第二十七轮: 三线直传(/v1/messages,/v1/responses)+删除路由别名;第二十八轮: element-plus 按需引入+死代码清理+前端支持格式列/API Key 文档
This commit is contained in:
1 parent
1b54802ad3
commit
4c1973b13d
28 files changed
+3016
-1263
No files matched your search
@@ -77,6 +77,9 @@
|
||||
</div>
|
||||
<div><b>{{ t('apidoc.auth') }}</b> <span class="code">{{ t('apidoc.authVal') }}</span></div>
|
||||
<div><b>{{ t('apidoc.modelPick') }}</b> <span>{{ t('apidoc.modelPickVal') }}</span></div>
|
||||
<!-- 第二十七轮:三条协议线各自的请求格式不同,先在这里点明「去哪看支持哪些线」,
|
||||
免得用户点了 400 才知道格式选错(400 文案也会列出该模型支持的线)。 -->
|
||||
<div><b>{{ t('apidoc.formats') }}</b> <span>{{ t('apidoc.formatsVal') }}</span></div>
|
||||
<div><b>{{ t('apidoc.ctype') }}</b> <span>{{ t('apidoc.ctypeVal') }}</span></div>
|
||||
</div>
|
||||
|
||||
@@ -141,12 +144,19 @@ const limit = ref<number | null>(null) // null = 不限(admin)
|
||||
const base = window.location.origin
|
||||
|
||||
// 端点表:与 app/main.py 的真实路由一一对应(别写成 README 里才有的东西)
|
||||
// 第二十七轮:三条协议线并排 —— chat/completions(OpenAI 兼容,走专用路径)、
|
||||
// messages(Anthropic)、responses(OpenAI Responses)。后两条是「直传」:原始 JSON 进、
|
||||
// 上游响应原样出,网关不翻译字段;某个模型能不能用这条线,看「供应商与模型」页的
|
||||
// 「支持的格式」列(用错线会在入口 400 并列出该模型支持哪些线)。
|
||||
const endpoints = computed(() => [
|
||||
{ method: 'GET', path: '/v1/models', desc: t('apidoc.epModels') },
|
||||
{ method: 'POST', path: '/v1/chat/completions', desc: t('apidoc.epChat') },
|
||||
{ method: 'POST', path: '/v1/messages', desc: t('apidoc.epMessages') },
|
||||
{ method: 'POST', path: '/v1/responses', desc: t('apidoc.epResponses') },
|
||||
{ method: 'POST', path: '/v1/images/generations', desc: t('apidoc.epImages') },
|
||||
{ method: 'POST', path: '/v1/videos', desc: t('apidoc.epVideoCreate') },
|
||||
{ method: 'GET', path: '/v1/videos/{video_id}?model=...', desc: t('apidoc.epVideoPoll') },
|
||||
{ method: 'GET', path: '/v1/media/download?url=...', desc: t('apidoc.epDownload') },
|
||||
{ method: 'GET', path: '/history/{kind}', desc: t('apidoc.epHistory') },
|
||||
{ method: 'GET', path: '/logs', desc: t('apidoc.epLogs') },
|
||||
{ method: 'GET', path: '/metrics', desc: t('apidoc.epMetrics') },
|
||||
@@ -154,8 +164,9 @@ const endpoints = computed(() => [
|
||||
])
|
||||
|
||||
const notes = computed(() => [
|
||||
t('apidoc.noteVision'), t('apidoc.noteN1'), t('apidoc.noteVideo'),
|
||||
t('apidoc.notePoll'), t('apidoc.noteMedia'), t('apidoc.noteKey'), t('apidoc.noteAudit'),
|
||||
t('apidoc.noteVision'), t('apidoc.noteCross'), t('apidoc.noteConvId'), t('apidoc.noteN1'),
|
||||
t('apidoc.noteVideo'), t('apidoc.notePoll'), t('apidoc.noteMedia'), t('apidoc.noteDownload'),
|
||||
t('apidoc.noteKey'), t('apidoc.noteAudit'),
|
||||
])
|
||||
|
||||
// 示例里的 Key 用占位符 $GW_KEY(不把真 Key 渲染进文档;本页的 Key 明文只在上方列表里回显)
|
||||
@@ -166,7 +177,15 @@ const examples = computed(() => {
|
||||
{ title: t('apidoc.exChat'), code:
|
||||
`curl ${base}/v1/chat/completions \\
|
||||
${H} \\
|
||||
-d '{"model":"wjd","messages":[{"role":"user","content":"${t('apidoc.sampleChat')}"}]}'` },
|
||||
-d '{"model":"agnes-3.0-flash","messages":[{"role":"user","content":"${t('apidoc.sampleChat')}"}]}'` },
|
||||
{ title: t('apidoc.exMessages'), code:
|
||||
`curl ${base}/v1/messages \\
|
||||
${H} \\
|
||||
-d '{"model":"${t('apidoc.sampleModelMessages')}","max_tokens":64,"messages":[{"role":"user","content":"${t('apidoc.sampleChat')}"}]}'` },
|
||||
{ title: t('apidoc.exResponses'), code:
|
||||
`curl ${base}/v1/responses \\
|
||||
${H} \\
|
||||
-d '{"model":"${t('apidoc.sampleModelResponses')}","input":"${t('apidoc.sampleChat')}","max_output_tokens":64}'` },
|
||||
{ title: t('apidoc.exImg'), code:
|
||||
`curl ${base}/v1/images/generations \\
|
||||
${H} \\
|
||||
@@ -185,7 +204,7 @@ curl "${base}/v1/videos/task_xxx?model=agnes-video-2.5-flash" \\
|
||||
`from openai import OpenAI
|
||||
|
||||
c = OpenAI(base_url="${base}/v1", api_key="wjd-xxxxxxxx")
|
||||
r = c.chat.completions.create(model="wjd", messages=[{"role": "user", "content": "${t('apidoc.sampleChat')}"}])
|
||||
r = c.chat.completions.create(model="agnes-3.0-flash", messages=[{"role": "user", "content": "${t('apidoc.sampleChat')}"}])
|
||||
print(r.choices[0].message.content)` },
|
||||
]
|
||||
})
|
||||
|
||||
+22
-34
@@ -104,15 +104,12 @@
|
||||
</div>
|
||||
|
||||
<div v-for="msg in messages" :key="msg.id" class="msg" :class="msg.role === 'user' ? 'me' : 'ai'">
|
||||
<!-- 助手:降级/服务信息 -->
|
||||
<!-- 助手:服务信息(第二十七轮起没有"降级"这回事 —— 路由别名已删除) -->
|
||||
<div v-if="msg.role === 'assistant' && msg.meta" class="resp-meta">
|
||||
<el-tag size="small" :type="msg.meta.fallback ? 'warning' : 'success'" effect="light">
|
||||
<template v-if="msg.meta.fallback">{{ t('chat.fallback', { provider: msg.meta.provider }) }}</template><template v-else>{{ t('chat.servedBy', { provider: msg.meta.provider }) }}</template>
|
||||
<el-tag size="small" type="success" effect="light">
|
||||
{{ t('chat.servedBy', { provider: msg.meta.provider }) }}
|
||||
</el-tag>
|
||||
<span class="meta-txt">
|
||||
<template v-if="msg.meta.fallback">{{ t('chat.requestedTo', { req: msg.meta.requested, served: msg.meta.served }) }}</template>
|
||||
<template v-else>{{ msg.meta.served }}</template>
|
||||
</span>
|
||||
<span class="meta-txt">{{ msg.meta.served }}</span>
|
||||
<span v-if="msg.usage || msg.cost != null" class="meta-txt">
|
||||
· {{ msg.cost != null ? `¥${msg.cost}` : '' }}
|
||||
<template v-if="msg.usage">{{ tokensText(msg.usage) }}</template>
|
||||
@@ -199,15 +196,7 @@
|
||||
</el-tooltip>
|
||||
<input ref="fileEl" type="file" accept="image/*" multiple class="hide-file" @change="onFiles" />
|
||||
|
||||
<el-select v-model="params.model" class="model-sel" size="small" :disabled="streaming" filterable :placeholder="t('chat.routeGroup')">
|
||||
<el-option-group :label="t('chat.routeGroup')">
|
||||
<el-option v-for="r in routes" :key="r.id" :value="r.id" :label="chainLabel(r)">
|
||||
<span class="opt">
|
||||
<span>{{ chainLabel(r) }}</span>
|
||||
<Icon v-if="r.vision" name="eye" :size="13" />
|
||||
</span>
|
||||
</el-option>
|
||||
</el-option-group>
|
||||
<el-select v-model="params.model" class="model-sel" size="small" :disabled="streaming" filterable :placeholder="t('chat.pickModel')">
|
||||
<el-option-group :label="t('chat.textModels')">
|
||||
<el-option v-for="m in textModels" :key="m.id" :value="m.id" :label="modelLabel(m)">
|
||||
<span class="opt">
|
||||
@@ -289,36 +278,36 @@ const router = useRouter()
|
||||
const { t } = useI18n()
|
||||
|
||||
// ── 模型选项 ──
|
||||
const routes = ref<any[]>([])
|
||||
// 第二十七轮: 路由别名(wjd)功能已整体删除 —— /v1/models 里只剩真实模型,
|
||||
// 调用方选哪个模型就是哪个(网关不再"自动挑最快模型")。
|
||||
const textModels = ref<any[]>([])
|
||||
async function loadModels() {
|
||||
try {
|
||||
const j = await api('/v1/models')
|
||||
const data: any[] = j.data || []
|
||||
routes.value = data.filter((x) => x.type === 'route')
|
||||
textModels.value = data.filter((x) => x.type !== 'route')
|
||||
textModels.value = data.filter((x) => x.type !== 'image' && x.type !== 'video')
|
||||
// 默认模型:优先 agnes-3.0-flash(旗舰),否则用列表第一个。
|
||||
// 同时兜住"本地存着旧模型 id(比如已删除的 wjd)"的情况 —— 认不出来就换默认,
|
||||
// 免得下拉框空着、发出去却被网关 400。
|
||||
if (!textModels.value.some((m) => m.id === params.model)) {
|
||||
const def = textModels.value.find((m) => m.id === 'agnes-3.0-flash')
|
||||
params.model = def ? def.id : (textModels.value[0]?.id || '')
|
||||
}
|
||||
} catch (e: any) {
|
||||
if (e && e.status === 401) { router.push('/login'); return }
|
||||
ElMessage.error(t('chat.loadModelsErr', { msg: (e && e.message) || e }))
|
||||
}
|
||||
}
|
||||
function chainLabel(r: any) {
|
||||
const chain = (r.models || []).join(' → ')
|
||||
// 括号样式(全角/半角)也交给 i18n:英文里用半角更自然
|
||||
return t('chat.chainLabel', { id: r.id, chain: chain || t('chat.emptyChain') })
|
||||
}
|
||||
|
||||
// ── 视觉能力(第十三轮)──
|
||||
// 网关 /v1/models 会回 vision 字段(Agnes 3.0 Flash = true,其余文本模型默认 false)。
|
||||
// 带图请求走路由别名时网关会把视觉模型排到链首;选了**不支持视觉的真实模型**时
|
||||
// 这里提前告警并提供一键切换,避免"发了图但模型根本没看"。
|
||||
// 第二十七轮: 路由链删除后网关不再"把视觉模型排到链首" —— 选了不支持视觉的模型时,
|
||||
// 这里提前告警并提供一键切换,避免"发了图但模型根本没看"。
|
||||
const visionModels = computed(() =>
|
||||
textModels.value.filter((m) => m.vision).map((m) => m.id))
|
||||
const visionOk = computed(() => {
|
||||
const m = routes.value.find((r) => r.id === params.model)
|
||||
if (m) return !!m.vision || !!(m.models || []).some((id: string) => visionModels.value.includes(id))
|
||||
const t2 = textModels.value.find((x) => x.id === params.model)
|
||||
return !!t2?.vision
|
||||
const m = textModels.value.find((x) => x.id === params.model)
|
||||
return !!m?.vision
|
||||
})
|
||||
const firstVisionModel = computed(() => visionModels.value[0] || '')
|
||||
function useVisionModel() {
|
||||
@@ -330,7 +319,8 @@ function modelLabel(m: any) {
|
||||
|
||||
// ── 参数与状态 ──
|
||||
const params = reactive({
|
||||
model: 'wjd',
|
||||
// 空串 = 还没拿到模型列表;loadModels() 里填入默认模型(第二十七轮: 不再默认 wjd)
|
||||
model: '',
|
||||
temperature: 0.7,
|
||||
top_p: 1,
|
||||
max_tokens: null as number | null,
|
||||
@@ -654,12 +644,11 @@ async function runOnce(input: string) {
|
||||
}
|
||||
reply.usage = j?.usage || undefined
|
||||
reply.cost = j?.estimated_cost_cny ?? undefined
|
||||
if (j?.route || j?.provider) {
|
||||
if (j?.provider || j?.served_model) {
|
||||
reply.meta = {
|
||||
served: j.served_model || j.model || params.model,
|
||||
provider: j.provider_name || j.provider,
|
||||
requested: j.model || params.model,
|
||||
fallback: !!(j.route && j.route.fallback_used),
|
||||
}
|
||||
}
|
||||
} catch (e: any) {
|
||||
@@ -687,7 +676,6 @@ async function runStream(_input: string) {
|
||||
served: chunk.served_model || chunk.model || params.model,
|
||||
provider: chunk.provider_name || chunk.provider,
|
||||
requested: chunk.model || params.model,
|
||||
fallback: !!(chunk.route && chunk.route.fallback_used),
|
||||
}
|
||||
}
|
||||
if (chunk.usage && !chunk.choices?.length) {
|
||||
|
||||
@@ -41,16 +41,16 @@
|
||||
<div class="sep" />
|
||||
|
||||
<div class="card-h" style="margin-bottom: 8px">
|
||||
<b>{{ t('dashboard.routeAlias') }}</b>
|
||||
<span class="sub">{{ t('dashboard.routeChain') }}</span>
|
||||
<b>{{ t('dashboard.byProtocol') }}</b>
|
||||
<span class="sub">{{ t('dashboard.byProtocolSub') }}</span>
|
||||
</div>
|
||||
<div class="pv" style="gap: 7px">
|
||||
<div v-for="(r, i) in routeRows" :key="r.name" class="pv-i" style="font-size: 12px">
|
||||
<div v-for="(r, i) in protoRows" :key="r.name" class="pv-i" style="font-size: 12px">
|
||||
<span class="pill mute">{{ i + 1 }}</span>
|
||||
<span class="code flex-1">{{ r.name }}</span>
|
||||
<span class="st muted-2 nowrap">{{ r.short }}</span>
|
||||
</div>
|
||||
<div v-if="!routeRows.length" class="hint">{{ t('dashboard.noData') }}</div>
|
||||
<div v-if="!protoRows.length" class="hint">{{ t('dashboard.noData') }}</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -94,7 +94,6 @@
|
||||
<span>{{ t('dashboard.running') }}</span>
|
||||
<span>{{ t('dashboard.uptime') }} {{ uptimeText }}</span>
|
||||
<span>{{ t('dashboard.inflight') }} {{ health.in_flight ?? '-' }} / {{ health.in_flight_peak ?? '-' }}</span>
|
||||
<span>{{ t('dashboard.fallback') }} {{ health.fallback_total ?? 0 }}</span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -116,7 +115,7 @@ const { resolved } = useTheme() // 主题变化时重算图表配色
|
||||
const health = ref<any>({})
|
||||
const metrics = ref<any>({})
|
||||
const models = ref<any>({})
|
||||
const routes = ref<any[]>([])
|
||||
const modelsList = ref<any[]>([])
|
||||
const loading = ref(false)
|
||||
const err = ref('')
|
||||
|
||||
@@ -149,7 +148,6 @@ const cards = computed(() => {
|
||||
{ k: t('dashboard.requests'), v: total.value, note: t('dashboard.noteOkFail', { ok: totalOk.value, fail: totalFail.value }) },
|
||||
{ k: t('dashboard.successRate'), v: rate.value.toFixed(1) + '%', note: t('dashboard.noteFail', { n: totalFail.value }) },
|
||||
{ k: t('dashboard.avgLatency'), v: avgP50.value.toFixed(2) + 's', note: t('dashboard.noteP95', { v: maxP95.value.toFixed(2) }) },
|
||||
{ k: t('dashboard.fallbackShort'), v: health.value.fallback_total ?? 0, note: t('dashboard.noteInflight', { n: health.value.in_flight ?? 0 }) },
|
||||
]
|
||||
})
|
||||
|
||||
@@ -171,12 +169,14 @@ const providerRows = computed(() => {
|
||||
})
|
||||
})
|
||||
|
||||
const routeRows = computed(() => {
|
||||
const m = models.value
|
||||
return routes.value.map((r: any) => {
|
||||
const chain: string[] = (m[r.id] || []).map((x: any) => (typeof x === 'string' ? x : x.id || x.name))
|
||||
return { name: r.id, short: chain.length ? t('models.chainCount', { n: chain.length }) : '—' }
|
||||
})
|
||||
// 第二十七轮: 路由别名链已删除 → 这里改成"每条协议线各有几个模型"
|
||||
// (三线直传后这个分布才是运维真正关心的:哪条线现在有货)
|
||||
const protoRows = computed(() => {
|
||||
const count: Record<string, number> = {}
|
||||
for (const m of modelsList.value) {
|
||||
for (const p of (m.protocols || ['chat/completions'])) count[p] = (count[p] || 0) + 1
|
||||
}
|
||||
return Object.keys(count).sort().map((k) => ({ name: k, short: t('dashboard.modelCountN', { n: count[k] }) }))
|
||||
})
|
||||
|
||||
const callRows = computed(() => {
|
||||
@@ -258,14 +258,10 @@ async function load() {
|
||||
try {
|
||||
const um = await api('/v1/models')
|
||||
const data = um.data || []
|
||||
routes.value = data.filter((x: any) => x.type === 'route')
|
||||
modelsList.value = data
|
||||
const map: Record<string, string> = {}
|
||||
for (const x of data) if (x.type !== 'route') map[x.id] = x.provider_name || ''
|
||||
for (const x of data) map[x.id] = x.provider_name || ''
|
||||
textModels.value = map
|
||||
const list = data.filter((x: any) => x.type === 'route')
|
||||
const m: Record<string, any> = {}
|
||||
for (const r of list) m[r.id] = r.models || []
|
||||
models.value = m
|
||||
} catch { /* 模型列表可选 */ }
|
||||
} catch (e: any) {
|
||||
if (e && e.status === 401) { router.push('/login'); return }
|
||||
|
||||
@@ -122,7 +122,8 @@ async function load() {
|
||||
value: envs[env].value || '',
|
||||
show: false,
|
||||
}))
|
||||
warns.value = (body.meta?.warnings || []).concat(body.meta?.route_warnings || [])
|
||||
// 第二十七轮: 路由告警(meta.route_warnings)随路由功能删除,体检结论只看 warnings
|
||||
warns.value = body.meta?.warnings || []
|
||||
} catch (e: any) {
|
||||
err.value = (e?.body?.detail || e?.message || String(e))
|
||||
} finally {
|
||||
|
||||
@@ -36,15 +36,14 @@
|
||||
<div class="grid-eq">
|
||||
<div class="card">
|
||||
<div class="card-h">
|
||||
<b>{{ t('metrics.routeVsProvider') }}</b>
|
||||
<b>{{ t('metrics.byProvider') }}</b>
|
||||
<span class="sub">{{ t('metrics.snapshot') }}</span>
|
||||
<div class="legend">
|
||||
<span><i style="background: var(--chart-a)" />ok</span>
|
||||
<span><i style="background: var(--err)" />fail</span>
|
||||
<span><i style="background: var(--warn)" />fallback</span>
|
||||
</div>
|
||||
</div>
|
||||
<EChart :option="routeOpt" height="250px" />
|
||||
<EChart :option="providerOpt" height="250px" />
|
||||
</div>
|
||||
<div class="card">
|
||||
<div class="card-h">
|
||||
@@ -88,7 +87,6 @@
|
||||
<div class="about-line">
|
||||
<b>{{ t('metrics.snapshot') }}</b>
|
||||
<span>{{ t('metrics.uptime') }} {{ fmtUptime }}</span>
|
||||
<span>{{ t('metrics.fallback') }} {{ data.fallback_total ?? 0 }}</span>
|
||||
<span>{{ t('metrics.inflight') }} {{ data.in_flight ?? 0 }} / {{ data.in_flight_peak ?? 0 }}</span>
|
||||
</div>
|
||||
</div>
|
||||
@@ -156,7 +154,8 @@ const cards = computed(() => {
|
||||
{ k: t('metrics.requests'), v: all, note: t('dashboard.noteOkFail', { ok, fail }) },
|
||||
{ k: t('metrics.failCount'), v: fail, note: t('metrics.failRateNote', { v: rate.toFixed(1) }) },
|
||||
{ k: t('metrics.tokenUsage'), v: (tk.prompt || 0) + (tk.completion || 0), note: t('metrics.tokenNote', { p: tk.prompt ?? 0, c: tk.completion ?? 0 }) },
|
||||
{ k: t('metrics.inflightPeak'), v: `${data.value.in_flight ?? 0} / ${data.value.in_flight_peak ?? 0}`, note: t('metrics.fallback') + ' ' + (data.value.fallback_total ?? 0) },
|
||||
// 第二十七轮: fallback 计数随路由功能删除 → 这张卡片的注脚改成运行时长
|
||||
{ k: t('metrics.inflightPeak'), v: `${data.value.in_flight ?? 0} / ${data.value.in_flight_peak ?? 0}`, note: t('metrics.uptime') + ' ' + fmtUptime.value },
|
||||
]
|
||||
})
|
||||
|
||||
@@ -194,27 +193,26 @@ const provOpt = computed<EChartsCoreOption>(() => {
|
||||
}
|
||||
})
|
||||
|
||||
const routeOpt = computed<EChartsCoreOption>(() => {
|
||||
// 第二十七轮: 路由维度指标随路由功能删除(routes/fallback_total 已不在 /metrics 里),
|
||||
// 这里改成按供应商看 成功 / 失败(供应商是现在唯一的"聚合维度")。
|
||||
const providerOpt = computed<EChartsCoreOption>(() => {
|
||||
void resolved.value
|
||||
const c = chartTheme()
|
||||
const r = data.value.routes || {}
|
||||
const ks = Object.keys(r)
|
||||
const names = ks.length ? ks : ['wjd']
|
||||
const get = (k: string, f: string) => (r[k] || {})[f] || 0
|
||||
const p = data.value.providers || {}
|
||||
const names = Object.keys(p)
|
||||
const get = (k: string, f: string) => (p[k] || {})[f] || 0
|
||||
const ok = names.map((n) => get(n, 'ok'))
|
||||
const fail = names.map((n) => get(n, 'fail'))
|
||||
const fallback = names.map((n) => get(n, 'fallback'))
|
||||
return {
|
||||
tooltip: { trigger: 'axis', axisPointer: { type: 'shadow' } },
|
||||
legend: legend(['ok', 'fail', 'fallback']),
|
||||
legend: legend(['ok', 'fail']),
|
||||
grid,
|
||||
graphic: emptyTip([ok, fail, fallback], t('metrics.none')),
|
||||
graphic: emptyTip([ok, fail], t('metrics.none')),
|
||||
xAxis: categoryAxis(names, 10),
|
||||
yAxis: valueAxis('', 1),
|
||||
series: [
|
||||
{ name: 'ok', type: 'bar', stack: 'r', data: ok, itemStyle: { color: c.a } },
|
||||
{ name: 'fail', type: 'bar', stack: 'r', data: fail, itemStyle: { color: c.err } },
|
||||
{ name: 'fallback', type: 'bar', stack: 'r', data: fallback, itemStyle: { color: c.warn } },
|
||||
{ name: 'ok', type: 'bar', stack: 'p', data: ok, itemStyle: { color: c.a } },
|
||||
{ name: 'fail', type: 'bar', stack: 'p', data: fail, itemStyle: { color: c.err } },
|
||||
],
|
||||
}
|
||||
})
|
||||
|
||||
@@ -11,36 +11,32 @@
|
||||
</div>
|
||||
|
||||
<div class="grid2">
|
||||
<!-- 路由链:只读展示(排序策略在后端,页面不写盘) -->
|
||||
<!-- 路由别名 + 全部文本模型延迟(一键测速填充) -->
|
||||
<!-- 全部文本模型 + 一键测速(延迟逐行填充;测速按模型自己的协议线探测) -->
|
||||
<div class="card">
|
||||
<div class="card-h">
|
||||
<b>{{ t('models.routeAliasTitle') }}</b>
|
||||
<b>{{ t('models.allTextModels') }}</b>
|
||||
<span class="sub">{{ t('models.speedtestHint') }}</span>
|
||||
<span style="flex:1"></span>
|
||||
<el-button size="small" :loading="latTesting" @click="runSpeedtest()">
|
||||
{{ latTesting ? t('models.testingShort') : t('models.speedtest') }}
|
||||
</el-button>
|
||||
</div>
|
||||
|
||||
<div v-for="r in routeRows" :key="r.name" class="route-block">
|
||||
<div class="route-head">
|
||||
<span class="code route-name">{{ r.name }}</span>
|
||||
<span style="flex:1"></span>
|
||||
<el-button size="small" :loading="latTesting" @click="runSpeedtest()">
|
||||
{{ latTesting ? t('models.testingShort') : t('models.speedtest') }}
|
||||
</el-button>
|
||||
</div>
|
||||
</div>
|
||||
<div v-if="!routeRows.length" class="hint">{{ t('models.noRoute') }}</div>
|
||||
|
||||
<div class="lat-head">
|
||||
<span class="muted-2 hint">{{ t('models.allTextModels') }}</span>
|
||||
<span style="flex:1"></span>
|
||||
<span class="muted-2 hint">{{ t('models.latency') }}</span>
|
||||
</div>
|
||||
<div v-for="m in textModelRows" :key="m.id" class="st-item">
|
||||
<div class="st-row">
|
||||
<div class="st-row" :title="rowTitle(m)">
|
||||
<Icon v-if="m.vision" name="eye" :size="12" class="vision" />
|
||||
<!-- 第二十五轮:该模型的参数被上游固定(如 temperature 只能是 1),
|
||||
挂锁标注 + 悬浮说明,省掉「为什么我传的参数不生效」这类困惑。 -->
|
||||
<Icon v-if="m.paramNote" name="lock" :size="12" class="plock" :title="m.paramNote" />
|
||||
<span class="code">{{ m.id }}</span>
|
||||
<!-- 支持的格式不在这里铺标签:这行还要放供应商/延迟/测速按钮,窄卡放不下第三颗
|
||||
(悬停整行可见格式 + 本次测速走的线,见 rowTitle)。权威展示在下方表格的
|
||||
「支持的格式」列。 -->
|
||||
<span class="muted-2 st-prov">{{ m.provider }}</span>
|
||||
<span style="flex:1"></span>
|
||||
<span class="pill st-lat" :class="latCls(m.id)">
|
||||
@@ -87,20 +83,42 @@
|
||||
<b>{{ t('models.modelListTitle') }}</b>
|
||||
<span class="sub">{{ t('models.capability') }}</span>
|
||||
<div class="pager">
|
||||
<span class="pill mute">{{ t('models.routeCount', { n: routeRows.length }) }}</span>
|
||||
<span class="pill mute">{{ t('models.textModelCount', { n: textModelRows.length }) }}</span>
|
||||
</div>
|
||||
</div>
|
||||
<el-table :data="modelRows" size="small" v-loading="loading">
|
||||
<el-table-column :label="t('models.id')" min-width="200">
|
||||
<el-table-column :label="t('models.id')" min-width="185">
|
||||
<template #default="{ row }"><span class="code">{{ row.id }}</span></template>
|
||||
</el-table-column>
|
||||
<el-table-column :label="t('models.type')" width="100">
|
||||
<el-table-column :label="t('models.type')" width="90">
|
||||
<template #default="{ row }"><span class="pill" :class="typeCls(row.type)">{{ t(typeKey(row.type)) }}</span></template>
|
||||
</el-table-column>
|
||||
<el-table-column :label="t('models.provider')" min-width="150">
|
||||
<el-table-column :label="t('models.provider')" min-width="140">
|
||||
<template #default="{ row }">{{ row.provider_name || '—' }}</template>
|
||||
</el-table-column>
|
||||
<el-table-column :label="t('models.capability')" width="190">
|
||||
<!-- 第二十七轮追加:支持的格式(三条协议线)——
|
||||
后端 /v1/models 里每个文本模型带 protocols 数组(chat/completions、messages、
|
||||
responses 的一个子集)。这里只做展示,但它有实际约束力:用不在列表里的格式
|
||||
调网关,会在入口被 400 挡下(网关不做跨格式转换,见 /v1/messages 的 400 文案)。
|
||||
图像/视频模型走专用端点,不涉及三条协议线,统一显示「不适用」。
|
||||
width 取 300:实测三颗标签(chat/completions=120px + messages=67px + responses=74px
|
||||
+ 间距)并排一行需 ~273px,留足余量让多线模型那行也单行,不挤到换行。 -->
|
||||
<el-table-column width="300">
|
||||
<template #header>
|
||||
<el-tooltip :content="t('models.protocolHint')" placement="top">
|
||||
<span class="proto-th">{{ t('models.protocols') }}</span>
|
||||
</el-tooltip>
|
||||
</template>
|
||||
<template #default="{ row }">
|
||||
<span v-if="protocolsOf(row).length" class="proto-cell">
|
||||
<span v-for="p in protocolsOf(row)" :key="p" class="pill proto" :title="protoTitle(p)">{{ p }}</span>
|
||||
</span>
|
||||
<el-tooltip v-else :content="t('models.protocolNaHint')" placement="top">
|
||||
<span class="muted-2">{{ t('models.protocolNa') }}</span>
|
||||
</el-tooltip>
|
||||
</template>
|
||||
</el-table-column>
|
||||
<el-table-column :label="t('models.capability')" width="170">
|
||||
<template #default="{ row }">
|
||||
<span v-if="row.vision" class="pill ok cap">
|
||||
<Icon name="eye" :size="12" />{{ t('models.visionTag') }}
|
||||
@@ -111,7 +129,7 @@
|
||||
<span v-if="!row.vision && !paramKeys(row).length" class="muted-2">—</span>
|
||||
</template>
|
||||
</el-table-column>
|
||||
<el-table-column :label="t('models.keySet')" width="120">
|
||||
<el-table-column :label="t('models.keySet')" width="90">
|
||||
<template #default="{ row }">
|
||||
<span class="pill" :class="row.key_set ? 'ok' : 'err'">
|
||||
{{ row.key_set ? t('common.yes') : t('common.no') }}
|
||||
@@ -138,14 +156,27 @@ const health = ref<any>({})
|
||||
const loading = ref(false)
|
||||
const err = ref('')
|
||||
|
||||
const typeKeyMap: Record<string, string> = { text: 'models.text', image: 'models.image', video: 'models.video', route: 'models.route' }
|
||||
const typeClsMap: Record<string, string> = { text: 'mute', image: 'warn', video: 'warn', route: 'ok' }
|
||||
const typeKeyMap: Record<string, string> = { text: 'models.text', image: 'models.image', video: 'models.video' }
|
||||
const typeClsMap: Record<string, string> = { text: 'mute', image: 'warn', video: 'warn' }
|
||||
function typeKey(ty: string) { return typeKeyMap[ty] || ty }
|
||||
function typeCls(ty: string) { return typeClsMap[ty] || 'mute' }
|
||||
|
||||
// ── 支持的格式(第二十七轮)──
|
||||
// 取值范围与后端 PROTOCOLS 一致:chat/completions(OpenAI 兼容线)、messages(Anthropic 线)、
|
||||
// responses(OpenAI Responses 线)。**名字直接取各家标准端点名**,不另起中文别名 —— 配置、
|
||||
// 日志、前端标签、上游文档四处同名,出问题时对得上号。
|
||||
function protocolsOf(row: any): string[] {
|
||||
if (!row || row.type !== 'text') return [] // 图像/视频模型走专用端点,没有协议线概念
|
||||
return (row.protocols as string[]) || []
|
||||
}
|
||||
// 每个格式标签的悬浮说明:这条线对应哪个端点(点进说明文档也是这个对应关系)
|
||||
function protoTitle(p: string): string { return `POST /v1/${p}` }
|
||||
|
||||
const latTesting = ref(false)
|
||||
const latCurrentId = ref('') // 当前正在测的模型 id:该行延迟位显示加载图标
|
||||
const latByModel = ref<Record<string, { ok: boolean; latency_ms: number | null; error: string }>>({})
|
||||
// protocol 由后端返回:探针**按模型自己的协议线**挑一条(优先级 chat → messages → responses),
|
||||
// 记下来才能在悬浮提示里说清「这次多少毫秒是走哪条线测的」——多线模型不写清楚会让人误解。
|
||||
const latByModel = ref<Record<string, { ok: boolean; latency_ms: number | null; error: string; protocol: string }>>({})
|
||||
async function runSpeedtest() {
|
||||
if (latTesting.value) return
|
||||
// 逐个测速:按列表顺序,测一个立刻显示那一行、再测下一个;当前测的行显示加载图标。
|
||||
@@ -155,17 +186,17 @@ async function runSpeedtest() {
|
||||
latTesting.value = true
|
||||
for (const id of ids) {
|
||||
latCurrentId.value = id
|
||||
let row: { ok: boolean; latency_ms: number | null; error: string }
|
||||
let row: { ok: boolean; latency_ms: number | null; error: string; protocol: string }
|
||||
try {
|
||||
const j = await api('/v1/models/speedtest', { method: 'POST', body: JSON.stringify({ model: id }) })
|
||||
const r: any[] = (j && j.results) || []
|
||||
const hit = r[0]
|
||||
row = hit
|
||||
? { ok: !!hit.ok, latency_ms: hit.latency_ms ?? null, error: hit.error || '' }
|
||||
: { ok: false, latency_ms: null, error: t('models.speedtestFail') }
|
||||
? { ok: !!hit.ok, latency_ms: hit.latency_ms ?? null, error: hit.error || '', protocol: hit.protocol || '' }
|
||||
: { ok: false, latency_ms: null, error: t('models.speedtestFail'), protocol: '' }
|
||||
} catch (e: any) {
|
||||
// 单个模型出错不中断整轮,标记失败后继续下一个
|
||||
row = { ok: false, latency_ms: null, error: (e && e.message) || String(e) }
|
||||
row = { ok: false, latency_ms: null, error: (e && e.message) || String(e), protocol: '' }
|
||||
}
|
||||
latByModel.value = { ...latByModel.value, [id]: row } // 响应式替换 → 该行即时更新
|
||||
}
|
||||
@@ -182,11 +213,11 @@ async function retestOne(id: string) {
|
||||
const r: any[] = (j && j.results) || []
|
||||
const hit = r[0]
|
||||
const row = hit
|
||||
? { ok: !!hit.ok, latency_ms: hit.latency_ms ?? null, error: hit.error || '' }
|
||||
: { ok: false, latency_ms: null, error: t('models.speedtestFail') }
|
||||
? { ok: !!hit.ok, latency_ms: hit.latency_ms ?? null, error: hit.error || '', protocol: hit.protocol || '' }
|
||||
: { ok: false, latency_ms: null, error: t('models.speedtestFail'), protocol: '' }
|
||||
latByModel.value = { ...latByModel.value, [id]: row }
|
||||
} catch (e: any) {
|
||||
latByModel.value = { ...latByModel.value, [id]: { ok: false, latency_ms: null, error: (e && e.message) || String(e) } }
|
||||
latByModel.value = { ...latByModel.value, [id]: { ok: false, latency_ms: null, error: (e && e.message) || String(e), protocol: '' } }
|
||||
} finally {
|
||||
latCurrentId.value = ''
|
||||
}
|
||||
@@ -208,8 +239,8 @@ function latCls(id: string): string {
|
||||
return row ? (row.ok ? 'ok' : 'err') : 'mute'
|
||||
}
|
||||
|
||||
const routes = computed(() => items.value.filter((x) => x.type === 'route'))
|
||||
const models = computed(() => items.value.filter((x) => x.type !== 'route'))
|
||||
// 第二十七轮: 路由别名条目(type === 'route')已从 /v1/models 消失 → 这里只剩真实模型
|
||||
const models = computed(() => items.value)
|
||||
|
||||
const providerOf = computed(() => {
|
||||
const m: Record<string, string> = {}
|
||||
@@ -222,16 +253,6 @@ const visionOf = computed(() => {
|
||||
return m
|
||||
})
|
||||
|
||||
const routeRows = computed(() =>
|
||||
routes.value.map((r) => {
|
||||
const chain: string[] = r.models || []
|
||||
return {
|
||||
name: r.id,
|
||||
models: chain.map((id) => ({ id, provider: providerOf.value[id] || '—', vision: visionOf.value[id] })),
|
||||
providerCount: new Set(chain.map((id) => providerOf.value[id] || '—')).size,
|
||||
}
|
||||
}),
|
||||
)
|
||||
const textModelRows = computed(() =>
|
||||
models.value.filter((x) => x.type === 'text').map((m) => ({
|
||||
id: m.id,
|
||||
@@ -239,9 +260,21 @@ const textModelRows = computed(() =>
|
||||
vision: !!m.vision,
|
||||
// 模型级强制参数(第二十五轮):被上游固定住的采样参数,用挂锁标注出来。
|
||||
paramNote: paramKeys(m).length ? paramNote(m) : '',
|
||||
// 支持的格式(第二十七轮):悬浮这一行就能看到「能用哪几条线 + 本次测速走的哪条」
|
||||
formats: protocolsOf(m),
|
||||
})),
|
||||
)
|
||||
|
||||
// 测速行的悬浮提示:先说这个模型支持哪些格式,再说这次测的是哪条线
|
||||
// (多线模型不标注的话,"12 ms"到底测的是哪条线是看不出来的)。
|
||||
function rowTitle(m: any): string {
|
||||
const lines = (m.formats || []).join(' / ') || t('models.protocolNa')
|
||||
const p = latByModel.value[m.id]?.protocol
|
||||
return p
|
||||
? `${t('models.protocolHintRow', { lines })}· ${t('models.probedLine', { p })}`
|
||||
: t('models.protocolHintRow', { lines })
|
||||
}
|
||||
|
||||
// ── 模型级强制参数(第二十五轮)──
|
||||
// 后端 /v1/models 在 params 里给出「该模型发往上游前会被强制覆盖的参数」
|
||||
// (例:kimi-k2.7-code 只接受 temperature=1)。这里只做展示,不提供编辑入口。
|
||||
@@ -279,7 +312,6 @@ const cards = computed(() => [
|
||||
{ k: t('models.model'), v: models.value.length, note: t('models.providerCount2', { n: providerRows.value.length }) },
|
||||
{ k: t('models.textModels'), v: models.value.filter((m) => m.type === 'text').length, note: t('models.visionTag') + ' · ' + models.value.filter((m) => m.vision).length },
|
||||
{ k: t('models.imageModels'), v: models.value.filter((m) => m.type === 'image').length, note: t('images.title') },
|
||||
{ k: t('models.routes'), v: routes.value.length, note: t('models.routeAliasTitle') },
|
||||
])
|
||||
|
||||
onMounted(async () => {
|
||||
@@ -298,15 +330,20 @@ onMounted(async () => {
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.route-block { padding: 10px 0; border-bottom: 1px solid var(--line-2); }
|
||||
.route-block:last-child { border-bottom: 0; }
|
||||
.route-head { display: flex; align-items: center; gap: 8px; margin-bottom: 8px; }
|
||||
.route-name { font-weight: 700; color: var(--text); font-size: 13px; }
|
||||
.chain { display: flex; align-items: center; gap: 6px; flex-wrap: wrap; }
|
||||
.chain-item { display: inline-flex; align-items: center; gap: 6px; }
|
||||
.arrow { color: var(--muted-2); }
|
||||
.vision { color: var(--primary); }
|
||||
.plock { color: var(--warn); }
|
||||
/* 支持的格式:三条线是并列关系(没有谁更优),统一用主题色弱底,
|
||||
不用 ok/warn/err —— 否则「messages」看起来像警告、「responses」像被禁用。 */
|
||||
.proto {
|
||||
color: var(--primary); background: var(--primary-soft);
|
||||
font-family: ui-monospace, SFMono-Regular, Menlo, monospace; /* 与全局 .code 同一套 */
|
||||
font-size: 11px; padding: 2px 7px;
|
||||
}
|
||||
.proto-cell { display: inline-flex; align-items: center; gap: 5px; flex-wrap: wrap; }
|
||||
.proto-th { border-bottom: 1px dotted var(--muted-2); cursor: help; }
|
||||
.prov { padding: 10px 0; border-bottom: 1px solid var(--line-2); }
|
||||
.prov:last-child { border-bottom: 0; }
|
||||
.prov-top { display: flex; align-items: center; gap: 8px; }
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
<template>
|
||||
<div class="page">
|
||||
<div class="card">
|
||||
<div class="ph-title">「{{ title }}」页面</div>
|
||||
<div class="ph-sub">该功能在后续里程碑开发(M2 对话 / M3 媒体 / M4 指标日志 等)。</div>
|
||||
</div>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup lang="ts">
|
||||
import { computed } from 'vue'
|
||||
import { useRoute } from 'vue-router'
|
||||
const route = useRoute()
|
||||
const title = computed(() => (route.meta.title as string) || '')
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.ph-title { font-size: 18px; font-weight: 600; }
|
||||
.ph-sub { color: var(--muted); margin-top: 8px; }
|
||||
</style>
|
||||
@@ -67,7 +67,7 @@
|
||||
<div class="set-row">
|
||||
<div class="lb">{{ t('settings.defaultModel') }}</div>
|
||||
<div class="rt">
|
||||
<el-select v-model="defs.model" size="small" clearable :placeholder="t('chat.routeGroup')" style="width: 210px">
|
||||
<el-select v-model="defs.model" size="small" clearable :placeholder="t('chat.pickModel')" style="width: 210px">
|
||||
<el-option v-for="m in textModels" :key="m" :label="m" :value="m" />
|
||||
</el-select>
|
||||
</div>
|
||||
@@ -179,10 +179,6 @@
|
||||
<div class="lb">{{ t('dashboard.inflight') }}</div>
|
||||
<div class="rt">{{ health.in_flight ?? '-' }} / {{ health.in_flight_peak ?? '-' }}</div>
|
||||
</div>
|
||||
<div class="set-row">
|
||||
<div class="lb">{{ t('dashboard.fallback') }}</div>
|
||||
<div class="rt">{{ health.fallback_total ?? 0 }}</div>
|
||||
</div>
|
||||
<div class="set-row" style="align-items: flex-start">
|
||||
<div class="lb">{{ t('settings.providerStatus') }}</div>
|
||||
<div class="rt" style="flex-wrap: wrap; justify-content: flex-end">
|
||||
@@ -228,8 +224,8 @@ const err = ref('')
|
||||
const { t, locale } = useI18n()
|
||||
const { theme, followSystem, setTheme, setFollowSystem } = useTheme()
|
||||
|
||||
// 对话默认模型下拉(老板决策:wjd 链路 = 全部文本模型;这里同样覆盖全部文本模型)
|
||||
const TEXT_MODELS = ['wjd',
|
||||
// 对话默认模型下拉(覆盖全部文本模型;第二十七轮: wjd 路由别名已删除,不再有"别名"选项)
|
||||
const TEXT_MODELS = [
|
||||
'agnes-3.0-flash', 'agnes-2.5-flash', 'ark-code-latest',
|
||||
// OpenCode Go(订阅编程模型,17 个文本模型)
|
||||
'glm-5.3-flash', 'glm-5.3', 'glm-5.2', 'glm-5.1',
|
||||
@@ -252,7 +248,9 @@ const savingDefs = ref(false)
|
||||
|
||||
function loadDefs() {
|
||||
const d = getChatDefaults()
|
||||
defs.model = d.model ?? 'wjd'
|
||||
// 第二十七轮: 默认模型不再回落到 wjd(该别名已删除)—— 认不出就留空串,
|
||||
// Settings 的模型下拉在 onMounted 里会用真实模型列表兜底。
|
||||
defs.model = d.model ?? ''
|
||||
defs.temperature = d.temperature ?? 0.7
|
||||
defs.top_p = d.top_p ?? 1
|
||||
defs.max_tokens = d.max_tokens ?? null
|
||||
@@ -315,8 +313,8 @@ onMounted(async () => {
|
||||
// 默认模型下拉用真实模型列表(拿不到就退回内置候选)
|
||||
try {
|
||||
const um = await api('/v1/models')
|
||||
const list = (um.data || []).filter((x: any) => x.type !== 'route').map((x: any) => x.id)
|
||||
if (list.length) textModels.value = ['wjd', ...list]
|
||||
const list = (um.data || []).filter((x: any) => x.type !== 'image' && x.type !== 'video').map((x: any) => x.id)
|
||||
if (list.length) textModels.value = list
|
||||
} catch { /* 模型列表可选 */ }
|
||||
} catch (e: any) {
|
||||
if (e && e.status === 401) { router.push('/login'); return }
|
||||
|
||||
Reference in new issue
Block a user