mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-09 16:02:36 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents split work into tasks. A task can have a parent task. > - Today agents can nest tasks to any depth: parent, child, grandchild, and deeper. > - Deep agent-made trees are hard to follow, and an agent that works on a child task makes grandchildren by default. > - This pull request limits agent-created trees to two levels: a top-level task and its children. > - A request for a grandchild does not fail. The server puts the new task beside the requester and tells the agent. > - Board users keep full control. They can still nest to any depth. Existing deep trees stay valid. > - The pull request also records which task created each new task, so the audit trail stays complete when the parent changes. ## Linked Issues or Issue Description No public issue exists. This is the feature description. Related: #16853 (budgets that include descendant work) also reasons about task trees; this change does not alter its traversal. **Subsystem affected** Issues (tasks): create, child create and move in the issue service and routes. Agent tools, chat suggestions and creation provenance use these paths. **Problem or motivation** Agents create subtasks as deep as they want. An agent that runs on a child task gets that child as the default parent, so its follow-ups become grandchildren. The trees become deep and hard to read. The parent link is also the only record of which task created a follow-up, so that record is lost when the parent changes. **Proposed solution** Limit agent-created trees to a parent and its children. When an agent asks for a grandchild, put the new task under the requester's parent and return `parentAdjusted`. Do not reject the request. Keep board users unrestricted. Record the originating task in a new server-set `origin_issue_id` column. Keep `origin_run_id` as the originating run. **Alternatives considered** Reject grandchild requests with an error. We did not do this, because agents then fail mid-task. Add a database constraint. We did not do this, because existing deep trees must stay valid and nesting can return later. ## What Changed - Add `MAX_AGENT_TASK_HIERARCHY_DEPTH` (2) and the `IssueParentAdjustment` type in `packages/shared`. - Add `resolveNewTaskParent` and `planIssueParentChange` in `server/src/services/issues.ts`. `create`, `createChild` and `update` use the agent limit by default (`parentDepthPolicy: "flatten"`). - The issue create, `/children` and PATCH routes pass `allow_nested` for board users. For agents, the routes check authorization against the parent that the server actually writes. - The requester keeps its behavior when the server moves a task beside it: `blockParentUntilDone` blocks the requester, and the new task inherits the requester's workspace and privacy. - The server never moves a task above a low-trust boundary root that contains the requester. - These subsystems keep any depth, because they find their work by parent: watchdog reviews, monitor recovery, email-channel placement, and routines that a person configured. - An agent move of a task that has children skips only the parent change and returns `reason: "has_children"`. - Add `issues.origin_issue_id` (nullable, `on delete set null`, indexed) in migration `0434`. Only the server sets it. The `createdFrom` detail field, the `createdFromIssueId` filter and task-creation provenance read it first. - Chat prompts now let a chat agent create one task, a task with children, or separate tasks. The conversation is never a parent. - The runner `create_task` tool accepts an optional `parentTaskId`. A chat agent can create a top-level task and then put subtasks under it. The run must be able to read and change the parent. A conversation is never a parent. The depth limit still applies. Project tools map the field to `parentId` through the issue route. The protocol manifest, semantic contracts and eval fixture are regenerated. - Watchdog runs that have an active watchdog keep their requested parent on all create paths, because their access is limited to the watched subtree. - Fix a bug that the test drive found: the chat (MCP) `create_task` ignored the requested `status`, so a `backlog` task became `todo` and started to run. It now uses the same rule as the native tool. - Update `skills/paperclip`, `doc/SPEC-implementation.md`, and add the plan `doc/plans/2026-11-05-two-level-task-hierarchy.md`. ## Verification - `cd server && npx vitest run src/__tests__/agent-task-hierarchy-depth.test.ts src/__tests__/agent-task-hierarchy-depth-routes.test.ts`: 19 new tests for service and route behavior, all pass. - Related suites (64 files: issues service, thread interactions, privacy, watchdogs, provenance, runner tool authority, decisions, routines, project tools): 1208 tests pass. Two tests changed because of the intended behavior and pass now. Two `email-channels.integration` tests fail locally because the test cannot find a bundled skill file from this worktree path. This change does not touch that code. - `packages/db`: migration safety, snapshot drift and journal tests pass. - Typecheck passes for `server`, `packages/shared`, `packages/db`, `cli` and `ui` (local `ui` errors come only from generated Storybook catalog files that are absent). - Local test drive on an isolated instance with real Claude agents: 29 of 29 use cases pass, including an agent on a child task (follow-ups placed beside it, with the notice) and a chat that creates a top-level task with three subtasks. - I did not run the full `pnpm test:run` or `pnpm build` locally. CI runs them. ## Risks - Behavior change for agents: some follow-ups that were grandchildren are now siblings. The parent of the requester is woken when all its children finish, which now includes these tasks. - The runner `create_task` input contract adds one optional field, so the protocol manifest and the pack contract change. The tool output does not change: it shows the actual `parentId`, and the activity log records `parentAdjusted`. - Migration `0434` adds a nullable column, a foreign key and an index. It does not backfill rows. - `IssueCreationSource.run` is now nullable. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use (shell, file edits, local test runs). ## 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 - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [ ] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
110 lines
7.3 KiB
TypeScript
110 lines
7.3 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import { activityLog, agents, companies, createDb, heartbeatRuns, issues } from "@paperclipai/db";
|
|
import { createFullDatabaseResponseCapture, installDatabaseResponseCapture } from "./helpers/full-database-response-capture.js";
|
|
import { eq } from "drizzle-orm";
|
|
import { afterAll, beforeAll, describe, expect, it } from "vitest";
|
|
import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "./helpers/embedded-postgres.js";
|
|
import { resolveIssueCreationSource, runBoundIssueReference } from "../services/issue-creation-source.js";
|
|
|
|
const support = await getEmbeddedPostgresTestSupport();
|
|
|
|
describe.skipIf(!support.supported)("creation source run projections", () => {
|
|
const companyId = randomUUID(), otherCompanyId = randomUUID(), agentId = randomUUID();
|
|
const sourceId = randomUUID(), secondId = randomUUID(), foreignId = randomUUID();
|
|
let database: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>>;
|
|
let db: ReturnType<typeof createDb>;
|
|
let childNumber = 100;
|
|
|
|
beforeAll(async () => {
|
|
database = await startEmbeddedPostgresTestDatabase("creation-source-read-");
|
|
db = createDb(database.connectionString);
|
|
await db.insert(companies).values([
|
|
{ id: companyId, name: "Creation source fixture", issuePrefix: "CSR" },
|
|
{ id: otherCompanyId, name: "Foreign source fixture", issuePrefix: "FSR" },
|
|
]);
|
|
await db.insert(agents).values({ id: agentId, companyId, name: "Source agent", adapterType: "process" });
|
|
await db.insert(issues).values([
|
|
{ id: sourceId, companyId, title: "Source task", identifier: "CSR-1", issueNumber: 1 },
|
|
{ id: secondId, companyId, title: "Second source task", identifier: "CSR-2", issueNumber: 2 },
|
|
{ id: foreignId, companyId: otherCompanyId, title: "Foreign task", identifier: "FSR-1", issueNumber: 1 },
|
|
]);
|
|
}, 60_000);
|
|
|
|
afterAll(async () => {
|
|
await db?.$client.end();
|
|
await database?.cleanup();
|
|
});
|
|
|
|
async function fixture(values: Partial<typeof heartbeatRuns.$inferInsert>) {
|
|
const [run] = await db.insert(heartbeatRuns).values({ companyId, agentId, status: "succeeded", ...values }).returning();
|
|
const number = childNumber++;
|
|
const [child] = await db.insert(issues).values({ companyId, title: "Created task", identifier: `CSR-${number}`,
|
|
issueNumber: number, originRunId: run.id }).returning();
|
|
return { run, child };
|
|
}
|
|
|
|
it.each(["scoped", "legacy task key", "legacy nested identifier"])("omits saved run payloads for %s bindings while preserving provenance and storage", async (binding) => {
|
|
const bulk = "retained-source-context🙂".repeat(32_768);
|
|
const contextSnapshot = binding === "scoped"
|
|
? { issueId: sourceId, paperclipIssue: { id: sourceId, retainedDescription: bulk }, retainedLaunchInput: bulk }
|
|
: binding === "legacy task key"
|
|
? { taskKey: "CSR-1", paperclipIssue: { retainedDescription: bulk }, retainedLaunchInput: bulk }
|
|
: { paperclipIssue: { id: "CSR-1", retainedDescription: bulk }, retainedLaunchInput: bulk };
|
|
const { run, child } = await fixture({ contextSnapshot,
|
|
runnerProfileJson: { retainedInput: bulk }, stdoutExcerpt: bulk, stderrExcerpt: bulk, resultJson: { retainedReceipt: bulk } });
|
|
expect(run.issueId).toBe(binding === "scoped" ? sourceId : null);
|
|
expect(run.nativeIssueId).toBeNull();
|
|
const observed = createDb(database.connectionString), events: Array<Record<string, unknown>> = [], now = Date.now();
|
|
const capture = createFullDatabaseResponseCapture({ start: now - 100, end: now + 59_000 }, event => events.push(event));
|
|
installDatabaseResponseCapture(observed, { heartbeatRuns, issues }, capture);
|
|
try {
|
|
const result = await resolveIssueCreationSource(observed, child);
|
|
capture.flush();
|
|
const reads = events.filter(event => event.table === "heartbeat_runs" && event.operation === "select");
|
|
expect(reads.reduce((count, event) => count + Number(event.calls), 0)).toBe(1);
|
|
expect(reads.reduce((bytes, event) => bytes + Number(event.responseValueBytes), 0)).toBeLessThan(8192);
|
|
expect(result).toMatchObject({ run: { id: run.id, companyId, agentId }, sourceIssue: { id: sourceId } });
|
|
expect(runBoundIssueReference(result!.run!)).toBe(binding === "scoped" ? sourceId : "CSR-1");
|
|
for (const key of ["runnerProfileJson", "stdoutExcerpt", "stderrExcerpt", "resultJson"]) expect(result!.run).not.toHaveProperty(key);
|
|
expect((await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, run.id)))[0]).toEqual(run);
|
|
expect(JSON.stringify(events)).not.toContain("retained-source-context");
|
|
} finally {
|
|
capture.flush();
|
|
await observed.$client.end();
|
|
}
|
|
});
|
|
|
|
it.each([
|
|
{ label: "native identity", nativeIssueId: sourceId, issueId: secondId, contextSnapshot: { issueId: secondId }, expected: sourceId },
|
|
{ label: "issue scope", issueId: sourceId, contextSnapshot: { issueId: secondId }, expected: sourceId },
|
|
{ label: "legacy issue id", contextSnapshot: { issueId: sourceId, taskId: secondId }, expected: sourceId },
|
|
{ label: "typed task id fallback", contextSnapshot: { issueId: 42, taskId: sourceId }, expected: sourceId },
|
|
{ label: "nested issue identifier", contextSnapshot: { issueId: " ", paperclipIssue: { id: "CSR-1", ignored: "payload" }, taskKey: "CSR-2" }, expected: sourceId },
|
|
{ label: "typed nested id fallback", contextSnapshot: { paperclipIssue: { id: 42 }, taskKey: "CSR-1" }, expected: sourceId },
|
|
{ label: "foreign context", contextSnapshot: { taskId: foreignId }, expected: null },
|
|
{ label: "null context", contextSnapshot: null, expected: null },
|
|
])("preserves binding precedence for $label", async ({ label: _label, expected, ...values }) => {
|
|
const { child } = await fixture(values);
|
|
expect((await resolveIssueCreationSource(db, child))?.sourceIssue.id ?? null).toBe(expected);
|
|
});
|
|
|
|
it.each([42, "scalar", ["issueId", sourceId]])("does not invent a task binding from malformed context %j", async (context) => {
|
|
const { child } = await fixture({ contextSnapshot: context as unknown as Record<string, unknown> });
|
|
expect(await resolveIssueCreationSource(db, child)).toBeNull();
|
|
});
|
|
|
|
it("preserves historical activity lookup, current bindings, and missing or foreign source denial", async () => {
|
|
const { run, child } = await fixture({ contextSnapshot: { taskKey: "CSR-1" } });
|
|
await db.update(issues).set({ originRunId: null }).where(eq(issues.id, child.id));
|
|
await db.insert(activityLog).values({ companyId, actorType: "system", actorId: "fixture", action: "issue.created",
|
|
entityType: "issue", entityId: child.id, runId: run.id });
|
|
expect((await resolveIssueCreationSource(db, { ...child, originRunId: null }))?.sourceIssue.id).toBe(sourceId);
|
|
await db.update(heartbeatRuns).set({ contextSnapshot: { taskKey: "CSR-2" } }).where(eq(heartbeatRuns.id, run.id));
|
|
expect((await resolveIssueCreationSource(db, child))?.sourceIssue.id).toBe(secondId);
|
|
expect(await resolveIssueCreationSource(db, { ...child, companyId: otherCompanyId })).toBeNull();
|
|
expect(await resolveIssueCreationSource(db, { ...child, originRunId: randomUUID() })).toBeNull();
|
|
await db.update(heartbeatRuns).set({ contextSnapshot: { taskId: child.id } }).where(eq(heartbeatRuns.id, run.id));
|
|
expect(await resolveIssueCreationSource(db, child)).toBeNull();
|
|
});
|
|
});
|