Files
PaperClipAI/server/src/services/native-runtime/native-execution-input.test.ts
T
DottaandPaperclip 27d35314be feat: connect experimental Cursor Cloud to native Runner (#18069)
## Thinking Path

> - Paperclip helps people manage AI agents at work.
> - Native Runner owns execution and task authority.
> - Operators need an explicit native Cursor Cloud choice.
> - Tools/files need company, task, session and run scope.
> - This connects setup and lifecycle to Runner Core.
> - Legacy agents retain their selected runtime/history.

## Linked Issues or Issue Description

Depends on #18068. Managed-only API placement and API-owned Stop
containment are in #18310. Refs #5664, #11803, #17299, and #17471. No
duplicate native integration was found.

## What Changed

- Add explicit native setup, Test, saved settings and dispatch with
no-prompt account/catalog/callback checks.
- Scope MCP to company, agent, task, session and run through
authenticated HTTPS. Register verified artifacts/work products; preserve
unpriced accounting, completion and budgets.
- Connect Question/Plan continuation, cold handoff and admitted fresh
sessions; recheck waiting admission under the task lock.
- Present audited Stop intent while preserving physical containment
proof; bound typed Stop metadata. Preserve title edits through
preference/navigation readiness.
- Select one live/history representation per run to prevent duplicate
settled cards. Integrate upstream task/read-state/retry/schema contracts
and repair two test fixtures.

## Verification

Core #18068 merged normally as `3910352c923a`. Product head
`5a60f541c982` has passing repository CI/build/browser checks, including
required `ci / verify` and `ci / e2e`, plus a fresh exact-head Greptile
5/5 review with zero unresolved threads. Two non-required external app
checks remain pending: Paperclip Review is queued waiting for its
assigned agent; Superagent Security Scan is reviewing the diff. These
are not claimed completed. The normal merge endpoint enforces the
repository rules; no policy or status override is used. The dependent
Top PR is addressing its fresh deferred-Stop review finding.

Product `5a60f541c982` passed 270 UI and 20 selected
Cloud/native/disk-full tests, UI/server typechecks, tokens and maps.
Top’s clean normal merge passed tokens/maps/diff checks; its matrix is
pending. Earlier receipts retain Core’s 47 Rust, 4 compiled-native
retirement and 19 settlement controls, normal Runner build, and runtime
9af build/recursive typecheck. Reproduced loading/shutdown CI fixture
failures passed 7/7 browser and 121/121 unit tests, including a
broken-unsubscribe negative control. No timeout/oracle was relaxed.

The actual-parent restack adopts 75 mainline paths, including
schema/permission and generic runtime changes, beyond the prior two
fixture repairs and client projection fix. The full difference from
hosted `9af1a5de42a2` is therefore larger than four files; backend
source also differs. The merged config-read checks match Core391, and
the Cursor placement/runtime/relay/selection modules match frozen9af;
selected affected regressions pass. Paid proof keeps its actual 9af
source/image identity. The separately tested live/history card fix is
not claimed deployed on that host.

On 9af, original saved settings survived reopening and fresh no-prompt
Test authenticated catalog/model/binding; no new Save is claimed. Fresh
Linux admission passed. With `claude-sonnet-4-5`, Artifact downloaded
exact 27 bytes and matched 121 canonical identities in complete
S3-served history. First Stop’s strict quiet FAILED on a 10.373-second
gap despite independent cancellation/no late artifact. One targeted
unchanged-sampler retry retained all 24 samples: 35.076 seconds quiet /
maximum gap 4.584 seconds, 67 ordered canonical identities, and separate
CANCELLED/artifact-absent status after the original 180-second deadline.
The pre-reload duplicate settled card is disclosed. Exact-ID cleanup for
the three new provider agents is awaiting authorization, so full grades
and the fresh Artifact’s post-cleanup download remain blocked. A
historical deleted-provider artifact was newly downloaded on 9af;
original F226 Question/Plan/reconnect and cleanup proof keep their
identities.

Retained failures: stale fixture 132/133; E8 48/135 with 87 reset-hook
failures; Mac 17 SQL failures/skips; earlier
title/startup/custody/Stop/deletion failures with unknown causes/bounded
recoveries; `dea023` Stop’s warning/50 duplicate identities; pre-repair
ACK and original Core CI failures. WSP’s 251-assertion, 7/8-suite
attempt failed physical PostgreSQL teardown; the unchanged wrapper rerun
passed 128. Retry alone establishes no cause or full local-suite pass.
All paid attempts remain recorded; vendor dollar cost is UNKNOWN.

## Risks

Experimental: Cursor independently acknowledges neither the effective
model nor instruction digest before the first prompt. Explicit values
are submitted and checked through behavior; unpriced provider dollar
cost stays UNKNOWN.

Callbacks need authenticated reachable HTTPS. Scope, revocation,
budgets, completion and cleanup remain authoritative. Operator Stop
intent is separate from physical containment. Saved legacy agents retain
their selected runtime. Prior shared title-save/deletion failures remain
disclosed.

## Model Used

OpenAI Codex, GPT-6 family, assisted with reasoning, repository tools,
code execution, browser verification, and delegated code review. The
serving model’s exact API ID and context window are not exposed. No
value is inferred from the model catalog.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used and the limits of available model
metadata
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have linked public issues or described the issue in this PR
- [x] I have not referenced internal or instance-local Paperclip issues
or links
- [x] My branch describes the change and contains no internal ticket ID
- [x] I have run the scoped local tests reported above; pending gates
are stated separately
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation
- [x] I have considered and documented the risks
- [x] All required CI gates pass on the current head
- [x] Fresh Greptile is 5/5 with no unresolved findings on the current
head
- [x] I will address all reviewer comments before requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-11-03 09:01:39 -06:00

730 lines
34 KiB
TypeScript

import { describe, expect, it } from "vitest";
import type { ExecutionContinuationEnvelope, AskUserQuestionsInteraction } from "@paperclipai/shared";
import { formatDurableQuestionResponseSummary } from "../question-response-delivery.js";
import { nativeCompletionSource, buildNativeCompletionContract } from "./completion-contracts.js";
import { renderPaperclipWakePrompt } from "@paperclipai/adapter-utils/server-utils";
import { buildNativeExecutionInput } from "./native-execution-input.js";
import { nativeRuntimeContextFixture } from "./runtime-context.test-fixture.js";
import { buildNativeModelEnvelope, canonicalNativeRuntimeContextDigest } from "../../vendor/paperclip-runner/index.js";
describe("LCA-05 explicit native work mode", () => {
it.each(["standard", "planning", "ask", "skill_test"])("title and description cannot override %s mode", (workMode) => {
for (const text of ["Inspect files", "Making a plan", "Create a report", "Research proposal", "Implement now; no plan needed"]) {
const input = buildNativeExecutionInput({
companyId: "10000000-0000-4000-8000-000000000001",
runId: "50000000-0000-4000-8000-000000000005",
agentId: "30000000-0000-4000-8000-000000000003",
issue: { id: "20000000-0000-4000-8000-000000000002", identifier: "MODE-1", title: text, description: text, workMode },
taskPrompt: text,
workspace: { id: "50000000-0000-4000-8000-000000000005", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: null,
provider: "codex",
codexReasoningEffort: "high",
codexWebSearch: "disabled",
planningContext: workMode === "planning" ? { documentId: null, baseRevisionId: null, baseRevisionNumber: 0, markdown: "", sha256: "a".repeat(64), reviewContext: {} } : null,
completionContract: { id: "70000000-0000-4000-8000-000000000007", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1", contract: { revision: "1", objective: "Deliver the requested work", criteria: [{ id: "output", requirement: "Deliver the requested work" }] } },
runtimeContext: nativeRuntimeContextFixture(),
});
expect(input.task.workMode).toBe(workMode);
expect(input.provider).toMatchObject({ kind: "codex", reasoningEffort: "high", webSearch: "disabled" });
expect(input.executionMode).toBe(workMode === "planning" ? "plan" : "default");
expect(input.task.title).toBe(text);
}
});
it.each(["standard", "planning", "ask"] as const)("preserves Cursor Cloud %s intent independently of its native harness mode", workMode => {
const planningContext = workMode === "planning" ? { documentId: "plan-document", baseRevisionId: "plan-revision-3", baseRevisionNumber: 3,
markdown: "# Pinned canonical plan", sha256: "a".repeat(64), reviewContext: { feedback: "Keep the requested scope" } } : null;
const input = buildNativeExecutionInput({
companyId: "10000000-0000-4000-8000-000000000001", runId: "50000000-0000-4000-8000-000000000005", agentId: "30000000-0000-4000-8000-000000000003",
issue: { id: "20000000-0000-4000-8000-000000000002", identifier: "MODE-1", title: "Create the requested result", description: null, workMode },
taskPrompt: "Follow the task's actual work mode.",
workspace: { id: "50000000-0000-4000-8000-000000000005", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null }, normalizedSessionId: null,
provider: "cursor_cloud", model: "explicit-cloud-model", cursorCloud: { schema: "paperclip.cursor-cloud.config.v1", repos: [{ url: "https://github.com/example/fixture" }] },
planningContext,
completionContract: { id: "70000000-0000-4000-8000-000000000007", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1",
contract: { revision: "1", objective: "Deliver the requested work", criteria: [{ id: "output", requirement: "Deliver the requested work" }] } },
runtimeContext: nativeRuntimeContextFixture(),
});
expect(input).toMatchObject({ task: { workMode }, executionMode: workMode === "planning" ? "plan" : "default", planningContext });
expect(buildNativeModelEnvelope(input)).toMatchObject({ task: { workMode }, executionMode: workMode === "planning" ? "plan" : "default", planningContext });
});
});
describe("native execution input external-chat framing", () => {
it.each([false, true])(
"projects the authoritative selected answer into an attested native chat prompt (resumed: %s)",
(resumedSession) => {
const interactionId = "80000000-0000-4000-8000-000000000008";
const sourceRunId = "90000000-0000-4000-8000-000000000009";
const wakePayload = {
reason: "issue_commented",
externalChatProvider: "telegram",
externalChatExecutionBound: true,
interactionId,
sourceRunId,
interactionKind: "ask_user_questions",
interactionStatus: "answered",
externalInteractionContinuation: true,
issue: {
id: "20000000-0000-4000-8000-000000000002",
workMode: "standard",
status: "in_review",
},
externalChatQuestionResponse: {
schema: "paperclip.external_chat_question_response.v1",
interactionId,
sourceRunId,
responseDeliveryId: "10000000-0000-4000-8000-000000000011",
sourceCommentId: "10000000-0000-4000-8000-000000000012",
endpointId: "10000000-0000-4000-8000-000000000013",
conversationId: "10000000-0000-4000-8000-000000000014",
bindingSha256: "a".repeat(64),
},
commentIds: ["10000000-0000-4000-8000-000000000012"],
latestCommentId: "10000000-0000-4000-8000-000000000012",
comments: [
{
id: "10000000-0000-4000-8000-000000000012",
body: "Ask for a color, then tell me the selected color.",
},
],
commentWindow: { requestedCount: 1, includedCount: 1, missingCount: 0 },
fallbackFetchNeeded: false,
};
const args: Parameters<typeof buildNativeExecutionInput>[0] = {
companyId: "10000000-0000-4000-8000-000000000001",
runId: "50000000-0000-4000-8000-000000000005",
agentId: "30000000-0000-4000-8000-000000000003",
issue: {
id: "20000000-0000-4000-8000-000000000002",
identifier: "CHAT-5",
title: "Old exact-output request",
description: null,
workMode: "standard",
},
taskPrompt:
"Continue the user's original request with their selected answer.",
initialCommunicationGuidance: "Initial Slack communication preferences.",
wakePayload,
resumedSession,
workspace: {
id: "50000000-0000-4000-8000-000000000005",
cwd: "/workspace",
repoUrl: null,
repoRef: null,
branchName: null,
},
normalizedSessionId: "60000000-0000-4000-8000-000000000006",
provider: "codex",
completionContract: {
id: "70000000-0000-4000-8000-000000000007",
sha256: `sha256:${"a".repeat(64)}`,
schemaVersion: "paperclip.run-result.v1",
contract: {
revision: "1",
objective: "Answer the user's selected choice",
criteria: [
{ id: "answer", requirement: "Return the actual color." },
],
},
},
runtimeContext: nativeRuntimeContextFixture(),
interactionResponses: [
{
interactionId,
kind: "ask_user_questions",
response: {
status: "answered",
result: {
version: 1,
answers: [{ questionId: "color", optionIds: ["amber"] }],
summaryMarkdown:
"Resolved questions and answers:\n- Choose a color: Amber",
},
},
},
],
};
const input = buildNativeExecutionInput(args);
expect(input.initialCommunicationGuidance).toBe("Initial Slack communication preferences.");
// The runtime adds this only after deciding whether provider recovery succeeded.
expect(input.task.prompt).not.toContain("Initial Slack communication preferences.");
expect(input.task.title).toBe("External chat follow-up");
expect(input.task.prompt).toContain("Amber");
expect(input.task.prompt).not.toContain("## Questions that need a user response");
expect(input.task.prompt).toContain(
"semantic completion summary is the user-visible final answer",
);
expect(input.task.prompt).not.toContain(
"including marking the task done",
);
expect(input.task.prompt.indexOf("Choose a color: Amber")).toBeLessThan(
input.task.prompt.indexOf(
"Ask for a color, then tell me the selected color.",
),
);
expect(wakePayload).not.toHaveProperty("questionResponse");
const mixedModalSummary = formatDurableQuestionResponseSummary({
id: interactionId,
kind: "ask_user_questions",
status: "answered",
sourceRunId,
payload: {
version: 1,
questions: [
{
id: "environment",
prompt: "Choose an environment",
selectionMode: "single",
options: [
{ id: "maple", label: "Maple" },
{ id: "cedar", label: "Cedar" },
],
},
{
id: "label",
prompt: "Enter the verification label",
selectionMode: "single",
options: [
{
id: "custom",
label: "Custom label",
freeText: true,
},
],
},
],
},
result: {
version: 1,
answers: [
{ questionId: "environment", optionIds: ["maple"] },
{
questionId: "label",
optionIds: [],
otherText: "amber compass 93",
},
],
summaryMarkdown: null,
},
} as unknown as AskUserQuestionsInteraction);
const mixedModal = buildNativeExecutionInput({
...args,
wakePayload: {
...wakePayload,
comments: [
{
...wakePayload.comments[0],
body: "Ask a NEW environment and verification-label question.",
},
],
},
interactionResponses: [
{
interactionId,
kind: "ask_user_questions",
response: {
status: "answered",
result: {
version: 1,
answers: [
{ questionId: "environment", optionIds: ["maple"] },
{
questionId: "label",
optionIds: [],
otherText: "amber compass 93",
},
],
summaryMarkdown: mixedModalSummary,
},
},
},
],
});
expect(mixedModalSummary).toContain("Maple");
expect(mixedModalSummary).toContain("amber compass 93");
expect(mixedModal.task.prompt.indexOf("Maple")).toBeLessThan(
mixedModal.task.prompt.indexOf("Ask a NEW environment"),
);
expect(mixedModal.task.prompt.indexOf("amber compass 93")).toBeLessThan(
mixedModal.task.prompt.indexOf("Ask a NEW environment"),
);
expect(mixedModal.task.prompt).toContain(
"only the answered questions listed above are resolved",
);
const unbound = buildNativeExecutionInput({
...args,
interactionResponses: [
{
...args.interactionResponses![0]!,
interactionId: "10000000-0000-4000-8000-000000000019",
},
],
});
expect(unbound.task.title).toBe("Old exact-output request");
expect(unbound.task.prompt).not.toContain(
"Native external-chat questions",
);
const earlierInteractionId = "10000000-0000-4000-8000-000000000020";
const sequential = buildNativeExecutionInput({
...args,
interactionResponses: [
{
interactionId: earlierInteractionId,
kind: "ask_user_questions",
response: {
status: "answered",
result: {
version: 1,
answers: [{ questionId: "shape", optionIds: ["circle"] }],
summaryMarkdown: "Choose a shape: Circle",
},
},
},
...args.interactionResponses!,
],
});
expect(sequential.task.title).toBe("External chat follow-up");
expect(sequential.task.prompt).toContain("Circle");
expect(sequential.task.prompt).toContain("Amber");
expect(sequential.task.prompt).not.toContain("## Questions that need a user response");
expect(
sequential.task.prompt.indexOf("Choose a shape: Circle"),
).toBeLessThan(sequential.task.prompt.indexOf("Choose a color: Amber"));
expect(
sequential.interactionResponses.map(
(response) => response.interactionId,
),
).toEqual([earlierInteractionId, interactionId]);
expect(wakePayload).not.toHaveProperty("questionResponse");
},
);
it.each([false, true])(
"uses neutral framing and real question tools for authenticated overflow chat (resumed: %s)",
(resumedSession) => {
const staleRootTitle = "Reply with exactly STALE-OVERFLOW-MARKER";
const input = buildNativeExecutionInput({
companyId: "10000000-0000-4000-8000-000000000001",
runId: "50000000-0000-4000-8000-000000000005",
issue: {
id: "20000000-0000-4000-8000-000000000002",
identifier: "CHAT-5",
title: staleRootTitle,
description: "Started from Discord.",
workMode: "standard",
},
taskPrompt: `Paperclip task context:\n- Title: ${JSON.stringify(staleRootTitle)}`,
resumedSession,
wakePayload: {
reason: "External chat message received",
externalChatProvider: "discord",
checkedOutByHarness: true,
issue: {
id: "20000000-0000-4000-8000-000000000002",
identifier: "CHAT-5",
title: staleRootTitle,
description: "Started from Discord.",
descriptionTruncated: false,
status: "in_progress",
workMode: "standard",
},
commentWindow: {
requestedCount: 2,
includedCount: 1,
missingCount: 1,
},
commentIds: ["comment-overflow-1", "comment-overflow-2"],
latestCommentId: "comment-overflow-2",
comments: [
{
id: "comment-overflow-2",
issueId: "20000000-0000-4000-8000-000000000002",
body: "Answer both queued messages.",
bodyTruncated: false,
authorType: "user",
},
],
fallbackFetchNeeded: true,
},
agentId: "30000000-0000-4000-8000-000000000003",
workspace: {
id: "50000000-0000-4000-8000-000000000005",
cwd: "/workspace",
repoUrl: null,
repoRef: null,
branchName: null,
},
normalizedSessionId: "60000000-0000-4000-8000-000000000006",
provider: "codex",
completionContract: {
id: "70000000-0000-4000-8000-000000000007",
sha256: `sha256:${"a".repeat(64)}`,
schemaVersion: "paperclip.run-result.v1",
contract: {
revision: "1",
objective: "Respond to all pending comments in order",
criteria: [
{
id: "objective",
requirement: "Read every current wake comment.",
},
],
},
},
runtimeContext: nativeRuntimeContextFixture(),
});
expect(input.task.title).toBe("External chat follow-up");
expect(input.task.description).toBeNull();
expect(input.task.prompt).toContain("read_current_wake_comments");
expect(input.task.prompt).toContain(staleRootTitle);
},
);
it.each([false, true])(
"keeps GitHub's task-only files and service-owned recovery navigation in the closed native input (resumed: %s)",
(resumedSession) => {
const args: Parameters<typeof buildNativeExecutionInput>[0] = {
companyId: "10000000-0000-4000-8000-000000000001",
runId: "50000000-0000-4000-8000-000000000005",
issue: {
id: "20000000-0000-4000-8000-000000000002",
identifier: "CHAT-5",
title: "Send a file",
description: null,
workMode: "standard",
},
taskPrompt: "Answer the current line review.",
wakePayload: {
reason: "External chat message received",
externalChatProvider: "github",
checkedOutByHarness: true,
issue: {
id: "20000000-0000-4000-8000-000000000002",
workMode: "standard",
},
comments: [
{
id: "review-comment",
body: "Make a text file and attach it here.",
},
],
commentIds: ["review-comment"],
latestCommentId: "review-comment",
commentWindow: {
requestedCount: 1,
includedCount: 1,
missingCount: 0,
},
fallbackFetchNeeded: false,
},
resumedSession,
agentId: "30000000-0000-4000-8000-000000000003",
workspace: {
id: "50000000-0000-4000-8000-000000000005",
cwd: "/workspace",
repoUrl: null,
repoRef: null,
branchName: null,
},
normalizedSessionId: "60000000-0000-4000-8000-000000000006",
provider: "codex",
completionContract: {
id: "70000000-0000-4000-8000-000000000007",
sha256: `sha256:${"a".repeat(64)}`,
schemaVersion: "paperclip.run-result.v1",
contract: {
revision: "1",
objective: "Prepare a file",
criteria: [
{ id: "objective", requirement: "Describe actual delivery." },
],
},
},
runtimeContext: nativeRuntimeContextFixture(),
};
const input = buildNativeExecutionInput(args);
expect(input.task.prompt).toContain(
"This GitHub App connection cannot upload file bytes into comments or review threads",
);
expect(input.task.prompt).toContain(
"do not say it is attached, displayed, downloadable, or available to open in this provider conversation",
);
expect(input.task.prompt).toContain(
"Preparation does not confirm provider delivery",
);
expect(input.task.prompt).toContain(
"Paperclip owns recovery navigation for unavailable GitHub attachments",
);
expect(input.task.prompt).toContain(
"after an accepted response, only when the current source remains authorized and a safe configured Board URL is available",
);
expect(input.task.prompt).toContain(
"A task URL missing from your prompt or tool results is not evidence that no task link can be provided",
);
expect(input.task.prompt).toContain(
"Do not invent a URL or promise that a link will appear",
);
expect(input.task.prompt).toContain(
"Briefly explain the unavailable input and ask the user to attach it directly to this Paperclip task or paste the needed text",
);
expect(input.task.prompt).toContain(
"Never infer the file's contents or substitute an older file",
);
const runtimeContext = nativeRuntimeContextFixture();
runtimeContext.skills = ["configured", "provider-mentioned"].map((name) => ({
key: `company/test/${name}`,
runtimeName: name,
versionId: null,
bundle: { ...runtimeContext.instructions.bundle },
}));
runtimeContext.aggregateDigest = canonicalNativeRuntimeContextDigest(runtimeContext);
const skillArgs = {
...args,
issue: { ...args.issue, description: "Stale provider message: /provider-mentioned" },
taskPrompt: `${args.taskPrompt}\nGitHub message: /provider-mentioned`,
runtimeContext,
githubInstructionSkillKeys: ["company/test/configured", "company/other/unknown"],
};
const skillInput = buildNativeExecutionInput(skillArgs);
expect(skillInput.task.description).toBe("Configured GitHub instruction skills:\n/configured");
expect(buildNativeModelEnvelope(skillInput)).toMatchObject({ requestedSkills: ["configured"] });
expect(buildNativeModelEnvelope(buildNativeExecutionInput({
...skillArgs, githubInstructionSkillKeys: [],
}))).toMatchObject({ requestedSkills: [] });
const wake = args.wakePayload as Record<string, unknown>;
for (const patch of [
{ externalChatProvider: "slack" },
{ externalChatProvider: "discord" },
{ externalChatProvider: "telegram" },
{ externalChatProvider: "microsoft-teams" },
{ externalChatProvider: null },
{ externalChatProvider: "GitHub" },
{ checkedOutByHarness: false },
]) {
const unrelated = buildNativeExecutionInput({
...args,
wakePayload: { ...wake, ...patch },
});
expect(unrelated.task.prompt).not.toContain(
"Paperclip owns recovery navigation for unavailable GitHub attachments",
);
if (["slack", "discord", "telegram", "microsoft-teams"].includes(patch.externalChatProvider ?? "")) {
const unrelatedSkills = buildNativeExecutionInput({
...skillArgs, wakePayload: { ...wake, ...patch },
});
expect(unrelatedSkills.task.description).toBeNull();
expect(buildNativeModelEnvelope(unrelatedSkills)).toMatchObject({ requestedSkills: [] });
}
}
},
);
it.each([
{ provider: "codex", resumedSession: false },
{ provider: "codex", resumedSession: true },
{ provider: "acpx", resumedSession: false },
{ provider: "acpx", resumedSession: true },
{ provider: "opencode", resumedSession: false },
{ provider: "opencode", resumedSession: true },
] as const)("keeps question documentation in the tool on $provider (resumed: $resumedSession)", ({ provider, resumedSession }) => {
const input = buildNativeExecutionInput({
companyId: "10000000-0000-4000-8000-000000000001",
runId: "50000000-0000-4000-8000-000000000005",
agentId: "30000000-0000-4000-8000-000000000003",
issue: { id: "20000000-0000-4000-8000-000000000002", identifier: "QA-1", title: "Welcome", description: null, workMode: "standard" },
taskPrompt: "Ask whether the welcome should sound warm or formal before writing it.",
workspace: { id: "40000000-0000-4000-8000-000000000004", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: resumedSession ? "60000000-0000-4000-8000-000000000006" : null,
provider, resumedSession,
acpxAgent: "claude",
model: provider === "acpx" ? "claude-sonnet-5" : provider === "opencode" ? "openai/gpt-5.5" : "gpt-5.6-sol",
completionContract: {
id: "70000000-0000-4000-8000-000000000007", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1",
contract: { revision: "1", objective: "Write a welcome after the user's answer", criteria: [{ id: "objective", requirement: "Use the selected tone" }] },
},
runtimeContext: nativeRuntimeContextFixture(),
});
expect(input.provider).toMatchObject(provider === "acpx"
? { kind: "acpx", permissionMode: "approve-all" }
: provider === "opencode" ? { kind: "opencode", permissionMode: "allow" }
: { kind: "codex", approvalPolicy: "never" });
expect(input.task.prompt).not.toContain("## Questions that need a user response");
expect(input.task.prompt).toContain("Use Paperclip's request_human_input for durable task questions.");
expect(input.task.prompt).not.toContain("payload.questionSet");
});
});
describe("follow-up context size", () => {
it("keeps old messages out of resume deltas while retaining scoped human answers", () => {
const message = (id: string, body: string) => ({
id, body, authorType: "user", authorId: "board", createdAt: "2026-09-17T00:00:00Z",
updatedAt: "2026-09-17T00:00:00Z", deleted: false, sourceTrust: null,
});
const oldBody = "PREVIOUS_TASK_TEXT ".repeat(1000);
const newBody = "Actually, save the plan first.";
const answerText = "No budget. Wait for my approval.";
const continuation: ExecutionContinuationEnvelope = {
version: 1, companyId: "company", issueId: "issue", objective: "Welcome",
trigger: { reason: "issue_commented", interactionId: "answer-id", sourceRunId: null },
originCommentIds: ["new"], messages: [message("old", oldBody), message("new", newBody)],
resumeDelta: { baseRunId: "previous-run", messages: [message("new", newBody)] },
humanResponses: [{ id: "answer-id", kind: "ask_user_questions", status: "answered",
resolvedByUserId: "board", resolvedAt: "2026-09-17T00:01:00Z",
result: { answers: [{ questionId: "scope", optionIds: [], otherText: answerText }] } }],
interactionOutcomes: [], completedWork: null, unresolvedInteractionIds: [],
coverage: { kind: "full_task_history", throughCommentId: "new", summaryThroughCommentId: null },
};
const wake = { executionContinuation: continuation };
const fresh = renderPaperclipWakePrompt(wake);
const resumed = renderPaperclipWakePrompt(wake, { resumedSession: true });
const contract = buildNativeCompletionContract({ title: "Welcome", description: oldBody }, {
immediateRequest: newBody, humanResponseId: "answer-id",
});
expect(fresh).toContain(oldBody);
expect(resumed).not.toContain("PREVIOUS_TASK_TEXT");
expect(resumed.split(newBody)).toHaveLength(2);
expect(resumed.split(answerText)).toHaveLength(2);
expect(resumed).toContain("earlier history remains in this session");
expect(JSON.stringify(contract)).not.toContain(oldBody);
expect(JSON.stringify(contract)).not.toContain(answerText);
expect(resumed.length + JSON.stringify(contract).length).toBeLessThan(fresh.length);
});
});
describe("native completion references", () => {
const source = nativeCompletionSource("description", "task", "Repeat. Repeat.");
const args: Parameters<typeof buildNativeExecutionInput>[0] = {
companyId: "company", runId: "run", agentId: "agent",
issue: { id: "task", identifier: "PAP-1", title: "Brief", description: "Repeat. Repeat.", workMode: "standard" },
taskPrompt: "Issue description:\nRepeat. Repeat.",
workspace: { id: "workspace", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: null,
runtimeContext: nativeRuntimeContextFixture(),
completionContract: {
id: "contract", sha256: "a".repeat(64), schemaVersion: "paperclip.completion-contract.v1",
contract: { revision: "1", objective: "Brief", criteria: [{ id: "objective", requirement: "Repeat. Repeat." }] },
sources: [{ id: "objective", source }],
},
};
it("binds only source identities and revisions attested by the task renderer", () => {
const input = buildNativeExecutionInput({ ...args, turnContext: {
version: 1,
assignment: { owner: "task_markdown", description: { id: source.id, revision: source.revision } },
events: { owner: "wake_prompt", comments: [] },
} });
expect(input.completionSources).toMatchObject({ contractRevision: "1", criteria: [{ id: "objective", source }] });
expect(input.completionContract.contract).toEqual(args.completionContract.contract);
expect(input.task.description).toBe("Repeat. Repeat.");
});
it.each([
undefined,
{ version: 1, assignment: { owner: "task_markdown", description: { id: "another-task", revision: source.revision } } },
{ version: 1, assignment: { owner: "task_markdown", description: { id: source.id, revision: "stale" } } },
])("keeps the full requirement when provenance is absent or stale", (turnContext) => {
const input = buildNativeExecutionInput({ ...args, turnContext });
expect(input.completionSources).toBeUndefined();
expect(input.completionContract.contract).toEqual(args.completionContract.contract);
});
});
describe("Cursor mode native execution projection", () => {
function fixture(acpxSessionMode?: "agent" | "plan" | "ask") {
return {
companyId: "company-1", runId: "run-1", agentId: "agent-1",
issue: { id: "issue-1", identifier: "MODE-1", title: "Review a plan", description: null, workMode: "standard" },
taskPrompt: "Review the project.",
workspace: { id: "workspace-1", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: null, provider: "acpx" as const, acpxAgent: "cursor" as const,
model: "exact-cursor-model", acpxSessionMode, acpxPermissionMode: "deny-all" as const,
completionContract: { id: "contract-1", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1", contract: { revision: "1", objective: "Review", criteria: [{ id: "output", requirement: "Review" }] } },
runtimeContext: nativeRuntimeContextFixture(),
};
}
it.each([undefined, "agent", "plan", "ask"] as const)("preserves mode %s independently of permissions and task planning", mode => {
const result = buildNativeExecutionInput(fixture(mode));
expect(result.provider).toMatchObject({ kind: "acpx", agent: "cursor", mode: mode ?? "agent", permissionMode: "deny-all" });
expect(result.executionMode).toBe("default");
expect(result.task.workMode).toBe("standard");
});
it("rejects a Cursor mode attached to another harness", () => {
expect(() => buildNativeExecutionInput({ ...fixture("plan"), acpxAgent: "copilot" })).toThrow("only for Cursor");
});
});
describe("Pi thinking native execution projection", () => {
function fixture(piThinkingLevel?: "off" | "low" | "high" | "max") {
return {
companyId: "company-1", runId: "run-1", agentId: "agent-1",
issue: { id: "issue-1", identifier: "MODE-1", title: "Review a plan", description: null, workMode: "standard" },
taskPrompt: "Review the project.",
workspace: { id: "workspace-1", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: null, provider: "acpx" as const, acpxAgent: "pi" as const,
model: "openrouter/deepseek/deepseek-v4-flash-0731", piThinkingLevel, acpxPermissionMode: "deny-all" as const,
completionContract: { id: "contract-1", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1", contract: { revision: "1", objective: "Review", criteria: [{ id: "output", requirement: "Review" }] } },
runtimeContext: nativeRuntimeContextFixture(),
};
}
it.each([undefined, "off", "low", "high", "max"] as const)("preserves mode %s independently of permissions and task planning", mode => {
const result = buildNativeExecutionInput(fixture(mode));
expect(result.provider).toMatchObject({ kind: "acpx", agent: "pi", piThinkingLevel: mode ?? "low", permissionMode: "deny-all" });
expect(result.executionMode).toBe("default");
expect(result.task.workMode).toBe("standard");
});
it("rejects a Pi thinking level attached to another harness", () => {
expect(() => buildNativeExecutionInput({ ...fixture("low"), acpxAgent: "copilot" })).toThrow("only for Pi");
});
});
describe("Claude effort and master home-mode compatibility", () => {
it.each([
["isolated", undefined, "v5"], ["preconfigured", undefined, "v7"],
["isolated", "high", "v9"], ["preconfigured", "high", "v9"],
] as const)("retains %s home mode with effort %s in %s", (homeMode, claudeEffort, version) => {
const value = buildNativeExecutionInput({
companyId: "company", runId: "run", agentId: "agent",
issue: { id: "issue", identifier: "CLA-1", title: "Useful output", description: null, workMode: "standard" },
taskPrompt: "Create the requested file.",
workspace: { id: "workspace", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: null, provider: "acpx", acpxAgent: "claude", model: "claude-opus-5-5",
acpxPermissionMode: "approve-all", homeMode, claudeEffort,
completionContract: { id: "contract", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1",
contract: { revision: "1", objective: "Create a file", criteria: [{ id: "output", requirement: "Create the file" }] } },
runtimeContext: nativeRuntimeContextFixture(),
});
expect(value.schema).toBe(`paperclip.native-execution-input.${version}`);
if (version !== "v5") expect(value).toHaveProperty("homeMode", homeMode);
if (claudeEffort) expect(value.provider).toHaveProperty("claudeEffort", claudeEffort);
expect(JSON.stringify(buildNativeModelEnvelope(value))).not.toContain("claudeEffort");
});
it.each([
["isolated", undefined, undefined, "v5"], ["isolated", "high", true, "v10"], ["isolated", undefined, false, "v10"],
] as const)("retains %s home mode with effort %s and search policy %s in %s", (homeMode, grokEffort, grokDisableWebSearch, version) => {
const value = buildNativeExecutionInput({
companyId: "company", runId: "run", agentId: "agent",
issue: { id: "issue", identifier: "CLA-1", title: "Useful output", description: null, workMode: "standard" },
taskPrompt: "Create the requested file.",
workspace: { id: "workspace", cwd: "/workspace", repoUrl: null, repoRef: null, branchName: null },
normalizedSessionId: null, provider: "acpx", acpxAgent: "grok", model: "grok-4.7",
acpxPermissionMode: "approve-all", homeMode, grokEffort, grokDisableWebSearch,
completionContract: { id: "contract", sha256: `sha256:${"a".repeat(64)}`, schemaVersion: "paperclip.run-result.v1",
contract: { revision: "1", objective: "Create a file", criteria: [{ id: "output", requirement: "Create the file" }] } },
runtimeContext: nativeRuntimeContextFixture(),
});
expect(value.schema).toBe(`paperclip.native-execution-input.${version}`);
if (version !== "v5") expect(value).toHaveProperty("homeMode", homeMode);
if (grokEffort) expect(value.provider).toHaveProperty("grokEffort", grokEffort);
if (grokDisableWebSearch !== undefined) expect(value.provider).toHaveProperty("grokDisableWebSearch", grokDisableWebSearch);
expect(JSON.stringify(buildNativeModelEnvelope(value))).not.toContain("grokEffort");
});
});