freezmo/lib/chat-client.ts
Martin Dvorak 756a6257a2 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.
2026-10-11 18:32:11 +00:00

105 lines
3.7 KiB
TypeScript

"use client";
import { ApiError, consumeNdjson } from "./client-api";
import { localeHeader, t } from "./i18n";
import { authHeaders } from "./settings";
import type { ChatSource } from "./chat";
/**
* Client for the streaming chat route. The conversation window and the chosen
* context chunks travel with every request (the server never stores either);
* the API key only ever goes to our own route in its usual header.
*/
export type ChatStreamEvent =
| { type: "token"; text: string }
| { type: "thinking"; text: string }
| { type: "done"; model: string }
| { type: "error"; error: string; kind?: string };
export type StreamChatInput = {
model?: string;
messages: { role: "user" | "assistant"; content: string }[];
context: (ChatSource & { text: string })[];
signal?: AbortSignal;
onToken: (text: string) => void;
onThinking: (text: string) => void;
onDone: (model: string) => void;
};
export async function streamChat(input: StreamChatInput): Promise<void> {
let response: Response;
try {
response = await fetch("/api/chat", {
method: "POST",
headers: { "Content-Type": "application/json", ...authHeaders(), ...localeHeader() },
body: JSON.stringify({
model: input.model || undefined,
messages: input.messages,
context: input.context,
}),
signal: input.signal,
});
} catch (error) {
if (error instanceof Error && error.name === "AbortError") {
throw new ApiError(t("api.cancelled"), "aborted");
}
throw new ApiError(t("api.unreachable"), "network");
}
if (!response.ok) {
const body = (await response.json().catch(() => null)) as { error?: string; kind?: string } | null;
throw new ApiError(body?.error ?? t("api.httpError", { status: response.status }), body?.kind);
}
let streamError: ApiError | null = null;
try {
await consumeNdjson(response, (raw) => {
const event = raw as ChatStreamEvent;
if (event.type === "token") input.onToken(event.text);
else if (event.type === "thinking") input.onThinking(event.text);
else if (event.type === "done") input.onDone(event.model);
else if (event.type === "error") streamError = new ApiError(event.error, event.kind);
});
} catch (error) {
// Aborting while the body is being read rejects the reader with an
// AbortError, not a fetch rejection — treat it as a user stop.
if (error instanceof Error && error.name === "AbortError") {
throw new ApiError(t("api.cancelled"), "aborted");
}
throw error;
}
if (streamError) throw streamError;
}
/**
* Turns attached photos (and any client-extracted document text) into plain
* text through the existing vision pipeline, so the chat model itself never
* needs to be multimodal.
*/
export async function extractChatAttachment(
input: { images?: string[]; text?: string },
options: { signal?: AbortSignal } = {},
): Promise<string> {
let response: Response;
try {
response = await fetch("/api/chat/extract", {
method: "POST",
headers: { "Content-Type": "application/json", ...authHeaders(), ...localeHeader() },
body: JSON.stringify(input),
signal: options.signal,
});
} catch (error) {
if (error instanceof Error && error.name === "AbortError") {
throw new ApiError(t("api.cancelled"), "aborted");
}
throw new ApiError(t("api.unreachable"), "network");
}
const body = (await response.json().catch(() => null)) as { text?: string; error?: string; kind?: string } | null;
if (!response.ok) {
throw new ApiError(body?.error ?? t("api.httpError", { status: response.status }), body?.kind);
}
if (!body?.text?.trim()) throw new ApiError(t("chat.attachEmpty"), "bad_response");
return body.text.trim();
}