile),
    environments: [localEnvironment], tasks: nativeCompletionTasks, expectedMatrixSize: 6,
    definitionMetadata: { version: 1, fixtureDigest: nativeCompletionDefinitionDigest(), instructions: "unchanged-master-production-default",
      providerTurns: 6, maximumAttemptsPerCell: 1, automaticRetryPolicy: "single_attempt", budgetMonthlyCents: NATIVE_COMPLETION_BUDGET_CENTS,
      grading: "original-assigned-skill-durable-document-plus-native-disposition-and-observable-final-order", scheduling: "explicit-only" },
  },
  {
    id: "context-integrity",
    label: "Context Integrity",
    manualOnly: true,
    description: "Explicit-only proof that ordered user comments and assigned skills stay bound to the current task context.",
    groups: ["context-integrity", "native", "legacy"],
    profiles: contextIntegrityProfiles,
    environments: [localEnvironment],
    tasks: contextIntegrityTasks,
    expectedMatrixSize: contextIntegrityProfiles.length * contextIntegrityTasks.length,
    definitionMetadata: {
      version: 1,
      instructions: "production",
      grading: "ordered-public-context-and-explicit-skill-invocation",
      scheduling: "explicit-only",
      paidCalls: "one provider run per skill case; two bounded turns per comment case",
      prerequisiteGate: PENDING_PROFILE_PREREQUISITES,
    },
  },
  {
    id: "stock-harness",
    label: "Stock harness with Paperclip",
    manualOnly: true,
    description: "Production-default hires, reduced shared prompts, assigned skills, continuation, and persistent chat.",
    groups: ["stock-harness", "native", "legacy"],
    profiles: [...contextIntegrityProfiles.filter(profile => !pendingContextIntegrityProfiles.includes(profile)),
      runnerProfiles.find(profile => profile.id === "legacy-opencode")!].map(productionDefaultHireProfile),
    environments: [localEnvironment],
    tasks: [...contextIntegrityTasks, chatTasks.find(task => task.id === "continuity-restart")!, paperclipDocumentTask]
      .map(task => ({ ...task, automaticRetryPolicy: "single_attempt" as const })),
    expectedMatrixSize: 26,
    excludedExecutionIds: ["legacy-codex", "legacy-acp-codex", "legacy-acp-claude", "runner-codex", "runner-acpx-claude", "runner-opencode"]
      .map(profile => `stock-harness.${profile}.local.${paperclipDocumentTask.id}`),
    definitionMetadata: {
      version: 2, instructions: "production-default-hire", scheduling: "explicit-only",
      automaticRetryPolicy: "single_attempt", maximumAttemptsPerCell: 1,
      sourceDigest: stockHarnessSourceDigest(),
      operationalSkillSources: stockHarnessSkillSources(),
      grading: "public-default-bundle-and-delivered-prompts-plus-independent-lifecycle-oracles",
      vendorBaseEvidence: "required deterministic Codex driver/runnerd/Rust gate; task success is not vendor-base proof",
      paidCalls: "one skill turn, two ordered-comment turns, three chat turns per profile",
    },
  },
  {
    id: APPROVAL_HISTORY_SUITE, label: "Onboarding approval history", manualOnly: true,
    description: "Interview, partial plan approval, approved hiring, a separate execution confirmation, and the writer’s saved result.",
    groups: ["onboarding", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id)),
    environments: [localEnvironment], tasks: [onboardingApprovalHistoryTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, sourceDigest: approvalHistoryDefinitionDigest(), scheduling: "explicit-only",
      automaticRetryPolicy: "single_attempt", maximumAttemptsPerCell: 1, expectedWorkRuns: 7,
      companyTaskBudgetCents: 500, maximumCompanyRuns: 12, attemptTimeoutMs: 900_000,
      instructions: "production-wizard-and-first-task", approvalSequence: "plan-checkbox-subset/hiring-checkbox/execution-confirmation",
      oracle: "persisted-human-decisions/current-plan-revision/assigned-child/one-worker-execution/saved-document/reload" },
  },
  {
    id: "first-task", label: "First-task onboarding",
    description: "Production onboarding, first replies, approval, and durable task execution.",
    groups: ["onboarding"],
    profiles: runnerProfiles.filter(profile => ["legacy-codex", "legacy-claude", "runner-codex", "runner-acpx-claude"].includes(profile.id)),
    environments: [localEnvironment], tasks: firstTaskTasks, expectedMatrixSize: 56,
    definitionMetadata: { version: 9, runGrading: "accepted-execution-or-explicit-plan-only", credentialPersistenceCheck: false, questionChoiceMinimum: 2, nativeSetup: "qualified-platform-wizard-saved-default", claudeDefaultTargets: ["darwin-arm64", "darwin-x64", "linux-x64", "linux-arm64"], legacySetup: "explicit-advanced-runner-choice", productionInstructions: true, qualityGrading: "informational" },
  },
  {
    id: CHAT_SETUP_HEALTH_SUITE, label: "Chat provider setup health", manualOnly: true,
    description: "Diagnostic only: one normal lifecycle hello, zero chat/task work; excluded from the 244 catalog scenarios.",
    groups: [], profiles: [chatFeatureExecutionProfile], environments: [localEnvironment], tasks: [chatSetupHealthTask], expectedMatrixSize: 1,
    definitionMetadata: { version: 1, sourceDigest: chatSetupHealthDigest, scheduling: "explicit-only", catalogScenario: false,
      maximumAttemptsPerCell: 1, maximumAutomaticSetupHellos: 1, expectedHeartbeatRuns: 0, canonicalQueries: 0,
      setupProbeUsage: "unavailable-outside-heartbeat-accounting" },
  },
  {
    id: CHAT_FEATURE_SUITE, label: "Chat feature journeys", manualOnly: true,
    description: "Executable catalog requests through Agent Chat, with independently graded persisted state.",
    groups: ["chat", "native"],
    profiles: [chatFeatureExecutionProfile,
      chatFeatureProfile(nativeProfile({ id: "runner-codex-subscription", label: "Native Codex subscription",
        provider: "codex", model: DEFAULT_CODEX_LOCAL_MODEL, credential: "CODEX_AUTH_JSON", supportedEnvironments: ["local"] })),
      chatFeatureProfile(runnerOpenCodeDeepSeek1017Profile)],
    environments: [localEnvironment], tasks: [...chatFeatureTasks, ...chatCatalogTasks], expectedMatrixSize: 5 + chatCatalogTasks.length,
    excludedExecutionIds: [
      ...chatCatalogTasks.map(task => `chat-features.runner-codex-subscription.local.${task.id}`),
      ...[...chatFeatureTasks, ...chatCatalogTasks].filter(task => task.id !== "create-backlog").map(task => `chat-features.runner-opencode-deepseek-1017.local.${task.id}`),
    ],
    definitionMetadata: { version: 3, nativeTimeoutPolicy: CHAT_NATIVE_TIMEOUT_POLICY, authoredTurnTimeouts: "legacy-declarations-retained-separately-not-effective-native-caps", definitionDigest: chatFeatureDefinitionDigest, inventoryDigest: chatCatalogInventoryDigest, frozenScenarioCount: 244, scheduling: "explicit-only",
      instructions: "production-role-defaults", companyAndAgentBudgetCents: CHAT_FEATURE_BUDGET_CENTS,
      unpricedUsagePolicy: "allow-through-public-budget-policy", taskRunLimits: "per-case-declared; agent daily admission ceiling 3",
      maximumAttemptsPerCell: 1, setupProbeUsage: "unavailable-outside-heartbeat-accounting",
      scenarios: [...chatFeatureScenarios, ...chatCatalogScenarios.filter(row => chatCatalogTasks.some(task => task.id === row.id))].map(({ id, capabilities }) => ({ id, capabilities })) },
  },
  {
    id: "agent-chat", label: "Persistent Agent Chat",
    description: "Task-backed conversations, session resets, and project plan handoff.",
    groups: ["chat"],
    profiles: runnerProfiles.filter(profile => ["legacy-codex", "legacy-claude", "runner-codex", "runner-acpx-claude"].includes(profile.id)).map(defaultPermissionProfile),
    environments: [localEnvironment], tasks: chatTasks, expectedMatrixSize: 28,
    excludedExecutionIds: ["legacy-codex", "legacy-claude"].flatMap(profile => ["reassign-task", "create-backlog"].map(task => `agent-chat.${profile}.local.${task}`)),
    definitionMetadata: { version: 9, clarificationGrading: "wrapped-information-fields-list", resetRunsCountedSeparately: true, permissions: "production-defaults", stopBoundary: "provider-turn-started", restartMemory: "required-after-restart" },
  },
  {
    id: "agent-chat-hardening", label: "Agent Chat Recovery and Coordination", manualOnly: true,
    description: "Native chat startup cancellation, committed sends, hiring, grounded status, and remote continuity.",
    groups: ["chat", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(profile => productionStoryProfile(defaultPermissionProfile(profile))),
    environments: [localEnvironment, daytonaWarmEnvironment], tasks: chatHardeningTasks, expectedMatrixSize: 18,
    excludedExecutionIds: ["runner-codex", "runner-acpx-claude"].flatMap(profile =>
      ["stop-startup-new-resume", "hire-delegate-reuse", "blocked-status-review"].map(task => `agent-chat-hardening.${profile}.daytona.${task}`)),
    definitionMetadata: { version: 5, permissions: "production-defaults", instructions: "production", grading: "durable-state-and-source-evidence", scheduling: "explicit-only", restartMemory: "required-after-restart", statusEvidence: "structured-current-blocker-and-active-run-count", readOnlyState: "public-mutation-contract-and-relations", hiringReference: "neutral-document-reference-line" },
  },
  {
    id: "hiring-templates", label: "Production Hiring Templates", manualOnly: true,
    description: "Production CEO and hiring skill/reference discovery, one coder hire, independently checked JSON artifacts and worker reuse.",
    groups: ["chat", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(profile => hiringTemplateProfile(defaultPermissionProfile(profile))),
    environments: [localEnvironment], tasks: hiringTemplateTasks, expectedMatrixSize: 2,
    definitionMetadata: { version: 1, definitionDigest: hiringTemplateDefinitionDigest, instructions: "source-revision-default-ceo", scheduling: "explicit-only",
      grading: "independent-json-and-read-receipts", baselineComparison: "same-fixture-source-derived-bundles", providerTurns: 5 },
  },
  {
    id: "agent-chat-stories", label: "Agent Chat Setup and Interruptions", manualOnly: true,
    description: "Experimental settings lifecycle and user follow-ups during active native work.",
    groups: ["chat", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(profile => productionStoryProfile(defaultPermissionProfile(profile))),
    environments: [localEnvironment], tasks: chatStoryTasks, expectedMatrixSize: 6,
    definitionMetadata: { version: 3, setup: "configured-native-agent", permissions: "production-defaults", interruptionBoundary: "provider-file-wait-in-agent-workspace", grading: "persisted-comments-and-plan-run-attributed", scheduling: "explicit-only" },
  },
  {
    id: "agent-chat-qualification", label: "Agent Chat Remaining Qualification", manualOnly: true,
    description: "Active ownership transfer, user recovery after worker loss, and grounded answer quality.",
    groups: ["chat", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(profile => productionStoryProfile(defaultPermissionProfile(profile))),
    environments: [localEnvironment], tasks: chatQualificationTasks, expectedMatrixSize: 6,
    definitionMetadata: { version: 10, instructionSetup: "read-before-write-base-hash", permissions: "production-defaults", instructions: "production", crashBoundary: "verified-native-worker-pid-at-file-wait", recovery: "new-user-message-after-verified-cleanup", answerGrading: "exact-grounded-propositions-plus-separate-semantic-review", scheduling: "explicit-only" },
  },
  {
    id: "confirmation-replies", label: "Conversational Approval Cards", manualOnly: true,
    description: "Persist approval/refusal from chat before execution, preserve card clicks, clarify ambiguous proposals, and answer historical questions after moving on.",
    groups: ["chat", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(profile => productionStoryProfile(defaultPermissionProfile(profile))),
    environments: [localEnvironment, runnerEnvironments.find(environment => environment.id === "daytona")!],
    excludedExecutionIds: ["runner-codex", "runner-acpx-claude"].flatMap(profile =>
      [...firstTaskTasks.filter(task => ["task-reply-accept", "interview-plan-accept", "reject-no-execution", "task-card-accept"].includes(task.id)), ...chatConfirmationTasks]
        .map(task => `confirmation-replies.${profile}.daytona.${task.id}`)
        .filter(id => id !== "confirmation-replies.runner-codex.daytona.task-card-accept")),
    tasks: [...firstTaskTasks.filter(task => ["task-reply-accept", "interview-plan-accept", "reject-no-execution", "task-card-accept"].includes(task.id)), ...chatConfirmationTasks],
    expectedMatrixSize: 13,
    definitionMetadata: { version: 8, planApproval: "execute-accepted-interview-scope", managedOnboarding: "ui-owned-qualification-and-physical-file", managedExpectedTaskRuns: 4, managedAutomaticRetries: 0, instructions: "production", grading: "card-message-provenance-before-child-creation", unansweredQuestionComposer: "history-card-only-including-fresh-dismissal", completionObservation: "120-seconds", scheduling: "explicit-only" },
  },
  {
    id: "completion-updates", label: "Delegated Completion Updates", manualOnly: true,
    description: "Qualify completion delivery in onboarding and idle, busy, multiple-task, and restart Agent Chat handoffs.",
    groups: ["chat", "native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id))
      .map(profile => productionStoryProfile(defaultPermissionProfile(profile))),
    environments: [localEnvironment],
    tasks: [...firstTaskTasks.filter(task => task.id === "interview-plan-accept"), ...chatCompletionTasks],
    expectedMatrixSize: 10,
    definitionMetadata: { version: 29, runGrading: "accepted-execution-or-explicit-plan-only", resultNavigation: "loaded-task-header", instructionSetup: "read-before-write-base-hash", requirementEvidence: "recorded-user-comments-and-resolved-answers", busyReferenceWait: "committed-conversation-document-response-held", busyBoundary: "source-tool-in-flight-and-public-deferred-wake", workerReference: "rsvp-code-in-saved-note", judge: "completion-quality-v14-observed-rendered-result-access", judgeMaxDollarsPerRequest: 0.5, instructions: "production", correlation: "authoritative-task-facts-required-in-reply-run", restartBoundary: "done-and-source-provider-at-reference-gate", idleBoundaryTimeoutMs: 180_000, workerBriefTimeoutMs: 240_000, workerBriefWorkspace: "run-isolated-task-directory", workerBriefEvidence: "released-start-time", grading: "post-completion-reply-and-result-access", semanticReview: "required-separately", chatBoundary: "worker-gated-until-source-idle", observationWindowMs: 120_000, scheduling: "explicit-only" },

  },
  ...(process.env.PAPERCLIP_RUNNER_E2E_CONNECTION_REVIEWS === "1" ? [connectionReviewSuite] : []),
  {
    id: FEEDBACK_PERSISTENCE_SUITE, label: "Feedback Persistence", manualOnly: true,
    description: "Real complaint and suggestion submissions, durable bodies, and retained tool receipts.",
    groups: ["native"],
    profiles: runnerProfiles.filter(profile => ["runner-codex", "runner-acpx-claude"].includes(profile.id)),
    environments: runnerEnvironments, tasks: [feedbackPersistenceTask(runnerTasks.find(task => task.id === "message-marker")!)], expectedMatrixSize: 4,
    definitionMetadata: { version: 2, owner: "runner-e2e-maintainers", scheduling: "explicit-only",
      sourceDigest: feedbackPersistenceDigest(runnerTasks.find(task => task.id === "message-marker")!), expectedWorkRuns: 1, automaticRetryPolicy: "single_attempt",
      budgetCents: 1_000, forecast: "unmeasured; gateway manifest required for bounded qualification",
      grading: "retained-exact-bodies-and-run-attributed-completed-tools", feedback: "synthetic-disposable-items" },
  },
  {
    id: "core-compatibility",
    label: "Core Runner Compatibility",
    description:
      "Major provider, runtime generation, and execution-environment compatibility.",
    groups: ["core"],
    profiles: runnerProfiles,
    environments: runnerEnvironments,
    tasks: runnerTasks,
    expectedMatrixSize: 48,
  },
  {
    id: "local-session-integrity",
    label: "Local Session Integrity",
    description:
      "Structured interaction and continuation qualification for every supported local profile.",
    groups: ["core"],
    profiles: runnerProfiles,
    environments: [localEnvironment],
    tasks: localIntegrityTasks,
    expectedMatrixSize: 16,
  },
  {
    id: "openrouter-model-breadth",
    label: "OpenRouter Model Breadth",
    description:
      "Weekly-ranked tool-capable OpenRouter models through native OpenCode on isolated local workspaces.",
    groups: ["breadth"],
    profiles: openRouterBreadthProfiles,
    environments: [localEnvironment],
    tasks: openRouterBreadthTasks,
    excludedExecutionIds: openRouterBreadthExcludedExecutionIds,
    expectedMatrixSize: 10,
    definitionMetadata: {
      rankingSnapshotId: openRouterRankingSnapshot.snapshotId,
      rankingContentHash: openRouterRankingSnapshot.contentHash,
      rankingCapturedAt: openRouterRankingSnapshot.capturedAt,
      rankingSourceUrl: openRouterRankingSnapshot.sourceUrl,
      excludedModelIds: openRouterBreadthExcludedModelIds,
      excludedExecutionIds: openRouterBreadthExcludedExecutionIds,
    },
  },
  {
    id: "daytona-warm-continuity",
    label: "Daytona Warm Continuity",
    description:
      "Three browser-driven turns on one reusable Daytona sandbox for legacy and native Codex.",
    groups: ["daytona", "warm"],
    profiles: codexContinuityProfiles,
    environments: [daytonaWarmEnvironment],
    tasks: [daytonaWarmContinuityTask],
    expectedMatrixSize: 2,
    definitionMetadata: { version: 5, nativeInstructions: "managed-incremental", managedFileBytes: 8 * 1024 * 1024,
      managedSaveReceipt: "latest-paginated-run-log-instruction-save" },
  },
  {
    id: "daytona-journal-continuity",
    label: "Daytona Large Journal Continuity",
    manualOnly: true,
    description: "Continue the same native session after separate ordinary tool invocations and their output grow its durable journal beyond 2 MiB.",
    groups: ["daytona", "warm"],
    profiles: warmCodexContinuityProfiles.filter((profile) => profile.id === "runner-codex"),
    environments: [daytonaWarmEnvironment],
    tasks: [daytonaLargeJournalTask],
    expectedMatrixSize: 1,
    definitionMetadata: { version: 6, warmPromptDigest: warmTurnDefinitionDigest, nativeInstructions: "fixed-external", journalMinimumBytes: 2 * 1024 * 1024, toolInvocations: 240, outputBytesPerInvocation: 65020, scheduling: "explicit-only" },
  },
  {
    id: "daytona-git-streaming",
    label: "Daytona Git Streaming",
    manualOnly: true,
    description: "Copy back 60,000 real untracked files and continue twice with a Git filename manifest above 32 MiB.",
    groups: ["daytona", "warm"],
    // Copyback plus the next preparation can exceed the ordinary five-minute
    // idle window for this 60,000-file workload. Keep the PID oracle strict
    // while explicitly retaining both runner and sandbox for the workload.
    profiles: codexContinuityProfiles.filter(profile => profile.id === "runner-codex").map(profile => ({
      ...profile,
      buildAgent(input: AgentFixtureBuildInput) {
        const agent = profile.buildAgent(input);
        // Managed agent-folder collection intentionally stops the provider at
        // every turn. Fixed external instructions exercise retained processes.
        return { ...agent, adapterConfig: {
          ...(agent.adapterConfig as Record<string, unknown>),
          idleTimeoutMs: 1_200_000,
          instructionsBundleMode: "external",
          instructionsRootPath: fileURLToPath(new URL("./fixtures/git-streaming/", import.meta.url)),
          instructionsEntryFile: "AGENTS.md",
          instructionsFilePath: fileURLToPath(new URL("./fixtures/git-streaming/AGENTS.md", import.meta.url)),
        } };
      },
    })),
    environments: [{
      ...daytonaWarmEnvironment,
      buildEnvironment(input: EnvironmentFixtureBuildInput) {
        const environment = daytonaWarmEnvironment.buildEnvironment(input);
        return { ...environment, config: { ...(environment.config as Record<string, unknown>), runnerIdleTimeoutMs: 1_200_000, autoStopInterval: 25, autoArchiveInterval: 30 } };
      },
    }],
    tasks: [daytonaGitStreamingTask],
    expectedMatrixSize: 1,
    definitionMetadata: { version: 9, instructions: "fixed-external", nativeIdleTimeoutMs: 1_200_000, autoStopIntervalMinutes: 25, generatedFileCount: 60_000, filenameBytes: 39_828_890, scheduling: "explicit-only", finalization: "committed-without-active-sync-or-retry", copyback: "all-generated-file-contents-change-each-turn" },
  },
  {
    id: "case-handoffs", label: "Persistent same-task case handoffs", manualOnly: true,
    description: "Explicit arithmetic and receipt workflows route one persistent case task through three native agents, with durable documents, public history and native tool receipts.",
    groups: ["native"],
    profiles: [nativeCompletionProfile(nativeProfile({ id: "runner-codex-subscription", label: "Native Codex subscription", provider: "codex", model: DEFAULT_CODEX_LOCAL_MODEL, credential: "CODEX_AUTH_JSON", supportedEnvironments: ["local"] })),
      ...runnerProfiles.filter(profile => profile.id === "runner-codex").map(nativeCompletionProfile)],
    environments: [localEnvironment], tasks: [caseHandoffTask, caseReceiptTask],
    expectedMatrixSize: 4,
    definitionMetadata: { version: 4,
      definitionDigest: createHash("sha256").update(caseHandoffDefinitionDigest()).update(caseReceiptDefinitionDigest()).digest("hex"),
      scheduling: "explicit-only", maximumProviderTurns: 6, maximumAttemptsPerCell: 1,
      grading: "public-primary-task-handoff-ledger-durable-documents-and-native-tool-receipts",
      credentialModes: ["isolated-company-subscription-login", "company-encrypted-api-secret-reference"],
      cases: {
        "same-task-roundtrip": { definitionDigest: caseHandoffDefinitionDigest(), budgetMonthlyCents: 1000, maximumProviderTurns: 6 },
        "receipt-smoke": { definitionDigest: caseReceiptDefinitionDigest(), budgetMonthlyCents: CASE_RECEIPT_BUDGET_CENTS,
          maximumProviderTurns: CASE_RECEIPT_MAX_TURNS, minimumProviderTurns: CASE_RECEIPT_MAX_TURNS,
          runTimeoutMs: CASE_RECEIPT_RUN_TIMEOUT_MS, reasoningEffort: "low", attemptTimeoutMs: 300_000,
          agentDailyRunCaps: { triage: 1, builder: 2, verifier: 1 } },
      } },
  },
  buildConnectionSuite(runnerProfiles, runnerEnvironments),
  buildGitHubReviewJourneySuite(runnerProfiles, runnerEnvironments),
  buildAntigravityJourneySuite(runnerEnvironments),
  {
    id: "repository-skills", label: "Repository skill packages", manualOnly: true,
    description: "Live private Poteto import and byte-for-byte delivery to local and Daytona agent runtimes.",
    groups: ["native"],
    profiles: runnerProfiles.filter(profile => profile.id === "runner-codex").map(repositorySkillsProfile),
    environments: [localEnvironment, daytonaWarmEnvironment], tasks: [repositorySkillsTask], expectedMatrixSize: 2,
    definitionMetadata: { version: 1, scheduling: "explicit-only", maximumAttemptsPerCell: 1,
      source: "paperclipai/poteto-stack", skills: ["architect", "bro"], grading: "independent-git-blob-hashes-and-file-modes-from-owned-runtime", budgetMonthlyCents: 1000 },
  },
] as const;

export function suiteDefinitionHash(suite: RunnerSuiteFixture) {
  return createHash("sha256")
    .update(
      JSON.stringify({
        id: suite.id,
        profiles: suite.profiles.map((profile) => ({
          id: profile.id,
          model: profile.model,
          qualification: profile.modelQualification,
          ...(profile.qualificationCandidate === "pi" ? { piThinkingLevel: PI_QUALIFICATION_THINKING_LEVEL } : {}),
        })),
        environments: suite.environments.map((environment) => ({
          id: environment.id,
          configurationKey: environment.configurationKey ?? "default",
        })),
        ...(suite.environmentOverrides ? { environmentOverrides: Object.entries(suite.environmentOverrides).map(([taskId, overrides]) => ({
          taskId, environments: Object.values(overrides).flatMap(environment => environment ? [{
            id: environment.id, configurationKey: environment.configurationKey ?? "default",
          }] : []),
        })) } : {}),
        tasks: suite.tasks.map((task) => ({
          id: task.id,
          flow: task.flow,
          expectedRunCount: task.expectedRunCount,
          ...(task.requiredCredentials ? { requiredCredentials: task.requiredCredentials } : {}),
          ...(task.minimumExpectedRunCount === undefined ? {} : { minimumExpectedRunCount: task.minimumExpectedRunCount }),
          restartServerBeforeQuestionAnswer:
            task.restartServerBeforeQuestionAnswer ?? false,
        })),
        excludedExecutionIds: [...(suite.excludedExecutionIds ?? [])].sort(),
        metadata: suite.definitionMetadata ?? null,
      }),
    )
    .digest("hex");
}

export function buildRunnerMatrix(
  suites: readonly RunnerSuiteFixture[] = runnerSuites,
): MatrixExecution[] {
  return suites.flatMap((suite) => {
    const excludedExecutionIds = new Set(suite.excludedExecutionIds ?? []);
    return suite.profiles.flatMap((profile) =>
      suite.environments
        .filter((environment) =>
          profile.supportedEnvironments.includes(environment.id),
        )
        .flatMap((environment) =>
          suite.tasks
            .map((task) => {
              const selectedEnvironment = suite.environmentOverrides?.[task.id]?.[environment.id] ?? environment;
              if (selectedEnvironment.id !== environment.id) throw new Error(`Fixture environment override changed provider ID for ${suite.id}.${task.id}`);
              return {
                id: `${suite.id}.${profile.id}.${environment.id}.${task.id}`,
                suite,
                suiteDefinitionHash: suiteDefinitionHash(suite),
                profile,
                environment: selectedEnvironment,
                task: suite.id === "confirmation-replies" && profile.id === "runner-codex" && environment.id === "daytona" && task.id === "task-card-accept"
                  ? { ...task, expectedRunCount: 4, automaticRetryPolicy: "single_attempt" as const }
                  : suite.id === "extended-harnesses" && profile.qualificationCandidate === "pi" && task.id === "file-edit-validate"
                    ? { ...task, buildPrompt: piFilePrompt }
                    : suite.id === "extended-harnesses" && profile.qualificationCandidate === "copilot" && task.id === "file-edit-validate"
                      ? { ...task, buildPrompt: copilotFilePrompt } : task,
                groups: [
                  ...new Set([
                    ...suite.groups,
                    ...profile.groups,
                    ...selectedEnvironment.groups,
                    ...task.groups,
                  ]),
                ],
                requiredCredentials: [
                  ...(["provider_connection", "github_review_journey", "antigravity_agent_journey"].includes(task.flow) ? [] : [profile.credential]),
                  ...(!["provider_connection", "github_review_journey", "antigravity_agent_journey"].includes(task.flow) && selectedEnvironment.credential ? [selectedEnvironment.credential] : []),
                  ...(task.requiredCredentials ?? []),
                ],
              };
            })
            .filter((execution) => !excludedExecutionIds.has(execution.id)),
        ),
    );
  });
}

function duplicateIds(values: readonly { id: string }[]) {
  const seen = new Set<string>();
  return values
    .map((value) => value.id)
    .filter((id) => {
      if (seen.has(id)) return true;
      seen.add(id);
      return false;
    });
}

function assertNoRawSecretValues(value: unknown, label: string) {
  if (typeof value === "string") {
    if (/\b(?:sk-(?:proj-)?|sk-ant-)[A-Za-z0-9_-]{12,}\b/.test(value)) {
      throw new Error(`${label} contains a raw secret-looking value`);
    }
    return;
  }
  if (Array.isArray(value)) {
    value.forEach((entry) => assertNoRawSecretValues(entry, label));
    return;
  }
  if (value && typeof value === "object") {
    Object.entries(value).forEach(([key, entry]) => {
      if (
        typeof entry === "string" &&
        /(?:api.?key|access.?token|credential|secret)$/i.test(key) &&
        entry.trim()
      ) {
        throw new Error(`${label} contains a raw credential at ${key}`);
      }
      assertNoRawSecretValues(entry, label);
    });
  }
}

export function validateRunnerCatalog(): MatrixExecution[] {
  const connectionSuite = runnerSuites.find(suite => suite.id === "provider-connections")!;
  const allProfiles = [cursorCloudProfile, ...connectionSuite.profiles, ...extendedHarnessProfiles, ...runnerProfiles, ...legacyAcpxProfiles, ...pendingContextIntegrityProfiles, ...openRouterBreadthProfiles, ...everydayProfiles.filter(p => !runnerProfiles.some(existing => existing.id === p.id))];
  const allTasks = [
    cursorCloudArtifactTask, cursorCloudFollowupTask, cursorCloudStopTask,
    repositorySkillsTask,
    ...piNativeTasks,
    ...copilotProtectionTasks,
    ...connectionSuite.tasks,
    extendedHarnessFileTask,
    ...contextIntegrityTasks,
    ...blockerTasks,
    ...accountingTasks,
    ...lifecycleLiveTasks,
    ...continuationTasks,
    questionResumeTask,
    ...everydayTasks,
    ...everydayReliabilityTasks,
    ...taskTitleTasks,
    ...runnerTasks,
    ...localIntegrityTasks,
    ...openRouterBreadthTasks,
    daytonaWarmContinuityTask,
    daytonaGitStreamingTask,
    instructionPersistenceTask,
    daytonaLargeJournalTask,
  ];
  for (const [label, values] of [
    ["suite", runnerSuites],
    ["profile", allProfiles],
    ["environment", runnerEnvironments],
    ["task", allTasks],
  ] as const) {
    const duplicates = duplicateIds(values);
    if (duplicates.length > 0)
      throw new Error(
        `Duplicate ${label} fixture ids: ${duplicates.join(", ")}`,
      );
  }

  const selectableGroups = new Set<string>(SELECTABLE_GROUPS);
  for (const fixture of [
    ...runnerSuites,
    ...allProfiles,
    ...runnerEnvironments,
    daytonaWarmEnvironment,
    ...allTasks,
  ]) {
    const unknownGroups = fixture.groups.filter(
      (group) => !selectableGroups.has(group),
    );
    if (unknownGroups.length > 0) {
      throw new Error(
        `Fixture ${fixture.id} declares unknown groups: ${unknownGroups.join(", ")}`,
      );
    }
  }

  const sampleRefs = Object.fromEntries(
    CREDENTIAL_NAMES.map((name, index) => [
      name,
      {
        type: "secret_ref" as const,
        secretId: `${String(index + 1).padStart(8, "0")}-1111-4111-8111-111111111111`,
        version: "latest" as const,
      },
    ]),
  );

  for (const environment of [...runnerEnvironments, daytonaWarmEnvironment]) {
    const payload = environment.buildEnvironment({
      secretRefs: sampleRefs,
      daytonaImage:
        "ghcr.io/paperclipai/paperclip-daytona-runner@sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
      executionId: "schema-validation",
    });
    createEnvironmentSchema.parse(payload);
    assertNoRawSecretValues(payload, `environment ${environment.id}`);
  }
  for (const profile of [...allProfiles, ...everydayProfiles]) {
    if (!CREDENTIAL_NAMES.includes(profile.credential)) {
      throw new Error(
        `Profile ${profile.id} declares unknown credential ${profile.credential}`,
      );
    }
    const unsupportedEnvironmentIds = profile.supportedEnvironments.filter(
      (environmentId) => !ENVIRONMENT_IDS.includes(environmentId),
    );
    if (unsupportedEnvironmentIds.length > 0) {
      throw new Error(
        `Profile ${profile.id} declares unknown environments: ${unsupportedEnvironmentIds.join(", ")}`,
      );
    }
    const payload = profile.buildAgent({
      environmentId: SAMPLE_UUID,
      environmentFixtureId: "local",
      workspacePath: "/tmp/paperclip-runner-e2e-schema",
      secretRefs: sampleRefs,
      executionId: "schema-validation",
    });
    createAgentSchema.parse(payload);
    assertNoRawSecretValues(payload, `profile ${profile.id}`);
  }

  const matrix = buildRunnerMatrix();
  const duplicateMatrixIds = duplicateIds(matrix);
  if (duplicateMatrixIds.length > 0) {
    throw new Error(
      `Duplicate matrix execution ids: ${duplicateMatrixIds.join(", ")}`,
    );
  }
  for (const suite of runnerSuites) {
    const suiteSize = matrix.filter(
      (execution) => execution.suite.id === suite.id,
    ).length;
    if (suiteSize !== suite.expectedMatrixSize) {
      throw new Error(
        `Expected ${suite.expectedMatrixSize} ${suite.id} executions; received ${suiteSize}`,
      );
    }
  }
  const expectedTotal = runnerSuites.reduce((total, suite) => total + suite.expectedMatrixSize, 0);
  if (matrix.length !== expectedTotal)
    throw new Error(`Expected ${expectedTotal} runner executions; received ${matrix.length}`);
  return matrix;
}

export const runnerMatrix = validateRunnerCatalog();

export function runnerExecutionById(id: string): MatrixExecution {
  const execution = runnerMatrix.find((candidate) => candidate.id === id);
  if (!execution) throw new Error(`Unknown runner E2E execution id: ${id}`);
  return execution;
}

export { productJourneys } from "./product-journeys/catalog.js";