Files
PaperClipAI/server/src/services/native-runtime/native-execution-input.test.ts
T
DottaandPaperclip ed2c22ea8c feat(connections): simplify dedicated GitHub App setup (#15416)
## Thinking Path

> - Paperclip manages agent work and the tools each agent can use.
> - GitHub bots need their own App identity and restricted repository
access.
> - Manual App configuration and repeated setup gates make that
connection hard to finish.
> - GitHub can create an App from a manifest, but people must approve
creation and repository access.
> - Each Paperclip stack should own configuration, credentials,
signature verification, and task admission.
> - This change uses Cloud as an encrypted callback and event gateway,
then completes setup in the stack.
> - GitHub review bots have their own experimental setting. Chat
connector opt-in does not control them.

## Linked Issues or Issue Description

**What existing behavior does this improve?**

Dedicated GitHub App setup, bot settings, and task-scoped GitHub
replies.

**Current behavior**

Users must configure an App, copy credentials, repeat repository
selection, and complete manual verification gates. Review settings are
hard to scan. Mentions in descriptions can be missed, and automatic
completion text can produce an extra GitHub comment.

**Proposed behavior**

Choose an agent and connect GitHub under a personal account or
organization. GitHub asks for creation and installation consent.
Paperclip resumes the same draft, stores secrets locally, imports
access, verifies delivery, and opens Settings. Each accepted request has
one editable App-owned comment for progress and results. Review
assessments produce deterministic checks for the reviewed commit.

**Breaking changes**

GitHub bots require their own default-off experimental opt-in. The
setup-method and delegated-agent screens are removed. Per-person
automatic-run flags remain readable but are replaced by author filters.
Existing connections, direct webhooks, saved restrictions, and manual
existing-App recovery remain supported.

Companion gateway:
https://github.com/paperclipai/paperclip-cloud/pull/688 (merged). The
roadmap and related PRs were checked; no duplicate dedicated-App wizard
was found.

## What Changed

- Add an independent **GitHub review bots** setting across the catalog,
routes, identity admission, and task controls. Existing bots continue
running when the UI setting is off.
- Replace setup with Choose agent and Connect GitHub. Support personal
and organization owners, inline low-trust conversion, saved drafts,
known organization suggestions, automatic completion, and same-App
recovery.
- Keep manifests, OAuth PKCE, credential exchange, vault storage,
installation verification, and original webhook-signature validation in
the stack. Use the Cloud sealed gateway for public callbacks and
outbound local delivery.
- Add resumable owner metadata in migration 0323. Retry a failed
registration renewal through the same durable replacement rather than
creating another App route.
- Support authorized mentions in issue and PR bodies, comments, inline
comments, and review summaries. Preserve attachments, edited-source
identity, duplicate protection, and lifecycle invalidation. Filter
requests explicitly addressed to another connected bot.
- Give agents task-scoped review, comment, and update tools. Update one
working comment through progress and final output. Close coalesced
requests and recover delayed acknowledgements, including deleted earlier
working comments. Preserve automatic replies for legacy connections
without saved review configuration. Preserve partial publication
evidence and quarantine uncertain automatic fallbacks without blocking
Board messages or questions.
- Reorganize Settings and Access with rich slash-skill instructions,
numeric passing scores, clear automation controls, formal-review
tooltips, member and contributor sections, and verified App branding
links. Preserve invalid score drafts and automation choices across tabs.
- Paginate repositories in 20-row batches with search and a true
connection-wide toggle. Batch verification at GitHub's 500-ID token
limit. Keep saved repository overrides while hiding their editor.
- Give each review a detail URL that remains usable beyond the newest
100 records. Synchronize the manager OpenAPI contracts and add recovery,
authorization, UI, and browser regressions.
- Reconcile the current master branch and retain its agent avatar,
feature catalog, and extracted heartbeat preparation code. Preserve a
saved test-drive port and recover from an occupied high port.

## Verification

- Focused UI, independent experimental-setting, and CLI tests: 199
passed.
- `pnpm -r typecheck`, `pnpm build`, and `pnpm check:token-gates`
passed. The broad local Vitest attempt was interrupted after resource
timeouts and stale expectations; the affected regressions passed focused
reruns. The latest-head full CI matrix passed, including all browser
shards, server/chat suites, builds, typechecking, canary packaging, and
Docker context integrity. A Docker Hub 429 required a CI retry; it
passed without changing the code.
- Final review repairs: 127 attachment/event tests and server typecheck
passed. All 13 final integration regressions passed under the normal CI
timeout, covering legacy reply compatibility, deleted coalesced
comments, inline-only review completion, progress edits, and native
final recovery. Restart-safe description/review attachments passed the
attachment suite.
- Final regressions: four reply/lifecycle tests, both native GitHub wait
tests, 171 feature-gate/reply-contract tests, the routed review preview,
and five scheduler/reply regressions passed. The final fixture repair
also passed all six setup-continuation cases and all three complete
chat-test shards in CI, covering terminal receipts and retries under the
normal CI timeout. One loaded-host receipt run exceeded its local
timeout; the exact case passed in an isolated rerun and the complete CI
shard.
- GitHub integration tests cover personal and organization setup, retry
recovery, edited mentions, attachment provenance, coalesced requests,
delayed acknowledgements, partial review writes, old review URLs, and
company boundaries.
- Browser qualification: both GitHub journeys, all five provider
setup/management journeys, and the GitHub uncertain-send recovery
journey passed. GitHub setup, reconnect, and task replies run with chat
disabled; chat enabled alone cannot expose GitHub bots. The disposable
qualification database was removed after testing.
- Earlier live qualification verified App-owned issue replies, native
slash-skill invocation, progress comment edits, and a 5/5 PR review with
a passing current-head check in the dedicated permissions-smoke
repository. These live checks did not use personal credentials as bot
execution authority.

## Risks

- Deploy the merged Cloud gateway protocol before the stack update. Each
callback and encrypted event must retain the original instance and
tenant binding.
- Migration 0323 uses idempotent column additions for test installations
that already applied the earlier draft migration number.
- A verified connection does not prove runtime isolation or a completed
review. Runtime checks remain separate.
- Required merge checks must be configured in GitHub. A passing numeric
score does not formally approve a PR; approval and request-changes tools
remain opt-in.
- Existing-App credentials cannot silently renew an uncertain manifest
exchange. Recovery preserves the existing App, draft, connection, and
agent.
- Repository changes save immediately. Global toggles affect all
currently available repositories, including unloaded rows, without
granting new installation access.
- A failed or uncertain tool write suppresses automatic fallback text;
the governed outbox retains its evidence. Deleted or replaced response
comments are not recreated through a personal credential fallback.
- GitHub logo upload remains an optional human action in GitHub App
settings. Runtime provisioning, delegated setup, screenshot publication,
and production push delivery remain deferred.

## Model Used

OpenAI Codex, based on GPT-6, with tool use and code execution. The
exact runtime model identifier and context size are not exposed in this
session.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [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 either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub references)
- [x] My branch name describes the change and contains no internal
Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass (focused suites; complete
test matrix is checked in CI)
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-10-09 17:01:20 -05:00

667 lines
29 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"])("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",
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" });
expect(input.executionMode).toBe(workMode === "planning" ? "plan" : "default");
expect(input.task.title).toBe(text);
}
});
});
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");
});
});