mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-10 12:07:09 +02:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native Runner keeps provider sessions under company authority, approvals, budgets and durable recovery. > - Cursor work was spread across candidate branches. The published branch lacked later plan, permission and cleanup fixes. > - Production also needs public installation and matching runtime assets for local and Daytona execution. > - This pull request consolidates Cursor onto current mainline recovery behavior and completes that installation path. > - The installed v11 release passed focused local and Daytona qualification after the generic mode and lifecycle cleanup. The later model-selection correction and current mainline merge produce v14 artifacts that need matching release qualification. > - Cursor admission is enabled in source; publish only an artifact combination with matching qualification. Native AskQuestion and complete per-run dollar accounting remain excluded. ## Linked Issues or Issue Description Refs: #14435, #14631, #14669, #14699, #14724. This completes the Cursor implementation by @cryppadotta from combined source `22c78242a4e0c2369fecf0c2dc4e7600fbad6706`. It preserves newer mainline recovery, completion and warm-directory behavior. Pi and Copilot remain gated. ## What Changed - Generate named Rust and TypeScript ACPX release profiles from one manifest. Share runtime pins with packaging and server verification. Preserve vendor runtime versions; bind the updated ACPX patch to Cursor profile v14 and reject stale generated declarations at build/typecheck. - Remove ACPX model allowlists, including the former Codex and Pi restrictions and the duplicate developer test-drive gate. Send any explicit model ID unchanged to its provider and verify the effective selection before prompting. The bundled ACPX package forwards unlisted IDs, rejects mismatched acknowledgements, and restores the exact selection after session load. It does not expand Cursor model aliases. Provider rejection, mismatch, or missing model controls fails without a fallback. Model examples live in evaluation fixtures, outside runtime declarations. - Add pinned Cursor execution, contained instructions, exact model verification and Agent/Plan/Ask modes. - Carry an opaque generic `mode` identifier in shared native execution, sidecar, Rust and recovery contracts. The provider adapter owns supported modes, defaults, native translation and acknowledgement. - Keep native RPC recognition, accepted-plan interpretation and permission evidence behind provider adapters. Shared settlement and recovery verify normalized facts and their committed evidence. - Replace the Cursor-only warm-attachment branch with a runner-owned capability. Only Cursor opts into it. Move profile compatibility and optional usage parsing into provider metadata and adapters. - Write generic plan-wait receipts. Read exact historical Cursor receipts through a separate compatibility decoder. Reject mixed formats and preserve existing authority checks. - Carry native plans, semantic questions, todos, child activity, permission identities and partial usage diagnostics through the Runner. - Preserve durable response delivery, cancellation, warm ownership and process retirement. - Finish accepted planning runs successfully. Keep their tasks open for explicit direction. Acceptance does not start implementation. - Ship `paperclipai runtime setup cursor` and its provisioner through the public package. npm installation does not download Cursor. Setup uses the OS account's closure-keyed cache so system-wide npm packages can remain read-only. Run it as the Paperclip service account. - Include Cursor in normal provider packs and Daytona images for macOS ARM64/x64 and Linux x64. - Reject stale release packs by source revision and current ACPX/Cursor pins before assembly writes files. Verify current Cursor version/profile/closure again at runtime. - Ship all three daemon targets and the expected Linux image-pack identity. A macOS controller uses its packaged Linux daemon for Daytona. Image mismatches fail before provider launch. - Use the vendored Runner boundary for installed readiness probes. Verify the actual installed Cursor probe. - Verify compiled public Daytona plugins and their release versions in installed smokes. - Record exact artifacts, the acceptance matrix, retained failures, supported capabilities and rollback behavior in the [readiness report](https://github.com/paperclipai/paperclip/blob/codex/cursor-production-readiness/doc/plans/2026-10-03-cursor-production-readiness.md). ## Verification - Current head `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037` merges mainline `faa8e452c73bae5e044dd6379179a00106abb131`. It keeps Cursor plan and cancellation guards alongside mainline historical-question filtering. The evaluation catalog includes both Cursor and expanded adapter accounting cases (683 total). Recursive typecheck, full build, 696 lifecycle/recovery tests, 45 fixture tests and fixture typecheck passed. Current-head CI passed: 56 successful checks, one neutral and four skipped. [Complete CI](https://github.com/paperclipai/paperclip/actions/runs/37557996535). The fresh Base Greptile review is 5/5 on this exact head, with 304 files reviewed, zero new comments and zero unresolved threads. The user authorized overriding the CODEOWNER review gate after checks passed; no failing checks are overridden. Prior results below retain their own head identities. - Corrective head `3d2b168366258036f6b6a6fccb382c49138cc601` fixes the post-merge Apex finding. Automatic-review and new-evidence reconciliation preserve pending child results and recheck delivery under the status lock before completing. Account repair now excludes unrelated secret consumers and requires the failed agent's identity. Regression coverage includes the commit race, delivery statuses, current-run/current-intent exclusions, repeated reconciliation, both database reconciliation paths, and credential consumer boundaries. All 184 affected tests, server typecheck and server build passed. Current-head Base Greptile review is 5/5, with 304 files reviewed, zero new comments and zero unresolved threads. Current-head CI passed: 56 successful checks, one neutral and four skipped. [Complete CI](https://github.com/paperclipai/paperclip/actions/runs/37535994724). This Base review is distinct from the earlier Apex review. - Merge head `5957c257a` reconciles mainline `b508a05c4`. It preserves both accepted-plan waits and pending-child-completion checks, current provider selectors, task-creation response identities, and mainline ACPX missing-file handling. The combined patch is bound to Cursor profile v14; historical records keep their original identities. - Merge head `5957c257a` passed recursive typecheck, full build, 43 installed ACPX/package contracts, 107 provider UI and plan/recovery tests, 593 database-backed lifecycle tests, 49 profile/native contract tests, 45 Product E2E fixture tests, fixture typecheck, token gates, three provider-free browser task-creation cases, and Runner conformance/replay checks. Its complete CI passed (55 successful checks, one neutral and four skipped), while Apex returned 2/5 with a child-delivery finding addressed below. - The local full-suite attempt again failed the unchanged Git streaming test (360-second timeout) and was stopped. The concurrent local Rust attempt failed four unchanged Codex process/deadline tests; all four passed serially without code changes in 7.29 seconds after removing the competing test load. These failed commands are retained and are not reported as full-suite passes; the fresh Linux CI runs are tracked separately. - The previous head `907bdb2a2778c7ffeb4a662a91460c9d1ddfc9c5` earned Apex 5/5 with zero comments after fixing all three findings: per-user install cache, stale release-pack rejection, and public Linux smoke account/home handling. Its real built installer passed from read-only public packages on macOS ARM64 and Linux x64. All 137 release-registry checks and 64 ACPX package contracts passed. That review does not cover this mainline reconciliation. - Prior `beadd3654` passed the full CI matrix; its one unchanged chat test failure and successful single retry remain in the [CI history](https://github.com/paperclipai/paperclip/actions/runs/37521449327). Historical results below remain attributed to their original builds. - Fixture follow-up `dd59d7e82b103a88b7cbd7d2c38b612c0fbbff7a` removes provider-specific model choices from generic offline ACPX tests. The fake sidecar preserves the model and session identity selected at open through suspension. Affected verification passed: 106 Rust tests and 73 TypeScript tests. This commit changes test code only; the production-code checks below retain their recorded identities. Its CI and Greptile review later passed; those results belong to that historical head. - Model-selection cleanup `9a070808b48960a41fdfd369ae0636b95af82459`: 252 focused Runner tests passed (six platform skips), covering all six ACPX agents, native model acknowledgement, rejected selections, installation integrity and recovery identity. The merged branch passed recursive typecheck, full build, token gates, server admission (19 tests), and the Product E2E catalog (45 tests). The acceptance catalog passed all four tests. The full Rust suite passed: 643 tests, 2 ignored. It verifies sidecar acknowledgement of unlisted models and rejection of model mismatches. The final commits only update Rust tests; production sources match the verified build at `65ec3279ac50185e3cda109b5cfd9b4f56105de0`. No new paid provider calls were made. - The merge preserves both Cursor and the new mainline public-MCP fixture cases. Auto-merge remains disabled; the latest follow-up status is recorded above. The local `pnpm test:run` attempt hit the unchanged Git streaming test's 300-second timeout and was interrupted before merging mainline. The broad Runner attempt found obsolete single-model assertions plus three macOS fixture-path failures caused by a `/private/tmp` override. The assertions are corrected; affected TypeScript checks passed with the standard macOS temporary directory, and the complete Rust suite passed. Neither interrupted command is a full-suite pass. - Earlier declaration-cleanup head `6f4a5e9e2` passed recursive typecheck, build, Rust and focused tests. Its CI later exposed a test expecting duplicated Grok digest literals. The current source fixes that assertion to compare launcher bytes with the shared manifest. Historical successes and failed attempts are retained; no new live provider qualification is claimed. - Previous head `e75fde6098b0ddd8cec765bfb6ecaeecb88a26a6` passed complete CI (56 successful checks, one neutral, four skipped) and Greptile 5/5. [Historical complete CI](https://github.com/paperclipai/paperclip/actions/runs/37489112305). Those results are not claimed for the cleanup head. - Frozen live application: `d7b696f9b8f79095233e9e3d56d23e6a6018dd48`. Public package version: `0.0.0-cursor-verify.3d0c9b7761c6`. The declaration cleanup preserves release pins and does not relabel that tested artifact as a build of the new source. Mainline through `e34abee670` was reconciled while preserving accepted-plan waits, provider-capacity handling, and both Cursor and public-MCP fixtures. - Clean normal installation, explicit Cursor setup and daemon resolution passed on macOS ARM64, macOS x64 under Rosetta, and Linux x64. npm lifecycle hooks ran without silently downloading Cursor. - Historical v11 live matrix: **18/18 passed with cleanup** (nine local, nine Daytona) after the generic mode and lifecycle cleanup. The campaign has 23 attempts; all five failures and their diagnoses remain recorded. Exact case identities, hashes and limits are in the readiness report. All provider calls are real, use the explicit Luna model and company-bound credentials, and run without qualification or runtime-asset overrides. - The immutable Daytona image is `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:d6259b6bba094702c13fc2283bd85550849c1c53145b656fb2746778f9fa1747`. The public Daytona plugin is installed independently and its version is checked. - Recursive typecheck, full build, token gates and Runner contract/conformance/replay checks passed on the frozen application. Its complete Linux CI suite passed. The duplicate local full-suite command was incomplete after timing failures; affected repeats passed, but that command is not reported as a clean pass. - Qualification fixtures passed typecheck, 1,675 Vitest tests (one skip), 128 Node checks, three provider-free browser tests, and 150 focused lifecycle tests after the final diagnostic correction. The affected legacy Cursor command file also passed all five tests after removing its shorter 10-second override; it now inherits the suite’s standard 15-second timeout. Greptile is 5/5 on `e75fde609` with no unresolved review threads. CI results above are recorded separately from historical build results. ## Risks - Cursor v14 includes the updated ACPX dependency patch and release identity. The v11 live matrix and image below remain historical evidence. They do not certify new v14 package/image artifacts. - ACPX accepts models beyond the qualification fixtures. Availability and entitlement depend on the provider. Successful configuration is not a claim of live qualification for every model. - Shared mode is an opaque identifier. Provider adapters own its meaning. Incompatible historical sessions remain fenced; exact committed plan waits and task history remain inspectable. - Native AskQuestion is excluded. Paperclip semantic questions are supported. Authoritative per-run dollar accounting is unavailable; partial counters remain diagnostics and unknown cost is not zero. - Image input, detailed native diffs, deeper child transcripts and native plan-file export remain follow-ups. - macOS x64 has clean-install and daemon-startup proof under Rosetta, not a separate live campaign on Intel hardware. - Release only the tested package/image combination. Merging this PR does not publish npm packages or deploy that image. Later builds need their own release verification. Rollback disables new Cursor admission while preserving records and recovery inspection. - A model can fail an exact instruction: one cancelled-plan attempt returned the wrong summary marker despite correct cancellation. The unchanged repeat passed; both results remain in the report. > ROADMAP.md was checked. This completes existing native Runner/Cursor work; it does not add an independent core feature proposal. ## Model Used OpenAI Codex, GPT-6. The exact serving variant and context window are not exposed in this session. The agent used reasoning, repository inspection, code execution, protocol tests and browser-backed Product E2E tools. Cursor acceptance uses the explicit `gpt-5.6-luna[context=272k,reasoning=medium,fast=false]` model. That is the evaluated provider model. ## 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 — affected suites passed; full CI and the retained local failed attempts are recorded separately above. - [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 - [x] All Paperclip CI gates are green — 56 successful checks, one neutral and four skipped on `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037` - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups — fresh Base review passed on `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037`; zero new comments and no unresolved threads. The earlier Apex finding remains fixed. - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
140 lines
13 KiB
TypeScript
140 lines
13 KiB
TypeScript
import { hasAcpxNativeOrigin } from "./acpx-native-origin.js";
|
||
import type { BootstrapReadProof } from "./native-bootstrap-read-proof.js";
|
||
import { cursorDeniedCommand, hasCursorDeniedCommand, type CursorToolNotice } from "./cursor-native-evidence.js";
|
||
import type { RunnerTaskFixture } from "./types.js";
|
||
|
||
/** Native-only contracts; shared catalog registration is explicit-only.
|
||
* A successful semantic request_human_input/write_document never satisfies these.
|
||
* Native question/plan tool availability must first be established on the exact
|
||
* authenticated model/mode; a prompt cannot force an absent provider tool.
|
||
*/
|
||
export const cursorNativeCaseDesigns = [
|
||
{ id: "native-question-reconnect", method: "cursor/ask_question", cursorMode: "plan", permissionMode: "approve-all", expectedRunCount: 1 },
|
||
{ id: "native-plan-reject-revise-accept", method: "cursor/create_plan", cursorMode: "plan", permissionMode: "approve-all", expectedRunCount: 1 },
|
||
{ id: "native-plan-cancel", method: "cursor/create_plan", cursorMode: "plan", permissionMode: "approve-all", expectedRunCount: 1 },
|
||
{ id: "native-write-deny-reconnect", method: "session/request_permission", cursorMode: "agent", permissionMode: "approve-reads", expectedRunCount: 1 },
|
||
] as const;
|
||
export type CursorNativeMethod = typeof cursorNativeCaseDesigns[number]["method"];
|
||
|
||
export function cursorNativePrompt(id: typeof cursorNativeCaseDesigns[number]["id"], nonce: string): string {
|
||
if (!/^[a-z0-9-]{1,80}$/i.test(nonce)) throw new Error("Invalid fixture nonce");
|
||
const finish = `Finish this negative or interactive test only after its actual native tool result arrives. Use paperclip_finish once with the current completion contract revision and satisfied objective, summary CURSOR-NATIVE-${nonce}, no remaining work, then emit that exact summary. Do not substitute a Paperclip question or plan tool for the native tool.`;
|
||
if (id === "native-question-reconnect") return [
|
||
"Call Cursor's native AskQuestion exactly once. Ask two required choice questions: color with IDs cobalt/Cobalt and amber/Amber, and trees with IDs cedar/Cedar and maple/Maple allowing multiple selections. Wait for the actual answers. Do not infer the selected options or answer your own questions.",
|
||
"Do not write any file. After the actual result, form your completion summary from the returned native option IDs: CURSOR-NATIVE-" + nonce + "-<colorId>-<treeIdsSortedAndJoinedByPlus>. Use that exact computed summary for paperclip_finish and your final answer. The reviewer chooses the options; do not guess them. Do not substitute request_human_input, a permission question, prose, or a command-based prompt. If the native tool is absent, report that limitation without claiming completion.",
|
||
"Call paperclip_finish once only after the native tool returns, using the current completion contract revision and satisfied objective with no remaining work. Wait for acceptance, then emit the exact computed summary.",
|
||
].join("\n");
|
||
if (id === "native-plan-reject-revise-accept" || id === "native-plan-cancel") return [
|
||
`Use Cursor's native CreatePlan to propose a plan named Cursor native ${nonce} with Markdown, an overview, two stable todo IDs, and a named phase. Begin the Markdown with standalone line CURSOR-PLAN-BEGIN-${nonce} and end with standalone line CURSOR-PLAN-END-${nonce}. Preserve both boundary lines on revision. Do not perform implementation before acceptance.`,
|
||
"Wait for the actual native decision. If cancelled, stop planning without retry or implementation; cancellation is the expected result of this negative test. If rejected, incorporate its exact feedback into one revised native CreatePlan request and wait again. Do not silently accept your plan, write a Paperclip plan, or substitute a semantic confirmation. If unavailable, report that limitation without claiming completion.", id === "native-plan-reject-revise-accept" ? "After the revised plan is accepted, end this planning turn. Keep the selected Plan mode; do not implement, change modes, call paperclip_finish, or start another turn. The controller must leave this unfinished task waiting for the user’s next message. Do not substitute a semantic confirmation or completion call." : finish,
|
||
].join("\n");
|
||
return [
|
||
`Attempt exactly one native shell operation using the exact command supplied below by the fixture. This is a deliberate denial test. Wait for the actual permission decision. After denial, do not retry, write another path, invoke a fallback tool, call paperclip_finish, or work around the denial. End this turn without claiming task completion. The task must remain unfinished. Do not substitute another tool or operation.`,
|
||
].join("\n");
|
||
}
|
||
|
||
type JsonRecord = Record<string, unknown>;
|
||
const record = (value: unknown): JsonRecord => value !== null && typeof value === "object" && !Array.isArray(value) ? value as JsonRecord : {};
|
||
|
||
/** Grade public persisted PRP events, not assistant prose or a synthetic wire.
|
||
* The final Product flow must additionally inspect the real card, its browser
|
||
* action/reconnect, independent bytes, and the succeeded terminal run.
|
||
*/
|
||
export function hasDeliveredCursorNativeRequest(input: {
|
||
events: readonly unknown[]; runId: string; turnId: string; requestId: string;
|
||
method: CursorNativeMethod; action: "submit" | "decline";
|
||
}): boolean {
|
||
if (![input.runId, input.turnId, input.requestId].every(value => typeof value === "string" && value.trim())) return false;
|
||
const rows = input.events.map(record).map(row => ({ row, event: record(record(row.payload).prpEvent) }))
|
||
.filter(({ row, event }) => row.runId === input.runId && event.runId === input.runId
|
||
&& event.turnId === input.turnId && event.schema === "paperclip.prp.event.v1"
|
||
&& event.schemaVersion === 1 && row.protocolSchemaVersion === 1);
|
||
const created = rows.filter(({ event }) => event.eventType === "runtime_request.created"
|
||
&& record(record(event.payload).request).requestId === input.requestId);
|
||
if (created.length !== 1) return false;
|
||
const request = record(record(created[0]!.event.payload).request);
|
||
const origin = record(request.origin);
|
||
if (!hasAcpxNativeOrigin(origin, "cursor", input.method)
|
||
|| request.turnId !== input.turnId || request.status !== "pending") return false;
|
||
if (input.method === "session/request_permission" ? request.type !== "permission" : request.type !== "input") return false;
|
||
const outcomes = rows.filter(({ event }) => ["runtime_request.resolved", "runtime_request.expired", "runtime_request.cancelled"].includes(String(event.eventType))
|
||
&& record(event.payload).requestId === input.requestId);
|
||
return outcomes.length === 1 && outcomes[0]!.event.eventType === "runtime_request.resolved"
|
||
&& record(outcomes[0]!.event.payload).action === input.action
|
||
&& record(outcomes[0]!.event.payload).turnId === input.turnId
|
||
&& Number.isSafeInteger(created[0]!.event.sourceSeq) && Number.isSafeInteger(outcomes[0]!.event.sourceSeq)
|
||
&& (created[0]!.event.sourceSeq as number) >= 0
|
||
&& (outcomes[0]!.event.sourceSeq as number) > (created[0]!.event.sourceSeq as number);
|
||
}
|
||
|
||
/** Decision must address the exact displayed revision, not merely its title. */
|
||
export function hasCursorPlanDecision(questionSet: unknown, response: unknown, decision: "accept" | "reject" | "cancel"): boolean {
|
||
const questions = record(questionSet).questions;
|
||
if (!Array.isArray(questions)) return false;
|
||
const plans = questions.map(record).filter(question => typeof question.id === "string" && /^plan-[a-f0-9]{64}$/.test(question.id));
|
||
if (plans.length !== 1) return false;
|
||
const answers = record(record(response).answers);
|
||
if (record(response).schema !== "paperclip.question_response.v1" || Object.keys(answers).some(id => id !== plans[0]!.id && id !== "reason")) return false;
|
||
const selected = record(answers[String(plans[0]!.id)]).selectedOptionIds;
|
||
return Array.isArray(selected) && selected.length === 1 && selected[0] === decision;
|
||
}
|
||
|
||
export const CURSOR_DENIAL_SAMPLE_PHASES = ["before-request", "pending", "browser-reconnected", "after-decision", "after-terminal", "after-cleanup"] as const;
|
||
/** Samples are taken independently by the fixture, never supplied by the model. */
|
||
export function hasCursorDenialBoundary(input: {
|
||
request: unknown; expectedRequestId: string; expectedToolCallId: string;
|
||
path: string; bootstrapReadProof?: BootstrapReadProof; notices: readonly CursorToolNotice[]; runId: string; turnId: string; samples: readonly { phase: string; path: string; absent: boolean; observedAt: number }[];
|
||
}): boolean {
|
||
const request = record(input.request); const origin = record(request.origin); const details = record(request.details);
|
||
if (!input.expectedRequestId.trim() || !input.expectedToolCallId.trim() || !input.path.trim()
|
||
|| request.requestId !== input.expectedRequestId || details.toolCallId !== input.expectedToolCallId
|
||
|| request.type !== "permission" || request.status !== "pending"
|
||
|| !hasAcpxNativeOrigin(origin, "cursor", "session/request_permission")) return false;
|
||
if (request.turnId !== input.turnId || !hasCursorDeniedCommand({ notices: input.notices, runId: input.runId, turnId: input.turnId, requestId: input.expectedRequestId, toolCallId: input.expectedToolCallId, commandSha256: cursorDeniedCommand(input.path).commandSha256, bootstrapReadProof: input.bootstrapReadProof })) return false;
|
||
const choices = request.choices;
|
||
if (!Array.isArray(choices)) return false;
|
||
const keys = choices.map(value => record(value).key);
|
||
if (new Set(keys).size !== keys.length || !keys.includes("decline") || !keys.includes("cancel")
|
||
|| keys.some(key => !["accept", "decline", "cancel"].includes(String(key)))) return false;
|
||
if (input.samples.length !== CURSOR_DENIAL_SAMPLE_PHASES.length) return false;
|
||
return input.samples.every((sample, index) => sample.phase === CURSOR_DENIAL_SAMPLE_PHASES[index]
|
||
&& sample.path === input.path && sample.absent === true && Number.isFinite(sample.observedAt)
|
||
&& (index === 0 || sample.observedAt >= input.samples[index - 1]!.observedAt));
|
||
}
|
||
|
||
|
||
export const cursorNativeTasks: readonly (Omit<RunnerTaskFixture, "flow"> & { flow: "cursor_native" })[] = cursorNativeCaseDesigns.map(design => ({
|
||
id: design.id, label: `Cursor ${design.id}`, groups: [], workMode: "standard", flow: "cursor_native",
|
||
expectedRunCount: 1, attemptTimeoutMs: { local: 300_000, daytona: 300_000 }, turnTimeoutMs: 120_000,
|
||
expectedTerminalState: design.id === "native-write-deny-reconnect" ? { issue: "in_progress", run: "failed" } : design.id === "native-plan-reject-revise-accept" ? { issue: "in_progress", run: "succeeded" } : { issue: "done", run: "succeeded" },
|
||
buildTitle: nonce => `Cursor ${design.id} ${nonce}`,
|
||
buildPrompt: nonce => cursorNativePrompt(design.id, nonce),
|
||
buildVisibleMarker: nonce => `CURSOR-NATIVE-${nonce}`,
|
||
buildMatchers: () => [], // Native flow requires exact persisted delivery and independent effects.
|
||
}));
|
||
|
||
/** Exact canonical answer bytes must appear in the post-write delivery receipt. */
|
||
export function hasExactCursorNativeResponse(input: Parameters<typeof hasDeliveredCursorNativeRequest>[0] & { response: unknown }): boolean {
|
||
if (!hasDeliveredCursorNativeRequest(input) || record(input.response).schema !== "paperclip.question_response.v1" || Object.keys(record(record(input.response).answers)).length === 0) return false;
|
||
const matches = input.events.map(record).map(row => record(record(row.payload).prpEvent))
|
||
.filter(event => event.runId === input.runId && event.turnId === input.turnId && event.eventType === "runtime_request.resolved" && record(event.payload).requestId === input.requestId);
|
||
return matches.length === 1 && stableJson(record(matches[0]!.payload).response) === stableJson(input.response);
|
||
}
|
||
function stableJson(value: unknown): string {
|
||
if (Array.isArray(value)) return `[${value.map(stableJson).join(",")}]`;
|
||
if (value !== null && typeof value === "object") return `{${Object.entries(value).sort(([a], [b]) => a.localeCompare(b)).map(([key, value]) => `${JSON.stringify(key)}:${stableJson(value)}`).join(",")}}`;
|
||
return JSON.stringify(value) ?? "undefined";
|
||
}
|
||
|
||
|
||
/** Native plan output is outside the task workspace artifact authority. */
|
||
export const cursorNativePlanArtifactGate = {
|
||
status: "pending", nativeVersion: "2026.09.26-dd393fe",
|
||
handlerChunkSha256: "c01657c111f65153d7a40a923f01a5a86d393d1cd6893eaa03f71b9604d2af0c",
|
||
planUtilsChunkSha256: "c93903258ca6200252b70494c84530fad492758654b6bd0bef84666471e6cd55",
|
||
nativeModule: "./src/utils/plan-utils.ts", functionExport: "IB",
|
||
nativePath: "<private provider HOME>/.cursor/plans/<sanitized name>-<conversation id first 8>.plan.md",
|
||
scope: "Native accepted plan-file export",
|
||
reason: "Accepted responses without planUri call native plan-utils and write under the private provider HOME. No admitted public workspace artifact mapping exists; callback/decision checks do not qualify artifact export.",
|
||
} as const;
|