Third revision: web search, MCP sign-in, exams, intelligent UI, clarifying questions
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 1m0s

- Built-in Parallel web search (keyless; optional sign-in for higher limits and research)
  with its own settings page; OAuth sign-in (RFC 9728/8414/7591, PKCE, RFC 8707) for any
  MCP server, with token refresh and pre-registered client support
- Friendly tool steps (icon, name, status; details on click) and ids stripped from results;
  per-chat tool switches; taller thinking box
- Exams within classes: exam tabs, scoped lists, uploads, imports and Generate; exam-only
  material for generation; class setting for what the groups are called
- Assistant can ask clarifying questions in an inline form before generating
- OpenUI blocks (charts, questions, flashcards, inputs) in assistant, Explain and share chats
- Explain beside the quiz on wide screens, grounded in the cited source pages
- Quiz results: percentage ring coloured by score band, rainbow at 100
- Share links: assistant button like the owner's, hidden during quizzes; documents readable
  in the browser
- Live draft and library updates over server-sent events

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Elijah 2026-11-15 20:30:00 -07:00
parent 60cf2322f7
commit c595e0ff2c
54 changed files with 4710 additions and 387 deletions

View file

@ -142,7 +142,7 @@ describe('MCP servers', () => {
await t.api('PATCH', `/api/ai/mcp/${server.id}`, { headers: { Authorization: 'Bearer wrong' } });
const bad = (await t.api('POST', `/api/ai/mcp/${server.id}/test`)).body.result;
expect(bad.ok).toBe(false);
expect(bad.message).toMatch(/401/);
expect(bad.message).toMatch(/did not accept the sign-in or token/);
expect((await t.api('GET', '/api/ai/mcp')).body.servers[0].lastTestOk).toBe(false);
expect((await t.api('POST', '/api/ai/mcp', { name: 'x', url: 'ftp://example.com' })).status).toBe(422);
@ -155,7 +155,7 @@ describe('MCP servers', () => {
await addServer({ instructions: 'Use for drug monographs only.' });
const events = await sse('/api/ai/chat', { message: 'Use the mcp drug reference for furosemide' });
const tools = events.filter((e) => e.type === 'tool').map((e) => e.tool);
expect(tools.some((x) => x.label === 'Drug ref: lookup_drug' && x.status === 'done')).toBe(true);
expect(tools.some((x) => x.label === 'Drug ref: Lookup drug' && x.status === 'done')).toBe(true);
const call = mcpServer.calls.find((c) => c.method === 'tools/call')!;
expect(call.params).toEqual({ name: 'lookup_drug', arguments: { drug: 'furosemide' } });
expect(call.session).toBe('sess-1');