Chat mode, phase 1: grounded streaming chat over your notes
Entry points (no sixth tab): Ask in the Library header (desktop button, phone icon), Ask about this deck in the deck menu, Ask a question on study/homework results (compact result travels as context), and a Chat row in the desktop sidebar. Phones get a full-screen route with back + New chat; the tab bar steps aside. - Client-side retrieval: chunk scoped decks (~800 tokens), BM25 against the question + recent turns, top chunks under ~7k tokens, each labelled with deck + section. Notes come from the deck's stored sourceText (already kept for Regenerate); decks without it fall back to generated content and the UI says so. - Stateless server: /api/chat validates against the CHAT_MODELS allowlist, trims the history to ~6k tokens, caps context at ~9k and streams token/thinking/done/error NDJSON. /api/chat/extract reduces attachments to text through the existing vision step. - UI: user bubbles + full-width assistant text, streaming with stop, auto-scroll that pauses with a jump-to-bottom button, safe markdown (React nodes, no HTML injection; KaTeX dynamically imported only when a message has math), Thinking row for reasoning, copy/regenerate/ edit-and-resend, model + context pickers (last model remembered), composer with visualViewport keyboard handling, safe-area, 16px textarea, Enter-to-send on desktop. - Usage-limit failures keep the draft and show the shared message with Settings/Ollama actions; stopping maps the reader abort to a clean stopped state; offline disables sending with a reason. - Settings: Keep notes text for chat toggle; deck menu: Delete notes text. RATE_LIMIT_CHAT + CHAT_MODELS in .env.example and README. - Tests: chat suite (63 checks, stub Ollama) wired into run-all. Full set: 12/12 suites, 487 checks. SW -> freezmo-v32. Also: tests/model-compare.mjs (diagnostic) benchmarks two models on the same notes (latency, repair rounds, activity types) so the gpt-oss vs gemma default can be decided on numbers; defaults unchanged.
This commit is contained in:
parent
6b6a6ea158
commit
756a6257a2
46 changed files with 3840 additions and 56 deletions
107
app/api/chat/extract/route.ts
Normal file
107
app/api/chat/extract/route.ts
Normal file
|
|
@ -0,0 +1,107 @@
|
|||
import { z } from "zod";
|
||||
|
||||
import { extractNotes, notesToText } from "@/lib/ai";
|
||||
import { authErrorMessage, authErrorKind, getServerConfig, resolveAuth } from "@/lib/config";
|
||||
import { friendlyErrorMessage, OllamaError } from "@/lib/ollama";
|
||||
import { rejectCrossOrigin, rejectOversizedBody, requestLocale } from "@/lib/http-guard";
|
||||
import { clientKey, rateLimit, rateLimitResponse } from "@/lib/rate-limit";
|
||||
import { translate } from "@/lib/i18n-dict";
|
||||
|
||||
export const runtime = "nodejs";
|
||||
export const dynamic = "force-dynamic";
|
||||
export const maxDuration = 300;
|
||||
|
||||
/** Same ceiling as deck generation: up to 16 resized photos. */
|
||||
const MAX_BODY_BYTES = 33554432;
|
||||
const MAX_IMAGE_CHARS = 8_000_000;
|
||||
|
||||
const requestSchema = z.object({
|
||||
images: z.array(z.string().min(32).max(MAX_IMAGE_CHARS)).max(16).optional(),
|
||||
text: z.string().max(120_000).optional(),
|
||||
});
|
||||
|
||||
/**
|
||||
* Turns chat attachments (photos, scanned pages, pasted document text) into
|
||||
* plain text with the existing vision pipeline, so any chat model — including
|
||||
* text-only ones — can use them. Never stores anything.
|
||||
*/
|
||||
export async function POST(request: Request) {
|
||||
const locale = requestLocale(request);
|
||||
const crossOrigin = rejectCrossOrigin(request);
|
||||
if (crossOrigin) return crossOrigin;
|
||||
const oversized = rejectOversizedBody(request, MAX_BODY_BYTES);
|
||||
if (oversized) return oversized;
|
||||
|
||||
const config = getServerConfig();
|
||||
|
||||
const limit = rateLimit(`chat:${clientKey(request)}`, config.rateLimits.chat, config.rateLimits.windowMs);
|
||||
if (!limit.allowed) return rateLimitResponse(limit, locale);
|
||||
|
||||
const auth = resolveAuth(config, request);
|
||||
if ("error" in auth) {
|
||||
return Response.json(
|
||||
{ error: authErrorMessage(locale, auth.error), kind: authErrorKind(auth.error) },
|
||||
{ status: 401 },
|
||||
);
|
||||
}
|
||||
|
||||
let payload: unknown;
|
||||
try {
|
||||
payload = await request.json();
|
||||
} catch {
|
||||
return Response.json({ error: translate(locale, "server.bodyNotJson") }, { status: 400 });
|
||||
}
|
||||
|
||||
const parsed = requestSchema.safeParse(payload);
|
||||
if (!parsed.success) {
|
||||
return Response.json(
|
||||
{ error: translate(locale, "server.invalidRequest", { detail: parsed.error.issues[0]?.message ?? "" }) },
|
||||
{ status: 400 },
|
||||
);
|
||||
}
|
||||
|
||||
const images = (parsed.data.images ?? []).map(stripDataUrlPrefix).filter(Boolean);
|
||||
const text = parsed.data.text?.trim() ?? "";
|
||||
if (images.length === 0 && !text) {
|
||||
return Response.json({ error: translate(locale, "server.needContent") }, { status: 400 });
|
||||
}
|
||||
|
||||
const abort = new AbortController();
|
||||
const timer = setTimeout(() => abort.abort(), config.timeoutMs);
|
||||
try {
|
||||
if (images.length === 0) {
|
||||
// Plain text needs no model call at all.
|
||||
return Response.json({ text: text.slice(0, 48_000) });
|
||||
}
|
||||
const extraction = await extractNotes({
|
||||
model: config.visionModel,
|
||||
repairModel: config.textModel,
|
||||
auth: auth.auth,
|
||||
images,
|
||||
text: text || undefined,
|
||||
signal: abort.signal,
|
||||
});
|
||||
const extracted = notesToText(extraction.notes).slice(0, 48_000);
|
||||
if (!extracted.trim()) {
|
||||
return Response.json({ error: translate(locale, "chat.attachEmpty"), kind: "bad_response" }, { status: 422 });
|
||||
}
|
||||
return Response.json({ text: extracted });
|
||||
} catch (error) {
|
||||
console.error("[api/chat/extract]", error instanceof OllamaError ? `${error.kind}: ${error.message}` : error);
|
||||
return Response.json(
|
||||
{
|
||||
error: friendlyErrorMessage(error, auth.auth.baseUrl, locale),
|
||||
kind: error instanceof OllamaError ? error.kind : "unknown",
|
||||
},
|
||||
{ status: 502 },
|
||||
);
|
||||
} finally {
|
||||
clearTimeout(timer);
|
||||
}
|
||||
}
|
||||
|
||||
function stripDataUrlPrefix(value: string): string {
|
||||
const commaIndex = value.indexOf(",");
|
||||
if (value.startsWith("data:") && commaIndex !== -1) return value.slice(commaIndex + 1);
|
||||
return value;
|
||||
}
|
||||
193
app/api/chat/route.ts
Normal file
193
app/api/chat/route.ts
Normal file
|
|
@ -0,0 +1,193 @@
|
|||
import { z } from "zod";
|
||||
|
||||
import { authErrorMessage, authErrorKind, getServerConfig, resolveAuth, resolveModelName } from "@/lib/config";
|
||||
import { friendlyErrorMessage, ollamaChatStream, OllamaError } from "@/lib/ollama";
|
||||
import { rejectCrossOrigin, rejectOversizedBody, requestLocale } from "@/lib/http-guard";
|
||||
import { clientKey, rateLimit, rateLimitResponse } from "@/lib/rate-limit";
|
||||
import { translate } from "@/lib/i18n-dict";
|
||||
import { buildChatSystemPrompt } from "@/lib/prompts";
|
||||
import { estimateTokens, trimHistory } from "@/lib/chat-trim";
|
||||
|
||||
export const runtime = "nodejs";
|
||||
export const dynamic = "force-dynamic";
|
||||
export const maxDuration = 300;
|
||||
|
||||
/** Context chunks (~7k tokens) plus a trimmed window plus JSON overhead. */
|
||||
const MAX_BODY_BYTES = 1_000_000;
|
||||
|
||||
/** Hard cap on the attached context, whatever the client sends. */
|
||||
const CONTEXT_TOKEN_BUDGET = 9000;
|
||||
|
||||
const requestSchema = z.object({
|
||||
model: z.string().min(1).max(120).optional(),
|
||||
messages: z
|
||||
.array(
|
||||
z.object({
|
||||
role: z.enum(["user", "assistant"]),
|
||||
content: z.string().min(1).max(20_000),
|
||||
}),
|
||||
)
|
||||
.min(1)
|
||||
.max(60),
|
||||
context: z
|
||||
.array(
|
||||
z.object({
|
||||
deckId: z.string().max(120),
|
||||
deckTitle: z.string().max(200),
|
||||
section: z.string().max(200),
|
||||
text: z.string().min(1).max(12_000),
|
||||
}),
|
||||
)
|
||||
.max(40)
|
||||
.optional(),
|
||||
});
|
||||
|
||||
type StreamEvent =
|
||||
| { type: "token"; text: string }
|
||||
| { type: "thinking"; text: string }
|
||||
| { type: "done"; model: string }
|
||||
| { type: "error"; error: string; kind?: string };
|
||||
|
||||
function encoder() {
|
||||
const enc = new TextEncoder();
|
||||
return (event: StreamEvent) => enc.encode(`${JSON.stringify(event)}\n`);
|
||||
}
|
||||
|
||||
export async function POST(request: Request) {
|
||||
const locale = requestLocale(request);
|
||||
const crossOrigin = rejectCrossOrigin(request);
|
||||
if (crossOrigin) return crossOrigin;
|
||||
const oversized = rejectOversizedBody(request, MAX_BODY_BYTES);
|
||||
if (oversized) return oversized;
|
||||
|
||||
const config = getServerConfig();
|
||||
|
||||
const limit = rateLimit(`chat:${clientKey(request)}`, config.rateLimits.chat, config.rateLimits.windowMs);
|
||||
if (!limit.allowed) return rateLimitResponse(limit, locale);
|
||||
|
||||
const auth = resolveAuth(config, request);
|
||||
if ("error" in auth) {
|
||||
return Response.json(
|
||||
{ error: authErrorMessage(locale, auth.error), kind: authErrorKind(auth.error) },
|
||||
{ status: 401 },
|
||||
);
|
||||
}
|
||||
|
||||
let payload: unknown;
|
||||
try {
|
||||
payload = await request.json();
|
||||
} catch {
|
||||
return Response.json({ error: translate(locale, "server.bodyNotJson") }, { status: 400 });
|
||||
}
|
||||
|
||||
const parsed = requestSchema.safeParse(payload);
|
||||
if (!parsed.success) {
|
||||
return Response.json(
|
||||
{
|
||||
error: translate(locale, "server.invalidRequest", {
|
||||
detail: parsed.error.issues
|
||||
.slice(0, 3)
|
||||
.map((issue) => `${issue.path.join(".") || "body"} ${issue.message}`)
|
||||
.join("; "),
|
||||
}),
|
||||
},
|
||||
{ status: 400 },
|
||||
);
|
||||
}
|
||||
|
||||
const { messages, context } = parsed.data;
|
||||
|
||||
// The model must come from the server's allowlist — never from the client.
|
||||
const allowed = config.chatModels.length > 0 ? config.chatModels : [config.textModel];
|
||||
const model = parsed.data.model ?? allowed[0];
|
||||
if (!allowed.some((entry) => entry.toLowerCase() === model.toLowerCase())) {
|
||||
return Response.json(
|
||||
{ error: translate(locale, "server.chatModelNotAllowed"), kind: "bad_model" },
|
||||
{ status: 400 },
|
||||
);
|
||||
}
|
||||
|
||||
const last = messages[messages.length - 1];
|
||||
if (last.role !== "user") {
|
||||
return Response.json({ error: translate(locale, "server.chatNeedsQuestion") }, { status: 400 });
|
||||
}
|
||||
|
||||
// Cap the context, then trim the conversation window.
|
||||
const keptContext: typeof context = [];
|
||||
let contextTokens = 0;
|
||||
for (const chunk of context ?? []) {
|
||||
const cost = estimateTokens(chunk.text);
|
||||
if (contextTokens + cost > CONTEXT_TOKEN_BUDGET) break;
|
||||
keptContext.push(chunk);
|
||||
contextTokens += cost;
|
||||
}
|
||||
const history = trimHistory(messages);
|
||||
|
||||
const system = buildChatSystemPrompt({
|
||||
context: keptContext.map((chunk) => ({
|
||||
deckTitle: chunk.deckTitle,
|
||||
section: chunk.section,
|
||||
text: chunk.text,
|
||||
})),
|
||||
});
|
||||
|
||||
const encode = encoder();
|
||||
const abort = new AbortController();
|
||||
const globalTimer = setTimeout(() => abort.abort(), config.timeoutMs);
|
||||
|
||||
const stream = new ReadableStream<Uint8Array>({
|
||||
async start(controller) {
|
||||
const send = (event: StreamEvent) => {
|
||||
try {
|
||||
controller.enqueue(encode(event));
|
||||
} catch {
|
||||
/* client went away */
|
||||
}
|
||||
};
|
||||
|
||||
try {
|
||||
const result = await ollamaChatStream({
|
||||
model,
|
||||
auth: auth.auth,
|
||||
messages: [{ role: "system", content: system }, ...history],
|
||||
signal: abort.signal,
|
||||
onToken: (text) => send({ type: "token", text }),
|
||||
onThinking: (text) => send({ type: "thinking", text }),
|
||||
});
|
||||
send({ type: "done", model: resolveModelName(result.model, auth.auth.directCloud) });
|
||||
} catch (error) {
|
||||
// A client-side stop aborts the upstream call: nothing to report.
|
||||
if (abort.signal.aborted && request.signal.aborted) {
|
||||
/* stopped by the user */
|
||||
} else {
|
||||
const message = friendlyErrorMessage(error, auth.auth.baseUrl, locale);
|
||||
console.error("[api/chat]", error instanceof OllamaError ? `${error.kind}: ${error.message}` : error);
|
||||
send({
|
||||
type: "error",
|
||||
error: message,
|
||||
kind: error instanceof OllamaError ? error.kind : "unknown",
|
||||
});
|
||||
}
|
||||
} finally {
|
||||
clearTimeout(globalTimer);
|
||||
try {
|
||||
controller.close();
|
||||
} catch {
|
||||
/* already closed */
|
||||
}
|
||||
}
|
||||
},
|
||||
cancel() {
|
||||
clearTimeout(globalTimer);
|
||||
abort.abort();
|
||||
},
|
||||
});
|
||||
|
||||
return new Response(stream, {
|
||||
headers: {
|
||||
"Content-Type": "application/x-ndjson; charset=utf-8",
|
||||
"Cache-Control": "no-store, no-transform",
|
||||
Connection: "keep-alive",
|
||||
},
|
||||
});
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue