feat(llm): add replay token metering (PR2 round 1)

This commit is contained in:
Hypatia May
2026-07-15 14:47:29 +08:00
parent c9efdf68f9
commit f038780ff6
61 changed files with 3393 additions and 2369 deletions

File diff suppressed because it is too large Load Diff

View File

@@ -11,6 +11,7 @@ import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
import * as Invariants from '@deepseek-ai/dsh-invariants'
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
/**
@@ -20,13 +21,7 @@ import type { SurfaceEvent } from '@deepseek-ai/dsh-session'
* surface-position semantics rather than raw-log scanning.
*/
const TOKENS_PER_BLOCK = 10
class ReproCompactService extends BasicCompactService {
override estimateContentTokens(blocks: readonly ContentBlock[]): number {
return blocks.length * TOKENS_PER_BLOCK
}
override async summarize(): Promise<{ summary: ContentBlock[]; model: string }> {
return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], model: 'stub' }
}
@@ -67,6 +62,9 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(TokenMeterService, {
models: { mock: { contextWindow: 64, charsPerToken: 1_000 } },
})
ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps))
ctx.tools.register(defineTool({
name: 'work',
@@ -80,9 +78,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr
// fires within the runaway turn.
const compact = new ReproCompactService(ctx, {
auto: true,
contextWindow: 64,
thresholdRatio: 0.5,
retainTokens: 20,
models: { mock: { thresholdRatio: 0.5, retainTokens: 20 } },
summarizationModel: '',
maxTokens: 8192,
compactionRetries: 1,

View File

@@ -0,0 +1,66 @@
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { pathToFileURL } from 'node:url'
import { afterEach, describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
import Include from '@cordisjs/plugin-include'
import LlmService from '@deepseek-ai/dsh-llm'
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
import BasicCompactService from '@deepseek-ai/dsh-compact-basic'
let root: string | undefined
let context: Context | undefined
afterEach(async () => {
await context?.fiber.dispose()
context = undefined
if (root !== undefined) await rm(root, { recursive: true, force: true })
root = undefined
})
describe('real Loader composition', () => {
it('loads the zero-config token-meter then compact-basic YAML pair', async () => {
root = await mkdtemp(join(tmpdir(), 'dsh-token-meter-loader-'))
const configPath = join(root, 'cordis.yml')
await writeFile(configPath, [
"- name: '@deepseek-ai/dsh-llm'",
"- name: '@deepseek-ai/dsh-token-meter'",
"- name: '@deepseek-ai/dsh-compact-basic'",
'',
].join('\n'))
context = new Context()
context.baseUrl = pathToFileURL(root).href + '/'
await context.plugin(Loader)
context.loader.builtins.include = Include
const modules = new Map<string, unknown>([
['@deepseek-ai/dsh-llm', LlmService],
['@deepseek-ai/dsh-token-meter', TokenMeterService],
['@deepseek-ai/dsh-compact-basic', BasicCompactService],
])
context.loader.internal = {
version: 'v2',
async import(specifier: string) {
if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`)
return modules.get(specifier)
},
} as unknown as NonNullable<typeof context.loader.internal>
await context.loader.create({
name: 'cordis:include',
config: { path: pathToFileURL(configPath).href },
})
await context.loader.await()
const unloaded = [...context.loader.entries()]
.filter(entry => entry.fiber === undefined && !entry.disabled)
.map(entry => entry.options.name)
expect(unloaded).toEqual([])
expect(context.tokenMeter.resolve('deepseek-v4-flash')).toMatchObject({
contextWindow: 128_000,
charsPerToken: 4,
})
expect(context.get('compact')).toBeInstanceOf(BasicCompactService)
})
})