fix(share): не утекать errorText тулов и провайдера анониму в публичном шэре (closes #394)

SECURITY. В публичном share-чате сырой текст ошибки тула или провайдера утекал
анонимному читателю. Три слоя, все обязательны:

(1) Рендер-гейт: prop showErrors в ToolCallCard (протянут через MessageList/
MessageItem), share-виджет передаёт false — сырой errorText не рисуется. Но
рендер-гейт маскирует только DOM, не байты.

(2) Санитизация на уровне share-тулсета (авторитетно): forShare оборачивает
execute каждого тула catch'ем. Своя ShareToolError (безопасные строки: «page not
available in this share») пробрасывается, ЛЮБАЯ другая ошибка → generic «tool
could not complete», полный текст только в серверный лог. Одно место закрывает
байты (атомарный tool-output-error фрейм v6), рендер и контекст модели; self-
correction сохранена.

(3) Анонимный onError пайпа: ShareToolError → её безопасное сообщение; иначе
describeProviderError (statusCode + тело: внутренний baseUrl/модель) только в лог,
читателю — фиксированная классифицированная строка (rate-limited/unavailable/
provider error).

Тест: интеграционный с РЕАЛЬНЫМ падением тула и провайдера — assert по СЫРЫМ SSE-
БАЙТАМ (не по DOM): секрет/baseUrl/стек отсутствуют, видна безопасная строка,
полный текст провайдера ушёл в серверный лог.
This commit is contained in:
2026-07-11 02:50:19 +03:00
parent e1ebd79f30
commit 26d9a70a1c
7 changed files with 396 additions and 11 deletions
@@ -47,6 +47,13 @@ interface MessageItemProps {
* agent's raw query/argument text.
*/
showInput?: boolean;
/**
* Forwarded to ToolCallCard: whether a failed tool card renders its raw
* errorText. Defaults to true (internal chat). The public share passes false so
* internal detail in a tool error is never painted (belt to the server-side
* byte sanitization).
*/
showErrors?: boolean;
/**
* Neutralize internal/relative markdown links in the rendered answer (drop
* their href so they become inert text). Defaults to false (internal chat,
@@ -125,6 +132,7 @@ function MessageItem({
message,
showCitations = true,
showInput = true,
showErrors = true,
neutralizeInternalLinks = false,
assistantName,
turnStreaming = false,
@@ -219,6 +227,7 @@ function MessageItem({
part={part as unknown as ToolUiPart}
showCitations={showCitations}
showInput={showInput}
showErrors={showErrors}
/>
);
}
@@ -284,6 +293,7 @@ export function arePropsEqual(
prev.signature === next.signature &&
prev.showCitations === next.showCitations &&
prev.showInput === next.showInput &&
prev.showErrors === next.showErrors &&
prev.neutralizeInternalLinks === next.neutralizeInternalLinks &&
prev.assistantName === next.assistantName &&
// The turn-end flip re-renders every row once (cheap, terminal event) —
@@ -32,6 +32,12 @@ interface MessageListProps {
* doesn't see the agent's raw query/argument text.
*/
showInput?: boolean;
/**
* Forwarded to MessageItem -> ToolCallCard: whether a failed tool card renders
* its raw errorText. Defaults to true (internal chat). The public share passes
* false so internal detail in a tool error is never painted.
*/
showErrors?: boolean;
/**
* Forwarded to MessageItem: neutralize internal/relative markdown links in
* the rendered answers (drop their href so they render as inert text).
@@ -127,6 +133,7 @@ export default function MessageList({
emptyState,
showCitations = true,
showInput = true,
showErrors = true,
neutralizeInternalLinks = false,
assistantName,
}: MessageListProps) {
@@ -217,6 +224,7 @@ export default function MessageList({
signature={messageSignature(message)}
showCitations={showCitations}
showInput={showInput}
showErrors={showErrors}
neutralizeInternalLinks={neutralizeInternalLinks}
assistantName={assistantName}
// Turn-level liveness, gated to the TAIL row: only the tail message
@@ -30,6 +30,16 @@ interface ToolCallCardProps {
* the extra summary line, leaving the card (the action log) intact.
*/
showInput?: boolean;
/**
* Whether to render the tool's raw errorText on a failed call. Defaults to true
* (the internal chat, where the operator may debug). The public share passes
* false: a tool error string can carry internal detail (an internal page title,
* a stack fragment, a provider message). This is the RENDER gate only — the
* authoritative fix also sanitizes the bytes server-side (see
* PublicShareChatToolsService.forShare), so a share reader never receives raw
* error text over the wire, not just never sees it painted (#394).
*/
showErrors?: boolean;
}
/**
@@ -41,6 +51,7 @@ export default function ToolCallCard({
part,
showCitations = true,
showInput = true,
showErrors = true,
}: ToolCallCardProps) {
const { t } = useTranslation();
const toolName = getToolName(part);
@@ -74,7 +85,7 @@ export default function ToolCallCard({
</Text>
)}
{state === "error" && part.errorText && (
{state === "error" && showErrors && part.errorText && (
<Text size="xs" c="red" mt={2}>
{part.errorText}
</Text>
@@ -168,6 +168,10 @@ export default function ShareAiWidget({
// Anonymous reader: suppress the tool-argument summary line so the
// agent's raw query/argument text isn't shown on the public share.
showInput={false}
// Anonymous reader: never paint a tool's raw errorText (it can carry
// internal detail). This is the render gate; the bytes are also
// sanitized server-side in PublicShareChatToolsService.forShare (#394).
showErrors={false}
// Anonymous reader: neutralize internal/relative links in the
// assistant's markdown so internal UUIDs/auth-gated routes don't
// leak as clickable links (external http(s) links are kept).
@@ -0,0 +1,241 @@
// Break the editor-ext import chain (share.service -> collaboration.util ->
// @docmost/editor-ext -> @tiptap/core) that is unresolvable in this jest env and
// pre-existingly breaks these specs. jsonToMarkdown is never reached in these
// tests (the tools fail before rendering markdown).
jest.mock('../../collaboration/collaboration.util', () => ({
jsonToMarkdown: () => '',
}));
import { Logger } from '@nestjs/common';
import { MockLanguageModelV3, simulateReadableStream } from 'ai/test';
import { PublicShareChatService } from './public-share-chat.service';
import { PublicShareChatToolsService } from './tools/public-share-chat-tools.service';
/**
* SECURITY integration guard for #394 (commit 5): a tool's or the provider's raw
* error text must NOT leak to an anonymous public-share reader.
*
* The render gate (ToolCallCard showErrors=false) hides the text in the DOM but
* NOT on the wire, so this test asserts on the RAW SSE BYTES the server writes —
* exactly the channel the render gate masks. We drive the real
* PublicShareChatService.stream() with a real share toolset (its underlying
* services mocked to fail) and a mock model, then inspect every byte piped to the
* fake socket.
*/
// A minimal ServerResponse stand-in that records every written chunk.
class FakeSocket {
chunks: string[] = [];
statusCode = 200;
writableEnded = false;
destroyed = false;
headersSent = false;
writeHead(): this {
this.headersSent = true;
return this;
}
setHeader(): void {}
removeHeader(): void {}
getHeader(): undefined {
return undefined;
}
flushHeaders(): void {}
write(chunk: unknown): boolean {
this.chunks.push(
typeof chunk === 'string' ? chunk : Buffer.from(chunk as never).toString('utf8'),
);
return true;
}
end(chunk?: unknown): void {
if (chunk) this.write(chunk);
this.writableEnded = true;
}
on(): this {
return this;
}
once(): this {
return this;
}
get body(): string {
return this.chunks.join('');
}
}
/** Mock model that issues one getSharePage tool call, then finishes with text. */
function toolCallingModel(): MockLanguageModelV3 {
let call = 0;
return new MockLanguageModelV3({
doStream: async () => {
call++;
if (call === 1) {
return {
stream: simulateReadableStream({
chunks: [
{ type: 'stream-start' as const, warnings: [] },
{ type: 'tool-input-start' as const, id: 't1', toolName: 'getSharePage' },
{ type: 'tool-input-end' as const, id: 't1' },
{
type: 'tool-call' as const,
toolCallId: 't1',
toolName: 'getSharePage',
input: '{"pageId":"secret-page"}',
},
{
type: 'finish' as const,
finishReason: { unified: 'tool-calls' as const, raw: 'tool_calls' },
usage: {
inputTokens: { total: 1, noCache: undefined, cacheRead: undefined, cacheWrite: undefined },
outputTokens: { total: 1, text: 1, reasoning: undefined },
},
},
],
}),
};
}
return {
stream: simulateReadableStream({
chunks: [
{ type: 'stream-start' as const, warnings: [] },
{ type: 'text-start' as const, id: '1' },
{ type: 'text-delta' as const, id: '1', delta: 'Sorry.' },
{ type: 'text-end' as const, id: '1' },
{
type: 'finish' as const,
finishReason: { unified: 'stop' as const, raw: 'stop' },
usage: {
inputTokens: { total: 1, noCache: undefined, cacheRead: undefined, cacheWrite: undefined },
outputTokens: { total: 1, text: 1, reasoning: undefined },
},
},
],
}),
};
},
});
}
/** Mock model whose stream emits a provider error carrying an internal secret. */
function providerErrorModel(secret: string): MockLanguageModelV3 {
return new MockLanguageModelV3({
doStream: async () => ({
stream: simulateReadableStream({
chunks: [
{ type: 'stream-start' as const, warnings: [] },
{
type: 'error' as const,
error: {
statusCode: 503,
message: 'Service Unavailable',
responseBody: `upstream ${secret} model=internal-gpt`,
},
},
],
}),
}),
});
}
function makeService(toolsService: PublicShareChatToolsService): {
svc: PublicShareChatService;
logSpy: jest.SpyInstance;
} {
const svc = Object.create(PublicShareChatService.prototype);
const logger = new Logger('test');
const logSpy = jest.spyOn(logger, 'error').mockImplementation(() => undefined);
jest.spyOn(logger, 'warn').mockImplementation(() => undefined);
svc.tools = toolsService;
svc.logger = logger;
svc.tokenBudget = { record: jest.fn().mockResolvedValue(undefined) };
return { svc, logSpy };
}
async function runStream(
svc: PublicShareChatService,
model: MockLanguageModelV3,
): Promise<FakeSocket> {
const socket = new FakeSocket();
await svc.stream({
workspaceId: 'ws1',
shareId: 'share1',
share: { id: 'share1', pageId: 'p1', sharedPage: { id: 'p1', title: 'Docs' } },
openedPage: null,
messages: [
{ id: 'm1', role: 'user', parts: [{ type: 'text', text: 'read the page' }] } as never,
],
res: { raw: socket } as never,
signal: new AbortController().signal,
model: model as never,
role: null,
});
// Let the piped stream drain fully.
await new Promise((r) => setTimeout(r, 300));
return socket;
}
describe('public share chat error leak (#394)', () => {
afterEach(() => jest.restoreAllMocks());
it('does NOT leak a tool\'s raw internal error to the SSE bytes (generic classified string instead)', async () => {
const SECRET = 'INTERNAL_baseUrl_http://provider.internal:8080/v1';
const shareService = {
// The canonical boundary throws a RAW internal error (with a secret).
resolveReadableSharePage: jest
.fn()
.mockRejectedValue(new Error(`db failed at ${SECRET} stack@line42`)),
};
const tools = new PublicShareChatToolsService(
shareService as never,
{} as never,
{} as never,
);
const { svc } = makeService(tools);
const socket = await runStream(svc, toolCallingModel());
// The tool-output-error frame is present on the wire...
expect(socket.body).toContain('tool-output-error');
// ...but it carries ONLY the generic classified string — never the secret,
// the raw driver message, or a stack fragment.
expect(socket.body).toContain('The tool could not complete the request.');
expect(socket.body).not.toContain(SECRET);
expect(socket.body).not.toContain('stack@line42');
expect(socket.body).not.toContain('db failed');
});
it('passes a SAFE ShareToolError message (page not available) through to the bytes', async () => {
const shareService = {
// Not found in this share -> the tool throws the classified SAFE message.
resolveReadableSharePage: jest.fn().mockResolvedValue(null),
};
const tools = new PublicShareChatToolsService(
shareService as never,
{} as never,
{} as never,
);
const { svc } = makeService(tools);
const socket = await runStream(svc, toolCallingModel());
expect(socket.body).toContain('tool-output-error');
expect(socket.body).toContain('not available in this share');
});
it('does NOT leak a provider error (statusCode + response body) to the SSE bytes', async () => {
const SECRET = 'http://provider.internal:8080';
const tools = new PublicShareChatToolsService(
{} as never,
{} as never,
{} as never,
);
const { svc, logSpy } = makeService(tools);
const socket = await runStream(svc, providerErrorModel(SECRET));
// The anon sees a fixed classified string, not the provider body/baseUrl/model.
expect(socket.body).toContain('temporarily unavailable');
expect(socket.body).not.toContain(SECRET);
expect(socket.body).not.toContain('internal-gpt');
// The FULL provider detail is logged server-side only.
const logged = logSpy.mock.calls.map((c) => String(c[0])).join('\n');
expect(logged).toContain(SECRET);
});
});
@@ -12,7 +12,10 @@ import { AiAgentRoleRepo } from '@docmost/db/repos/ai-agent-roles/ai-agent-roles
import { AiAgentRole } from '@docmost/db/types/entity.types';
import { AiService } from '../../integrations/ai/ai.service';
import { AiSettingsService } from '../../integrations/ai/ai-settings.service';
import { PublicShareChatToolsService } from './tools/public-share-chat-tools.service';
import {
PublicShareChatToolsService,
ShareToolError,
} from './tools/public-share-chat-tools.service';
import { buildShareSystemPrompt } from './public-share-chat.prompt';
import { roleModelOverride } from './roles/role-model-config';
import {
@@ -102,6 +105,30 @@ export function filterShareTranscript(messages: UIMessage[]): UIMessage[] {
);
}
/**
* Fixed, classified strings an ANONYMOUS share reader may see when the assistant
* stream fails (#394). These reveal NOTHING about the internal provider, its
* baseUrl, the model name, or the raw response body — unlike describeProviderError
* (which is for the server log / the authenticated operator only). We classify by
* HTTP status where available so the reader still gets a useful hint (retry vs.
* give up) without any internal detail.
*/
export function classifyAnonStreamError(error: unknown): string {
const status =
typeof error === 'object' && error !== null
? (error as { statusCode?: number }).statusCode
: undefined;
if (status === 429) {
return 'The assistant is receiving too many requests right now. Please try again shortly.';
}
if (typeof status === 'number' && status >= 500) {
return 'The assistant is temporarily unavailable. Please try again.';
}
// Any other failure (including a bare connection error with no status): a
// single neutral line. No provider identity, no config, no response body.
return 'The assistant could not complete your request. Please try again.';
}
/**
* Anonymous, read-only AI assistant for a single PUBLIC share tree.
*
@@ -318,11 +345,28 @@ export class PublicShareChatService {
result.pipeUIMessageStreamToResponse(res.raw, {
headers: { 'X-Accel-Buffering': 'no' },
onError: (error: unknown) => {
// Reuse the shared formatter so provider error formatting stays
// unified between the log line and the streamed error message — a
// share reader sees 402/429/503 causes consistently with the
// authenticated path.
return describeProviderError(error, 'AI stream error');
// SECURITY (#394): the string this returns is written verbatim into the
// SSE error frame delivered to an ANONYMOUS reader (for a tool failure
// it becomes the atomic `tool-output-error` frame's errorText; for a
// stream/provider failure, the terminal error frame).
//
// A ShareToolError is already a classified, safe tool message (see
// PublicShareChatToolsService.wrapToolErrors) — pass it through so the
// reader still gets the useful "page not available in this share" hint.
if (error instanceof ShareToolError) {
return error.message;
}
// Anything else is a provider/stream error. describeProviderError
// bundles the provider statusCode AND response body, which can carry the
// internal baseUrl or model name — NEVER expose that to the public. Log
// the full detail server-side only and return a fixed classified string.
this.logger.error(
`Public share chat pipe error: ${describeProviderError(
error,
'AI stream error',
)}`,
);
return classifyAnonStreamError(error);
},
});
@@ -7,6 +7,22 @@ import { PageRepo } from '@docmost/db/repos/page/page.repo';
import { jsonToMarkdown } from '../../../collaboration/collaboration.util';
import { modelFriendlyInput } from './model-friendly-input';
/**
* A tool error whose message is DELIBERATELY safe to expose to an anonymous
* share reader (and to the model, for self-correction). Every OTHER thrown error
* is treated as internal and replaced with a generic string by `wrapToolErrors`,
* so a raw exception message — an internal page title, a DB/stack fragment, a
* driver detail — never rides the public UI stream (#394).
*/
export class ShareToolError extends Error {}
// The only two classified strings an anonymous reader may ever see from a tool
// failure. The specific one keeps the model's self-correction useful ("try a
// different page"); the generic one reveals nothing about the internal fault.
const SHARE_TOOL_ERROR_NOT_AVAILABLE =
'The requested page is not available in this share.';
const SHARE_TOOL_ERROR_GENERIC = 'The tool could not complete the request.';
/**
* Isolated, READ-ONLY toolset for the ANONYMOUS public-share assistant.
*
@@ -44,7 +60,7 @@ export class PublicShareChatToolsService {
* are NO write tools, NO comments/history, NO cross-space or external tools.
*/
forShare(shareId: string, workspaceId: string): Record<string, Tool> {
return {
return this.wrapToolErrors({
searchSharePages: tool({
description:
'Search the pages of THIS published documentation share for a ' +
@@ -96,7 +112,7 @@ export class PublicShareChatToolsService {
execute: async ({ pageId }) => {
const id = (pageId ?? '').trim();
if (!id) {
throw new Error('A pageId is required.');
throw new ShareToolError('A pageId is required.');
}
// Resolve via the SINGLE canonical share-access boundary: confirms the
// page resolves to THIS share (recursive CTE up the tree, honouring
@@ -112,7 +128,7 @@ export class PublicShareChatToolsService {
workspaceId,
);
if (!resolved) {
throw new Error('That page is not part of this published share.');
throw new ShareToolError(SHARE_TOOL_ERROR_NOT_AVAILABLE);
}
const { page } = resolved;
@@ -193,6 +209,57 @@ export class PublicShareChatToolsService {
}
},
}),
};
});
}
/**
* Wrap every tool's `execute` so a THROWN error is sanitized in ONE place —
* closing the byte leak, the render, and the model context at once (#394).
*
* The AI SDK surfaces a tool-execution throw as an atomic `tool-output-error`
* frame on the v6 UI stream whose `errorText` is the thrown message; on the
* public share that frame goes straight to an anonymous reader. Unwrapped, a
* raw exception (an internal page title, a DB/stack fragment, a driver detail)
* would ride that frame verbatim. Here we catch it, LOG the full detail
* server-side only, and re-throw a CLASSIFIED, safe error: the tool's own
* intentional ShareToolError messages pass through (they keep the model's
* self-correction useful), everything else collapses to a generic string.
*/
private wrapToolErrors(
tools: Record<string, Tool>,
): Record<string, Tool> {
const wrapped: Record<string, Tool> = {};
for (const [name, t] of Object.entries(tools)) {
const original = t.execute;
if (typeof original !== 'function') {
wrapped[name] = t;
continue;
}
wrapped[name] = {
...t,
execute: async (args: unknown, options: unknown) => {
try {
return await (
original as (a: unknown, o: unknown) => Promise<unknown>
)(args, options);
} catch (err) {
const safe =
err instanceof ShareToolError
? err.message
: SHARE_TOOL_ERROR_GENERIC;
// Full detail to the server log ONLY — never to the anon.
this.logger.warn(
`Public share tool "${name}" failed: ${
err instanceof Error ? err.message : String(err)
}`,
);
// This safe string is ALL that rides the tool-output-error frame,
// becomes model context, and could be rendered — one choke point.
throw new ShareToolError(safe);
}
},
} as Tool;
}
return wrapped;
}
}