mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-06 10:48:12 +02:00
## Thinking Path > - Paperclip runs agents through local adapters and the native runner. > - Both paths must use the same installed provider CLI. > - New models require current harness releases. > - The runner still pins Codex 0.153.4, Claude SDK 0.3.263, and OpenCode 1.18.29. > - Changing the image alone would fail the runner's exact version and executable checks. > - This pull request updates those dependencies, integrity checks, controller checks, and image pins together. > - Shared installations can then run the current models without a task-time download. ## Linked Issues or Issue Description Refs #13829, which updates model choices and reasoning controls. Searches found no open PR that updates these runtime pins. **Current behavior** The shared provider pack ships old CLIs. Claude Code 2.1.263 cannot run Opus 5.5, which requires 2.1.280. Remote controllers reject provider packs whose versions differ from their declared pins. **Proposed behavior** Use Codex 0.156.0, Claude Agent SDK 0.3.280 / Claude Code 2.1.280, and OpenCode 1.18.32 throughout the runner. Keep the reviewed ACP bridge patches and one shared CLI installation per provider. **Reason and benefit** Current harnesses support the new model IDs while preserving executable verification and remote provider-pack compatibility checks. ## What Changed - Update dependency overrides, the Codex ACP package patch, runtime profiles, and remote controller pins. - Verify the new Claude Linux x64 and macOS arm64/x64 executables and Codex Linux x64 executable against integrity-verified npm archives. - Refresh OpenCode version checks, fixtures, and the runner configuration label. - Refresh the eval image's Grok, Gemini, Kimi, Cursor, and GitHub CLI pins and archive hashes. Hermes remains current at 0.19.0. - Refresh the build-time lock digest from clean pnpm 9.15.4 resolution. Leave lockfile commits to repository automation. - Document model compatibility and the separation between CLI runtimes and patched ACP bridges. ## Verification - `pnpm -r typecheck` and `pnpm build` passed. - Rust workspace release tests passed. - Package/patch and OpenCode binary-materialization contract tests: 11 passed. - Real Codex 0.156.0 startup-ownership and paginated session-resume probes passed with isolated synthetic homes and no model turn. - Codex app-server `thread/start` preserved `gpt-6-sol` and `gpt-6-luna`; no `turn/start` was sent. An unauthenticated built-in catalog does not include those account-served entries. - Installed Claude integrity probes passed for `claude-opus-5-5` and `claude-fable-5-1`. - `pnpm --filter @paperclipai/paperclip-runner test:opencode:qualification` passed with the actual OpenCode 1.18.32 executable under Node 24 and Node 25. The loopback provider exercise covers health/version, session creation/read/delete, SSE, and a completed async prompt. - `pnpm check:token-gates` passed. - The targeted runner suite passed 130 tests. Three macOS failures in snapshot module lookup and OpenCode final-message selection also reproduce on the unchanged base; Linux CI will provide the platform check. - [Final Linux CI](https://github.com/paperclipai/paperclip/actions/runs/35798076399): all gates passed. Four jobs needed one retry after their CI workers received shutdown signals. The PR has 55 successful checks, two skipped checks, Greptile 5/5, and no unresolved review threads. - Changed runner configuration UI tests: 5 passed. - Full macOS `pnpm test:run` reached 13,094 passing server tests, 84 skipped, and 18 failures before the wrapper stopped. Failures involved skill-cache publication permissions, missing bundled connector skills in the worktree, and a conversation-reset timing case. The 10 cache permission failures reproduce on the unchanged base; both conversation-reset cases passed on a targeted retry. The wrapper did not reach its later workspace/serialized groups locally; Linux CI covers those groups. - The local Docker daemon did not respond, so no local Docker build was run. No billable model requests were made. ## Risks - Deploy the matching controller and provider pack together. Older controllers enforce their previous exact pins. - Current upstream CLIs can change behavior. Existing protocol tests and isolated real Codex probes cover the integration boundaries; authenticated model inference is not part of these checks. - ACP bridge package versions and executable digests stay unchanged because their executable bytes are unchanged. Only the underlying CLI/SDK dependencies move. - No schema migration. Revert the runtime and image pins together to roll back. ## Model Used OpenAI GPT-6 via Codex, with repository tools, code execution, and web research. The exact serving model ID and context window were not exposed by this session. ## 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 for the changed surfaces and real-executable probes; full macOS-suite limitations are listed 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 - [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>
273 lines
8.2 KiB
JavaScript
273 lines
8.2 KiB
JavaScript
// Opt-in real Codex qualification; no model turn or live account data.
|
|
// Run from the repository root:
|
|
// node --import ./server/node_modules/tsx/dist/loader.mjs scripts/tests/native-cleanup-paginated-codex.mjs
|
|
// PAPERCLIP_TEST_CODEX_BINARY may select the exact installed Codex 0.156.0 binary.
|
|
// Fresh synthetic fixture directories are retained for inspection; never reuse live homes.
|
|
import { spawn, execFileSync } from "node:child_process";
|
|
import {
|
|
mkdtemp,
|
|
readdir,
|
|
mkdir,
|
|
writeFile,
|
|
rename,
|
|
cp,
|
|
readFile,
|
|
readlink,
|
|
realpath,
|
|
} from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import { join, dirname, relative, isAbsolute } from "node:path";
|
|
import { createInterface } from "node:readline";
|
|
import { createHash } from "node:crypto";
|
|
import { rebaseRetainedNativeCleanupProviderHome } from "../../server/src/services/native-runtime/native-session-executor.ts";
|
|
|
|
const codexBinary = process.env.PAPERCLIP_TEST_CODEX_BINARY ?? "codex";
|
|
if (
|
|
execFileSync(codexBinary, ["--version"], {
|
|
encoding: "utf8",
|
|
timeout: 10000,
|
|
}).trim() !== "codex-cli 0.156.0"
|
|
) {
|
|
throw new Error(
|
|
"This opt-in qualification requires Codex CLI 0.156.0. Requalify deliberately before changing the pin.",
|
|
);
|
|
}
|
|
const home = await mkdtemp(join(tmpdir(), "paperclip-paginated-probe-"));
|
|
const methods = [];
|
|
async function withServer(home, callback) {
|
|
const child = spawn(codexBinary, ["app-server"], {
|
|
cwd: home,
|
|
env: {
|
|
PATH: process.env.PATH ?? "/usr/bin:/bin",
|
|
HOME: home,
|
|
CODEX_HOME: home,
|
|
},
|
|
stdio: ["pipe", "pipe", "pipe"],
|
|
});
|
|
const finished = new Promise((resolve) => {
|
|
child.once("exit", (code, signal) => resolve({ code, signal }));
|
|
child.once("error", (error) => resolve({ error }));
|
|
});
|
|
child.stderr.on("data", () => {});
|
|
const pending = new Map();
|
|
let next = 0;
|
|
createInterface({ input: child.stdout }).on("line", (line) => {
|
|
const frame = JSON.parse(line);
|
|
if (frame.id != null && pending.has(frame.id)) {
|
|
const { resolve, reject, timer } = pending.get(frame.id);
|
|
pending.delete(frame.id);
|
|
clearTimeout(timer);
|
|
frame.error
|
|
? reject(new Error(JSON.stringify(frame.error)))
|
|
: resolve(frame.result);
|
|
}
|
|
});
|
|
const rpc = (method, params) =>
|
|
new Promise((resolve, reject) => {
|
|
methods.push(method);
|
|
const id = ++next;
|
|
const timer = setTimeout(
|
|
() => reject(new Error("local_rpc_timeout")),
|
|
10000,
|
|
);
|
|
pending.set(id, { resolve, reject, timer });
|
|
child.stdin.write(JSON.stringify({ id, method, params }) + "\n");
|
|
});
|
|
try {
|
|
await rpc("initialize", {
|
|
clientInfo: { name: "paperclip-fixture", version: "1" },
|
|
capabilities: { experimentalApi: true },
|
|
});
|
|
child.stdin.write(JSON.stringify({ method: "initialized" }) + "\n");
|
|
return await callback(rpc);
|
|
} finally {
|
|
let killTimer;
|
|
let deadline;
|
|
try {
|
|
child.stdin.end();
|
|
child.kill("SIGTERM");
|
|
killTimer = setTimeout(() => child.kill("SIGKILL"), 2000);
|
|
const exit = await Promise.race([
|
|
finished,
|
|
new Promise((_, reject) => {
|
|
deadline = setTimeout(
|
|
() => reject(new Error("fixture_child_exit_unproven")),
|
|
5000,
|
|
);
|
|
}),
|
|
]);
|
|
if (exit.error) throw exit.error;
|
|
} finally {
|
|
clearTimeout(killTimer);
|
|
clearTimeout(deadline);
|
|
for (const { timer } of pending.values()) clearTimeout(timer);
|
|
}
|
|
}
|
|
}
|
|
const result = await withServer(home, (rpc) =>
|
|
rpc("thread/start", { cwd: home, model: "gpt-5.6-luna", ephemeral: false }),
|
|
);
|
|
const threadId = result.thread.id;
|
|
const canonicalHome = await realpath(home);
|
|
const rolloutRelative = relative(canonicalHome, result.thread.path);
|
|
if (
|
|
!/^[a-f0-9-]{36}$/.test(threadId) ||
|
|
isAbsolute(rolloutRelative) ||
|
|
!rolloutRelative.startsWith("sessions/") ||
|
|
rolloutRelative.split("/").includes("..") ||
|
|
!rolloutRelative.endsWith(`-${threadId}.jsonl`)
|
|
) {
|
|
throw new Error("Provider fixture path escaped the exact temporary home");
|
|
}
|
|
const timestamp = new Date().toISOString();
|
|
// Same minimal paginated fixture shape as the pinned provider's own
|
|
// app-server/tests/common/rollout.rs. No model call or turn/start is sent.
|
|
const lines =
|
|
[
|
|
{
|
|
type: "session_meta",
|
|
payload: {
|
|
id: threadId,
|
|
session_id: threadId,
|
|
timestamp,
|
|
cwd: home,
|
|
originator: "codex",
|
|
cli_version: "0.156.0",
|
|
source: "cli",
|
|
model_provider: "openai",
|
|
selected_capability_roots: [],
|
|
history_mode: "paginated",
|
|
},
|
|
},
|
|
{
|
|
type: "response_item",
|
|
payload: {
|
|
type: "message",
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "input_text",
|
|
text: "Synthetic retained fixture. No action requested.",
|
|
},
|
|
],
|
|
},
|
|
},
|
|
{
|
|
type: "event_msg",
|
|
payload: {
|
|
type: "user_message",
|
|
message: "Synthetic retained fixture. No action requested.",
|
|
kind: "plain",
|
|
},
|
|
},
|
|
]
|
|
.map((v, ordinal) => JSON.stringify({ timestamp, ordinal, ...v }))
|
|
.join("\n") + "\n";
|
|
await mkdir(dirname(result.thread.path), { recursive: true });
|
|
await writeFile(result.thread.path, lines, { flag: "wx" });
|
|
// Materialize the synthetic persisted thread through the real provider so
|
|
// SQLite, paginated history and rollout selection use the producer schema.
|
|
await withServer(canonicalHome, (rpc) =>
|
|
rpc("thread/resume", {
|
|
threadId,
|
|
cwd: canonicalHome,
|
|
model: "gpt-5.6-luna",
|
|
excludeTurns: true,
|
|
}),
|
|
);
|
|
const original = `${canonicalHome}-archive`;
|
|
await rename(canonicalHome, original);
|
|
const fingerprint = async (root) => {
|
|
const files = [];
|
|
async function visit(relative) {
|
|
for (const entry of (
|
|
await readdir(join(root, relative), { withFileTypes: true })
|
|
).sort((a, b) => a.name.localeCompare(b.name))) {
|
|
const p = join(relative, entry.name);
|
|
if (entry.isDirectory()) await visit(p);
|
|
else if (entry.isFile())
|
|
files.push([
|
|
p,
|
|
createHash("sha256")
|
|
.update(await readFile(join(root, p)))
|
|
.digest("hex"),
|
|
]);
|
|
else if (entry.isSymbolicLink())
|
|
files.push([p, "symlink", await readlink(join(root, p))]);
|
|
else throw new Error("unsupported_synthetic_fixture_entry");
|
|
}
|
|
}
|
|
await visit("");
|
|
return createHash("sha256").update(JSON.stringify(files)).digest("hex");
|
|
};
|
|
const originalFingerprint = await fingerprint(original);
|
|
const copied = `${canonicalHome}-copy`;
|
|
await cp(original, copied, {
|
|
recursive: true,
|
|
filter: (source) => !["tmp", ".tmp"].includes(source.split("/").at(-1)),
|
|
});
|
|
const resume = (rpc) =>
|
|
rpc("thread/resume", {
|
|
threadId,
|
|
cwd: copied,
|
|
model: "gpt-5.6-luna",
|
|
excludeTurns: true,
|
|
});
|
|
let red;
|
|
try {
|
|
await withServer(copied, resume);
|
|
} catch (error) {
|
|
red = error.message;
|
|
}
|
|
if (!red?.includes(`no rollout found for thread id ${threadId}`)) {
|
|
console.log(JSON.stringify({ red, canonicalHome, copied, threadId }));
|
|
throw new Error("expected_exact_missing_paginated_path");
|
|
}
|
|
rebaseRetainedNativeCleanupProviderHome(
|
|
copied,
|
|
canonicalHome,
|
|
threadId,
|
|
"staging",
|
|
);
|
|
const green = await withServer(copied, resume);
|
|
if (green.thread.id !== threadId || green.thread.historyMode !== "paginated")
|
|
throw new Error("wrong_resumed_identity");
|
|
rebaseRetainedNativeCleanupProviderHome(
|
|
copied,
|
|
canonicalHome,
|
|
threadId,
|
|
"canonical",
|
|
);
|
|
await rename(copied, canonicalHome);
|
|
const activated = await withServer(canonicalHome, (rpc) =>
|
|
rpc("thread/resume", {
|
|
threadId,
|
|
cwd: canonicalHome,
|
|
model: "gpt-5.6-luna",
|
|
excludeTurns: true,
|
|
}),
|
|
);
|
|
if (
|
|
activated.thread.id !== threadId ||
|
|
activated.thread.historyMode !== "paginated"
|
|
)
|
|
throw new Error("wrong_activated_identity");
|
|
if (methods.some((method) => method === "turn/start"))
|
|
throw new Error("unexpected_provider_turn");
|
|
if (originalFingerprint !== (await fingerprint(original)))
|
|
throw new Error("original_fixture_changed");
|
|
console.log(
|
|
JSON.stringify({
|
|
red: "exact_paginated_path_missing",
|
|
green: true,
|
|
activatedResume: true,
|
|
threadId,
|
|
historyMode: green.thread.historyMode,
|
|
methods,
|
|
original,
|
|
canonicalHome,
|
|
originalFingerprint,
|
|
originalSnapshotPreserved: true,
|
|
}),
|
|
);
|