mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-21 16:27:18 +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>
45 lines
3.5 KiB
TypeScript
45 lines
3.5 KiB
TypeScript
import { beforeEach, describe, expect, it, vi } from "vitest";
|
|
import { heartbeatRuns, issues, issueThreadInteractions, issueApprovals, type Db } from "@paperclipai/db";
|
|
import type { PrpStructuredRunResult } from "../../vendor/paperclip-runner/index.js";
|
|
import { nativeCompletionFeedback } from "./native-completion-feedback.js";
|
|
|
|
const state = vi.hoisted(() => ({ blockers: 0 }));
|
|
vi.mock("./native-deliverable-feedback.js", () => ({
|
|
validateNativeDeliverableEvidence: vi.fn(async () => undefined),
|
|
publishedTaskDocuments: vi.fn(async () => []),
|
|
}));
|
|
vi.mock("./automatic-completion-reviews.js", () => ({ findAutomaticCompletionReviews: vi.fn(async () => []) }));
|
|
vi.mock("../agent-invokability.js", () => ({ evaluateAgentInvokabilityFromDb: vi.fn() }));
|
|
vi.mock("../issues.js", () => ({ issueService: () => ({ getDependencyReadiness: async () => ({ unresolvedBlockerCount: state.blockers }) }) }));
|
|
vi.mock("./native-review-participant.js", () => ({ readNativeReviewAssignmentContext: () => null, getNativeReviewAssignment: vi.fn() }));
|
|
vi.mock("../../vendor/paperclip-runner/index.js", () => ({ normalizePrpResultSignals: () => ({ verification: [], actionableAttentionRequests: [] }) }));
|
|
|
|
const result = { reportedWorkDisposition: "done", summary: "EXACT_PRIVATE_MARKER", completionClaim: { objectiveSatisfied: true, criteria: [], remainingWork: [] } } as unknown as PrpStructuredRunResult;
|
|
function database(options: { interaction?: boolean; approval?: boolean; review?: boolean } = {}): Db {
|
|
// Pure query double: no client, PostgreSQL process, or network is created.
|
|
return { select: () => ({ from: (table: unknown) => {
|
|
const rows = table === heartbeatRuns ? [{ id: "run", companyId: "company", nativeIssueId: "issue", contextSnapshot: {} }]
|
|
: table === issues ? [{ id: "issue", companyId: "company", status: "in_progress", ...(options.review ? { executionState: { status: "pending" } } : {}) }]
|
|
: table === issueThreadInteractions && options.interaction ? [{ id: "request", kind: "request_confirmation", title: "Decision" }]
|
|
: table === issueApprovals && options.approval ? [{ id: "approval" }] : [];
|
|
const query = { where: () => query, limit: () => query, innerJoin: () => query, then: (resolve: (value: unknown[]) => unknown) => Promise.resolve(rows).then(resolve) };
|
|
return query;
|
|
} }) } as unknown as Db;
|
|
}
|
|
beforeEach(() => { state.blockers = 0; });
|
|
describe("native completion feedback format precedence", () => {
|
|
it("honors requested final format only after normal completion acceptance without echoing the summary", async () => {
|
|
const feedback = await nativeCompletionFeedback(database(), "run", result);
|
|
expect(feedback).toContain("Follow the user's explicitly requested final-response format, including an exact response when requested.");
|
|
expect(feedback).toContain("Task status will be committed after this turn and workspace finalization finish.");
|
|
expect(feedback).toContain("Do not claim an approval is needed unless one was requested.");
|
|
expect(feedback).not.toContain(result.summary);
|
|
});
|
|
it.each(["interaction", "approval", "review", "dependency"] as const)("preserves %s governance feedback instead of granting format precedence", async mode => {
|
|
state.blockers = mode === "dependency" ? 1 : 0;
|
|
const feedback = await nativeCompletionFeedback(database({ interaction: mode === "interaction", approval: mode === "approval", review: mode === "review" }), "run", result);
|
|
expect(feedback).not.toContain("final-response format");
|
|
expect(feedback).toMatch(/still waiting|still pending|unresolved dependencies/);
|
|
});
|
|
});
|