Files
PaperClipAI/tests/runner-e2e/plan-task-skills.ts
T
DottaandPaperclip 16b7db35ff Shorten planning skills and measure task decomposition (#15296)
## Thinking Path

> - Paperclip manages work for AI agents.
> - Planning guidance helps agents choose owners and dependencies.
> - The runtime skill favors few tasks, but the catalog skill requires a
child-task breakdown.
> - Both add repeated process instructions that can distract from the
requested outcome.
> - This change keeps the ownership and dependency rules and removes the
required matrix and repeated checklist.
> - A bounded Product E2E comparison measures saved outcomes and task
handoffs before qualification.

## Linked Issues or Issue Description

Refs #11057. Related measurement work: #15218.

**What existing behavior does this improve?**
Planning and delegation through the runtime plan-to-tasks and bundled
task-planning skills.

**Current behavior**
The two skills contain about 1,900 words and conflicting guidance on
whether plans require child tasks.

**Proposed behavior**
Keep cohesive work with one owner. Split only for a real owner, parallel
output, dependency, independent review, or follow-up lifecycle. Preserve
existing authorization and planning mechanics.

## What Changed

- Shorten both skills to about 400 words combined. Preserve their keys
and installed-version behavior.
- Remove the duplicate operational-skill pointer and regenerate affected
source metadata.
- Add twelve explicit Product E2E cells: four scenarios with current,
short and disabled planning skills.
- Use the current task composer and actual create-response ID; calibrate
public skill APIs and browser creation without providers.
- Eliminate an observed collision in chat-test company prefixes with a
per-suite sequence.
- Grade saved documents, exact author/run attribution, child count,
prerequisite execution order, review boundaries and completion handoffs.
- Retain current skill bytes and report source, selections, run
accounting and failures.

## Verification

- `pnpm test:e2e:runner:typecheck`: pass.
- `pnpm test:e2e:runner:unit`: 1,287 Vitest tests and 128 Node checks
pass.
- `pnpm test:e2e:runner -- --list --suite plan-task-guidance`: twelve
local Codex cells.
- Archived current skills match master
`72ff3a9f27e581a27acb49771e8658bbb0bbaa47` exactly.
- Corrected fixture: three real public-API/database calibrations pass
with zero provider runs; all 35 evaluator checks and Product E2E
typecheck pass.
- Setup campaign
[37399550253](https://github.com/paperclipai/paperclip/actions/runs/37399550253)
was canceled after source review found unsupported bundled edits and
automatic core reinstallation. Its paid-cell step was skipped: zero
provider runs, no behavioral grade.
- The next setup
[37401094799](https://github.com/paperclipai/paperclip/actions/runs/37401094799)
failed before task creation on the old title-field selector: zero actual
runs, original FAIL retained, cleanup passed. A real browser/API
calibration of the new helper passes with paused non-provider agents and
zero runs.
- Full local typecheck/build pass. Full local tests retain one unchanged
five-minute Git streaming timeout (also fails isolated), 9,591 passes
and 5,796 skips. CI's chat failure was a proven random fixture-prefix
collision; five affected cases pass after the test-only repair.
- Paid behavior comparison and new-head CI/review remain pending. This
PR remains a draft.

## Risks

- The shorter text may change delegation decisions. Live outcomes are
not yet qualified.
- The initial comparison uses one profile and one attempt per cell. It
cannot establish cross-model reliability or cost trends.
- Disabled means unassigned company-owned copies; the company library
remains discoverable. This does not qualify global removal, automatic
accepted-plan wiring changes, or installed-copy migration.
- Skill availability does not prove a model read or cognitively used it.
- No provider/tool protocol, permission, timeout or runtime lifecycle
behavior changes in production.

## Model Used

OpenAI Codex (GPT-6), with repository inspection, code editing and tool
use. The exact backend model ID and context-window size are not exposed
in this session. The declared eval model is native Codex `gpt-5.6-sol`.

## 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

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-10-06 09:36:01 -05:00

55 lines
3.2 KiB
TypeScript

import { readFile } from "node:fs/promises";
import type { RunnerApi } from "./api.js";
import { PLAN_SKILLS, planHash, type PlanVariant } from "./plan-task-cases.js";
type SkillApi = Pick<RunnerApi, "get" | "post">;
export type PlanSkillSource = {
originalKey: string; key: string; id: string; sourcePath: string;
sha256: string; bytes: number; words: number; selected: boolean;
};
/** Bundled/catalog files are read-only and core inventory is automatically
* restored. Editable company copies preserve the source bytes and names;
* selection, rather than deletion, implements the unassigned control. */
export async function preparePlanSkills(api: SkillApi, companyId: string, variant: PlanVariant) {
const company = `/api/companies/${companyId}`;
const skills: PlanSkillSource[] = [];
for (const skill of PLAN_SKILLS) {
const relative = variant === "current" ? skill.current : skill.short;
const content = await readFile(new URL(`../../${relative}`, import.meta.url), "utf8");
const name = skill.key.split("/").at(-1)!;
const created = await api.post<{ id: string; key: string; sourceType: string }>(`${company}/skills`, {
name, slug: `eval-${name}`, markdown: content, sharingScope: "company",
});
if (created.sourceType !== "local_path") throw new Error("Planning fixture did not create an editable company skill");
const served = await api.get<{ content: string; editable: boolean }>(`${company}/skills/${created.id}/files?path=SKILL.md`);
if (!served.editable || planHash(served.content) !== planHash(content)) throw new Error(`Served skill differs from editable source ${relative}`);
skills.push({ originalKey: skill.key, key: created.key, id: created.id, sourcePath: relative,
sha256: planHash(content), bytes: Buffer.byteLength(content), words: content.split(/\s+/).filter(Boolean).length,
selected: variant !== "disabled" });
}
return skills;
}
export async function selectPlanSkills(api: SkillApi, companyId: string, agentId: string, sources: PlanSkillSource[]) {
const selected = sources.filter(s => s.selected).map(s => s.key);
await api.post(`/api/agents/${agentId}/skills/sync?companyId=${companyId}`, { desiredSkills: selected, mode: "replace" });
return verifyPlanSelection(api, companyId, agentId, sources);
}
export async function verifyPlanSelection(api: Pick<RunnerApi, "get">, companyId: string, agentId: string, sources: PlanSkillSource[]) {
const selected = sources.filter(s => s.selected).map(s => s.key);
const snapshot = await api.get<{ desiredSkills: string[] }>(`/api/agents/${agentId}/skills?companyId=${companyId}`);
if (JSON.stringify([...(snapshot.desiredSkills ?? [])].sort()) !== JSON.stringify([...selected].sort())) {
throw new Error("Planning skill selection differs from selected variant; comparison is uncomparable");
}
return snapshot;
}
export async function verifyPlanSkills(api: Pick<RunnerApi, "get">, companyId: string, sources: PlanSkillSource[]) {
for (const skill of sources) {
const served = await api.get<{ content: string }>(`/api/companies/${companyId}/skills/${skill.id}/files?path=SKILL.md`);
if (planHash(served.content) !== skill.sha256) throw new Error("Planning guidance changed during execution; comparison is uncomparable");
}
}