229 lines
8.5 KiB
TypeScript
229 lines
8.5 KiB
TypeScript
/**
|
|
* Web session model-directory and selection behavior: dynamic provider grouping,
|
|
* provider-local catalog failures, logged-target restoration without stale
|
|
* catalog injection, advisory pass-through models, and the prompt-assembly
|
|
* boundary for a running selection change.
|
|
*/
|
|
|
|
import { describe, expect, it } from 'vitest'
|
|
import { Context } from 'cordis'
|
|
import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent'
|
|
import type { Agent } from '@deepseek-ai/dsh-agent'
|
|
import LlmService, { LlmAdapter, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
|
import type {
|
|
GenerateOptions, LlmCallConfig, LlmModelInfo, LlmModelReasoningInfo, LlmProviderInfo,
|
|
LlmResolvedModelInfo, StreamChunk,
|
|
} from '@deepseek-ai/dsh-llm'
|
|
import SessionStore from '@deepseek-ai/dsh-session'
|
|
import type { SessionId } from '@deepseek-ai/dsh-session'
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
|
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
|
import type { RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
|
import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
|
|
import { createApiProxy } from '../src/api-proxy.ts'
|
|
|
|
let nextRpc = 1
|
|
function request<P>(payload: P): RpcRequest<P> {
|
|
return { rpcId: RpcId(`models-${String(nextRpc++)}`), payload }
|
|
}
|
|
|
|
class CatalogAdapter extends LlmAdapter {
|
|
constructor(
|
|
private readonly name: string,
|
|
private readonly models: readonly LlmModelInfo[] | Error,
|
|
private readonly reasoning?: LlmModelReasoningInfo,
|
|
private readonly exactError?: Error,
|
|
) {
|
|
super()
|
|
}
|
|
|
|
override providerInfo(provider: string): LlmProviderInfo {
|
|
return { id: provider, name: this.name }
|
|
}
|
|
|
|
override listModels(): Promise<readonly LlmModelInfo[]> {
|
|
return this.models instanceof Error
|
|
? Promise.reject(this.models)
|
|
: Promise.resolve(this.models)
|
|
}
|
|
|
|
override resolveModel(provider: string, model: string): Promise<LlmResolvedModelInfo> {
|
|
if (this.exactError !== undefined) return Promise.reject(this.exactError)
|
|
return Promise.resolve({
|
|
provider,
|
|
id: model,
|
|
name: model,
|
|
...this.reasoning === undefined ? {} : { reasoning: this.reasoning },
|
|
})
|
|
}
|
|
|
|
override async *stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
|
|
// Catalog tests never enter provider streaming.
|
|
}
|
|
}
|
|
|
|
const REASONING: LlmModelReasoningInfo = {
|
|
efforts: [
|
|
{ id: ReasoningEffortId('off'), name: 'Off' },
|
|
{ id: ReasoningEffortId('high'), name: 'High' },
|
|
{ id: ReasoningEffortId('max'), name: 'Max' },
|
|
],
|
|
defaultEffort: ReasoningEffortId('high'),
|
|
}
|
|
|
|
async function harness(logged?: {
|
|
provider: string
|
|
model: string
|
|
reasoningEffort?: ReasoningEffortId
|
|
}): Promise<{
|
|
ctx: Context
|
|
agent: Agent
|
|
sessionId: SessionId
|
|
}> {
|
|
const ctx = new Context()
|
|
await ctx.plugin(SessionStore)
|
|
await ctx.plugin(SystemPrompt, { persona: '' })
|
|
await ctx.plugin(LlmService)
|
|
await ctx.plugin(UserInteractionService)
|
|
await ctx.plugin(AgentRegistry)
|
|
ctx.llm.registerAdapter(['deepseek-official'], new CatalogAdapter('DeepSeek', [
|
|
{ provider: 'deepseek-official', id: 'deepseek-chat', name: 'DeepSeek Chat' },
|
|
{ provider: 'deepseek-official', id: 'deepseek-reasoner', name: 'DeepSeek Reasoner', description: 'Reasoning model' },
|
|
], REASONING))
|
|
ctx.llm.registerAdapter(['broken'], new CatalogAdapter('Broken Provider', new Error('catalog offline')))
|
|
ctx.llm.registerAdapter(['metadata-broken'], new CatalogAdapter('Metadata Broken', [
|
|
{ provider: 'metadata-broken', id: 'listed', name: 'Listed' },
|
|
], undefined, new Error('reasoning metadata offline')))
|
|
ctx.llm.registerAdapter(['empty'], new CatalogAdapter('Empty Provider', []))
|
|
ctx.llm.registerAdapter(['duplicate'], new CatalogAdapter('Duplicate Provider', [
|
|
{ provider: 'duplicate', id: 'same', name: 'Same' },
|
|
{ provider: 'duplicate', id: 'same', name: 'Same Again' },
|
|
]))
|
|
const session = ctx.sessions.create()
|
|
if (logged !== undefined) {
|
|
session.append('request/header', { header: { config: logged }, reason: 'initial' })
|
|
}
|
|
const agent = {
|
|
id: session.id,
|
|
session,
|
|
status: 'running',
|
|
ctx,
|
|
} as Agent
|
|
ctx.agents.register(agent)
|
|
return { ctx, agent, sessionId: session.id }
|
|
}
|
|
|
|
function expectValue<T>(response: { result: { ok: true; value: T } | { ok: false } }): T {
|
|
if (!response.result.ok) throw new Error('expected successful response')
|
|
return response.result.value
|
|
}
|
|
|
|
describe('Web session model selection', () => {
|
|
it('groups successful providers and leaves an unlisted current target out of the catalog', async () => {
|
|
const { ctx, sessionId } = await harness({
|
|
provider: 'deepseek-official',
|
|
model: 'private-preview',
|
|
reasoningEffort: ReasoningEffortId('max'),
|
|
})
|
|
const api = createApiProxy(ctx, { provider: 'deepseek-official', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
|
|
|
const catalog = expectValue(await api.sessions.models(request({ sessionId })))
|
|
expect(catalog.current).toEqual({
|
|
provider: 'deepseek-official',
|
|
model: 'private-preview',
|
|
reasoningEffort: 'max',
|
|
})
|
|
expect(catalog.groups).toEqual([{
|
|
id: 'deepseek-official',
|
|
name: 'DeepSeek',
|
|
models: [
|
|
{ id: 'deepseek-chat', name: 'DeepSeek Chat', reasoning: REASONING },
|
|
{
|
|
id: 'deepseek-reasoner',
|
|
name: 'DeepSeek Reasoner',
|
|
description: 'Reasoning model',
|
|
reasoning: REASONING,
|
|
},
|
|
],
|
|
}])
|
|
expect(catalog.failures).toEqual([
|
|
{ id: 'broken', name: 'Broken Provider', message: 'catalog offline' },
|
|
{ id: 'metadata-broken', name: 'Metadata Broken', message: 'reasoning metadata offline' },
|
|
{
|
|
id: 'duplicate',
|
|
name: 'Duplicate Provider',
|
|
message: 'adapter returned invalid or duplicate model metadata for provider "duplicate"',
|
|
},
|
|
])
|
|
await ctx.fiber.dispose()
|
|
})
|
|
|
|
it('accepts an advisory-unlisted model, rejects an unavailable provider, and switches only after the next assembly', async () => {
|
|
const { ctx, agent, sessionId } = await harness()
|
|
const api = createApiProxy(ctx, { provider: 'deepseek-official', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
|
|
const seed: LlmCallConfig = { provider: 'seed', model: 'seed', temperature: 0.2 }
|
|
const signal = new AbortController().signal
|
|
|
|
expect(expectValue(await api.sessions.models(request({ sessionId }))).current)
|
|
.toEqual({ provider: 'deepseek-official', model: 'deepseek-chat' })
|
|
expect((await ctx.systemPrompt.assemble()).variables)
|
|
.toMatchObject({ provider: 'deepseek-official', model: 'deepseek-chat' })
|
|
|
|
const selected = expectValue(await api.sessions.selectModel(request({
|
|
sessionId,
|
|
provider: 'deepseek-official',
|
|
model: 'private-preview',
|
|
reasoningEffort: 'max',
|
|
})))
|
|
expect(selected.selected).toEqual({
|
|
provider: 'deepseek-official',
|
|
model: 'private-preview',
|
|
reasoningEffort: 'max',
|
|
})
|
|
await expect(agentEvents(ctx, agent).waterfall(
|
|
'agent/request', 1, 0, signal, () => Promise.resolve(seed),
|
|
)).resolves.toMatchObject({ provider: 'deepseek-official', model: 'deepseek-chat' })
|
|
|
|
expect((await ctx.systemPrompt.assemble()).variables)
|
|
.toMatchObject({ provider: 'deepseek-official', model: 'private-preview' })
|
|
await expect(agentEvents(ctx, agent).waterfall(
|
|
'agent/request', 1, 1, signal, () => Promise.resolve(seed),
|
|
)).resolves.toMatchObject({
|
|
provider: 'deepseek-official',
|
|
model: 'private-preview',
|
|
reasoningEffort: 'max',
|
|
})
|
|
|
|
const unsupported = await api.sessions.selectModel(request({
|
|
sessionId,
|
|
provider: 'deepseek-official',
|
|
model: 'private-preview',
|
|
reasoningEffort: 'medium',
|
|
}))
|
|
expect(unsupported.result).toMatchObject({
|
|
ok: false,
|
|
error: {
|
|
code: 'model-unavailable',
|
|
message: 'provider "deepseek-official" model "private-preview" does not support reasoning effort "medium"',
|
|
},
|
|
})
|
|
|
|
const rejected = await api.sessions.selectModel(request({
|
|
sessionId,
|
|
provider: 'missing',
|
|
model: 'model',
|
|
}))
|
|
expect(rejected.result).toEqual({
|
|
ok: false,
|
|
error: {
|
|
code: 'model-unavailable',
|
|
message: 'no adapter registered for provider "missing"',
|
|
details: { provider: 'missing', model: 'model' },
|
|
},
|
|
})
|
|
expect(expectValue(await api.sessions.models(request({ sessionId }))).current)
|
|
.toEqual({ provider: 'deepseek-official', model: 'private-preview', reasoningEffort: 'max' })
|
|
await ctx.fiber.dispose()
|
|
})
|
|
})
|