v1.1 batch 1: markdown, message actions, tok/s+ctx, AI naming

Four features land together on this branch:

1. Markdown rendering — assistant messages go through react-markdown +
   remark-gfm. Fenced code blocks render via existing CodeBlock (with copy
   button); inline `code` is styled inline. User messages stay plain text.
   No raw HTML (no rehype-raw).

2. Per-message Copy + Regenerate. New endpoint
   POST /api/sessions/:id/messages/:message_id/regenerate validates the
   target (404/400/409), atomically deletes the target plus any later
   messages in the session, inserts a fresh streaming assistant row, and
   enqueues a normal inference run. The DELETE bound uses a SQL subquery
   (`created_at >= (SELECT created_at FROM messages WHERE id = $1)`)
   instead of a JS round-trip so postgres TIMESTAMPTZ µs precision is
   preserved — otherwise sub-ms clock_timestamp() differences between the
   user row and the assistant row collapsed to the same JS Date, pulling
   the triggering user message into the >= bound. New `messages_deleted`
   WS frame so already-connected clients prune the stale tail without
   needing a full snapshot resend.

3. tok/s + ctx counter. Five new nullable message columns: tokens_used,
   ctx_used, ctx_max, started_at, finished_at. started_at is set right
   before the OpenAI call in services/inference.ts (not in the route, not
   in the frame handler); finished_at + tokens_used + ctx_used + ctx_max
   are committed in the same UPDATE that flips status to 'complete'. The
   inference request now opts into stream_options.include_usage so the
   final chunk carries usage; defensive parsing also picks up timings.n_ctx
   when llama.cpp emits it (currently absent for our llama-swap models, so
   ctx_max stays NULL and the UI just shows `<used> ctx`). message_complete
   frame extended with tokens_used / ctx_used / ctx_max / started_at /
   finished_at / model. Frontend StatsLine in MessageBubble computes tok/s
   client-side from the timestamps and renders muted mono text below the
   body of completed assistant messages.

4. AI chat naming after the first turn. Backend services/auto_name.ts
   runs via setImmediate after the top-level inference resolves; it
   checks that there is exactly one completed assistant message and that
   the session has not been user-renamed (`name IS NULL OR name = '' OR
   name = 'New session'`), then fires a single non-streaming chat
   completion with the spec prompt. Qwen3 chat templates emit chain-of-
   thought into reasoning_content and burn the entire max_tokens budget
   without producing visible output, so the request includes
   `chat_template_kwargs: { enable_thinking: false }` and max_tokens=30.
   Title is trimmed, quote-stripped, "Title:" prefix dropped, and
   truncated to 60 chars before a guarded UPDATE on sessions.name. New
   `session_renamed` WS frame propagates to the open session view
   directly and to the project's session list via a tiny module-scope
   event bus (apps/web/src/hooks/sessionEvents.ts) — kept dumb: one event
   type, two methods, no library.

Cleanups: dropped the now-unused splitCodeBlocks export from CodeBlock.tsx
(react-markdown supersedes it), and added a long-form NOTE in auto_name.ts
documenting the enable_thinking + max_tokens pattern for any future Qwen-
family non-streaming utility calls (planned: fork-message, agent-routing,
web-search summarization).

Schema bootstrap remains idempotent (ADD COLUMN IF NOT EXISTS). Auth,
broker, clock_timestamp() conventions, and zod validation all unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-14 22:52:40 +00:00
parent a7f218e182
commit 2464d23bb6
18 changed files with 1559 additions and 94 deletions

View File

@@ -0,0 +1,32 @@
// Tiny in-app event bus for session metadata changes that need to propagate
// across hooks (e.g. AI rename arriving via WS in the session view needs to
// also refresh the sidebar's session list). One event type for now.
export interface SessionRenamedEvent {
type: 'session_renamed';
session_id: string;
name: string;
}
type SessionEvent = SessionRenamedEvent;
type Listener = (event: SessionEvent) => void;
const listeners = new Set<Listener>();
export const sessionEvents = {
emit(event: SessionEvent) {
for (const listener of listeners) {
try {
listener(event);
} catch {
// swallow — one bad listener shouldn't break others
}
}
},
subscribe(listener: Listener): () => void {
listeners.add(listener);
return () => {
listeners.delete(listener);
};
},
};

View File

@@ -1,5 +1,6 @@
import { useEffect, useRef, useState } from 'react';
import type { Message, WsFrame } from '@/api/types';
import { sessionEvents } from './sessionEvents';
interface State {
messages: Message[];
@@ -24,6 +25,11 @@ function applyFrame(state: State, frame: WsFrame): State {
tool_results: null,
status: 'streaming',
last_seq: 0,
tokens_used: null,
ctx_used: null,
ctx_max: null,
started_at: null,
finished_at: null,
created_at: new Date().toISOString(),
};
return { ...state, messages: [...state.messages, newMsg] };
@@ -76,16 +82,47 @@ function applyFrame(state: State, frame: WsFrame): State {
},
status: 'complete',
last_seq: 0,
tokens_used: null,
ctx_used: null,
ctx_max: null,
started_at: null,
finished_at: null,
created_at: new Date().toISOString(),
};
return { ...state, messages: [...state.messages, newMsg] };
}
case 'message_complete': {
const next = state.messages.map((m) =>
m.id === frame.message_id ? { ...m, status: 'complete' as const } : m
m.id === frame.message_id
? {
...m,
status: 'complete' as const,
...(frame.tokens_used !== undefined ? { tokens_used: frame.tokens_used } : {}),
...(frame.ctx_used !== undefined ? { ctx_used: frame.ctx_used } : {}),
...(frame.ctx_max !== undefined ? { ctx_max: frame.ctx_max } : {}),
...(frame.started_at !== undefined ? { started_at: frame.started_at } : {}),
...(frame.finished_at !== undefined ? { finished_at: frame.finished_at } : {}),
}
: m
);
return { ...state, messages: next };
}
case 'messages_deleted': {
const removeSet = new Set(frame.message_ids);
return {
...state,
messages: state.messages.filter((m) => !removeSet.has(m.id)),
};
}
case 'session_renamed': {
// Side-effect, not state — dispatch via event bus to other hooks.
sessionEvents.emit({
type: 'session_renamed',
session_id: frame.session_id,
name: frame.name,
});
return state;
}
case 'error': {
const next = frame.message_id
? state.messages.map((m) =>

View File

@@ -1,6 +1,7 @@
import { useCallback, useEffect, useState } from 'react';
import { api } from '@/api/client';
import type { Session } from '@/api/types';
import { sessionEvents } from './sessionEvents';
export function useSessions(projectId: string | undefined) {
const [sessions, setSessions] = useState<Session[] | null>(null);
@@ -24,6 +25,23 @@ export function useSessions(projectId: string | undefined) {
void refresh();
}, [refresh]);
useEffect(() => {
return sessionEvents.subscribe((event) => {
if (event.type !== 'session_renamed') return;
setSessions((prev) => {
if (!prev) return prev;
let changed = false;
const next = prev.map((s) => {
if (s.id !== event.session_id) return s;
if (s.name === event.name) return s;
changed = true;
return { ...s, name: event.name };
});
return changed ? next : prev;
});
});
}, []);
const create = useCallback(
async (body: { name?: string; model?: string; system_prompt?: string }) => {
if (!projectId) throw new Error('no project');