mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-27 02:44:50 +01:00
## Thinking Path > - Paperclip is the open source control plane for teams of AI agents. > - Agent runs currently use direct adapters and their established finalization paths. > - The new runner package needs one production integration before it can execute a real provider through the server. > - That integration must not change direct adapters or expose unsupported providers. > - The rollout must also preserve native runs that were already recorded when the feature flag changes. > - This pull request adds a default-off, Codex-only native execution path and its authority boundary. > - The benefit is a recoverable production vertical slice with explicit compatibility guards. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting server orchestration and adapter selection. **Problem or motivation** The runner package exists, but the server cannot yet start and recover a governed Codex run through it. A careless integration could also route existing direct adapters into the native runtime or lose cancellation and finalization state. **Proposed solution** Add a hidden `paperclip_runner` adapter for Codex. Keep it behind the default-off instance flag. Bind native execution, resume, cancellation, semantic tool authority, and finalization to the recorded company, issue, run, and coordinator identities. Leave every direct adapter on its existing path. **Alternatives considered** A multi-provider launch was rejected because only Codex has the complete production bridge in this series. Replacing direct adapter execution was rejected because the runner remains experimental. **Roadmap alignment** This work supports governed tool access, action attribution, and self-healing runs. It keeps the integration narrow and default-off. ## What Changed - Add the Codex-only native session executor and persisted resumption path. - Add run-scoped semantic tool projection, authorization, receipts, and idempotency. - Add audited native cancellation with durable issue and coordinator binding. - Add result fencing so a recorded result cannot reacquire the provider and run twice. - Reject fresh runner starts when the rollout flag is off while preserving recorded native recovery. - Keep direct adapters outside native status, cancellation, record creation, and finalization. - Add focused conformance, recovery, cancellation, status, portability, and compatibility coverage. ## Verification - GitHub Actions is the authoritative test environment for this large stack. - The PR policy and lightweight stack checks run while this is a middle PR. - The full required suite runs when this PR becomes the lowest unmerged or top PR. - Greptile will review this exact delta after the branch is pushed. ## Risks - The main risk is routing a legacy adapter into native execution. Runtime selection and heartbeat tests cover that boundary. - The next risk is stale or cross-company cancellation. Durable binding checks and transactional audit persistence cover it. - The adapter remains hidden and default-off. Only Codex is admitted. - There are no database migration, lockfile, or GitHub workflow changes in this PR. ## Stack 1. [Runner package, SDK, and developer tools](https://github.com/paperclipai/paperclip/pull/12608) 2. This PR: Codex production server integration 3. [Provider-neutral task-thread UI](https://github.com/paperclipai/paperclip/pull/12617) ## Model Used OpenAI Codex with GPT-5, extended reasoning, repository tools, and parallel review agents. ## 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 - [ ] 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 - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge
381 lines
12 KiB
TypeScript
381 lines
12 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import {
|
|
buildPaperclipTaskMarkdown,
|
|
mergeCoalescedContextSnapshot,
|
|
summarizeHeartbeatRunContextSnapshot,
|
|
summarizeHeartbeatRunListResultJson,
|
|
} from "../services/heartbeat.js";
|
|
|
|
describe("buildPaperclipTaskMarkdown", () => {
|
|
it("adds planning directives for assignment and comment task context", () => {
|
|
const assignment = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-1",
|
|
identifier: "PAP-3404",
|
|
title: "Plan first",
|
|
workMode: "planning",
|
|
description: null,
|
|
},
|
|
});
|
|
|
|
expect(assignment).toContain("- Work mode: \"planning\"");
|
|
expect(assignment).toContain("Make the plan only. Do not write code or perform implementation work.");
|
|
|
|
const commentWake = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-1",
|
|
identifier: "PAP-3404",
|
|
title: "Plan first",
|
|
workMode: "planning",
|
|
description: null,
|
|
},
|
|
wakeComment: {
|
|
id: "comment-1",
|
|
body: "Please revise the plan.",
|
|
},
|
|
});
|
|
|
|
expect(commentWake).toContain("Update the plan only. Do not write code or perform implementation work.");
|
|
|
|
const acceptedConfirmation = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-1",
|
|
identifier: "PAP-3404",
|
|
title: "Plan first",
|
|
workMode: "planning",
|
|
description: null,
|
|
},
|
|
interaction: {
|
|
kind: "request_confirmation",
|
|
status: "accepted",
|
|
},
|
|
});
|
|
|
|
expect(acceptedConfirmation).toContain(
|
|
"Implement the accepted plan on this issue when the work is small and cohesive.",
|
|
);
|
|
expect(acceptedConfirmation).not.toContain("Make the plan only.");
|
|
});
|
|
|
|
it("adds accepted-plan continuation guidance for standard-work issues when the wake is flagged as a plan continuation", () => {
|
|
const acceptedConfirmation = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-2",
|
|
identifier: "PAP-415",
|
|
title: "Implement the fix",
|
|
workMode: "standard",
|
|
description: null,
|
|
},
|
|
acceptedPlanContinuation: true,
|
|
});
|
|
|
|
expect(acceptedConfirmation).toContain("Accepted plan directive:");
|
|
expect(acceptedConfirmation).toContain(
|
|
"Implement the accepted plan on this issue when the work is small and cohesive.",
|
|
);
|
|
expect(acceptedConfirmation).not.toContain("- Work mode: \"planning\"");
|
|
});
|
|
|
|
it("adds answer-only guidance for ask-mode issues", () => {
|
|
const assignment = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-ask",
|
|
identifier: "PAP-416",
|
|
title: "Explain the tradeoff",
|
|
workMode: "ask",
|
|
description: null,
|
|
},
|
|
});
|
|
|
|
expect(assignment).toContain("- Work mode: \"ask\"");
|
|
expect(assignment).toContain("Ask mode directive:");
|
|
expect(assignment).toContain("Answer the question directly in the issue thread.");
|
|
expect(assignment).toContain("Do not write implementation code");
|
|
expect(assignment).toContain("do not produce an implementation plan");
|
|
});
|
|
|
|
it("adds dry-run containment guidance for skill-test issues", () => {
|
|
const assignment = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-skill-test",
|
|
identifier: "PAP-417",
|
|
title: "Test skill draft",
|
|
workMode: "skill_test",
|
|
description: null,
|
|
},
|
|
});
|
|
|
|
expect(assignment).toContain("- Work mode: \"skill_test\"");
|
|
expect(assignment).toContain("Skill test mode directive:");
|
|
expect(assignment).toContain("Make no durable changes outside this issue.");
|
|
expect(assignment).toContain("Write your final output as issue document `output`");
|
|
});
|
|
|
|
it("strips the description for the compact resume variant but keeps directives and the wake comment", () => {
|
|
const input = {
|
|
issue: {
|
|
id: "issue-1",
|
|
identifier: "PAP-3404",
|
|
title: "Ship the fix",
|
|
workMode: "standard",
|
|
description: "Full multi-paragraph brief that the session already received.",
|
|
},
|
|
wakeComment: {
|
|
id: "comment-1",
|
|
body: "Please also update the changelog.",
|
|
},
|
|
};
|
|
|
|
const full = buildPaperclipTaskMarkdown(input);
|
|
expect(full).toContain("Issue description:");
|
|
expect(full).toContain("Full multi-paragraph brief that the session already received.");
|
|
|
|
const compact = buildPaperclipTaskMarkdown({ ...input, includeDescription: false });
|
|
expect(compact).not.toContain("Issue description:");
|
|
expect(compact).not.toContain("Full multi-paragraph brief");
|
|
expect(compact).toContain("- Issue: \"PAP-3404\"");
|
|
expect(compact).toContain("Please also update the changelog.");
|
|
});
|
|
|
|
it("makes the latest wake comment the immediate follow-up request", () => {
|
|
const commentWake = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-follow-up",
|
|
identifier: "PAP-418",
|
|
title: "Original task",
|
|
workMode: "standard",
|
|
description: "Reply with the original answer.",
|
|
},
|
|
wakeComment: {
|
|
id: "comment-follow-up",
|
|
body: "Reply with the new answer instead.",
|
|
},
|
|
});
|
|
|
|
expect(commentWake).toContain("The latest wake comment is the immediate request for this run.");
|
|
expect(commentWake).toContain("Do not repeat an earlier requested output from the issue description");
|
|
expect(commentWake).toContain("Reply with the new answer instead.");
|
|
});
|
|
|
|
it("prefers ordinary comment planning guidance over stale accepted confirmation state", () => {
|
|
const commentWake = buildPaperclipTaskMarkdown({
|
|
issue: {
|
|
id: "issue-1",
|
|
identifier: "PAP-3404",
|
|
title: "Plan first",
|
|
workMode: "planning",
|
|
description: null,
|
|
},
|
|
wakeComment: {
|
|
id: "comment-1",
|
|
body: "Please revise the plan.",
|
|
},
|
|
interaction: {
|
|
kind: "request_confirmation",
|
|
status: "accepted",
|
|
},
|
|
});
|
|
|
|
expect(commentWake).toContain("Update the plan only. Do not write code or perform implementation work.");
|
|
expect(commentWake).not.toContain("Create child issues from the approved plan only");
|
|
});
|
|
});
|
|
|
|
describe("mergeCoalescedContextSnapshot", () => {
|
|
it("clears stale accepted-plan interaction state when merging a later ordinary comment wake", () => {
|
|
const merged = mergeCoalescedContextSnapshot(
|
|
{
|
|
issueId: "issue-1",
|
|
interactionId: "interaction-1",
|
|
interactionKind: "request_confirmation",
|
|
interactionStatus: "accepted",
|
|
continuationPolicy: "wake_assignee_on_accept",
|
|
checkboxSelection: {
|
|
prompt: "Delete selected files?",
|
|
selectedOptionIds: ["file-b"],
|
|
selectedOptions: [{ id: "file-b", label: "b.txt", description: "Generated build output" }],
|
|
},
|
|
wakeReason: "issue_commented",
|
|
},
|
|
{
|
|
issueId: "issue-1",
|
|
commentId: "comment-1",
|
|
wakeCommentId: "comment-1",
|
|
wakeReason: "issue_commented",
|
|
},
|
|
);
|
|
|
|
expect(merged.interactionId).toBeUndefined();
|
|
expect(merged.interactionKind).toBeUndefined();
|
|
expect(merged.interactionStatus).toBeUndefined();
|
|
expect(merged.continuationPolicy).toBeUndefined();
|
|
expect(merged.checkboxSelection).toBeUndefined();
|
|
expect(merged.commentId).toBe("comment-1");
|
|
expect(merged.wakeCommentId).toBe("comment-1");
|
|
});
|
|
|
|
it("preserves resolved interaction state for the interaction wake itself", () => {
|
|
const merged = mergeCoalescedContextSnapshot(
|
|
{
|
|
issueId: "issue-1",
|
|
},
|
|
{
|
|
issueId: "issue-1",
|
|
interactionId: "interaction-1",
|
|
interactionKind: "request_confirmation",
|
|
interactionStatus: "accepted",
|
|
continuationPolicy: "wake_assignee_on_accept",
|
|
checkboxSelection: {
|
|
prompt: "Delete selected files?",
|
|
selectedOptionIds: ["file-b"],
|
|
selectedOptions: [{ id: "file-b", label: "b.txt", description: "Generated build output" }],
|
|
},
|
|
wakeReason: "issue_commented",
|
|
},
|
|
);
|
|
|
|
expect(merged.interactionId).toBe("interaction-1");
|
|
expect(merged.interactionKind).toBe("request_confirmation");
|
|
expect(merged.interactionStatus).toBe("accepted");
|
|
expect(merged.continuationPolicy).toBe("wake_assignee_on_accept");
|
|
expect(merged.checkboxSelection).toEqual({
|
|
prompt: "Delete selected files?",
|
|
selectedOptionIds: ["file-b"],
|
|
selectedOptions: [{ id: "file-b", label: "b.txt", description: "Generated build output" }],
|
|
});
|
|
});
|
|
|
|
it("preserves a deferred interaction when a later comment joins its successor wake", () => {
|
|
const merged = mergeCoalescedContextSnapshot(
|
|
{
|
|
issueId: "issue-1",
|
|
interactionId: "interaction-1",
|
|
interactionKind: "request_confirmation",
|
|
interactionStatus: "accepted",
|
|
continuationPolicy: "wake_assignee_on_accept",
|
|
wakeReason: "issue_commented",
|
|
},
|
|
{
|
|
issueId: "issue-1",
|
|
commentId: "comment-1",
|
|
wakeCommentId: "comment-1",
|
|
wakeReason: "issue_commented",
|
|
},
|
|
{ preserveExistingInteractionContinuation: true },
|
|
);
|
|
|
|
expect(merged.interactionId).toBe("interaction-1");
|
|
expect(merged.interactionKind).toBe("request_confirmation");
|
|
expect(merged.interactionStatus).toBe("accepted");
|
|
expect(merged.continuationPolicy).toBe("wake_assignee_on_accept");
|
|
expect(merged.commentId).toBe("comment-1");
|
|
expect(merged.wakeCommentId).toBe("comment-1");
|
|
});
|
|
|
|
it("keeps a queued comment when an interaction joins its successor wake", () => {
|
|
const merged = mergeCoalescedContextSnapshot(
|
|
{
|
|
issueId: "issue-1",
|
|
commentId: "comment-1",
|
|
wakeCommentId: "comment-1",
|
|
wakeCommentIds: ["comment-1"],
|
|
wakeReason: "issue_commented",
|
|
},
|
|
{
|
|
issueId: "issue-1",
|
|
interactionId: "interaction-1",
|
|
interactionKind: "ask_user_questions",
|
|
interactionStatus: "answered",
|
|
continuationPolicy: "wake_assignee_on_accept",
|
|
wakeReason: "issue_commented",
|
|
},
|
|
{ preserveExistingInteractionContinuation: true },
|
|
);
|
|
|
|
expect(merged.interactionId).toBe("interaction-1");
|
|
expect(merged.interactionKind).toBe("ask_user_questions");
|
|
expect(merged.interactionStatus).toBe("answered");
|
|
expect(merged.commentId).toBe("comment-1");
|
|
expect(merged.wakeCommentId).toBe("comment-1");
|
|
expect(merged.wakeCommentIds).toEqual(["comment-1"]);
|
|
});
|
|
});
|
|
|
|
describe("summarizeHeartbeatRunContextSnapshot", () => {
|
|
it("keeps only the small retry/linking fields needed by the client", () => {
|
|
const summarized = summarizeHeartbeatRunContextSnapshot({
|
|
issueId: "issue-1",
|
|
taskId: "task-1",
|
|
taskKey: "PAP-1",
|
|
commentId: "comment-1",
|
|
wakeCommentId: "comment-2",
|
|
wakeReason: "retry_failed_run",
|
|
wakeSource: "on_demand",
|
|
wakeTriggerDetail: "manual",
|
|
paperclipWake: {
|
|
comments: [
|
|
{
|
|
body: "x".repeat(50_000),
|
|
},
|
|
],
|
|
},
|
|
executionStage: {
|
|
summary: "large nested object that should not be sent back in run lists",
|
|
},
|
|
});
|
|
|
|
expect(summarized).toEqual({
|
|
issueId: "issue-1",
|
|
taskId: "task-1",
|
|
taskKey: "PAP-1",
|
|
commentId: "comment-1",
|
|
wakeCommentId: "comment-2",
|
|
wakeReason: "retry_failed_run",
|
|
wakeSource: "on_demand",
|
|
wakeTriggerDetail: "manual",
|
|
});
|
|
});
|
|
|
|
it("returns null when no allowed fields are present", () => {
|
|
expect(
|
|
summarizeHeartbeatRunContextSnapshot({
|
|
paperclipWake: { comments: [{ body: "hello" }] },
|
|
}),
|
|
).toBeNull();
|
|
});
|
|
});
|
|
|
|
describe("summarizeHeartbeatRunListResultJson", () => {
|
|
it("keeps only summary fields and parses numeric cost aliases", () => {
|
|
expect(
|
|
summarizeHeartbeatRunListResultJson({
|
|
summary: "Completed the task",
|
|
result: "Updated three files",
|
|
message: "",
|
|
error: null,
|
|
totalCostUsd: "1.25",
|
|
costUsd: "0.75",
|
|
costUsdCamel: "0.5",
|
|
}),
|
|
).toEqual({
|
|
summary: "Completed the task",
|
|
result: "Updated three files",
|
|
total_cost_usd: 1.25,
|
|
cost_usd: 0.75,
|
|
costUsd: 0.5,
|
|
});
|
|
});
|
|
|
|
it("returns null when projected fields are empty", () => {
|
|
expect(
|
|
summarizeHeartbeatRunListResultJson({
|
|
summary: "",
|
|
result: null,
|
|
message: undefined,
|
|
error: " ",
|
|
totalCostUsd: "abc",
|
|
}),
|
|
).toBeNull();
|
|
});
|
|
});
|