Files
newapi-yx-diy/web/src/components/table/usage-logs/modals/ChannelAffinityUsageCacheModal.jsx
Seefs 540cf6c991 fix: channel affinity (#2799)
* fix: channel affinity log styles

* fix: Issue with incorrect data storage when switching key sources

* feat: support not retrying after a single rule configuration fails

* fix: render channel affinity tooltip as multiline content

* feat: channel affinity cache hit

* fix: prevent ChannelAffinityUsageCacheModal infinite loading and hide data before fetch

* chore: format backend with gofmt and frontend with prettier/eslint autofix
2026-02-02 14:37:31 +08:00

201 lines
5.9 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

/*
Copyright (C) 2025 QuantumNous
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as
published by the Free Software Foundation, either version 3 of the
License, or (at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
For commercial licensing, please contact support@quantumnous.com
*/
import React, { useEffect, useMemo, useRef, useState } from 'react';
import { Modal, Descriptions, Spin, Typography } from '@douyinfe/semi-ui';
import { API, showError, timestamp2string } from '../../../../helpers';
const { Text } = Typography;
function formatRate(hit, total) {
if (!total || total <= 0) return '-';
const r = (Number(hit || 0) / Number(total || 0)) * 100;
if (!Number.isFinite(r)) return '-';
return `${r.toFixed(2)}%`;
}
function formatTokenRate(n, d) {
const nn = Number(n || 0);
const dd = Number(d || 0);
if (!dd || dd <= 0) return '-';
const r = (nn / dd) * 100;
if (!Number.isFinite(r)) return '-';
return `${r.toFixed(2)}%`;
}
const ChannelAffinityUsageCacheModal = ({
t,
showChannelAffinityUsageCacheModal,
setShowChannelAffinityUsageCacheModal,
channelAffinityUsageCacheTarget,
}) => {
const [loading, setLoading] = useState(false);
const [stats, setStats] = useState(null);
const requestSeqRef = useRef(0);
const params = useMemo(() => {
const x = channelAffinityUsageCacheTarget || {};
return {
rule_name: (x.rule_name || '').trim(),
using_group: (x.using_group || '').trim(),
key_hint: (x.key_hint || '').trim(),
key_fp: (x.key_fp || '').trim(),
};
}, [channelAffinityUsageCacheTarget]);
useEffect(() => {
if (!showChannelAffinityUsageCacheModal) {
requestSeqRef.current += 1; // invalidate inflight request
setLoading(false);
setStats(null);
return;
}
if (!params.rule_name || !params.key_fp) {
setLoading(false);
setStats(null);
return;
}
const reqSeq = (requestSeqRef.current += 1);
setStats(null);
setLoading(true);
(async () => {
try {
const res = await API.get('/api/log/channel_affinity_usage_cache', {
params,
disableDuplicate: true,
});
if (reqSeq !== requestSeqRef.current) return;
const { success, message, data } = res.data || {};
if (!success) {
setStats(null);
showError(t(message || '请求失败'));
return;
}
setStats(data || {});
} catch (e) {
if (reqSeq !== requestSeqRef.current) return;
setStats(null);
showError(t('请求失败'));
} finally {
if (reqSeq !== requestSeqRef.current) return;
setLoading(false);
}
})();
}, [
showChannelAffinityUsageCacheModal,
params.rule_name,
params.using_group,
params.key_hint,
params.key_fp,
t,
]);
const rows = useMemo(() => {
const s = stats || {};
const hit = Number(s.hit || 0);
const total = Number(s.total || 0);
const windowSeconds = Number(s.window_seconds || 0);
const lastSeenAt = Number(s.last_seen_at || 0);
const promptTokens = Number(s.prompt_tokens || 0);
const completionTokens = Number(s.completion_tokens || 0);
const totalTokens = Number(s.total_tokens || 0);
const cachedTokens = Number(s.cached_tokens || 0);
const promptCacheHitTokens = Number(s.prompt_cache_hit_tokens || 0);
return [
{ key: t('规则'), value: s.rule_name || params.rule_name || '-' },
{ key: t('分组'), value: s.using_group || params.using_group || '-' },
{
key: t('Key 摘要'),
value: params.key_hint || '-',
},
{
key: t('Key 指纹'),
value: s.key_fp || params.key_fp || '-',
},
{ key: t('TTL'), value: windowSeconds > 0 ? windowSeconds : '-' },
{
key: t('命中率'),
value: `${hit}/${total} (${formatRate(hit, total)})`,
},
{
key: t('Prompt tokens'),
value: promptTokens,
},
{
key: t('Cached tokens'),
value: `${cachedTokens} (${formatTokenRate(cachedTokens, promptTokens)})`,
},
{
key: t('Prompt cache hit tokens'),
value: promptCacheHitTokens,
},
{
key: t('Completion tokens'),
value: completionTokens,
},
{
key: t('Total tokens'),
value: totalTokens,
},
{
key: t('最近一次'),
value: lastSeenAt > 0 ? timestamp2string(lastSeenAt) : '-',
},
];
}, [stats, params, t]);
return (
<Modal
title={t('渠道亲和性:上游缓存命中')}
visible={showChannelAffinityUsageCacheModal}
onCancel={() => setShowChannelAffinityUsageCacheModal(false)}
footer={null}
centered
closable
maskClosable
width={640}
>
<div style={{ padding: 16 }}>
<div style={{ marginBottom: 12 }}>
<Text type='tertiary' size='small'>
{t(
'命中判定usage 中存在 cached tokens例如 cached_tokens/prompt_cache_hit_tokens即视为命中。',
)}
</Text>
</div>
<Spin spinning={loading} tip={t('加载中...')}>
{stats ? (
<Descriptions data={rows} />
) : (
<div style={{ padding: '24px 0' }}>
<Text type='tertiary' size='small'>
{loading ? t('加载中...') : t('暂无数据')}
</Text>
</div>
)}
</Spin>
</div>
</Modal>
);
};
export default ChannelAffinityUsageCacheModal;