mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-21 00:05:49 +02:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Issue interactions give agents and people a structured decision record. > - Resolver routes used different authorization rules. > - Some routes blocked valid agents, including task watchdogs with normal issue access. > - The API did not show who could resolve a pending interaction. > - This pull request gives every interaction kind one resolver policy evaluator. > - The benefit is a clear decision path with consistent governance and company isolation. ## Linked Issues or Issue Description Fixes: #8087 Refs: #7403 Related PR: #11082 proposes board-only confirmation rules. This change keeps human-only review as an explicit policy. **What happened?** Agents could create issue interactions. Some resolver routes still required board access. This left valid agent confirmations pending. Task watchdogs could see the same problem without board identity. **Expected behavior** Every interaction kind must use one resolver policy contract. The contract must support `anyone`, `not_creator`, and `human_only`. It must also apply all normal governance controls. **Steps to reproduce** 1. Create a `request_confirmation` interaction as an agent. 2. Resolve it with another authorized agent. 3. Observe the board-only denial. **Paperclip version or commit** The problem exists on `master` before this change. **Deployment mode** Local development with `pnpm dev`. ## What Changed - Add canonical policies for `anyone`, `not_creator`, and `human_only`. - Use one server evaluator for every interaction kind. - Apply named addressees, company limits, review rules, and task watchdog scope. - Charge cross-issue resolutions to the existing per-run action limit. - Return the effective resolver audience in attention and interaction data. - Show the audience, governance choices, and denial reasons in the board UI. - Add telemetry, API documents, product documents, and regression fixtures. - Add migration provenance for safe legacy behavior. - Make migration `0218` safe for complete replays and partial prior runs. ## Product Rules - An interaction records a response. It does not grant authority for the next action. - `anyone` lets any authorized issue participant respond. - `not_creator` requires a responder other than the interaction creator. - `human_only` requires an authorized person. - A named addressee, company policy, or governed action can narrow the audience. - These controls cannot widen the audience. - A task watchdog uses the same rules as an ordinary agent. - A task watchdog does not receive board authority. - An agent resolution on another issue uses the shared cross-issue action limit. - Legacy pending interactions keep their earlier restrictions. - The UI shows the effective audience and a permanent denial reason. ## Verification - `pnpm --filter @paperclipai/db check:migrations` - `pnpm --filter @paperclipai/db typecheck` - `pnpm exec vitest run packages/db/src/issue-thread-interaction-resolver-policy-migration.test.ts` - The focused PostgreSQL test applies migration `0218` twice. - The test also completes a partial prior run and preserves existing provenance. - The latest GitHub head has 29 successful checks. - The opt-in Storybook visual check skipped as expected. - Greptile reports 5/5 with no open comments. ## Risks - New interaction writes use `anyone` by default. - Callers must select `not_creator` or `human_only` when they need stricter review. - Legacy pending interactions keep the old creator and human restrictions. - Migration `0218` fills only missing provenance fields during recovery. - Cross-issue resolutions can reach the existing action limit. - The shared evaluator affects every interaction kind. - Route, service, database, shared contract, and UI tests cover these rules. > This work matches the Agent Reviews and Approvals direction in `ROADMAP.md`. It does not duplicate a planned item. ## Model Used OpenAI Codex, GPT-5. The runtime does not expose the exact deployment ID or context window. The agent used reasoning, repository tools, shell commands, and test execution. ## 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 linked public issues or described the issue with the required labels - [x] I have not referenced internal Paperclip issues or links - [x] My branch name describes the change and contains no internal ticket id - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation - [x] I have considered and documented the risks - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open comments - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
217 lines
7.9 KiB
TypeScript
217 lines
7.9 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import {
|
|
CROSS_ISSUE_INFLUENCE_ENFORCE_AT,
|
|
CROSS_ISSUE_INFLUENCE_LIMIT,
|
|
crossIssueInfluenceLimitError,
|
|
evaluateCrossIssueInfluenceLimit,
|
|
observeCrossIssueInfluence,
|
|
} from "../services/cross-issue-influence-limit.ts";
|
|
|
|
function counterDb(
|
|
initialCount = 0,
|
|
runOverrides: Record<string, unknown> | null = {},
|
|
) {
|
|
let observedCount = initialCount;
|
|
const inserted: Array<Record<string, unknown>> = [];
|
|
const tx = {
|
|
select: (selection: Record<string, unknown>) => ({
|
|
from: () => ({
|
|
where: () => {
|
|
if (Object.keys(selection).includes("count")) {
|
|
return {
|
|
then: (resolve: (rows: unknown[]) => unknown) => resolve([{ count: observedCount }]),
|
|
};
|
|
}
|
|
return {
|
|
for: () => ({
|
|
then: (resolve: (rows: unknown[]) => unknown) => resolve(runOverrides === null ? [] : [{
|
|
id: "11111111-1111-4111-8111-111111111111",
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
responsibleUserId: "user-1",
|
|
contextSnapshot: { issueId: "44444444-4444-4444-8444-444444444444" },
|
|
...runOverrides,
|
|
}]),
|
|
}),
|
|
};
|
|
},
|
|
}),
|
|
}),
|
|
insert: () => ({
|
|
values: async (value: Record<string, unknown>) => {
|
|
inserted.push(value);
|
|
if (value.action === "issue.cross_issue_influence_observed") observedCount += 1;
|
|
},
|
|
}),
|
|
};
|
|
return {
|
|
db: {
|
|
transaction: async (callback: (value: typeof tx) => Promise<unknown>) => callback(tx),
|
|
},
|
|
inserted,
|
|
get observedCount() {
|
|
return observedCount;
|
|
},
|
|
};
|
|
}
|
|
|
|
describe("cross-issue influence limit rollout", () => {
|
|
it("logs observations without enforcement during the one-week rollout", () => {
|
|
const decision = evaluateCrossIssueInfluenceLimit({
|
|
priorCount: CROSS_ISSUE_INFLUENCE_LIMIT,
|
|
now: new Date(CROSS_ISSUE_INFLUENCE_ENFORCE_AT.getTime() - 1),
|
|
});
|
|
|
|
expect(decision).toMatchObject({
|
|
allowed: true,
|
|
mode: "log_only",
|
|
count: CROSS_ISSUE_INFLUENCE_LIMIT + 1,
|
|
cap: CROSS_ISSUE_INFLUENCE_LIMIT,
|
|
});
|
|
});
|
|
|
|
it("allows the twentieth influence and fails closed on the twenty-first after the flip", () => {
|
|
const now = CROSS_ISSUE_INFLUENCE_ENFORCE_AT;
|
|
expect(evaluateCrossIssueInfluenceLimit({ priorCount: 19, now })).toMatchObject({
|
|
allowed: true,
|
|
mode: "enforce",
|
|
count: 20,
|
|
cap: 20,
|
|
});
|
|
|
|
const rejected = evaluateCrossIssueInfluenceLimit({ priorCount: 20, now });
|
|
expect(rejected).toMatchObject({
|
|
allowed: false,
|
|
mode: "enforce",
|
|
count: 21,
|
|
cap: 20,
|
|
});
|
|
const capError = crossIssueInfluenceLimitError(rejected, {
|
|
actorLabel: "Fable",
|
|
issueIdentifier: "TASK-482",
|
|
});
|
|
expect(capError.details).toMatchObject({
|
|
code: "cross_issue_influence_cap_exceeded",
|
|
cap: 20,
|
|
count: 21,
|
|
mode: "enforce",
|
|
enforceAt: CROSS_ISSUE_INFLUENCE_ENFORCE_AT.toISOString(),
|
|
});
|
|
// Plan §6: the 429 names the boundary, who can act, and the way forward.
|
|
expect(capError.error).toContain("20");
|
|
expect(capError.error).toContain("Who can act:");
|
|
expect(capError.error).toContain("Try this:");
|
|
expect(capError.error).toContain("next heartbeat");
|
|
expect(capError.details.boundary).toContain("20");
|
|
expect(capError.details.whoCanAct).toContain("Fable");
|
|
});
|
|
|
|
it("uses one durable counter for cross-issue comments, PATCH updates, and interaction resolutions", async () => {
|
|
const fake = counterDb();
|
|
const base = {
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
runId: "11111111-1111-4111-8111-111111111111",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
targetIssueId: "55555555-5555-4555-8555-555555555555",
|
|
now: new Date(CROSS_ISSUE_INFLUENCE_ENFORCE_AT.getTime() - 1),
|
|
} as const;
|
|
|
|
await expect(observeCrossIssueInfluence(fake.db as never, { ...base, kind: "comment" }))
|
|
.resolves.toMatchObject({ count: 1, allowed: true });
|
|
await expect(observeCrossIssueInfluence(fake.db as never, { ...base, kind: "update" }))
|
|
.resolves.toMatchObject({ count: 2, allowed: true });
|
|
await expect(observeCrossIssueInfluence(fake.db as never, { ...base, kind: "interaction_resolution" }))
|
|
.resolves.toMatchObject({ count: 3, allowed: true });
|
|
|
|
expect(fake.observedCount).toBe(3);
|
|
expect(fake.inserted.map((row) => (row.details as { kind: string }).kind))
|
|
.toEqual(["comment", "update", "interaction_resolution"]);
|
|
});
|
|
|
|
it("counts an interaction resolution against a budget already spent on comments", async () => {
|
|
const fake = counterDb(CROSS_ISSUE_INFLUENCE_LIMIT);
|
|
|
|
await expect(observeCrossIssueInfluence(fake.db as never, {
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
runId: "11111111-1111-4111-8111-111111111111",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
targetIssueId: "55555555-5555-4555-8555-555555555555",
|
|
kind: "interaction_resolution",
|
|
now: CROSS_ISSUE_INFLUENCE_ENFORCE_AT,
|
|
})).resolves.toMatchObject({
|
|
allowed: false,
|
|
mode: "enforce",
|
|
count: CROSS_ISSUE_INFLUENCE_LIMIT + 1,
|
|
});
|
|
expect(fake.inserted).toEqual([
|
|
expect.objectContaining({ action: "issue.cross_issue_influence_cap_rejected" }),
|
|
]);
|
|
});
|
|
|
|
it("does not count same-issue writes", async () => {
|
|
const fake = counterDb(0, {
|
|
contextSnapshot: { issueId: "55555555-5555-4555-8555-555555555555" },
|
|
});
|
|
await expect(observeCrossIssueInfluence(fake.db as never, {
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
runId: "11111111-1111-4111-8111-111111111111",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
targetIssueId: "55555555-5555-4555-8555-555555555555",
|
|
kind: "comment",
|
|
})).resolves.toBeNull();
|
|
expect(fake.inserted).toEqual([]);
|
|
});
|
|
|
|
it.each([
|
|
["missing", null],
|
|
["wrong-agent", { agentId: "aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa" }],
|
|
["wrong-company", { companyId: "aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa" }],
|
|
] as const)("fails closed for a %s locked run", async (_label, runOverrides) => {
|
|
const fake = counterDb(0, runOverrides);
|
|
|
|
await expect(observeCrossIssueInfluence(fake.db as never, {
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
runId: "11111111-1111-4111-8111-111111111111",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
targetIssueId: "55555555-5555-4555-8555-555555555555",
|
|
kind: "comment",
|
|
})).rejects.toMatchObject({
|
|
status: 403,
|
|
details: { code: "cross_issue_influence_run_context_required" },
|
|
});
|
|
expect(fake.inserted).toEqual([]);
|
|
});
|
|
|
|
it("fails closed before querying for a malformed run id", async () => {
|
|
const fake = counterDb();
|
|
|
|
await expect(observeCrossIssueInfluence(fake.db as never, {
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
runId: "attacker-controlled-run-id",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
targetIssueId: "55555555-5555-4555-8555-555555555555",
|
|
kind: "comment",
|
|
})).rejects.toMatchObject({
|
|
status: 403,
|
|
details: { code: "cross_issue_influence_run_context_required" },
|
|
});
|
|
expect(fake.inserted).toEqual([]);
|
|
});
|
|
|
|
it("fails closed when the persisted run has no source issue", async () => {
|
|
const fake = counterDb(0, { contextSnapshot: {} });
|
|
|
|
await expect(observeCrossIssueInfluence(fake.db as never, {
|
|
companyId: "22222222-2222-4222-8222-222222222222",
|
|
runId: "11111111-1111-4111-8111-111111111111",
|
|
agentId: "33333333-3333-4333-8333-333333333333",
|
|
targetIssueId: "55555555-5555-4555-8555-555555555555",
|
|
kind: "update",
|
|
})).rejects.toMatchObject({
|
|
status: 403,
|
|
details: { code: "cross_issue_influence_run_context_required" },
|
|
});
|
|
expect(fake.inserted).toEqual([]);
|
|
});
|
|
});
|