mirror of
https://git.sync.wtf/troed/oc-ls-stats.git
synced 2026-08-31 09:43:38 +03:00
495 lines
15 KiB
TypeScript
495 lines
15 KiB
TypeScript
/** @jsxImportSource @opentui/solid */
|
|
import type { TuiPlugin, TuiPluginModule } from "@opencode-ai/plugin/tui"
|
|
import { createMemo, createSignal } from "solid-js"
|
|
|
|
type StreamSample = {
|
|
at: number
|
|
tokens: number
|
|
}
|
|
|
|
const STREAM_WINDOW_MS = 5_000
|
|
const LIVE_STALE_MS = 1_500
|
|
const SINGLE_SAMPLE_MS = 1_000
|
|
const SLOT_POLL_MS = 500
|
|
type MessageTiming = {
|
|
sessionID: string
|
|
requestStartAt: number
|
|
firstResponseAt?: number
|
|
firstTokenAt?: number
|
|
lastTokenAt?: number
|
|
lastToolCallAt?: number
|
|
}
|
|
|
|
type SessionAverage = {
|
|
totalTokens: number
|
|
totalDurationMs: number
|
|
totalTtftMs: number
|
|
messageCount: number
|
|
}
|
|
|
|
type TrackerState = {
|
|
streamSamplesBySession: Record<string, StreamSample[]>
|
|
messageTimingByID: Record<string, MessageTiming>
|
|
sessionAverageByID: Record<string, SessionAverage>
|
|
lastPrefillRate: number
|
|
lastGeneratedTps: number
|
|
}
|
|
|
|
function estimateStreamTokens(delta: string) {
|
|
return Math.max(1, Math.ceil(Buffer.byteLength(delta, "utf8") / 5))
|
|
}
|
|
|
|
function parseJSONC(text: string): unknown {
|
|
let result = ""
|
|
let inString = false
|
|
let escape = false
|
|
let i = 0
|
|
|
|
while (i < text.length) {
|
|
const ch = text[i]
|
|
|
|
if (escape) {
|
|
result += ch
|
|
escape = false
|
|
i++
|
|
continue
|
|
}
|
|
|
|
if (ch === "\\") {
|
|
result += ch
|
|
escape = true
|
|
i++
|
|
continue
|
|
}
|
|
|
|
if (ch === '"') {
|
|
result += ch
|
|
inString = !inString
|
|
i++
|
|
continue
|
|
}
|
|
|
|
if (inString) {
|
|
result += ch
|
|
i++
|
|
continue
|
|
}
|
|
|
|
if (ch === "/" && text[i + 1] === "/") {
|
|
while (i < text.length && text[i] !== "\n") i++
|
|
continue
|
|
}
|
|
|
|
if (ch === "/" && text[i + 1] === "*") {
|
|
i += 2
|
|
while (i < text.length - 1 && !(text[i] === "*" && text[i + 1] === "/")) i++
|
|
i += 2
|
|
result += " "
|
|
continue
|
|
}
|
|
|
|
if (ch === ",") {
|
|
const next = text.indexOf(/[\s}\]]/, i + 1)
|
|
if (next !== -1 && /[\s}\]]/.test(text[next])) {
|
|
i++
|
|
continue
|
|
}
|
|
}
|
|
|
|
result += ch
|
|
i++
|
|
}
|
|
|
|
return JSON.parse(result)
|
|
}
|
|
|
|
function stripBaseUrlPath(baseURL: string): string {
|
|
try {
|
|
const url = new URL(baseURL)
|
|
return `${url.origin}`
|
|
} catch {
|
|
return baseURL.replace(/\/v1(\/.*)?$/, "").replace(/\/$/, "") || baseURL
|
|
}
|
|
}
|
|
|
|
function extractProviderUrls(config: unknown): string[] {
|
|
if (!config || typeof config !== "object") return []
|
|
const obj = config as Record<string, unknown>
|
|
const provider = obj.provider
|
|
if (!provider || typeof provider !== "object") return []
|
|
|
|
const urls: string[] = []
|
|
for (const [_key, val] of Object.entries(provider as Record<string, unknown>)) {
|
|
if (val && typeof val === "object") {
|
|
const opts = (val as Record<string, unknown>).options
|
|
if (opts && typeof opts === "object") {
|
|
const baseURL = (opts as Record<string, unknown>).baseURL || (opts as Record<string, unknown>).base_url
|
|
if (typeof baseURL === "string" && baseURL.includes("localhost")) {
|
|
urls.push(stripBaseUrlPath(baseURL))
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return urls
|
|
}
|
|
|
|
async function loadConfigUrls(api: Parameters<TuiPlugin>[0]): Promise<string[]> {
|
|
try {
|
|
const configPath = api.state.path.config
|
|
const resp = await fetch(`file://${configPath}`)
|
|
if (!resp.ok) return []
|
|
const text = await resp.text()
|
|
const config = parseJSONC(text)
|
|
return extractProviderUrls(config)
|
|
} catch {
|
|
return []
|
|
}
|
|
}
|
|
|
|
async function fetchMetrics(baseUrl: string, model?: string): Promise<Record<string, number> | null> {
|
|
try {
|
|
const url = model ? `${baseUrl}/metrics?model=${encodeURIComponent(model)}` : `${baseUrl}/metrics`
|
|
const resp = await fetch(url)
|
|
if (!resp.ok) return null
|
|
const text = await resp.text()
|
|
const result: Record<string, number> = {}
|
|
for (const line of text.split("\n")) {
|
|
const match = line.match(/^(llamacpp:[\w_]+)\s+(\d+(?:\.\d+)?)/)
|
|
if (match) {
|
|
result[match[1]] = parseFloat(match[2])
|
|
}
|
|
}
|
|
return result
|
|
} catch {
|
|
return null
|
|
}
|
|
}
|
|
|
|
async function fetchSlots(baseUrl: string, model?: string): Promise<unknown | null> {
|
|
try {
|
|
const url = model ? `${baseUrl}/slots?model=${encodeURIComponent(model)}` : `${baseUrl}/slots`
|
|
const resp = await fetch(url)
|
|
if (!resp.ok) return null
|
|
return await resp.json()
|
|
} catch {
|
|
return null
|
|
}
|
|
}
|
|
|
|
function formatRate(value: number, label: "TPS" | "AVG" | "P") {
|
|
if (!Number.isFinite(value) || value <= 0) return undefined
|
|
if (value >= 100) return `${Math.round(value)}${label === "TPS" ? " TPS" : label === "P" ? "PPS" : ""}`
|
|
if (value >= 10) return `${value.toFixed(1)}${label === "TPS" ? " TPS" : label === "P" ? "PPS" : ""}`
|
|
return `${value.toFixed(2)}${label === "TPS" ? " TPS" : label === "P" ? "PPS" : ""}`
|
|
}
|
|
|
|
function formatTtft(value: number) {
|
|
if (!Number.isFinite(value) || value < 0) return undefined
|
|
return `${value.toFixed(1)}s`
|
|
}
|
|
|
|
function activeDurationMs(samples: StreamSample[], tailAt?: number) {
|
|
if (samples.length === 0) return 0
|
|
if (samples.length === 1) {
|
|
const tailDuration = tailAt ? Math.max(0, tailAt - samples[0].at) : SINGLE_SAMPLE_MS
|
|
return Math.min(Math.max(tailDuration, 250), SINGLE_SAMPLE_MS)
|
|
}
|
|
|
|
let duration = 0
|
|
for (let i = 1; i < samples.length; i++) {
|
|
duration += Math.max(0, samples[i].at - samples[i - 1].at)
|
|
}
|
|
|
|
if (tailAt) {
|
|
duration += Math.max(0, tailAt - samples[samples.length - 1].at)
|
|
}
|
|
|
|
return Math.max(duration, SINGLE_SAMPLE_MS)
|
|
}
|
|
|
|
function SessionPromptRight(props: {
|
|
api: Parameters<TuiPlugin>[0]
|
|
sessionID: string
|
|
tracker: TrackerState
|
|
version: () => number
|
|
clock: () => number
|
|
}) {
|
|
const sessionAverage = createMemo(() => {
|
|
props.version()
|
|
const totals = props.tracker.sessionAverageByID[props.sessionID]
|
|
if (!totals || totals.totalTokens <= 0 || totals.totalDurationMs <= 0) return undefined
|
|
return formatRate(totals.totalTokens / (totals.totalDurationMs / 1000), "AVG")
|
|
})
|
|
|
|
const sessionTtft = createMemo(() => {
|
|
props.version()
|
|
const totals = props.tracker.sessionAverageByID[props.sessionID]
|
|
if (!totals || totals.messageCount <= 0 || totals.totalTtftMs < 0) return undefined
|
|
return formatTtft(totals.totalTtftMs / totals.messageCount / 1000)
|
|
})
|
|
|
|
const liveTps = createMemo(() => {
|
|
props.version()
|
|
props.clock()
|
|
const status = props.api.state.session.status(props.sessionID)
|
|
if (status?.type === "idle") return undefined
|
|
const samples = props.tracker.streamSamplesBySession[props.sessionID] ?? []
|
|
if (samples.length === 0) return undefined
|
|
const now = Date.now()
|
|
const relevant = samples.filter((sample) => now - sample.at <= STREAM_WINDOW_MS)
|
|
if (relevant.length === 0) return undefined
|
|
const lastSample = relevant[relevant.length - 1]
|
|
if (!lastSample || now - lastSample.at > LIVE_STALE_MS) return undefined
|
|
const total = relevant.reduce((sum, sample) => sum + sample.tokens, 0)
|
|
const durationSeconds = activeDurationMs(relevant, now) / 1000
|
|
if (durationSeconds <= 0) return undefined
|
|
return formatRate(total / durationSeconds, "AVG")
|
|
})
|
|
|
|
const prefillRate = createMemo(() => {
|
|
props.version()
|
|
const rate = props.tracker.lastPrefillRate
|
|
if (!Number.isFinite(rate) || rate <= 0) return undefined
|
|
return formatRate(rate, "P")
|
|
})
|
|
|
|
const generatedTps = createMemo(() => {
|
|
props.version()
|
|
const rate = props.tracker.lastGeneratedTps
|
|
if (!Number.isFinite(rate) || rate <= 0) return undefined
|
|
return formatRate(rate, "AVG")
|
|
})
|
|
|
|
const text = createMemo(() => {
|
|
const live = liveTps() ?? "-"
|
|
const avg = sessionAverage() ?? "-"
|
|
const ttft = sessionTtft() ?? "-"
|
|
const p = prefillRate()
|
|
const g = generatedTps()
|
|
const parts = [`TPS ${live}`, `AVG ${avg}`, `TTFT ${ttft}`]
|
|
if (p) parts.push(`P ${p}`)
|
|
if (g) parts.push(`G ${g}`)
|
|
return parts.join(" | ")
|
|
})
|
|
|
|
return <>{text() ? <text fg={props.api.theme.current.textMuted}>{text()}</text> : null}</>
|
|
}
|
|
|
|
const tui: TuiPlugin = async (api) => {
|
|
console.log("[oc-ls-stats] TUI plugin loaded!")
|
|
const tracker: TrackerState = {
|
|
streamSamplesBySession: {},
|
|
messageTimingByID: {},
|
|
sessionAverageByID: {},
|
|
lastPrefillRate: 0,
|
|
lastGeneratedTps: 0,
|
|
}
|
|
const [version, setVersion] = createSignal(0)
|
|
const [clock, setClock] = createSignal(Date.now())
|
|
|
|
const bump = () => setVersion((value) => value + 1)
|
|
|
|
const pruneSamples = (now = Date.now()) => {
|
|
let changed = false
|
|
|
|
for (const [sessionID, samples] of Object.entries(tracker.streamSamplesBySession)) {
|
|
const next = samples.filter((sample) => now - sample.at <= STREAM_WINDOW_MS)
|
|
if (next.length !== samples.length) {
|
|
changed = true
|
|
if (next.length > 0) tracker.streamSamplesBySession[sessionID] = next
|
|
else delete tracker.streamSamplesBySession[sessionID]
|
|
}
|
|
}
|
|
|
|
if (changed) bump()
|
|
}
|
|
|
|
const clearLiveSamples = (sessionID: string) => {
|
|
if (!tracker.streamSamplesBySession[sessionID]?.length) return
|
|
delete tracker.streamSamplesBySession[sessionID]
|
|
bump()
|
|
}
|
|
|
|
const appendSample = (sessionID: string, messageID: string, sample: StreamSample) => {
|
|
const now = sample.at
|
|
tracker.streamSamplesBySession[sessionID] = [
|
|
...(tracker.streamSamplesBySession[sessionID] ?? []).filter((item) => now - item.at <= STREAM_WINDOW_MS),
|
|
sample,
|
|
]
|
|
const timing = tracker.messageTimingByID[messageID]
|
|
if (timing) {
|
|
tracker.messageTimingByID[messageID] = timing.firstTokenAt
|
|
? { ...timing, lastTokenAt: now }
|
|
: {
|
|
...timing,
|
|
firstResponseAt: timing.firstResponseAt ?? now,
|
|
firstTokenAt: now,
|
|
lastTokenAt: now,
|
|
}
|
|
}
|
|
bump()
|
|
}
|
|
|
|
let llamaServerUrls: string[] = ["http://localhost:8080"]
|
|
let llamaServerModel: string | undefined
|
|
|
|
const pollMetrics = async () => {
|
|
if (!llamaServerUrls.length) return
|
|
|
|
let model = llamaServerModel
|
|
if (!model) {
|
|
const routeSessionID = api.route.current.params?.sessionID
|
|
if (routeSessionID) {
|
|
const session = api.state.session.get(routeSessionID)
|
|
if (session?.model?.id) {
|
|
model = session.model.id
|
|
}
|
|
}
|
|
}
|
|
|
|
for (const baseUrl of llamaServerUrls) {
|
|
const metrics = await fetchMetrics(baseUrl, model)
|
|
if (!metrics) continue
|
|
|
|
const promptTps = metrics["llamacpp:prompt_tokens_seconds"]
|
|
const predictedTps = metrics["llamacpp:predicted_tokens_seconds"]
|
|
|
|
if (Number.isFinite(promptTps) && promptTps > 0) {
|
|
tracker.lastPrefillRate = promptTps
|
|
}
|
|
if (Number.isFinite(predictedTps) && predictedTps > 0) {
|
|
tracker.lastGeneratedTps = predictedTps
|
|
}
|
|
|
|
if (tracker.lastPrefillRate > 0 || tracker.lastGeneratedTps > 0) {
|
|
bump()
|
|
}
|
|
}
|
|
}
|
|
|
|
const onDelta = api.event.on("message.part.delta", (evt) => {
|
|
if (evt.properties.field !== "text") return
|
|
const parts = api.state.part(evt.properties.messageID)
|
|
const part = parts.find((item) => item.id === evt.properties.partID)
|
|
if (!part) return
|
|
if (part.type !== "text" && part.type !== "reasoning") return
|
|
appendSample(evt.properties.sessionID, evt.properties.messageID, {
|
|
at: Date.now(),
|
|
tokens: estimateStreamTokens(evt.properties.delta),
|
|
})
|
|
})
|
|
|
|
const onMessage = api.event.on("message.updated", (evt) => {
|
|
if (evt.properties.info.role !== "assistant") return
|
|
|
|
if (!evt.properties.info.time.completed) {
|
|
const existing = tracker.messageTimingByID[evt.properties.info.id]
|
|
tracker.messageTimingByID[evt.properties.info.id] = {
|
|
sessionID: evt.properties.sessionID,
|
|
requestStartAt: evt.properties.info.time.created,
|
|
firstResponseAt: existing?.firstResponseAt,
|
|
firstTokenAt: existing?.firstTokenAt,
|
|
lastTokenAt: existing?.lastTokenAt,
|
|
lastToolCallAt: existing?.lastToolCallAt,
|
|
}
|
|
bump()
|
|
return
|
|
}
|
|
|
|
const timing = tracker.messageTimingByID[evt.properties.info.id]
|
|
if (timing?.sessionID === evt.properties.sessionID && typeof timing.firstResponseAt === "number") {
|
|
const totalTokens = evt.properties.info.tokens.output + evt.properties.info.tokens.reasoning
|
|
const endAt =
|
|
evt.properties.info.finish === "tool-calls"
|
|
? timing.lastToolCallAt
|
|
: evt.properties.info.time.completed
|
|
const durationMs = typeof endAt === "number" ? Math.max(endAt - timing.firstResponseAt, 1) : undefined
|
|
const ttftMs = Math.max(timing.firstResponseAt - timing.requestStartAt, 0)
|
|
if (totalTokens > 0 && durationMs) {
|
|
const totals = tracker.sessionAverageByID[evt.properties.sessionID] ?? {
|
|
totalTokens: 0,
|
|
totalDurationMs: 0,
|
|
totalTtftMs: 0,
|
|
messageCount: 0,
|
|
}
|
|
tracker.sessionAverageByID[evt.properties.sessionID] = {
|
|
totalTokens: totals.totalTokens + totalTokens,
|
|
totalDurationMs: totals.totalDurationMs + durationMs,
|
|
totalTtftMs: totals.totalTtftMs + ttftMs,
|
|
messageCount: totals.messageCount + 1,
|
|
}
|
|
}
|
|
}
|
|
delete tracker.messageTimingByID[evt.properties.info.id]
|
|
pruneSamples(evt.properties.info.time.completed)
|
|
bump()
|
|
})
|
|
|
|
const onPart = api.event.on("message.part.updated", (evt) => {
|
|
if (evt.properties.part.type !== "tool") return
|
|
if (
|
|
evt.properties.part.state.status === "running" ||
|
|
evt.properties.part.state.status === "completed" ||
|
|
evt.properties.part.state.status === "error"
|
|
) {
|
|
clearLiveSamples(evt.properties.sessionID)
|
|
}
|
|
const timing = tracker.messageTimingByID[evt.properties.part.messageID]
|
|
if (!timing) return
|
|
if (evt.properties.part.state.status === "pending") {
|
|
tracker.messageTimingByID[evt.properties.part.messageID] = {
|
|
...timing,
|
|
firstResponseAt: timing.firstResponseAt ?? evt.properties.time,
|
|
}
|
|
bump()
|
|
return
|
|
}
|
|
if (evt.properties.part.state.status !== "running") return
|
|
tracker.messageTimingByID[evt.properties.part.messageID] = {
|
|
...timing,
|
|
lastToolCallAt: evt.properties.part.state.time.start,
|
|
}
|
|
bump()
|
|
})
|
|
|
|
const timer = setInterval(() => {
|
|
setClock(Date.now())
|
|
pruneSamples()
|
|
}, 1000)
|
|
|
|
const slotTimer = setInterval(async () => {
|
|
await pollMetrics()
|
|
}, SLOT_POLL_MS)
|
|
|
|
api.lifecycle.onDispose(() => {
|
|
onDelta()
|
|
onMessage()
|
|
onPart()
|
|
clearInterval(timer)
|
|
clearInterval(slotTimer)
|
|
})
|
|
|
|
try {
|
|
if (!llamaServerUrls.length) {
|
|
llamaServerUrls = await loadConfigUrls(api)
|
|
}
|
|
} catch (e) {
|
|
console.error("[oc-ls-stats] loadConfigUrls error:", e)
|
|
}
|
|
|
|
api.slots.register({
|
|
slots: {
|
|
session_prompt_right(_ctx, value) {
|
|
return <SessionPromptRight api={api} sessionID={value.session_id} tracker={tracker} version={version} clock={clock} />
|
|
},
|
|
},
|
|
})
|
|
}
|
|
|
|
const plugin: TuiPluginModule & { id: string } = {
|
|
id: "@troed/oc-ls-stats",
|
|
tui,
|
|
}
|
|
|
|
export default plugin
|