mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-07 16:11:46 +02:00
## Thinking Path > - Paperclip manages AI agents and the tools they may use. > - Connection setup separates provider preference from permission to use a tool. > - The first native connection baseline could not exercise its intended decisions. > - The browser used mutable task titles, and the provider fixture already granted access. > - Native provider-choice instructions also disagreed with the preferred question format. Schema rejection gave no field guidance. > - This pull request repairs those test preconditions and native guidance, then fixes restart/approval defects exposed by the corrected baseline. It also restores missing OpenCode tool-error evidence. > - The benefit is an inspectable baseline before any further instruction reduction. ## Linked Issues or Issue Description Refs #15407. The original 15-cell baseline remains 0 PASS / 15 FAIL. Ten cells stopped on stale titles, two Codex cells had schema denials, two OpenCode cells used already-granted tools, and one Claude cell returned no native result. No intended user decisions were submitted. The exact invalid Codex field and underlying Claude failure cause remain unknown. [Original campaign](https://github.com/paperclipai/paperclip/actions/runs/37562577199) · [Original report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37562577199-1/index.html) ## What Changed - Match the browser's task route and visible identifier instead of a title the agent can change. - Start native provider-choice fixtures with no agent tool access. Verify the public effective-access records. - In the positive case, select Arcade, then grant its exact HubSpot tool through the real access card. Require both saved decisions and exactly one observed call. - Return a canonical `providerQuestionSet` for native input and retain the equivalent legacy `providerQuestion`. - Keep invalid input rejected. Return bounded schema locations and required field names without submitted values. - Preserve Claude's exact session/content identity while allowing authenticated registered instruction-copy paths to rotate on a new run. - Reject duplicate approval reports for an existing exact tool-action card before they create another human review. - Wait for a recorded service-approval continuation within the existing deadline; retain missing or failed continuation grades. - Forward OpenCode tool activity through the runner facade, preserving bounded errors and execution-part identity without inventing host-call joins or exposing arguments. - Preserve original grades, costs, scope limits and diagnoses in the dated repair report. ## Verification - Eval typecheck passes. Support suite: 1,801 PASS, one intentional skip; Node checks: 128 PASS. - Connection/schema tests: 51 PASS. Real-server public fixture setup: one PASS with zero providers. - Browser support regression: five PASS, including renamed and wrong tasks. - Focused Rust safe-feedback test: one PASS. - Repository typecheck and build pass before the latest master replay. Post-replay connection/shared/real-server fixture checks: 52 PASS; eval typecheck passes. The browser review fix additionally passes all five browser checks and seven suite checks. - The full local repository run was interrupted incomplete after about 45 minutes, with five integration failures retained. All five pass in a separate targeted invocation (1,250 unrelated tests skipped). No full local-suite pass or root cause for the initial local failures is claimed. - Corrected frozen source `162cc90fdabe7f505b88ae095044531b82784c92`: **10 PASS / 5 FAIL** across the [passing Codex canary](https://github.com/paperclipai/paperclip/actions/runs/37575158761) and [remaining 14 cells](https://github.com/paperclipai/paperclip/actions/runs/37576261807). The canary passes all 17 checks. Claude's two provider-choice continuations fail on restart, Claude service approval exposes an early evaluator rejection, Codex service approval creates a duplicate approval, and OpenCode provider-second times out after both decisions with no HubSpot call. No original result is regraded. - Final ledgers count 31 actual runs: 27 succeeded, two failed, two cancelled during cleanup. All 15 cleanup/budget checks pass. The late Claude continuation is absent from its earlier workflow snapshot; it remains in the result/API/final ledger. Original evidence retains 279 hashes. Recorded LLM subtotal $0.04553787 is incomplete billing, not actual total cost; local runtime is unmetered. - New repair regressions reproduce the Claude attach failure, duplicate approval acceptance and dropped OpenCode tool events before their respective fixes. Nine Rust attachment checks, 127 ACPX host/adapter tests, 33 completion/control-plane checks, nine eval deadline tests, 59 OpenCode proxy/driver tests, one Rust tool-error/redaction check, and TypeScript/Rust composer parity pass. Eval typecheck, repository typecheck and build pass. Existing support coverage is 1,802 PASS plus 128 Node PASS, one intentional support skip; two additional deadline tests also pass. - New-source full CI/review and live canaries are pending. The next bounded selection is Claude provider-decline, Codex service-approve and one OpenCode provider-second diagnostic with repaired event evidence. No broader campaign or instruction-reduction qualification is claimed. - Initial corrected campaign [37574251834](https://github.com/paperclipai/paperclip/actions/runs/37574251834) was cancelled during shared build after review found the breadcrumb whitespace assumption. Its matrix job has zero steps and no provider execution. The real adjacent-span browser regression now reproduces the old failure and passes after the fix. ## Risks - The corrected baseline remains 10/15. The new restart/approval fixes require live qualification; OpenCode evidence forwarding does not itself establish or fix its prior behavioral failure. - The positive provider case now expects three runs, including separate access approval. Its new results are distinct from the original invalid fixture. - The old Claude missing-result cause and rejected Codex field are unknown. These repairs do not retroactively explain or erase either failure. - Path rotation must preserve prompt, custom instruction, skill/content identity and protected provider settings; regression checks reject stale or changed content. No connection authorization, JSON schema, budget, cleanup, or final-result requirement is relaxed. Historical Everyday prompts and gateway setup remain unchanged. ## Model Used OpenAI Codex, GPT-6. The exact deployment variant and context window are not exposed in this session. Used repository inspection, code editing, test execution and retained-evidence analysis. ## 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>
185 lines
9.4 KiB
TypeScript
185 lines
9.4 KiB
TypeScript
import { describe, expect, it, vi } from "vitest";
|
|
import { pollUntil } from "./api.js";
|
|
import { classifyFailure } from "./failure-classifier.js";
|
|
import { storyHasDurableServiceContinuation, storyHasDurableAgentReviewContinuation, storyHasStrandedBlockedLeaf, storyReviewContinuationTimeoutDetail, type StoryIssue } from "./everyday-observations.js";
|
|
|
|
describe("workflow timeout classification", () => {
|
|
it("does not classify observed task data as an infrastructure error", async () => {
|
|
vi.useFakeTimers();
|
|
try {
|
|
const pending = pollUntil({
|
|
label: "everyday hire-reuse settled",
|
|
deadlineAt: Date.now() + 10,
|
|
intervalMs: 10,
|
|
load: async () => ({
|
|
status: "in_progress",
|
|
connection: "server unavailable",
|
|
secret: "plaintext in an ordinary task description",
|
|
}),
|
|
accept: () => false,
|
|
});
|
|
const caught = pending.catch((error: unknown) => error);
|
|
await vi.advanceTimersByTimeAsync(11);
|
|
const error = await caught;
|
|
expect(classifyFailure(error)).toBe("candidate_failure");
|
|
expect((error as Error).message).not.toContain(
|
|
"ordinary task description",
|
|
);
|
|
} finally {
|
|
vi.useRealTimers();
|
|
}
|
|
});
|
|
it("keeps a failed network read retryable", async () => {
|
|
vi.useFakeTimers();
|
|
try {
|
|
const caught = pollUntil({
|
|
label: "task state",
|
|
deadlineAt: Date.now() + 10,
|
|
intervalMs: 10,
|
|
load: async () => {
|
|
throw new Error("ECONNRESET");
|
|
},
|
|
accept: () => false,
|
|
}).catch((error: unknown) => error);
|
|
await vi.advanceTimersByTimeAsync(11);
|
|
expect(classifyFailure(await caught)).toBe("transient_infrastructure");
|
|
} finally {
|
|
vi.useRealTimers();
|
|
}
|
|
});
|
|
});
|
|
|
|
|
|
describe("review continuation deadline", () => {
|
|
function fixture(now: number) {
|
|
const issues: StoryIssue[] = [
|
|
{ id: "parent", companyId: "company", title: "parent", status: "blocked", blockedTransitionAt: new Date(now - 1000).toISOString() },
|
|
{ id: "child", parentId: "parent", companyId: "company", title: "child", status: "done", interactions: [{
|
|
id: "review", issueId: "child", kind: "request_confirmation", status: "accepted",
|
|
addresseeAgentId: "lead", resolvedByAgentId: "lead", resolvedByRunId: "review-run",
|
|
resolvedAt: new Date(now).toISOString(), result: { version: 1, outcome: "accepted" },
|
|
payload: { target: { type: "custom", key: "native_completion_review", revisionId: "decision" } },
|
|
}] },
|
|
];
|
|
const runs = [{ id: "review-run", companyId: "company", agentId: "lead", status: "succeeded", finishedAt: new Date(now).toISOString() }];
|
|
return { issues, runs };
|
|
}
|
|
|
|
it("uses the review timeout detail only with stranded work and durable review evidence", () => {
|
|
const state = fixture(Date.now());
|
|
expect(
|
|
storyReviewContinuationTimeoutDetail(state.issues, "parent", "lead", state.runs, ["lead"]),
|
|
).toBe("task is Blocked without an active continuation after accepted review");
|
|
state.issues[1]!.interactions = [];
|
|
expect(
|
|
storyReviewContinuationTimeoutDetail(state.issues, "parent", "lead", state.runs, ["lead"]),
|
|
).toBeUndefined();
|
|
const completed = fixture(Date.now());
|
|
completed.issues[0]!.status = "done";
|
|
expect(
|
|
storyReviewContinuationTimeoutDetail(
|
|
completed.issues, "parent", "lead", completed.runs, ["lead"],
|
|
),
|
|
).toBeUndefined();
|
|
});
|
|
|
|
it("permits a delayed parent continuation within the existing deadline", async () => {
|
|
vi.useFakeTimers();
|
|
try {
|
|
const start = Date.now();
|
|
const state = fixture(start);
|
|
const pending = pollUntil({
|
|
label: "review handoff", deadlineAt: start + 30_000, intervalMs: 1000,
|
|
load: async () => {
|
|
if (Date.now() >= start + 20_000) state.issues[0]!.status = "done";
|
|
return state;
|
|
},
|
|
accept: ({ issues }) => issues.every((issue) => issue.status === "done"),
|
|
reject: ({ issues, runs }) => storyHasStrandedBlockedLeaf(issues, "lead") &&
|
|
!storyHasDurableAgentReviewContinuation(issues, "parent", "lead", runs)
|
|
? "task is Blocked without an active continuation" : undefined,
|
|
});
|
|
const caught = pending.catch((error: unknown) => error);
|
|
await vi.advanceTimersByTimeAsync(20_001);
|
|
expect(await caught).toBe(state);
|
|
} finally { vi.useRealTimers(); }
|
|
});
|
|
|
|
it("reports a missing wake specifically when the existing deadline expires", async () => {
|
|
vi.useFakeTimers();
|
|
try {
|
|
const state = fixture(Date.now());
|
|
const pending = pollUntil({
|
|
label: "review handoff", deadlineAt: Date.now() + 30_000, intervalMs: 1000,
|
|
load: async () => state, accept: () => false,
|
|
timeoutDetail: (last) => last && storyReviewContinuationTimeoutDetail(
|
|
last.issues, "parent", "lead", last.runs, ["lead"],
|
|
),
|
|
});
|
|
const caught = pending.catch((error: unknown) => error);
|
|
await vi.advanceTimersByTimeAsync(30_001);
|
|
const error = await caught;
|
|
expect((error as Error).message).toContain("Blocked without an active continuation after accepted review");
|
|
expect(classifyFailure(error)).toBe("candidate_failure");
|
|
} finally { vi.useRealTimers(); }
|
|
});
|
|
|
|
it("uses the generic timeout when durable review evidence is absent", async () => {
|
|
vi.useFakeTimers();
|
|
try {
|
|
const state = fixture(Date.now());
|
|
state.issues[1]!.interactions = [];
|
|
const pending = pollUntil({
|
|
label: "review handoff", deadlineAt: Date.now() + 30_000, intervalMs: 1000,
|
|
load: async () => state, accept: () => false,
|
|
timeoutDetail: (last) => last && storyReviewContinuationTimeoutDetail(
|
|
last.issues, "parent", "lead", last.runs, ["lead"],
|
|
),
|
|
});
|
|
const caught = pending.catch((error: unknown) => error);
|
|
await vi.advanceTimersByTimeAsync(30_001);
|
|
const error = await caught;
|
|
expect(error).toBeInstanceOf(Error);
|
|
expect((error as Error).message).not.toContain("after accepted review");
|
|
expect(classifyFailure(error)).toBe("candidate_failure");
|
|
} finally { vi.useRealTimers(); }
|
|
});
|
|
});
|
|
|
|
describe("approved service continuation deadline", () => {
|
|
it.each([true, false])("keeps the original deadline for a delayed dispatch (arrives: %s)", async arrives => {
|
|
vi.useFakeTimers();
|
|
try {
|
|
const start = Date.now();
|
|
const issues: StoryIssue[] = [{ id: "task", companyId: "company", title: "Briefing", status: "blocked", assigneeAgentId: "agent", interactions: [{
|
|
id: "approval", issueId: "task", sourceRunId: "first", createdByAgentId: "agent", kind: "request_confirmation", status: "accepted", continuationPolicy: "wake_assignee",
|
|
resolvedAt: new Date(start - 1000).toISOString(), payload: { toolAction: { version: 1, actionRequestId: "action" } }, result: { outcome: "accepted", toolAction: { status: "executed" } },
|
|
}] }];
|
|
const runs = [{ id: "first", companyId: "company", agentId: "agent", status: "succeeded", finishedAt: new Date(start).toISOString() }];
|
|
const caught = pollUntil({ label: "service continuation", deadlineAt: start + 30_000, intervalMs: 1000,
|
|
load: async () => { if (arrives && Date.now() >= start + 20_000) issues[0]!.status = "done"; return { issues, runs }; },
|
|
accept: state => state.issues[0]!.status === "done",
|
|
reject: state => storyHasStrandedBlockedLeaf(state.issues, "agent") && !storyHasDurableServiceContinuation(state.issues, "task", "agent", state.runs) ? "stranded" : undefined,
|
|
timeoutDetail: state => state && storyHasDurableServiceContinuation(state.issues, "task", "agent", state.runs) ? "missing service continuation" : undefined,
|
|
}).catch((error: unknown) => error);
|
|
await vi.advanceTimersByTimeAsync(30_001);
|
|
const result = await caught;
|
|
if (arrives) expect(result).toEqual({ issues, runs });
|
|
else { expect((result as Error).message).toContain("missing service continuation"); expect(classifyFailure(result)).toBe("candidate_failure"); }
|
|
} finally { vi.useRealTimers(); }
|
|
});
|
|
it("waits for dispatch only until the same response has been consumed", () => {
|
|
const issues: StoryIssue[] = [{ id: "task", companyId: "company", title: "Briefing", status: "blocked", assigneeAgentId: "agent", interactions: [{
|
|
id: "approval", issueId: "task", sourceRunId: "first", createdByAgentId: "agent", kind: "request_confirmation", status: "accepted", continuationPolicy: "wake_assignee",
|
|
resolvedAt: "2026-10-07T05:37:19Z", payload: { toolAction: { version: 1, actionRequestId: "action" } }, result: { outcome: "accepted", toolAction: { status: "executed" } },
|
|
}] }];
|
|
const runs = [{ id: "first", companyId: "company", agentId: "agent", status: "succeeded", finishedAt: "2026-10-07T05:37:28Z" }];
|
|
expect(storyHasDurableServiceContinuation(issues, "task", "agent", runs)).toBe(true);
|
|
expect(storyHasDurableServiceContinuation(issues, "task", "other", runs)).toBe(false);
|
|
const continued = [...runs, { id: "next", companyId: "company", agentId: "agent", status: "succeeded", runnerProfileJson: { nativeExecutionInput: { interactionResponses: [{ interactionId: "approval" }] } } }];
|
|
expect(storyHasDurableServiceContinuation(issues, "task", "agent", continued)).toBe(false);
|
|
issues[0]!.interactions![0]!.result = { outcome: "accepted", toolAction: { status: "failed" } };
|
|
expect(storyHasDurableServiceContinuation(issues, "task", "agent", runs)).toBe(false);
|
|
});
|
|
});
|