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>
76 lines
4.3 KiB
TypeScript
76 lines
4.3 KiB
TypeScript
import { projectDiscoverySchema, createProjectSchema, createIssueSchema, setIssueTitleSchema, requiredQualityReviewSchema } from "@paperclipai/shared";
|
|
import { z } from "zod";
|
|
import { CAPABILITY_SEMANTIC_TOOL_CATALOG } from "../vendor/paperclip-runner/index.js";
|
|
import { badRequest } from "../errors.js";
|
|
|
|
export const PROJECT_TOOL_NAMES = ["create_project", "list_project_repositories", "list_projects"];
|
|
export function projectToolDefinitions(workMode: string, includeTask = false) {
|
|
return CAPABILITY_SEMANTIC_TOOL_CATALOG.filter(tool =>
|
|
(PROJECT_TOOL_NAMES.includes(tool.operationId) || includeTask && ["create_task", "set_task_title"].includes(tool.operationId))
|
|
&& tool.allowedModes.includes(workMode as "standard"),
|
|
).map(tool => ({ name: tool.operationId, description: tool.description,
|
|
inputSchema: tool.operationId === "create_project"
|
|
? z.toJSONSchema(createProjectSchema.extend({ idempotencyKey: z.string().min(1).max(255) }))
|
|
: tool.inputSchema,
|
|
}));
|
|
}
|
|
|
|
/** All transports use the normal authenticated API, including its validation and audit path. */
|
|
export async function callProjectTool(input: {
|
|
name: string; arguments: Record<string, unknown>; apiUrl: string; token: string;
|
|
companyId: string; issueId: string; agentId: string; conversation: boolean; receiptOnly?: boolean;
|
|
}) {
|
|
if (input.receiptOnly && input.name !== "create_project") throw badRequest("Receipt recovery is only supported for project creation");
|
|
const args = input.arguments;
|
|
const page = input.name === "list_projects" ? projectDiscoverySchema.parse(args) : null;
|
|
let path = `/companies/${input.companyId}/projects`;
|
|
let body: unknown;
|
|
if (input.name === "set_task_title") {
|
|
path = `/issues/${input.issueId}/title`;
|
|
body = setIssueTitleSchema.parse(args);
|
|
} else if (input.name === "list_project_repositories") path = `/companies/${input.companyId}/project-repositories`;
|
|
else if (page) {
|
|
const query = new URLSearchParams({ view: "summary", limit: String(page.limit) });
|
|
if (page.cursor) query.set("cursor", page.cursor);
|
|
path += `?${query}`;
|
|
}
|
|
else if (input.name === "create_project") {
|
|
body = createProjectSchema.extend({ idempotencyKey: z.string().min(1).max(255) }).parse(args);
|
|
} else if (input.name === "create_task") {
|
|
const key = z.string().min(1).max(150).parse(args.idempotencyKey);
|
|
path = `/companies/${input.companyId}/issues`;
|
|
body = createIssueSchema.parse({
|
|
title: args.title, description: args.description, priority: args.priority,
|
|
projectId: args.projectId, initialPlan: args.initialPlan,
|
|
...(args.requiredQualityReview !== undefined ? {
|
|
executionPolicy: { requiredQualityReview: requiredQualityReviewSchema.parse(args.requiredQualityReview) },
|
|
} : {}),
|
|
assigneeAgentId: args.assigneeActorId ?? (args.assigneeUserId ? null : input.agentId),
|
|
assigneeUserId: args.assigneeUserId,
|
|
// An explicit parent goes through the route's depth placement and
|
|
// authorization; a conversation itself is never a parent.
|
|
parentId: typeof args.parentTaskId === "string" && args.parentTaskId
|
|
? args.parentTaskId
|
|
: (input.conversation ? null : input.issueId),
|
|
// Same rule as the native tool: backlog is honored and never wakes an
|
|
// agent; otherwise unresolved blockers make the task blocked.
|
|
status: args.status === "backlog" ? "backlog"
|
|
: Array.isArray(args.blockedByTaskIds) && args.blockedByTaskIds.length ? "blocked" : "todo",
|
|
blockedByIssueIds: args.blockedByTaskIds,
|
|
idempotencyKey: `chat-handoff:${input.issueId}:${key}`,
|
|
});
|
|
} else throw badRequest("Unknown project tool");
|
|
const response = await fetch(`${input.apiUrl.replace(/\/+$/, "").replace(/\/api$/, "")}/api${path}`, {
|
|
method: input.name === "set_task_title" ? "PUT" : body ? "POST" : "GET",
|
|
headers: { Authorization: `Bearer ${input.token}`, "Content-Type": "application/json",
|
|
...(input.receiptOnly ? { "X-Paperclip-Receipt-Only": "true" } : {}),
|
|
},
|
|
...(body ? { body: JSON.stringify(body) } : {}),
|
|
signal: AbortSignal.timeout(60_000),
|
|
});
|
|
if (input.receiptOnly && response.status === 204) return undefined;
|
|
const result = await response.json();
|
|
if (!response.ok) throw new Error(typeof result.error === "string" ? result.error : `Project tool failed (${response.status})`);
|
|
return result;
|
|
}
|