fix(acpx): only treat an error result as a Claude sign-in failure (#21921)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Claude agents run through the Claude ACP bridge (`claude-agent-acp`
0.73.0), which Paperclip patches in `patches/`
> - The bridge reads Claude Code's final result for each turn. If the
result text contains "Please run /login", the bridge fails the turn as a
sign-in failure
> - That check does not look at `is_error`. A successful reply that
quotes the CLI's sign-in hint also fails the turn
> - Agents quote that hint when they report the output of a `claude`
command that they ran. The work is done, but the run fails with "ACP
agent reported a terminal access failure."
> - Upstream fixed this in
[agentclientprotocol/claude-agent-acp#1103](https://github.com/agentclientprotocol/claude-agent-acp/pull/1103)
(commit
[`6e97e07`](https://github.com/agentclientprotocol/claude-agent-acp/commit/6e97e071c581002b43d9556dbd1d1376ebf9516f),
released in 0.81.1), "fix: gate login result text on error state"
> - This pull request ports that upstream change into the 0.73.0 bridge
patch
> - The benefit is that a correct, finished run is not reported as a
failed sign-in

## Linked Issues or Issue Description

Upstream fix:
[agentclientprotocol/claude-agent-acp#1103](https://github.com/agentclientprotocol/claude-agent-acp/pull/1103)
(commit
[`6e97e07`](https://github.com/agentclientprotocol/claude-agent-acp/commit/6e97e071c581002b43d9556dbd1d1376ebf9516f),
released in 0.81.1). This pull request ports it.

Refs #14089. That pull request fixes the same class of problem in the
Claude CLI lane (`execute.ts`). This pull request fixes the ACP lane.

Related: #14093 shows the same error text, but it has a different cause.
This pull request does not fix #14093.

**What happened?**

An agent ran a script that calls the `claude` CLI without credentials.
The CLI printed "Not logged in · Please run /login". The agent finished
its task and quoted that text in its final reply. Claude Code ended the
turn with a successful result (`is_error: false`). The bridge saw
"Please run /login" in the result text and failed the turn with
`auth_required`. Paperclip then failed the run with "ACP agent reported
a terminal access failure."

**Expected behavior**

A successful result completes the turn. Only an error result with the
sign-in hint is a sign-in failure.

**Steps to reproduce**

1. Run a Claude agent on the ACP lane.
2. Make the model's final reply contain the text "Please run /login"
(for example, quote the output of `claude -p hi` without credentials).
3. See that the run fails with "ACP agent reported a terminal access
failure." The new test in this pull request does these steps against a
local API stand-in.

**Agent adapter(s) involved**

`claude_local` on the ACP engine, and the Runner's ACPX Claude profile.
Both use the same patched bridge.

## What Changed

- `patches/@agentclientprotocol__claude-agent-acp@0.73.0.patch`: port
[agentclientprotocol/claude-agent-acp#1103](https://github.com/agentclientprotocol/claude-agent-acp/pull/1103)
(commit
[`6e97e07`](https://github.com/agentclientprotocol/claude-agent-acp/commit/6e97e071c581002b43d9556dbd1d1376ebf9516f),
released in 0.81.1). It has two parts, the same as upstream:
- The `success` result check is now `message.is_error &&
message.result.includes("Please run /login")`. A successful result that
quotes the sign-in hint no longer fails the turn.
- The goal-command check also requires `message.is_error`. A `/goal`
command whose successful result quotes the sign-in hint no longer rolls
the session goal back.
- Both patch comments name the upstream change. All other patch hunks
are unchanged.
-
`packages/paperclip-runner/src/drivers/acpx/acpx-runtime-adapter.claude-login-text.test.ts`:
a new test. It runs the real bridge and the bundled Claude Code against
a local API stand-in. The model's reply quotes the sign-in hint, and the
test expects the turn to complete.

## Verification

- Red: on `master`'s patch, the new test fails with
`{"status":"failed","error":{"message":"ACP agent reported a terminal
access failure."}}`.
- Green: with this patch, the new test passes (`status: "completed"`,
`stopReason: "end_turn"`).
- I ran Claude Code 2.1.286 (the bundled version) with no credentials.
Its real sign-in failure is a result with `is_error: true` and the text
"Not logged in · Please run /login". The guard still catches it. The
separate synthetic sign-in message check is unchanged.
- The goal-command part has no new test here. The upstream change adds a
test for it. The runner's `session-goals.test.ts` passes with the new
patch.
- `node --test scripts/acpx-patch-packaging.test.mjs`: 26 passed.
- `node --test
packages/paperclip-runner/test/acpx-codex-package-contract.test.mjs`: 9
passed.
- Runner real-bridge Claude tests
(`acpx-runtime-adapter.claude-*.test.ts`,
`acpx-runtime-adapter.test.ts`,
`claude-scheduling-tools.claude-acp.test.ts`,
`runner-tool-bridge.claude-*.test.ts`): 139 passed.
- `claude-local` ACP tests (`acp.test.ts`, `acp.auth.test.ts`,
`acp.quota.test.ts`): 95 passed.
- `pnpm --filter @paperclipai/paperclip-runner run
typecheck:typescript`: passed.
- I did not commit `pnpm-lock.yaml`. The patch hash changes, and CI
resolves the lockfile for this run.

## Risks

- Low risk. The change adds one condition to each of two checks in the
bridge patch. Both match the upstream change.
- The bridge's `commandDigest` does not change, because the patch does
not touch `dist/index.js`. Saved sessions are not reset.
- A sign-in failure that Claude Code reports as a successful, non-error
result is no longer caught by this check. Claude Code 2.1.286 reports
sign-in failures as error results, and upstream uses the same rule.

## Model Used

Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use
(shell, file edits, subagents) and extended 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
#` / `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
- [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

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Nicky LeachandClaude Opus 5.5 authored and GitHub committed 2026-11-16 12:14:57 -08:00
1 parent cc9ff75cb8
commit fb288f5666
2 files changed
+132 -5

No files matched your search

@@ -0,0 +1,107 @@
import { spawn } from "node:child_process";
import { mkdir, mkdtemp, rm } from "node:fs/promises";
import { createServer } from "node:http";
import { createRequire } from "node:module";
import { tmpdir } from "node:os";
import { join } from "node:path";
import type { AcpRuntimeEvent } from "acpx/runtime";
import { expect, it, vi } from "vitest";
import { openCodexAcpxRuntime } from "./acpx-runtime-adapter.js";
import type { VerifiedAcpxCommandLease } from "./installation-integrity.js";
import { resolveQualifiedAcpxProfile } from "./qualified-profiles.js";
import type { AcpxRuntimePortOpenOptions } from "./runtime-host.js";
const QUOTED_LOGIN_TEXT = 'The probe exited 1: "Not logged in · Please run /login". I posted its output.';
async function runTurn() {
const root = await mkdtemp(join(tmpdir(), "claude-login-text-"));
const home = join(root, "home"), cwd = join(root, "workspace"), config = join(home, ".claude");
await Promise.all([mkdir(config, { recursive: true }), mkdir(cwd)]);
let sequence = 0;
const api = createServer(async (request, response) => {
let raw = "";
for await (const chunk of request) raw += chunk;
if (request.method === "GET") {
response.writeHead(200, { "content-type": "application/json" });
response.end(JSON.stringify({ data: [], has_more: false }));
return;
}
if (request.url?.includes("count_tokens")) {
response.writeHead(200, { "content-type": "application/json" });
response.end(JSON.stringify({ input_tokens: 1 }));
return;
}
const body = JSON.parse(raw || "{}") as { model?: string; stream?: boolean };
const model = body.model ?? "claude-sonnet-5";
if (body.stream !== true) {
response.writeHead(200, { "content-type": "application/json" });
response.end(JSON.stringify({ id: "msg_fixture", type: "message", role: "assistant", model,
content: [{ type: "text", text: "OK" }], stop_reason: "end_turn", usage: { input_tokens: 1, output_tokens: 1 } }));
return;
}
const frames: Array<Record<string, unknown>> = [
{ type: "message_start", message: { id: `msg_${++sequence}`, type: "message", role: "assistant", model, content: [],
stop_reason: null, stop_sequence: null, usage: { input_tokens: 7, output_tokens: 0 } } },
{ type: "content_block_start", index: 0, content_block: { type: "text", text: "" } },
{ type: "content_block_delta", index: 0, delta: { type: "text_delta", text: QUOTED_LOGIN_TEXT } },
{ type: "content_block_stop", index: 0 },
{ type: "message_delta", delta: { stop_reason: "end_turn", stop_sequence: null }, usage: { output_tokens: 3 } },
{ type: "message_stop" },
];
response.writeHead(200, { "content-type": "text/event-stream" });
for (const frame of frames) response.write(`event: ${frame.type}\ndata: ${JSON.stringify(frame)}\n\n`);
response.end();
});
await new Promise<void>(resolve => api.listen(0, "127.0.0.1", resolve));
const address = api.address() as { port: number };
const entry = createRequire(import.meta.url).resolve("@agentclientprotocol/claude-agent-acp/dist/index.js");
const command: VerifiedAcpxCommandLease = {
spawn: (args, input) => spawn(process.execPath, [entry, ...(args ?? [])], { ...input, detached: true, stdio: ["pipe", "pipe", "pipe"] }),
close: async () => undefined,
};
const options: AcpxRuntimePortOpenOptions = {
command,
profile: resolveQualifiedAcpxProfile("claude", "claude-sonnet-5"),
cwd,
stateDirectory: join(root, "state"),
providerSessionKey: "claude-login-text",
permissionMode: "approve-all",
permissionPolicy: { autoApprove: ["read", "write", "execute", "other"], defaultAction: "approve" },
launchEnvironment: { HOME: home, CLAUDE_CONFIG_DIR: config, PATH: "/usr/bin:/bin", TMPDIR: root,
ANTHROPIC_API_KEY: "local-fixture-only", ANTHROPIC_BASE_URL: `http://127.0.0.1:${address.port}`,
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC: "1", DISABLE_TELEMETRY: "1", DISABLE_ERROR_REPORTING: "1", ENABLE_TOOL_SEARCH: "false" },
credentialFenceFds: [42, 43] as const,
activateCredentialFenceOwner: async () => undefined,
systemInstructions: "Report the probe output.",
mcpServers: [],
retainFailedAdmissionCleanup: vi.fn(),
} as AcpxRuntimePortOpenOptions;
let port: Awaited<ReturnType<typeof openCodexAcpxRuntime>> | undefined;
try {
port = await openCodexAcpxRuntime(options, {
awaitProviderOwnership: async () => undefined,
awaitProviderExit: child => new Promise<void>(resolve => child.once("exit", () => resolve())),
});
const turn = port.startTurn({ text: "Run the probe and report its output.", requestId: "turn-1",
onPermissionRequest: async () => ({ outcome: "allow_once" }) });
const events: AcpRuntimeEvent[] = [];
for await (const event of turn.events) events.push(event);
return { result: await turn.result, events };
} finally {
try { await port?.close({ reason: "sign-in hint verified" }); }
finally {
api.closeAllConnections();
await new Promise<void>(resolve => api.close(() => resolve()));
await rm(root, { recursive: true, force: true, maxRetries: 5, retryDelay: 50 });
}
}
}
it("completes a turn whose successful reply quotes the CLI's sign-in hint through the real ACP stream", async () => {
const { result, events } = await runTurn();
expect(result).toMatchObject({ status: "completed", stopReason: "end_turn" });
expect(JSON.stringify(events)).toContain("Please run /login");
}, 60_000);
@@ -1,5 +1,5 @@
diff --git a/dist/acp-agent.js b/dist/acp-agent.js
index 0214a50..73f0c16 100644
index 0214a50..a68121d 100644
--- a/dist/acp-agent.js
+++ b/dist/acp-agent.js
@@ -2490,11 +2490,88 @@ export class ClaudeAcpAgent {
@@ -117,7 +117,18 @@ index 0214a50..73f0c16 100644
await subagents.finishTask(message.task_id, message.patch.status, sendUpdate);
session.liveBackgroundTasks.delete(message.task_id);
}
@@ -2922,9 +3002,19 @@ export class ClaudeAcpAgent {
@@ -2794,7 +2874,9 @@ export class ClaudeAcpAgent {
session.pendingGoalUpdate = undefined;
const goalCommandFailed = message.is_error ||
message.stop_reason === "refusal" ||
- ("result" in message && message.result.includes("Please run /login"));
+ ("result" in message &&
+ message.is_error &&
+ message.result.includes("Please run /login"));
if (goalCommandFailed) {
await this.publishGoal(params.sessionId, pendingGoalUpdate.previous ?? null);
}
@@ -2922,9 +3004,19 @@ export class ClaudeAcpAgent {
amount: message.total_cost_usd,
currency: "USD",
},
@@ -140,7 +151,16 @@ index 0214a50..73f0c16 100644
},
});
}
@@ -4506,6 +4596,48 @@ export class ClaudeAcpAgent {
@@ -3081,7 +3173,7 @@ export class ClaudeAcpAgent {
}
switch (message.subtype) {
case "success": {
- if (message.result.includes("Please run /login")) {
+ if (message.is_error && message.result.includes("Please run /login")) {
await failActiveWithSessionFailure("auth_required", RequestError.authRequired(), message.result);
break;
}
@@ -4506,6 +4598,48 @@ export class ClaudeAcpAgent {
* `$/cancel_request`, and our local abort race settles even if the client
* ignores it. A `cancelled` outcome, request rejection, and local abort all
* surface the same "Tool use aborted" the callers already expect. */
@@ -189,7 +209,7 @@ index 0214a50..73f0c16 100644
async requestPermissionFromClient(params, toolName, signal, parentToolUseId, ownerSessionId = params.sessionId) {
if (signal.aborted)
throw new Error("Tool use aborted");
@@ -5311,14 +5443,24 @@ export class ClaudeAcpAgent {
@@ -5311,14 +5445,24 @@ export class ClaudeAcpAgent {
settingSources: ["user", "project", "local"],
...(thinking !== undefined && { thinking }),
...userProvidedOptions,
@@ -215,7 +235,7 @@ index 0214a50..73f0c16 100644
...mcpServers,
...(fileChangeAuditSupport
? { [FILE_CHANGE_AUDIT_SERVER_NAME]: fileChangeAuditSupport.mcpServer }
@@ -5329,6 +5471,16 @@ export class ClaudeAcpAgent {
@@ -5329,6 +5473,16 @@ export class ClaudeAcpAgent {
allowDangerouslySkipPermissions: ALLOW_BYPASS,
permissionMode: initialPermissionMode,
canUseTool: this.canUseTool(sessionId),