feat(web): turn speed metrics and composer context meter
Assistant footers and the stats line gain TTFT/tok-per-second readings folded from step timings; context occupancy moves off the stats line onto a composer ring whose panel shows a heuristic system/tools/messages breakdown from the new token-meter contextBreakdown session projection.
This commit is contained in:
Yif
@@ -0,0 +1,195 @@
|
||||
// contextBreakdown projection: heuristic system/tools/message composition,
|
||||
// plus the shared estimator's pricing branches.
|
||||
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { createMessage, createUserMessage } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock, ToolSchema } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import SessionProjectionRegistry from '@deepseek-ai/dsh-session-projection'
|
||||
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
|
||||
import type { ContextBreakdownProjection } from '@deepseek-ai/dsh-token-meter/client'
|
||||
import { contextBreakdownProjectionDefinition } from '../src/breakdown-projection.ts'
|
||||
import {
|
||||
estimateContent,
|
||||
estimateHeader,
|
||||
estimateMessage,
|
||||
estimateSystemTokens,
|
||||
estimateToolsTokens,
|
||||
} from '../src/estimate.ts'
|
||||
|
||||
const CONFIG = { provider: 'test', model: 'test-model' }
|
||||
|
||||
const TOOLS: ToolSchema[] = [{
|
||||
name: 'bash',
|
||||
description: 'run a command',
|
||||
parameters: { type: 'object', properties: {} },
|
||||
}]
|
||||
|
||||
async function harness(): Promise<{ ctx: Context; session: Session }> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SessionProjectionRegistry)
|
||||
await ctx.plugin(TokenMeterService)
|
||||
return { ctx, session: ctx.sessions.create() }
|
||||
}
|
||||
|
||||
const projected = (ctx: Context, session: Session): ContextBreakdownProjection => {
|
||||
const value = ctx.sessionProjections.snapshot(session).values.contextBreakdown
|
||||
if (value === undefined) throw new Error('contextBreakdown projection is not registered')
|
||||
return value
|
||||
}
|
||||
|
||||
function appendUser(session: Session, text: string): number {
|
||||
return session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text }],
|
||||
source: { kind: 'user' },
|
||||
}), { surfaceOp: 'append' }).seq
|
||||
}
|
||||
|
||||
describe('contextBreakdown session projection', () => {
|
||||
it('serves zeros for an empty log', async () => {
|
||||
const { ctx, session } = await harness()
|
||||
expect(projected(ctx, session)).toEqual({ systemTokens: 0, toolsTokens: 0, messageTokens: 0 })
|
||||
})
|
||||
|
||||
it('prices the newest envelope last-wins and pushes no change for a restated one', async () => {
|
||||
const { ctx, session } = await harness()
|
||||
session.append('request/header', {
|
||||
header: { config: CONFIG, system: 'You are terse.', tools: TOOLS },
|
||||
reason: 'initial',
|
||||
})
|
||||
expect(projected(ctx, session)).toEqual({
|
||||
systemTokens: estimateSystemTokens({ config: CONFIG, system: 'You are terse.' }),
|
||||
toolsTokens: estimateToolsTokens({ config: CONFIG, tools: TOOLS }),
|
||||
messageTokens: 0,
|
||||
})
|
||||
|
||||
const changed: string[] = []
|
||||
ctx.sessionProjections.onChanged((_session, key) => { changed.push(key) })
|
||||
session.append('request/header', {
|
||||
header: { config: CONFIG, system: 'You are terse.', tools: TOOLS },
|
||||
reason: 'change',
|
||||
})
|
||||
session.append('todo/write', { todos: [] })
|
||||
expect(changed).not.toContain('contextBreakdown')
|
||||
|
||||
// A system-less, tool-less envelope prices back to zero.
|
||||
session.append('request/header', { header: { config: CONFIG }, reason: 'change' })
|
||||
expect(projected(ctx, session)).toEqual({ systemTokens: 0, toolsTokens: 0, messageTokens: 0 })
|
||||
})
|
||||
|
||||
it('sums surface appends and skips an empty-content assistant message', async () => {
|
||||
const { ctx, session } = await harness()
|
||||
appendUser(session, 'abcd')
|
||||
session.append('step/start', { turn: 1, step: 1 })
|
||||
session.append('assistant/message', {
|
||||
turn: 1,
|
||||
step: 1,
|
||||
message: createMessage({
|
||||
role: 'assistant',
|
||||
content: [],
|
||||
source: { kind: 'model', provider: 'mock', model: 'mock' },
|
||||
}),
|
||||
usage: { inputTokens: 9, outputTokens: 0 },
|
||||
}, { surfaceOp: 'append', sourceEventSeqs: [] })
|
||||
session.append('step/end', { turn: 1, step: 1 })
|
||||
// 'abcd' prices to 9 (1 text + 4 block + 4 role); the usage-only assistant
|
||||
// message derives to no transcript entry and adds nothing.
|
||||
expect(projected(ctx, session).messageTokens).toBe(9)
|
||||
})
|
||||
|
||||
it('shrinks the message figure when a replacement compacts the surface', async () => {
|
||||
const { ctx, session } = await harness()
|
||||
const first = appendUser(session, 'before compaction, a longer message')
|
||||
const second = appendUser(session, 'and a second entry')
|
||||
const summary = createUserMessage({
|
||||
content: [{ type: 'text', text: 'summary' }],
|
||||
source: { kind: 'plugin', plugin: 'test' },
|
||||
})
|
||||
session.append('user/message', summary, {
|
||||
surfaceOp: { op: 'replace', start: first, end: second },
|
||||
sourceEventSeqs: [first, second],
|
||||
})
|
||||
expect(projected(ctx, session).messageTokens).toBe(estimateMessage(summary))
|
||||
})
|
||||
|
||||
it('fails loud on a replace range absent from the folded surface', () => {
|
||||
const definition = contextBreakdownProjectionDefinition
|
||||
const replace = (start: number, end: number): SessionEvent => ({
|
||||
type: 'user/message',
|
||||
seq: 9,
|
||||
time: 0,
|
||||
data: createUserMessage({ content: [{ type: 'text', text: 'x' }], source: { kind: 'user' } }),
|
||||
surfaceOp: { op: 'replace', start, end },
|
||||
sourceEventSeqs: [start, end],
|
||||
} as unknown as SessionEvent)
|
||||
const append = (seq: number): SessionEvent => ({
|
||||
type: 'user/message',
|
||||
seq,
|
||||
time: 0,
|
||||
data: createUserMessage({ content: [{ type: 'text', text: 'x' }], source: { kind: 'user' } }),
|
||||
surfaceOp: 'append',
|
||||
} as unknown as SessionEvent)
|
||||
let state = definition.init()
|
||||
state = definition.apply(state, append(1))
|
||||
state = definition.apply(state, append(3))
|
||||
expect(() => definition.apply(state, replace(7, 3))).toThrow('invalid current range')
|
||||
expect(() => definition.apply(state, replace(1, 7))).toThrow('invalid current range')
|
||||
expect(() => definition.apply(state, replace(3, 1))).toThrow('invalid current range')
|
||||
})
|
||||
|
||||
it('restores from a JSON checkpoint and unregisters with the token-meter fiber', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SessionProjectionRegistry)
|
||||
const meterFiber = await ctx.plugin(TokenMeterService)
|
||||
const session = ctx.sessions.create()
|
||||
session.append('request/header', {
|
||||
header: { config: CONFIG, system: 'You are terse.' },
|
||||
reason: 'initial',
|
||||
})
|
||||
appendUser(session, 'abcd')
|
||||
const checkpoint = JSON.parse(JSON.stringify(
|
||||
ctx.sessionProjections.checkpoint(session),
|
||||
)) as ReturnType<typeof ctx.sessionProjections.checkpoint>
|
||||
|
||||
await meterFiber.dispose()
|
||||
expect(ctx.sessionProjections.snapshot(session).values).not.toHaveProperty('contextBreakdown')
|
||||
|
||||
await ctx.plugin(TokenMeterService)
|
||||
expect(ctx.sessionProjections.viewCheckpoint(checkpoint).contextBreakdown).toEqual({
|
||||
systemTokens: estimateSystemTokens({ config: CONFIG, system: 'You are terse.' }),
|
||||
toolsTokens: 0,
|
||||
messageTokens: 9,
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe('shared estimator', () => {
|
||||
it('prices every content-block shape under the fixed heuristic', () => {
|
||||
expect(estimateContent([{ type: 'text', text: 'abcd' }])).toBe(5)
|
||||
expect(estimateContent([{ type: 'reasoning', text: 'abcdefgh' }] as ContentBlock[])).toBe(6)
|
||||
expect(estimateContent([{ type: 'tool-call', id: 'c' as never, name: 'bash', arguments: '{"a":1}' }])).toBe(7)
|
||||
expect(estimateContent([{
|
||||
type: 'tool-result', toolCallId: 'c' as never,
|
||||
content: [{ type: 'text', text: 'abcd' }],
|
||||
}])).toBe(9)
|
||||
const unknown = { type: 'mystery', payload: 'abc' } as unknown as ContentBlock
|
||||
expect(estimateContent([unknown])).toBe(4 + Math.ceil(JSON.stringify(unknown).length / 4))
|
||||
})
|
||||
|
||||
it('prices envelope parts independently and absent parts to zero', () => {
|
||||
expect(estimateSystemTokens(undefined)).toBe(0)
|
||||
expect(estimateSystemTokens({ config: CONFIG })).toBe(0)
|
||||
expect(estimateSystemTokens({ config: CONFIG, system: 'abcdefgh' })).toBe(6)
|
||||
expect(estimateToolsTokens(undefined)).toBe(0)
|
||||
expect(estimateToolsTokens({ config: CONFIG, tools: [] })).toBe(0)
|
||||
expect(estimateToolsTokens({ config: CONFIG, tools: TOOLS }))
|
||||
.toBe(Math.ceil(JSON.stringify(TOOLS).length / 4) + 4)
|
||||
expect(estimateHeader(undefined)).toBe(0)
|
||||
expect(estimateHeader({ config: CONFIG, system: 'abcdefgh', tools: TOOLS }))
|
||||
.toBe(6 + Math.ceil(JSON.stringify(TOOLS).length / 4) + 4)
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user