mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-11 05:31:46 +02:00
da887ea3e9
## Thinking Path > - Paperclip manages AI agents that work on assigned tasks. > - The task composer lets a person choose an assignee, model, and effort for the next run. > - A Paperclip Runner agent can use Codex as its provider. > - The composer hid Codex effort for that agent because it checked only the older Codex adapter. > - The native Runner input also did not carry an effort choice to Codex. > - This pull request carries the chosen effort from the composer to each Codex turn. > - People can now select a supported effort and get the effort they selected. ## Linked Issues or Issue Description Refs #14322 **What happened?** The composer showed a model but no effort slider when the assignee used Paperclip Runner with the Codex provider. A task-level model override also did not reach the native Runner input. **Expected behavior** The composer shows effort choices for a known Codex model. The next native Codex turn uses the selected model and effort. **Steps to reproduce** 1. Open a task composer. 2. Select an agent that uses Paperclip Runner with the Codex provider. 3. Select a known Codex model such as `gpt-6-astra`. 4. Open the assignee and model picker. The effort slider is missing before this change. ## What Changed - Show known Codex effort levels for Paperclip Runner Codex assignees. - Save the task effort override in the native run input and send it to Codex on each turn. - Apply the task's merged model and effort overrides when the native run starts. - Apply a task model override for OpenCode Runner without changing the agent's provider. - Add Runner effort tests and desktop and mobile Storybook cases. ## Verification - `pnpm -r typecheck` passed. - `pnpm build` passed. - `pnpm build-storybook` passed. - `pnpm check:token-gates` passed. - Focused UI, server, Runner contract, and Codex driver tests passed. - The full CI test matrix, build, typecheck, and canary dry run passed on the latest head. ## Risks - Native Runner inputs add an optional Codex effort field to the current v5 input. Older inputs keep their previous behavior. - A known model rejects an effort that its catalog does not support. Unknown models do not show a slider. > This fixes an existing composer bug. I checked `ROADMAP.md`; it does not describe this bug as planned work. ## Model Used OpenAI Codex, GPT-6. The exact deployment ID and context window are not exposed in this session. The model used reasoning, code execution, and repository tools. ## 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 `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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> Co-authored-by: OpenAI GPT-6 Astra <noreply@openai.com>
588 lines
25 KiB
TypeScript
588 lines
25 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";
|
|
|
|
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 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",
|
|
);
|
|
}
|
|
},
|
|
);
|
|
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);
|
|
});
|
|
});
|