v1.13.19-html-artifact-panes: pane-based artifact viewer with on-request HTML

Every assistant message gets an "Open in pane" affordance that opens the
message in the workspace splitter — Markdown pane (Copy + Download .md) by
default; HTML pane (Download .html only) when the model emits a self-contained
<!DOCTYPE html> or fenced ```html artifact. BOOCHAT.md rule keeps Markdown
default at every length; HTML opt-in on explicit user request.

Backend: services/artifacts.ts (slug derivation + write helpers with
symlink-escape guard via realpath-after-mkdir), routes/artifacts.ts (POST
download + GET stream with nosniff + CSP sandbox defense-in-depth), HTML
detection in finalizeCompletion writing a new message_parts.kind='html_artifact'
row (schema CHECK extended via v1.13.13 pattern), graceful 1MB cap via the
pure decideHtmlArtifactWrite helper. PartKind union extended.

Frontend: MarkdownRenderer.tsx extracted from MessageBubble's inline
MarkdownBody for reuse; MarkdownArtifactPane.tsx + HtmlArtifactPane.tsx with
loading/error states; pane state is reference-only ({chat_id, message_id,
title}) — content fetched on mount to keep workspace_panes jsonb small and
avoid 1MB blobs riding session_workspace_updated frames. iframe sandbox
locked to allow-scripts allow-clipboard-write allow-downloads with no
allow-same-origin, srcDoc not src. openInPane discriminates 404 (expected
fallback) from real errors (toast + bail). PanelRightOpen icon button with
mobile 44px tap-target.

31 new server unit tests including a real-symlink filesystem case; 332/332
server tests passing, tsc clean both sides, pnpm -C apps/web build green.
Smoke deferred to first deploy.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-23 12:43:13 +00:00
parent 1a889dcde3
commit ad45b28250
24 changed files with 1864 additions and 195 deletions

View File

@@ -0,0 +1,261 @@
import { mkdtemp, mkdir, readFile, rm, symlink } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { afterEach, beforeEach, describe, expect, it } from 'vitest';
import {
decideHtmlArtifactWrite,
deriveHtmlSlug,
deriveHtmlTitle,
deriveMarkdownSlug,
detectHtmlArtifact,
HTML_ARTIFACT_MAX_BYTES,
writeHtmlArtifact,
writeMarkdownArtifact,
} from '../artifacts.js';
import { PathScopeError } from '../path_guard.js';
describe('deriveMarkdownSlug', () => {
it('uses the first # heading when present', () => {
expect(deriveMarkdownSlug('# Hello World\n\nbody')).toBe('hello-world');
});
it('falls back to first 6 words', () => {
const s = deriveMarkdownSlug('the quick brown fox jumps over the lazy dog');
expect(s).toBe('the-quick-brown-fox-jumps-over');
});
it('returns "artifact" for empty input', () => {
expect(deriveMarkdownSlug('')).toBe('artifact');
});
it('caps at 60 chars and lowercases', () => {
const long = '# ' + 'A'.repeat(200);
const s = deriveMarkdownSlug(long);
expect(s.length).toBeLessThanOrEqual(60);
expect(s).toMatch(/^[a-z0-9-]+$/);
});
it('strips trailing punctuation', () => {
expect(deriveMarkdownSlug('# Hello, World!!!')).toBe('hello-world');
});
});
describe('deriveHtmlSlug', () => {
it('prefers payload.title when set', () => {
expect(
deriveHtmlSlug({ html_content: '<html></html>', title: 'My Title' }),
).toBe('my-title');
});
it('falls back to <title> tag', () => {
expect(
deriveHtmlSlug({
html_content: '<html><head><title>Page Title</title></head></html>',
title: null,
}),
).toBe('page-title');
});
it('falls back to first <h1> when no <title>', () => {
expect(
deriveHtmlSlug({
html_content: '<html><body><h1>Heading One</h1></body></html>',
title: null,
}),
).toBe('heading-one');
});
it('falls back to inner text words', () => {
expect(
deriveHtmlSlug({
html_content: '<div>one two three four five six seven</div>',
title: null,
}),
).toBe('one-two-three-four-five-six');
});
});
describe('deriveHtmlTitle', () => {
it('returns <title> content', () => {
expect(deriveHtmlTitle('<html><head><title>T</title></head></html>')).toBe('T');
});
it('falls back to <h1>', () => {
expect(deriveHtmlTitle('<body><h1>H</h1></body>')).toBe('H');
});
it('falls back to first 80 chars of inner text', () => {
const html = '<div>' + 'x '.repeat(100) + '</div>';
const t = deriveHtmlTitle(html);
expect(t).not.toBeNull();
expect(t!.length).toBeLessThanOrEqual(80);
});
it('returns null for empty html', () => {
expect(deriveHtmlTitle('')).toBeNull();
});
});
describe('detectHtmlArtifact', () => {
it('detects <!DOCTYPE html> prefix case-insensitively', () => {
const html = '<!doctype HTML><html><body>x</body></html>';
expect(detectHtmlArtifact(html)).toBe(html);
});
it('strips leading/trailing whitespace before matching', () => {
const html = '\n\n<!DOCTYPE html>\n<html></html>\n';
expect(detectHtmlArtifact(html)).toBe(html.trim());
});
it('detects fenced ```html block wrapping entire message', () => {
const wrapped = '```html\n<!DOCTYPE html>\n<html></html>\n```';
expect(detectHtmlArtifact(wrapped)).toContain('<!DOCTYPE html>');
});
it('rejects plain markdown', () => {
expect(detectHtmlArtifact('# heading\n\nsome text')).toBeNull();
});
it('rejects message with prose before the doctype', () => {
expect(
detectHtmlArtifact('Here you go: <!DOCTYPE html><html></html>'),
).toBeNull();
});
it('rejects empty input', () => {
expect(detectHtmlArtifact('')).toBeNull();
expect(detectHtmlArtifact(' \n ')).toBeNull();
});
it('rejects fenced block without doctype/<html>', () => {
expect(detectHtmlArtifact('```html\n<div>x</div>\n```')).toBeNull();
});
it('accepts fenced block containing <html> tag (no doctype)', () => {
const r = detectHtmlArtifact('```html\n<html><body>x</body></html>\n```');
expect(r).toContain('<html>');
});
});
describe('writeMarkdownArtifact / writeHtmlArtifact', () => {
let projectRoot: string;
beforeEach(async () => {
projectRoot = await mkdtemp(join(tmpdir(), 'artifacts-test-'));
});
afterEach(async () => {
await rm(projectRoot, { recursive: true, force: true });
});
it('writes a markdown artifact under .boocode/artifacts/', async () => {
const result = await writeMarkdownArtifact(
{ content: '# Hello\n\nbody' },
{ projectId: 'pid', projectRoot },
);
expect(result.path).toMatch(/\.boocode\/artifacts\/hello-\d+\.md$/);
expect(result.url).toMatch(/^\/api\/projects\/pid\/artifacts\/hello-\d+\.md$/);
const written = await readFile(result.path, 'utf8');
expect(written).toBe('# Hello\n\nbody');
});
it('writes an html artifact', async () => {
const result = await writeHtmlArtifact(
{
html_content: '<!DOCTYPE html><html><head><title>X</title></head></html>',
char_count: 56,
title: 'X',
},
{ projectId: 'pid', projectRoot },
);
expect(result.path).toMatch(/\.boocode\/artifacts\/x-\d+\.html$/);
const written = await readFile(result.path, 'utf8');
expect(written).toContain('<!DOCTYPE html>');
});
it('creates the artifacts directory if absent', async () => {
// Confirm the writer mkdir-recursive's the artifacts dir on first call.
const result = await writeMarkdownArtifact(
{ content: '# T' },
{ projectId: 'pid', projectRoot },
);
expect(result.path).toContain('.boocode/artifacts');
});
});
describe('1MB cap behavior', () => {
it('reports the correct byte threshold', () => {
expect(HTML_ARTIFACT_MAX_BYTES).toBe(1_048_576);
});
it('exceeds threshold for oversize payload', () => {
const oversize = '<!DOCTYPE html>' + 'A'.repeat(HTML_ARTIFACT_MAX_BYTES);
expect(Buffer.byteLength(oversize, 'utf8')).toBeGreaterThan(
HTML_ARTIFACT_MAX_BYTES,
);
});
it('detectHtmlArtifact still returns content above the cap (cap is checked by caller)', () => {
// Detection is content-shape; the cap check lives in finalizeCompletion
// (error-handler.ts). This test pins that contract: the helper does not
// silently drop oversize payloads on the floor.
const big = '<!DOCTYPE html>' + 'x'.repeat(2_000_000);
expect(detectHtmlArtifact(big)).not.toBeNull();
});
});
describe('decideHtmlArtifactWrite', () => {
// Pure helper extracted from finalizeCompletion's cap-skip branch. Pins
// the warn-and-skip decision without mocking the full InferenceContext.
it('returns write=true for payloads under the cap', () => {
const html = '<!DOCTYPE html><html></html>';
const decision = decideHtmlArtifactWrite(html);
expect(decision.write).toBe(true);
expect(decision.byteLen).toBe(Buffer.byteLength(html, 'utf8'));
});
it('returns write=false with cap_exceeded reason for oversize payloads', () => {
const big = '<!DOCTYPE html>' + 'x'.repeat(HTML_ARTIFACT_MAX_BYTES);
const decision = decideHtmlArtifactWrite(big);
expect(decision.write).toBe(false);
if (!decision.write) {
expect(decision.reason).toBe('cap_exceeded');
expect(decision.byteLen).toBeGreaterThan(HTML_ARTIFACT_MAX_BYTES);
}
});
it('accepts payload exactly at the cap (boundary)', () => {
// byteLen === cap should write; only strictly greater skips.
const exact = 'x'.repeat(HTML_ARTIFACT_MAX_BYTES);
const decision = decideHtmlArtifactWrite(exact);
expect(decision.write).toBe(true);
expect(decision.byteLen).toBe(HTML_ARTIFACT_MAX_BYTES);
});
});
describe('symlink escape protection', () => {
// Closes the gap where `.boocode/artifacts` is a symlink pointing
// outside the project root. The lexical prefix check on the resolved
// candidate path passes (it's under projectRoot textually), but the
// post-mkdir realpath verification must catch the escape.
let projectRoot: string;
let outside: string;
beforeEach(async () => {
projectRoot = await mkdtemp(join(tmpdir(), 'artifacts-symlink-root-'));
outside = await mkdtemp(join(tmpdir(), 'artifacts-symlink-outside-'));
});
afterEach(async () => {
await rm(projectRoot, { recursive: true, force: true });
await rm(outside, { recursive: true, force: true });
});
it('throws PathScopeError when .boocode/artifacts is a symlink to outside the project', async () => {
// Create .boocode dir, then make `artifacts` a symlink pointing outside.
await mkdir(join(projectRoot, '.boocode'), { recursive: true });
await symlink(outside, join(projectRoot, '.boocode', 'artifacts'));
await expect(
writeMarkdownArtifact(
{ content: '# Hello' },
{ projectId: 'pid', projectRoot },
),
).rejects.toBeInstanceOf(PathScopeError);
});
});

View File

@@ -0,0 +1,255 @@
// v1.14.x-html-artifact-panes: artifact writer + slug derivation.
//
// Writes Markdown and HTML artifacts to `<projectRoot>/.boocode/artifacts/`
// as plain files. Returns `{path, url}` where:
// - path is the absolute on-disk path
// - url is a project-scoped REST URL pointing at the GET download route
// registered in routes/artifacts.ts. The route streams the file with
// Content-Disposition: attachment.
//
// Path safety: we do NOT use path_guard.ts (it realpaths and throws ENOENT
// for files that don't exist yet, which artifact creation requires).
// Instead we mirror the v1.13.18 codecontext_client.ts pattern: resolve
// the candidate path against the realpath'd projectRoot, then verify the
// result starts with projectRoot + sep (or equals projectRoot).
import { mkdir, realpath, writeFile } from 'node:fs/promises';
import { resolve, sep } from 'node:path';
import { PathScopeError } from './path_guard.js';
import type { Message } from '../types/api.js';
export interface HtmlArtifactPayload {
html_content: string;
char_count: number;
title: string | null;
}
export interface ArtifactWriteResult {
path: string;
url: string;
}
const ARTIFACT_SUBDIR = '.boocode/artifacts';
// ---- slug helpers ----
// Lowercase, replace non-alnum runs with '-', trim leading/trailing '-',
// collapse repeated '-', cap at 60 chars. Empty → 'artifact'.
function slugify(input: string): string {
const cleaned = input
.toLowerCase()
.replace(/[^a-z0-9]+/g, '-')
.replace(/^-+|-+$/g, '')
.replace(/-{2,}/g, '-')
.slice(0, 60)
.replace(/^-+|-+$/g, '');
return cleaned || 'artifact';
}
function firstHeading(md: string): string | null {
// Match the first `# ` ATX heading at the start of a line.
const m = md.match(/^[ \t]*#[ \t]+(.+?)\s*$/m);
if (!m) return null;
const text = m[1]?.trim() ?? '';
return text.length > 0 ? text : null;
}
function firstNWords(s: string, n: number): string {
const words = s.trim().split(/\s+/).filter(Boolean).slice(0, n);
return words.join(' ');
}
export function deriveMarkdownSlug(messageContent: string): string {
const heading = firstHeading(messageContent);
if (heading) return slugify(heading);
const sixWords = firstNWords(messageContent, 6);
return slugify(sixWords);
}
// Strip HTML tags for inner-text extraction. Crude but sufficient for slug
// derivation — we're not rendering, just finding readable words.
function stripTags(html: string): string {
return html
.replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, ' ')
.replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, ' ')
.replace(/<[^>]+>/g, ' ')
.replace(/\s+/g, ' ')
.trim();
}
function extractTitleTag(html: string): string | null {
const m = html.match(/<title[^>]*>([\s\S]*?)<\/title>/i);
if (!m) return null;
const text = stripTags(m[1] ?? '').trim();
return text.length > 0 ? text : null;
}
function extractH1(html: string): string | null {
const m = html.match(/<h1[^>]*>([\s\S]*?)<\/h1>/i);
if (!m) return null;
const text = stripTags(m[1] ?? '').trim();
return text.length > 0 ? text : null;
}
export function deriveHtmlSlug(payload: {
html_content: string;
title: string | null;
}): string {
if (payload.title && payload.title.trim().length > 0) {
return slugify(payload.title);
}
const title = extractTitleTag(payload.html_content);
if (title) return slugify(title);
const h1 = extractH1(payload.html_content);
if (h1) return slugify(h1);
const inner = stripTags(payload.html_content);
return slugify(firstNWords(inner, 6));
}
// Derive title for the html_artifact part payload: <title> → first <h1> →
// first 80 chars of inner text. Returns null if nothing useful is found.
export function deriveHtmlTitle(html: string): string | null {
const t = extractTitleTag(html);
if (t) return t;
const h1 = extractH1(html);
if (h1) return h1;
const inner = stripTags(html);
if (inner.length === 0) return null;
return inner.slice(0, 80);
}
// ---- HTML detection (B4) ----
// Returns the inner HTML content if `text` is a recognised HTML artifact:
// - starts with <!DOCTYPE html> (case-insensitive, whitespace-trimmed), OR
// - wrapped entirely in a fenced ```html ... ``` block.
// Returns null if neither matches.
export function detectHtmlArtifact(text: string): string | null {
const trimmed = text.trim();
if (trimmed.length === 0) return null;
if (/^<!doctype\s+html/i.test(trimmed)) {
return trimmed;
}
// Fenced ```html block consuming the entire (trimmed) message. Allow an
// optional trailing newline before the closing fence.
const fence = trimmed.match(/^```html\s*\n([\s\S]*?)\n?```\s*$/i);
if (fence) {
const inner = fence[1] ?? '';
if (/^\s*<!doctype\s+html/i.test(inner) || /<html[\s>]/i.test(inner)) {
return inner.trim();
}
}
return null;
}
// ---- path resolution ----
// Resolve `<projectRoot>/.boocode/artifacts/<filename>` and verify the
// result stays under projectRoot. Mirrors the v1.13.18 codecontext_client.ts
// approach: realpath projectRoot first, then prefix-check the candidate.
// Throws on escape.
async function resolveArtifactPath(
projectRoot: string,
filename: string,
): Promise<{ resolvedRoot: string; artifactsDir: string; absPath: string }> {
const resolvedRoot = await realpath(projectRoot);
const artifactsDir = resolve(resolvedRoot, ARTIFACT_SUBDIR);
const absPath = resolve(artifactsDir, filename);
// Lexical prefix check on the resolved candidates. (The `!== resolvedRoot`
// branch was dead — ARTIFACT_SUBDIR is non-empty so artifactsDir always
// differs from resolvedRoot.)
if (!artifactsDir.startsWith(resolvedRoot + sep)) {
throw new PathScopeError(
`artifacts dir escapes project root: ${artifactsDir}`,
);
}
if (!absPath.startsWith(artifactsDir + sep)) {
throw new PathScopeError(
`artifact filename escapes artifacts dir: ${filename}`,
);
}
return { resolvedRoot, artifactsDir, absPath };
}
// After mkdir, realpath the artifacts dir and re-verify it stays under
// resolvedRoot. Closes the symlink-escape gap: if `.boocode/artifacts` (or
// any ancestor below resolvedRoot) is a symlink pointing outside the
// project, the lexical check in resolveArtifactPath passes but the actual
// write lands outside the sandbox. Throws PathScopeError on escape.
async function assertArtifactsDirSafe(
artifactsDir: string,
resolvedRoot: string,
): Promise<void> {
const realDir = await realpath(artifactsDir);
if (realDir !== resolvedRoot && !realDir.startsWith(resolvedRoot + sep)) {
throw new PathScopeError(
`artifacts dir resolves outside project root: ${realDir}`,
);
}
}
// Pure decision helper for whether finalizeCompletion should write the
// `html_artifact` part. Exported for unit testing the cap-skip branch.
// Returns `{write: true, byteLen}` when the payload is under the cap, or
// `{write: false, byteLen, reason: 'cap_exceeded'}` when oversize.
export type HtmlArtifactDecision =
| { write: true; byteLen: number }
| { write: false; byteLen: number; reason: 'cap_exceeded' };
export function decideHtmlArtifactWrite(
htmlContent: string,
): HtmlArtifactDecision {
const byteLen = Buffer.byteLength(htmlContent, 'utf8');
if (byteLen > HTML_ARTIFACT_MAX_BYTES) {
return { write: false, byteLen, reason: 'cap_exceeded' };
}
return { write: true, byteLen };
}
function buildUrl(projectId: string, filename: string): string {
return `/api/projects/${projectId}/artifacts/${encodeURIComponent(filename)}`;
}
export interface WriteContext {
projectId: string;
projectRoot: string;
}
export async function writeMarkdownArtifact(
message: Pick<Message, 'content'>,
ctx: WriteContext,
): Promise<ArtifactWriteResult> {
const slug = deriveMarkdownSlug(message.content);
const filename = `${slug}-${Date.now()}.md`;
const { resolvedRoot, artifactsDir, absPath } = await resolveArtifactPath(
ctx.projectRoot,
filename,
);
await mkdir(artifactsDir, { recursive: true });
await assertArtifactsDirSafe(artifactsDir, resolvedRoot);
await writeFile(absPath, message.content, 'utf8');
return { path: absPath, url: buildUrl(ctx.projectId, filename) };
}
export async function writeHtmlArtifact(
payload: HtmlArtifactPayload,
ctx: WriteContext,
): Promise<ArtifactWriteResult> {
const slug = deriveHtmlSlug(payload);
const filename = `${slug}-${Date.now()}.html`;
const { resolvedRoot, artifactsDir, absPath } = await resolveArtifactPath(
ctx.projectRoot,
filename,
);
await mkdir(artifactsDir, { recursive: true });
await assertArtifactsDirSafe(artifactsDir, resolvedRoot);
await writeFile(absPath, payload.html_content, 'utf8');
return { path: absPath, url: buildUrl(ctx.projectId, filename) };
}
// 1MB cap on HTML artifacts (proposal S6). Larger payloads are not written
// to the `html_artifact` part — the assistant text lands as plain content
// and a warning is logged. Streaming abort was considered but the graceful
// "no artifact, plain text falls back" path is simpler and lossless from
// the user's perspective.
export const HTML_ARTIFACT_MAX_BYTES = 1_048_576;

View File

@@ -1,7 +1,14 @@
import type { MessageMetadata, Session } from '../../types/api.js';
import {
decideHtmlArtifactWrite,
detectHtmlArtifact,
deriveHtmlTitle,
HTML_ARTIFACT_MAX_BYTES,
} from '../artifacts.js';
import * as modelContext from '../model-context.js';
import { maybeFlagForCompaction } from './payload.js';
import { insertParts, partsFromAssistantMessage } from './parts.js';
import type { PartInsert } from './parts.js';
import type { InferenceContext, StreamResult, TurnArgs } from './turn.js';
export async function handleAbortOrError(
@@ -120,17 +127,42 @@ export async function finalizeCompletion(
// a kind='reasoning' part alongside the text.
// TODO(v1.13.1): wrap the UPDATE above and this insertParts in a single
// sql.begin before flipping read authority to message_parts.
await insertParts(
ctx.sql,
partsFromAssistantMessage({
content,
tool_calls: null,
reasoning: result.reasoning,
}).map((p) => ({
...p,
message_id: assistantMessageId,
})),
);
const baseParts: PartInsert[] = partsFromAssistantMessage({
content,
tool_calls: null,
reasoning: result.reasoning,
}).map((p) => ({
...p,
message_id: assistantMessageId,
}));
// v1.14.x-html-artifact-panes: opportunistic HTML detection. Adds a
// SIBLING html_artifact part — never replaces the text part. 1MB cap is
// graceful: oversized payloads are skipped and the assistant message
// lands as plain content (warn logged).
const htmlContent = detectHtmlArtifact(content);
if (htmlContent !== null) {
const decision = decideHtmlArtifactWrite(htmlContent);
if (!decision.write) {
ctx.log.warn(
{ assistantMessageId, byteLen: decision.byteLen, cap: HTML_ARTIFACT_MAX_BYTES },
'html_artifact exceeded 1MB cap; skipping artifact part',
);
} else {
const title = deriveHtmlTitle(htmlContent);
const nextSeq = baseParts.reduce((m, p) => Math.max(m, p.sequence), -1) + 1;
baseParts.push({
message_id: assistantMessageId,
sequence: nextSeq,
kind: 'html_artifact',
payload: {
html_content: htmlContent,
char_count: htmlContent.length,
title,
},
});
}
}
await insertParts(ctx.sql, baseParts);
// v1.11: flag for compaction on the terminal turn too. Catches the common
// case of a turn that hit the limit without invoking tools.
await maybeFlagForCompaction(ctx, chatId, updated);

View File

@@ -11,13 +11,16 @@ import type { ToolCall, ToolResult } from '../../types/api.js';
// (schema.sql adds 'synthesis' to message_parts_kind_chk on startup). The
// dispatch's claim that no schema migration was needed assumed kind was a
// bare text column — it isn't; the constraint enumerates allowed values.
// v1.14.x-html-artifact-panes: 'html_artifact' added. Schema CHECK constraint
// in schema.sql updated in lockstep.
export type PartKind =
| 'text'
| 'tool_call'
| 'tool_result'
| 'reasoning'
| 'step_start'
| 'synthesis';
| 'synthesis'
| 'html_artifact';
export interface PartInsert {
message_id: string;