mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-08 01:57:31 +01:00
## Thinking Path > - Paperclip manages AI agents and their work. > - The experimental Runner owns provider processes and durable sessions. > - Pi needs working task execution and human controls. > - The five-PR stack must preserve changes already on master. > - Each layer now carries the complete integrated source for a safe sequential fallback. > - This PR belongs to native GitHub stack #15602, ending at #14956. ## Linked Issues or Issue Description Refs #14436, #14631, #14743 and #14956. Ship Pi 1.0 through the experimental Paperclip Runner. The five PRs are #14921, #14922, #14923, #14924 and #14956. The user authorized the complete merge after checks pass. Existing `pi_local` execution is unchanged. Accounting and wider provider/platform qualification remain deferred. ## What Changed - Recover missing final replies after workspace finalization changes owners, using accepted-turn evidence without rerunning work or granting external-chat publication. - Preserve the admitted Pi instruction root across warm runs, while retaining changed-root rejection. - Give Pi a bounded 15-second default shutdown grace so stop, drain acknowledgement and durable suspension can complete. Explicit deadlines and other providers retain their existing behavior. - Integrate the Pi 1.0 runtime and master contracts. - Use Pi profile 22. Preserve explicit caller-selected models and exact native thinking levels. Keep Pi's wrapper, helper, extension and question/control behavior unchanged from the qualified profile-19 runtime. - Preserve master's Dot lifecycle and consent fields, configured task environment, status guards and current Codex/Claude dependency versions. Cursor stays qualified. Copilot stays pending; profile 17 binds the changed shared protocol validation sources. - Exclude general AWS IAM credentials from Pi static/custom provider bindings and selected task projections; preserve the provider-scoped Bedrock bearer key. Profile 21 is retained as historical provenance. Rust and cloud install probes use the current declaration. - Patch bundled brace-expansion 5.0.9 to the exact official 5.0.12 payload. Pin the patch and complete runtime closures. Include the patch in normal installed setup tooling. Keep the upstream Pi shrinkwrap as provenance and permit only this exact security correction. - Include current attestation files in the Docker build context. Keep the repository lockfile unchanged from master. CI and private image builds resolve manifest changes before their frozen installation. ## Verification - Full local `pnpm -r typecheck` passes, including Runner Rust, server and UI. Focused integration checks pass: 194 Runner admission/environment tests, 63 profile/credential tests with one expected skip, 152 Dot/UI configuration tests, and Pi transcript/notice tests. - Full local `pnpm build` passes on the final source. - Fresh final-source checks pass: all 698 Rust workspace tests (32 binaries), 156 credential/profile/controller tests with one expected skip, Runner TypeScript typecheck, and 20 package/setup/sandbox tests. - The profile-21 Pi materializer passes on the native host with the official pinned Node 24.21.0 and its npm. It verifies all 150 locked packages, the patched dependency and the exact closure. Setup/package bundle tests and UI token gates pass. - The old hashes were reproduced for all three supported targets before calculating the patched graph. New closure hashes are darwin-arm64 `282022db10150c6632b3444df421342e7d534bdf5d5fb1097a2e79d0625a2bcf`, darwin-x64 `64e251e19009f755c0b04f73ce2138246faab71a961b0f13d75ebfcc34bef12e`, and linux-x64 `713b1fdff42fb56a1518bdc084f181d70bee8ebadc3e4b1d76321ed9108c8410`. Independent native platform execution is separate from graph identity reproduction. - Historical cloud qualification remains unchanged: all seven core cases pass on shipping source `10dc43c9ec65d88c2f782d62afb296d09494f215`, harness `1a4408a48cfb5a1f094a311141c257c92cd7a893`, image `sha256:5b3a775b383591bda1b0c1889e509acc70ce7f37c53f09733c81d59037f02280`, and accepted Sonnet 4.6/low fixture. All 215 canonical files and all seven cleanup checks pass independent verification. These are profile-19 results and are not relabeled as fresh profile-22 runs. - Current Pi digest: `sha256:e92078bee3c23bec4100aa589013a44613d054cd686826534025d8019e9f39a9`. [The readiness plan](https://github.com/paperclipai/paperclip/blob/codex/pi-production-readiness/doc/plans/2026-10-02-pi-production-readiness.md) preserves campaign and failed-attempt provenance. - Merge only after every PR's current-head CI and fresh review pass. Linux CI covers the full suites, build and browser tests. The local embedded Postgres API-authority suite cannot start on this macOS/Node 26 host, so Linux CI must confirm that suite. ### Fresh profile-22 core qualification — 2026-10-08 All seven accepted core cases pass canonically on Pi profile 22, with `openrouter/anthropic/claude-sonnet-4.6` and native-confirmed low thinking. This model is a fixture; production accepts the caller's explicit Pi provider/model. Runtime/install source: `3241a992f2a7703e59e97ed0fd3e5d6405de4401`. Frozen accepted harness: `1a4408a48cfb5a1f094a311141c257c92cd7a893`. Immutable cloud image: `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:506f22db7edd78f37c0c40bec1cc084af1850455026dbf467194bfbb8fcef141`. Pi digest: `sha256:e92078bee3c23bec4100aa589013a44613d054cd686826534025d8019e9f39a9`. [Hosted Linux image and clean-install verification](https://github.com/paperclipai/paperclip/actions/runs/37868328023) passes, including all 20 source-bound archives, normal CLI/Pi setup, companion import and the production pack reader. This exact installation source includes the latest master integration and the corrected Pi warm instruction-root fence. Full local typecheck/build and current-head hosted CI verify the final stack. All 13 focused real-root regressions pass. The full local executor suite passed 662 tests; 15 database tests could not start the Mac embedded PostgreSQL service. Hosted Linux CI passes the full required verification and E2E checks. These fresh results keep their own source identity; profile-19 results remain historical. | Core path | Canonical campaign | Retained archive SHA-256 | | --- | --- | --- | | File edit, validation, download and Done | `pi-core22-replyfix-0-1791511228` | 23 files; `a473e8603a3dd4737863291f8d3d1e392391f0b16d433c3e0e0e9d8baf7a97b0` | | Pending question and controller restart | `pi-core22-replyfix-1-1791511376` | 33 files; `6b829c4eb74e1f32a89c692a4ae7130dbfc1c6d3cf13915effe2103d9e242c8e` | | Three-turn session/process/workspace continuity | `pi-core22-replyfix-2-1791511587` | 23 files; `7a87021f8f9a3fdd3c58bb4467f8d82c635e3ea4795d6e75f144d9aa14818df8` | | Four typed questions and browser reconnects | `pi-core22-replyfix-3-1791511881` | 42 files; `9e31755252be1f4f9cb0626c984c142d4d1ae5f5bee3a7af08444db8d12c280a` | | Plan approval and completion | `pi-core22-replyfix-4-1791512031` | 22 files; `a0383ce1aab38e7b5a25ce0e9dd3bebea5c037ebd96ae6b29dae19015da2ae2c` | | Same-turn steering and permission denial | `pi-core22-replyfix-5-1791512261` | 39 files; `c929b8c7070f0b66aedc17e65ca46e6beab1e363926ac9f7e2a75fb250f05949` | | Stop during pending permission | `pi-core22-replyfix-6-1791512390` | 33 files; `7f0a58ae0f4d5bfc76149435f4e322537089c5bd16e7ffe9b5ad71f10a621a07` | All 215 canonical files (28714587 bytes) are independently hash-verified. All seven cleanup grades pass, with no owned runtime process or temporary root after each case. Automatic retries are zero. The owned cloud host stopped normally after retention. The prior profile-22 warm attempt remains failed and separately retained: archive SHA-256 `1e54eba5ec72b50cee1534b23d1d1d4f21a090006b8a64501ba70db972abfde5`. Its original canonical classification is preserved. Diagnosis reproduced a product bug comparing an agent-files root against an unset checkpoint-only field. The fix stores the admitted physical root separately from the adopted per-run collection capability. The real-root regression fails before the fix and passes afterward, including rejection of a changed physical root. Fixture, grader, model and all seven accepted case IDs are unchanged; this fresh campaign tests final-reply publication after file registration first. The intermediate restart attempt also remains failed and retained: archive SHA-256 `5dcaefdf1d17cf4cd54fd4cf810f45e736667392339b8ce7caf08bb4e225277f`. Its original canonical classification is preserved. Pi resumed, wrote the verified answer and completed its task; exact runner suspension was proven, but idle stop consumed about 5.2s and left under 3s for the drain acknowledgement. The Pi-only default shutdown grace is now 15s, preserving a full 5s drain round trip and a finite suspension reserve. Explicit caller deadlines, other provider defaults, literal drain receipts and exact suspension identity checks remain unchanged. The timing regression fails before this correction and passes afterward; all 18 focused settlement tests and Runner typecheck pass. The final-source file attempt is also preserved as failed (`candidate_failure`), archive SHA-256 `db6767b6773ea618997927ac77bdb005a5ac81492c7b9c0ffbc900449f829bc9`. Native edit, validation, exact downloadable artifact and Done/succeeded all passed, and the exact final reply was durably recorded. A workspace recovery owner completed before the live heartbeat reached presentation, leaving that reply absent from task chat. Recovery now materializes only a completed final reply from the accepted turn of an ordinary internal Done task, preserving issue/run/contract binding, suppression, external-chat authorization and same-run deduplication. The database regression covers the generated file-preparation receipt, suppression, unapproved external continuation and replay. Server typecheck and all 49 response-selection tests pass; hosted Linux verifies the database regression because embedded PostgreSQL cannot start on this Mac. The delayed-final-answer database regression passes on [the final root-source Linux server shard](https://github.com/paperclipai/paperclip/actions/runs/37868262553/job/113628594152), alongside 1,108 passing tests. The first root Runner shard had one unchanged durable-resume test exceed its 5-second timeout; the identical top-source shard and the isolated exact test passed. One rerun of that failed job and its required aggregate passed without source or test changes. The original failed job log and the single-rerun receipt remain retained. ### October 9 merge verification Current merge head: `5a8fe63512a7166aaef5cf50065a25008aa8b44b`. All current-head checks pass, including `ci / verify` and `ci / e2e`; exact-head Greptile review is 5/5 with no unresolved threads. Current master conflicts are resolved. The user authorized the maintainer override of the code-owner review gate after these checks. The seven retained live core cases remain bound to source `3241a992f2a7703e59e97ed0fd3e5d6405de4401` and its recorded cloud image. ## Risks - The security correction changes the dependency closure and profile identity. Old sessions must reopen on the new profile. Exact identities and credential bindings fail closed. - The runner remains experimental and requires explicit selection. Legacy Pi Local is unchanged. Caller model IDs pass through; the E2E model is a fixture. - Accounting and the broad platform/provider matrix remain deferred. This merge does not publish a release or deploy a service. ## Model Used OpenAI GPT-6 through Codex assisted with reasoning, repository inspection, editing and tool use. The exact serving ID and context window are not exposed in this session. Final live qualification uses Pi 1.0.0 with `openrouter/anthropic/claude-sonnet-4.6` and native-confirmed low thinking. ## 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 #` 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 - [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 - [x] 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>
375 lines
27 KiB
JavaScript
375 lines
27 KiB
JavaScript
import assert from "node:assert/strict";
|
|
import { spawn } from "node:child_process";
|
|
import { once } from "node:events";
|
|
import { mkdtemp, mkdir, readFile, realpath, rm, writeFile } from "node:fs/promises";
|
|
import { createRequire, stripTypeScriptTypes } from "node:module";
|
|
import { tmpdir } from "node:os";
|
|
import { dirname, join, resolve } from "node:path";
|
|
import { StringDecoder } from "node:string_decoder";
|
|
import test from "node:test";
|
|
import { fileURLToPath } from "node:url";
|
|
|
|
// Optional test-only package location permits the isolated Pi branch to test
|
|
// before the integration owner updates package.json and the shared lockfile.
|
|
const packageJson = process.env.PAPERCLIP_TEST_PI_ACP_PACKAGE
|
|
?? createRequire(import.meta.url).resolve("pi-acp/package.json");
|
|
const packageRoot = dirname(packageJson);
|
|
const packageMetadata = JSON.parse(await readFile(packageJson, "utf8"));
|
|
const packageSource = await readFile(join(packageRoot, "dist/index.js"), "utf8");
|
|
const helperSource = await readFile(join(packageRoot, "dist/paperclip-runtime.js"), "utf8");
|
|
const localHelper = await readFile(new URL("../src/drivers/acpx/pi-acp-runtime.ts", import.meta.url), "utf8");
|
|
const normalize = (source) => source.split("\n").map((line) => line.trimEnd()).join("\n");
|
|
|
|
test("Pi patch embeds the reviewed helper and pins exact upstream version", () => {
|
|
assert.equal(packageMetadata.version, "0.0.33");
|
|
assert.equal(normalize(helperSource), normalize(stripTypeScriptTypes(localHelper)));
|
|
assert.match(packageSource, /createPiLaunchSpec\(params, process\.env\)/);
|
|
assert.match(packageSource, /shell: false/);
|
|
assert.match(packageSource, /snapshotPiWorkspaceFile\(this\.cwd, abs\)/);
|
|
});
|
|
|
|
async function fixture(t, extra = {}) {
|
|
const root = await realpath(await mkdtemp(join(tmpdir(), "paperclip-pi-acp-contract-")));
|
|
await mkdir(join(root, "workspace")); await mkdir(join(root, "agent"));
|
|
await writeFile(join(root, "extension.js"), "export default function() {}\n");
|
|
const fakePi = fileURLToPath(new URL("../test-fixtures/pi-acp/fake-pi.mjs", import.meta.url));
|
|
const child = spawn(process.execPath, [join(packageRoot, "dist/index.js")], {
|
|
cwd: join(root, "workspace"), stdio: "pipe",
|
|
env: {
|
|
PATH: process.env.PATH, HOME: root, PI_CODING_AGENT_DIR: join(root, "agent"),
|
|
PAPERCLIP_ACPX_ISOLATED_CONTEXT: "1", PAPERCLIP_PI_READ_ONLY: "0",
|
|
PAPERCLIP_PI_NODE_EXECUTABLE: await realpath(process.execPath),
|
|
PAPERCLIP_PI_ENTRYPOINT: fakePi, PAPERCLIP_PI_EXTENSION_PATH: join(root, "extension.js"),
|
|
...extra,
|
|
},
|
|
});
|
|
let stderr = ""; child.stderr.on("data", (chunk) => { stderr += chunk; });
|
|
const pending = new Map(); const notifications = []; const requests = [];
|
|
let id = 0; let answer = async (request) => request.method === "session/request_permission"
|
|
? { outcome: { outcome: "selected", optionId: "allow_once" } }
|
|
: { action: "accept", content: { answer: "Paperclip" } };
|
|
const send = (value) => child.stdin.write(JSON.stringify(value) + "\n");
|
|
const receive = (line) => {
|
|
const message = JSON.parse(line);
|
|
if (message.method && Object.hasOwn(message, "id")) {
|
|
requests.push(message);
|
|
void answer(message).then((result) => send({ jsonrpc: "2.0", id: message.id, result }));
|
|
} else if (Object.hasOwn(message, "id")) {
|
|
const waiter = pending.get(message.id); pending.delete(message.id);
|
|
if (message.error) waiter?.reject(new Error(JSON.stringify(message.error))); else waiter?.resolve(message.result);
|
|
} else notifications.push(message);
|
|
};
|
|
const decoder = new StringDecoder("utf8"); let buffered = "";
|
|
child.stdout.on("data", (chunk) => {
|
|
buffered += decoder.write(chunk);
|
|
for (;;) { const at = buffered.indexOf("\n"); if (at < 0) break; const line = buffered.slice(0, at); buffered = buffered.slice(at + 1); if (line.trim()) receive(line); }
|
|
});
|
|
child.once("exit", () => { for (const waiter of pending.values()) waiter.reject(new Error(`wrapper exited: ${stderr}`)); pending.clear(); });
|
|
const call = (method, params) => new Promise((resolve_, reject) => {
|
|
const requestId = ++id;
|
|
const timer = setTimeout(() => { pending.delete(requestId); reject(new Error(`timeout: ${method}: ${stderr}`)); }, 5000);
|
|
pending.set(requestId, { resolve: (value) => { clearTimeout(timer); resolve_(value); }, reject: (error) => { clearTimeout(timer); reject(error); } });
|
|
send({ jsonrpc: "2.0", id: requestId, method, params });
|
|
});
|
|
t.after(async () => {
|
|
child.stdin.end();
|
|
if (child.exitCode === null) { const timer = setTimeout(() => child.kill("SIGKILL"), 3000); await once(child, "exit"); clearTimeout(timer); }
|
|
await rm(root, { recursive: true, force: true });
|
|
});
|
|
const initialized = await call("initialize", { protocolVersion: 1, clientCapabilities: { elicitation: { form: {} } } });
|
|
return { call, notify(method, params) { send({ jsonrpc: "2.0", method, params }); }, initialized, root, notifications, requests, setAnswer(value) { answer = value; } };
|
|
}
|
|
|
|
test("actual patched ACP process streams thinking and waits for settlement with usage", async (t) => {
|
|
const f = await fixture(t);
|
|
assert.equal(f.initialized.agentCapabilities._meta.paperclipPi.steering, true);
|
|
assert.deepEqual(f.initialized.authMethods, []);
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const result = await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "hello" }] });
|
|
assert.equal(result.stopReason, "end_turn"); assert.equal(result.usage.inputTokens, 11); assert.equal(result.usage.totalTokens, 16);
|
|
assert.ok(f.notifications.some((event) => event.params?.update?.sessionUpdate === "agent_thought_chunk"));
|
|
assert.ok(f.notifications.some((event) => event.params?.update?.content?.text === "hello🌒\u2028world"));
|
|
});
|
|
|
|
for (const scenario of ["narration-final", "tool-only", "empty-final"]) test(`actual patched wrapper preserves native message provenance for ${scenario}`, async t => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
for (let warm = 0; warm < 2; warm++) {
|
|
const from = f.notifications.length;
|
|
await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: scenario }] });
|
|
const updates = f.notifications.slice(from).map(event => event.params?.update).filter(update => update?.sessionUpdate === "agent_message_chunk");
|
|
assert.ok(updates.every(update => /^pi-message-[a-f0-9]{64}$/.test(update.messageId)));
|
|
assert.equal(updates[0]._meta.kind, "start"); assert.equal(updates[0].content.text, "");
|
|
assert.equal(updates[1].content.text, "Calling finish.");
|
|
assert.equal(updates[2]._meta.kind, "end:toolUse");
|
|
if (scenario === "tool-only") assert.equal(updates.length, 3);
|
|
else {
|
|
assert.equal(updates[3]._meta.kind, "start"); assert.notEqual(updates[3].messageId, updates[0].messageId);
|
|
assert.equal(updates[4].content.text, scenario === "empty-final" ? "" : "EXACT_MARKER");
|
|
assert.equal(updates[5]._meta.kind, "end:stop");
|
|
}
|
|
}
|
|
});
|
|
|
|
for (const scenario of ["missing-message-start", "duplicate-message-start", "mismatched-message-end", "missing-message-end"]) test(`actual wrapper rejects malformed native boundaries: ${scenario}`, async t => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
await assert.rejects(f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: scenario }] }), /exited|Internal error/);
|
|
const failure = f.notifications.find(event => event.method === "paperclip/pi_notice" && event.params.category === "runtime_failure");
|
|
assert.ok(failure, "native failure notice is flushed before prompt rejection");
|
|
assert.ok(["rpc_delta_boundary_invalid", "assistant_boundary_invalid"].includes(failure.params.details.reason));
|
|
assert.equal(failure.params.severity, "error");
|
|
});
|
|
|
|
test("actual patched ACP process scopes recycled native IDs across iterations and warm prompts", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
for (let turn = 0; turn < 2; turn++) await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "reused-tool-ids" }] });
|
|
const updates = f.notifications.map(event => event.params?.update).filter(update => update?.toolCallId);
|
|
const starts = updates.filter(update => update.sessionUpdate === "tool_call");
|
|
assert.equal(starts.length, 6);
|
|
assert.equal(new Set(starts.map(update => update.toolCallId)).size, 6, "each model iteration has an independent tool identity");
|
|
for (const start of starts) {
|
|
assert.match(start.toolCallId, /^pi-[a-f0-9]{64}$/);
|
|
const lifecycle = updates.filter(update => update.toolCallId === start.toolCallId);
|
|
assert.ok(lifecycle.some(update => update.status === "in_progress"));
|
|
assert.equal(lifecycle.filter(update => ["failed", "completed"].includes(update.status)).length, 1);
|
|
assert.ok(lifecycle.every(update => update._meta.paperclipPi.nativeToolCallId === "call_0"));
|
|
}
|
|
assert.deepEqual(starts.map(update => update._meta.paperclipPi.modelIteration), [1, 2, 3, 5, 6, 7]);
|
|
});
|
|
|
|
test("cancellation closes the iteration before a warm prompt reuses native IDs", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const active = f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "long" }] });
|
|
// The acknowledged native control is a FIFO barrier proving prompt admission.
|
|
await f.call("pi/steer", { sessionId: session.sessionId, message: "fixture admission fence" });
|
|
f.notify("session/cancel", { sessionId: session.sessionId }); await active;
|
|
const warm = await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "reused-tool-ids" }] });
|
|
assert.equal(warm.stopReason, "end_turn");
|
|
const starts = f.notifications.map(event => event.params?.update).filter(update => update?.sessionUpdate === "tool_call");
|
|
assert.deepEqual(starts.map(update => update._meta.paperclipPi.modelIteration), [2, 3, 4]);
|
|
assert.equal(new Set(starts.map(update => update.toolCallId)).size, 3);
|
|
});
|
|
|
|
test("acknowledged native cancellation preserves partial usage and refuses service-failure metadata", async t => {
|
|
const f = await fixture(t, { PI_FIXTURE_CANCEL_ERROR: "1" });
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const active = f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "long" }] });
|
|
await f.call("pi/steer", { sessionId: session.sessionId, message: "fixture admission fence" });
|
|
f.notify("session/cancel", { sessionId: session.sessionId });
|
|
const result = await active;
|
|
assert.equal(result.stopReason, "cancelled");
|
|
assert.equal(result._meta, undefined);
|
|
assert.equal(result.usage.inputTokens, 11);
|
|
assert.equal(result.usage.outputTokens, 3);
|
|
assert.equal(result.usage.cachedReadTokens, undefined);
|
|
assert.equal(result.usage._meta.paperclipPi.costUsd, undefined);
|
|
});
|
|
|
|
test("warm load uses stable display-only history IDs distinct from live execution", async (t) => {
|
|
const f = await fixture(t, { PI_FIXTURE_HISTORY: "1" });
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const loads = [];
|
|
for (let load = 0; load < 2; load++) {
|
|
f.notifications.length = 0;
|
|
await f.call("session/load", { sessionId: session.sessionId, cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const starts = f.notifications.map(event => event.params?.update).filter(update => update?.sessionUpdate === "tool_call");
|
|
assert.equal(starts.length, 2);
|
|
const historicalMessage = f.notifications.map(event => event.params?.update).find(update => update?.content?.text === "Historical reply");
|
|
assert.match(historicalMessage.messageId, /^pi-history-message-[a-f0-9]{64}$/);
|
|
assert.deepEqual(historicalMessage._meta, { origin: "pi-history-assistant", source: "pi-session-history-v1", kind: "history" });
|
|
assert.notEqual(starts[0].toolCallId, starts[1].toolCallId);
|
|
for (const start of starts) {
|
|
assert.match(start.toolCallId, /^pi-history-[a-f0-9]{64}$/);
|
|
assert.equal(start._meta.paperclipPi.nativeToolCallId, "call_0");
|
|
assert.equal(start._meta.paperclipPi.identityScope, "history-display-only");
|
|
}
|
|
loads.push(starts.map(update => update.toolCallId));
|
|
}
|
|
assert.deepEqual(loads[0], loads[1]);
|
|
f.notifications.length = 0;
|
|
await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "reused-tool-ids" }] });
|
|
assert.ok(f.notifications.map(event => event.params?.update).filter(update => update?.toolCallId).every(update => /^pi-[a-f0-9]{64}$/.test(update.toolCallId)));
|
|
});
|
|
|
|
test("actual patched ACP process keeps text questions separate from native permissions", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "question" }] });
|
|
assert.equal(f.requests.length, 1); assert.notEqual(f.requests[0].method, "session/request_permission");
|
|
await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "permission" }] });
|
|
assert.equal(f.requests[1].method, "session/request_permission");
|
|
assert.equal(f.requests[1].params.options[1].kind, "allow_always");
|
|
});
|
|
|
|
for (const [method, answer, expected] of [["select", "Blue", { value: "Blue" }], ["confirm", false, { confirmed: false }], ["input", "Ada", { value: "Ada" }], ["editor", "New\ntext", { value: "New\ntext" }]]) {
|
|
test(`actual patched ACP ${method} question round-trips through form elicitation`, async t => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
f.setAnswer(async () => ({ action: "accept", content: { answer } }));
|
|
await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: `native-question-${method}` }] });
|
|
assert.equal(f.requests.length, 1); assert.notEqual(f.requests[0].method, "session/request_permission");
|
|
assert.equal(f.requests[0].params._meta.paperclipPi.method, method);
|
|
const response = f.notifications.map(event => event.params?.update?.content?.text).find(text => text?.includes('"extension_ui_response"'));
|
|
assert.deepEqual(JSON.parse(response), { type: "extension_ui_response", id: `native-${method}`, ...expected });
|
|
});
|
|
}
|
|
|
|
test("actual patched ACP reports unsupported external UI as an error and stops the session", async t => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
await assert.rejects(f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "oversized-question" }] }), /exited/);
|
|
assert.equal(f.requests.length, 0);
|
|
assert.ok(f.notifications.some(event => event.method === "paperclip/pi_notice" && event.params?.summary === "Pi structured question is unsupported or invalid; the session was stopped"));
|
|
});
|
|
|
|
test("native steering is explicit and does not replace the active ACP turn", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const prompt = f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "long" }] });
|
|
assert.equal((await f.call("pi/steer", { sessionId: session.sessionId, message: "focus" })).disposition, "queued");
|
|
assert.equal((await f.call("pi/follow_up", { sessionId: session.sessionId, message: "then finish" })).disposition, "queued");
|
|
assert.equal((await prompt).stopReason, "end_turn");
|
|
await assert.rejects(f.call("pi/steer", { sessionId: session.sessionId, message: "too late" }), /active turn/);
|
|
});
|
|
|
|
for (const disposition of ["handled", "started", "missing", "malformed"]) for (const method of ["pi/steer", "pi/follow_up"]) {
|
|
test(`${method} never claims delivery for Pi 1 disposition ${disposition}`, async (t) => {
|
|
const f = await fixture(t, { PI_FIXTURE_INPUT_DISPOSITION: disposition });
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const prompt = f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "long" }] });
|
|
await assert.rejects(f.call(method, { sessionId: session.sessionId, message: "not queued" }), /not queued by the native runtime/);
|
|
f.notify("session/cancel", { sessionId: session.sessionId });
|
|
await prompt;
|
|
});
|
|
}
|
|
|
|
test("provider exit fails promptly and missing owned extension fails admission", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
await assert.rejects(f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "die" }] }), /exited/);
|
|
const missing = await fixture(t, { PI_FIXTURE_EXTENSION_FAIL: "1" });
|
|
await assert.rejects(missing.call("session/new", { cwd: join(missing.root, "workspace"), mcpServers: [] }), /failed admission/);
|
|
});
|
|
|
|
test("provider failure is typed and unadmitted slash commands cannot bypass controls", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const result = await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "failure" }] });
|
|
assert.equal(result._meta.jetbrains.air.sessionFailure.severity, "error");
|
|
await assert.rejects(f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: "/export /outside/report.html" }] }), /not admitted/);
|
|
});
|
|
|
|
for (const [outcome, expected] of [
|
|
["success", "Retry finished, resuming."],
|
|
["failure", "Retry failed; the provider request did not recover."],
|
|
["unknown", "Retry finished; the provider did not report an outcome."],
|
|
]) {
|
|
test(`actual patched ACP retry ${outcome} reports only its stated outcome`, async (t) => {
|
|
const f = await fixture(t);
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const result = await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: `retry-${outcome}` }] });
|
|
const messages = f.notifications.filter(event => event.method === "paperclip/pi_notice").map(event => event.params.summary);
|
|
assert.ok(f.notifications.filter(event => event.params?.update?.sessionUpdate === "agent_message_chunk").every(event => !event.params.update.content.text.includes("Retry")));
|
|
assert.ok(messages.includes(expected));
|
|
if (outcome !== "success") assert.ok(messages.every((text) => !text.includes("resuming")));
|
|
if (outcome === "failure") assert.equal(result._meta.jetbrains.air.sessionFailure.severity, "error");
|
|
else assert.equal(result._meta?.jetbrains?.air?.sessionFailure, undefined);
|
|
});
|
|
}
|
|
|
|
test("manual and automatic compaction retain native progress and usage", async (t) => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const prompt = (text) => f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text }] });
|
|
const manual = await prompt("/compact");
|
|
assert.equal(manual.usage.inputTokens, 5); assert.equal(manual.usage.totalTokens, 8);
|
|
assert.equal(manual.usage._meta.paperclipPi.provenance, "assistant_message_and_compaction_receipts");
|
|
const automatic = await prompt("auto-compact");
|
|
assert.equal(automatic.usage.inputTokens, 16); assert.equal(automatic.usage.totalTokens, 24);
|
|
assert.equal(automatic.usage._meta.paperclipPi.costUsd, 0.03);
|
|
assert.ok(f.notifications.some((event) => event.method === "paperclip/pi_notice" && event.params?.summary === "Context compaction finished."));
|
|
const retried = await prompt("retry-compact");
|
|
assert.equal(retried.usage.inputTokens, undefined);
|
|
assert.equal(retried.usage._meta.paperclipPi.costUsd, undefined);
|
|
assert.ok(f.notifications.some((event) => event.method === "paperclip/pi_notice" && event.params?.summary === "Context summarization is retrying a provider request."));
|
|
const active = prompt("long"); await new Promise((resolve) => setTimeout(resolve, 25));
|
|
await assert.rejects(prompt("/compact"), /requires an idle session/);
|
|
f.notify("session/cancel", { sessionId: session.sessionId }); await active;
|
|
assert.match(packageSource, /this\.request\(\{ type: "compact", customInstructions \}, 120000\)/);
|
|
});
|
|
|
|
for (const outcome of ["success", "failure", "oversized"]) {
|
|
test(`actual patched ACP Bash ${outcome} retains standard structured tool data`, async (t) => {
|
|
const f = await fixture(t);
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const result = await f.call("session/prompt", { sessionId: session.sessionId, prompt: [{ type: "text", text: `bash-${outcome}` }] });
|
|
assert.equal(result.stopReason, "end_turn");
|
|
const updates = f.notifications.map((event) => event.params?.update).filter((update) => update?._meta?.paperclipPi?.nativeToolCallId === "bash-fixture");
|
|
assert.deepEqual(updates[0].rawInput, { command: outcome === "failure" ? "printf failure >&2; exit 7" : "printf done", timeout: 3 });
|
|
assert.deepEqual(updates[1].rawOutput, { content: [{ type: "text", text: "partial" }] });
|
|
const terminal = updates.at(-1);
|
|
assert.equal(terminal.status, outcome === "failure" ? "failed" : "completed");
|
|
if (outcome === "oversized") {
|
|
assert.equal(terminal.rawOutput._meta.paperclipPi.omitted, "tool value exceeds 65536 bytes");
|
|
assert.ok(terminal.rawOutput._meta.paperclipPi.originalBytes > 65536);
|
|
assert.ok(Buffer.byteLength(JSON.stringify(terminal.rawOutput)) < 256);
|
|
} else {
|
|
assert.deepEqual(terminal.rawOutput, { content: [{ type: "text", text: outcome === "failure" ? "failure\n" : "done\n" }], details: { exitCode: outcome === "failure" ? 7 : 0, truncated: false } });
|
|
}
|
|
// Preserve existing terminal consumers without inferring a canonical exit code.
|
|
assert.equal(terminal._meta.terminal_exit.exit_code, outcome === "failure" ? 7 : 0);
|
|
});
|
|
}
|
|
|
|
|
|
const thoughtOption = configuration => configuration.configOptions.find(option => option.id === "thought_level");
|
|
const assertedThinking = (configuration, current, levels = ["off", "low", "high", "max"]) => {
|
|
assert.equal(configuration.modes.currentModeId, current);
|
|
assert.deepEqual(configuration.modes.availableModes.map(mode => mode.id), levels);
|
|
assert.equal(thoughtOption(configuration).currentValue, current);
|
|
assert.deepEqual(thoughtOption(configuration).options.map(option => option.value), levels);
|
|
};
|
|
|
|
test("thinking modes use native capabilities and preserve effective max across warm load", async t => {
|
|
const f = await fixture(t);
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
assertedThinking(session, "off");
|
|
for (const level of ["high", "low", "max"]) {
|
|
const result = await f.call("session/set_config_option", { sessionId: session.sessionId, configId: "thought_level", value: level });
|
|
assert.equal(thoughtOption(result).currentValue, level);
|
|
assert.equal(f.notifications.filter(event => event.params?.update?.sessionUpdate === "current_mode_update").at(-1).params.update.currentModeId, level);
|
|
}
|
|
assertedThinking(await f.call("session/load", { sessionId: session.sessionId, cwd: join(f.root, "workspace"), mcpServers: [] }), "max");
|
|
await f.call("session/set_mode", { sessionId: session.sessionId, modeId: "off" });
|
|
assert.equal(f.notifications.filter(event => event.params?.update?.sessionUpdate === "current_mode_update").at(-1).params.update.currentModeId, "off");
|
|
});
|
|
|
|
test("unsupported thinking aliases are rejected before native mutation on both ACP routes", async t => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
for (const level of ["minimal", "medium", "xhigh", "unknown"]) {
|
|
await assert.rejects(f.call("session/set_mode", { sessionId: session.sessionId, modeId: level }), /Unsupported thinking level/);
|
|
await assert.rejects(f.call("session/set_config_option", { sessionId: session.sessionId, configId: "thought_level", value: level }), /Unsupported thinking level/);
|
|
}
|
|
await assert.rejects(readFile(join(f.root, "agent/thinking-calls.jsonl")), { code: "ENOENT" });
|
|
assertedThinking(await f.call("session/load", { sessionId: session.sessionId, cwd: join(f.root, "workspace"), mcpServers: [] }), "off");
|
|
});
|
|
|
|
test("model changes refresh supported modes and truthful effective state", async t => {
|
|
const f = await fixture(t); const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
await f.call("session/set_mode", { sessionId: session.sessionId, modeId: "low" });
|
|
const result = await f.call("session/set_config_option", { sessionId: session.sessionId, configId: "model", value: "openrouter/fixture-alternate" });
|
|
assert.equal(thoughtOption(result).currentValue, "high");
|
|
assert.deepEqual(thoughtOption(result).options.map(option => option.value), ["off", "high"]);
|
|
await assert.rejects(f.call("session/set_mode", { sessionId: session.sessionId, modeId: "low" }), /Unsupported thinking level/);
|
|
});
|
|
|
|
for (const method of ["session/set_mode", "session/set_config_option"]) test(`${method} rejects native silent clamping without a false success update`, async t => {
|
|
const f = await fixture(t, { PI_FIXTURE_THINKING_CLAMP: "1" });
|
|
const session = await f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] });
|
|
const from = f.notifications.length;
|
|
await assert.rejects(f.call(method, { sessionId: session.sessionId, ...(method === "session/set_mode" ? { modeId: "low" } : { configId: "thought_level", value: "low" }) }), /Internal error|did not apply/);
|
|
assert.ok(!f.notifications.slice(from).some(event => event.params?.update?.sessionUpdate === "current_mode_update"));
|
|
assert.deepEqual((await readFile(join(f.root, "agent/thinking-calls.jsonl"), "utf8")).trim().split("\n").map(JSON.parse), ["low"]);
|
|
});
|
|
|
|
for (const capability of ["failed", "duplicate", "unknown", "empty", "missing"]) test(`thinking admission rejects ${capability} native capabilities`, async t => {
|
|
const f = await fixture(t, { PI_FIXTURE_THINKING_CAPABILITIES: capability });
|
|
await assert.rejects(f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] }), /Internal error/);
|
|
});
|
|
for (const current of ["future", "medium"]) test(`thinking admission rejects unsupported effective state ${current}`, async t => {
|
|
const f = await fixture(t, { PI_FIXTURE_THINKING_CURRENT: current });
|
|
await assert.rejects(f.call("session/new", { cwd: join(f.root, "workspace"), mcpServers: [] }), /Internal error/);
|
|
});
|