feat(apiproxy): make the default model a user setting the picker writes

The route a new session starts from was frozen into the gateway's
composition entry, so switching models in a conversation reached only that
conversation and every later session went back to the shipped default.

The gateway now owns an `api-gateway` settings section: the entry is the
base layer and the user document layers over it, so `session.selectModel`
records an accepted switch as the default for the next session. The write
is wholesale rather than a merge — switching to a model with no reasoning
effort has to clear a stored one — and a storage failure is reported
without undoing the switch, which already applies to its own session.

`targetFor` now resolves its tiers on every read instead of seeding once:
an explicit selection, else the session's own logged request header, else
the live default. That is what keeps a session that has run a turn deriving
its route from its log forever after, while a session still blank — New
Session reuses one rather than minting another — starts from a default
saved after it was created.
This commit is contained in:
Yichen Jiang
2026-08-07 13:23:19 +08:00
parent 079d71d591
commit f2d1a29636
18 changed files with 274 additions and 58 deletions

View File

@@ -27,7 +27,7 @@ async function harness(): Promise<{ ctx: Context; api: ApiProxy }> {
await ctx.plugin(UserInteractionService)
await ctx.plugin(AgentRegistry)
await ctx.plugin(ApprovalService)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
return { ctx, api }
}
@@ -217,7 +217,7 @@ describe('approval pending registry', () => {
await ctx.plugin(ApprovalService)
let api!: ApiProxy
const fiber = ctx.plugin(Object.assign((fiberCtx: Context) => {
api = createApiProxy(fiberCtx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
api = createApiProxy(fiberCtx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
}, { inject: ['sessions', 'agents', 'userInteraction', 'approval'] }))
await fiber.await()
const abort = new AbortController()

View File

@@ -35,7 +35,7 @@ async function harness(): Promise<{ ctx: Context; api: ApiProxy; attach: (sessio
await ctx.plugin(AgentRegistry)
return {
ctx,
api: createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }),
api: createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }),
attach: (session) => {
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
},

View File

@@ -62,7 +62,7 @@ describe('sessions.list cold merge', () => {
return undefined
},
})
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const response = await api.sessions.list(request({}))
expect(response.result.ok).toBe(true)
@@ -90,7 +90,7 @@ describe('attached updatedAt excludes end-seed', () => {
await ctx.plugin(SessionStore)
await ctx.plugin(UserInteractionService)
await ctx.plugin(AgentRegistry)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
// Old work, resumed just now: the log tail would report the pickup.
const worked = 1_000_000
@@ -148,7 +148,7 @@ describe('cold history recovery view', () => {
inspect: (id: SessionId, signal?: AbortSignal) => coordinator.inspect(id, signal),
locate: () => undefined,
} as never)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const history = await api.sessions.history(request({ sessionId, beforeSeq: 2, maxMessages: 10 }))
if (!history.result.ok) throw new Error('history failed')
@@ -216,7 +216,7 @@ describe('subagent ownership fence', () => {
locate: () => undefined,
} as never)
const resume = vi.spyOn(ctx.agents, 'resume')
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const history = await api.sessions.history(request({ sessionId }))
expect(history.result.ok).toBe(true)
@@ -275,7 +275,7 @@ describe('subagent ownership fence', () => {
// instead of answering `agent-busy`.
const resume = vi.spyOn(ctx.agents, 'resume')
.mockRejectedValue(new Error('registry unavailable in this bench'))
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const prompt = await api.sessions.prompt(request({
sessionId,
@@ -316,7 +316,7 @@ describe('subagent ownership fence', () => {
})
const startingChild = { id: startingSession.id, session: startingSession, status: 'idle', ctx } as Agent
ctx.agents.enter(startingChild, parent)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const stopped = await api.sessions.cancel(request({ sessionId: originChild.id }))
expect(stopped.result.ok).toBe(false)
@@ -362,7 +362,7 @@ describe('subagent ownership fence', () => {
const followup = vi.fn()
const agent = { id: session.id, session, status: 'idle', ctx, followup } as unknown as Agent
ctx.agents.register(agent)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const response = await api.sessions.prompt(request({
sessionId: agent.id,
@@ -380,7 +380,7 @@ describe('degenerate composition (no persistence, no factory)', () => {
await ctx.plugin(SessionStore)
await ctx.plugin(AgentRegistry)
await ctx.plugin(UserInteractionService)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const listed = await api.sessions.list(request({}))
expect(listed.result.ok).toBe(true)
@@ -405,7 +405,7 @@ describe('degenerate composition (no persistence, no factory)', () => {
list: () => Promise.resolve([]),
inspect,
} as never)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const response = await api.sessions.history(request({ sessionId: sid('session-missing') }))
expect(response.result.ok).toBe(false)
@@ -431,7 +431,7 @@ describe('sessions.prompt synchronous rejection', () => {
followup: () => { throw new Error('agent "session-throwing" lifecycle disposed') },
steer: () => { throw new Error('agent "session-throwing" lifecycle disposed') },
} as unknown as Agent)
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
for (const mode of ['queue', 'steer'] as const) {
const response = await api.sessions.prompt(request({
@@ -475,7 +475,7 @@ describe('sessions.prompt synchronous rejection', () => {
ctx.agents.register(child)
throw new Error('session id already published')
})
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const models = await api.sessions.models(request({ sessionId }))
expect(models.result.ok).toBe(false)

View File

@@ -25,7 +25,7 @@ import type { RpcRequest, RpcResponse } from '../src/api/rpc.ts'
import { RpcId } from '../src/api/rpc.ts'
import { createApiProxy } from '../src/api-proxy.ts'
const DEFAULTS = { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }
const DEFAULTS = { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
function request<P>(payload: P): RpcRequest<P> {
return { rpcId: RpcId(`req-${String(nextRpc++)}`), payload }

View File

@@ -24,7 +24,7 @@ import type { RpcRequest, RpcResponse } from '../src/api/rpc.ts'
import { RpcId } from '../src/api/rpc.ts'
import { createApiProxy } from '../src/api-proxy.ts'
const DEFAULTS = { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }
const DEFAULTS = { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
let nextRpc = 1
function request<P>(payload: P): RpcRequest<P> {

View File

@@ -82,8 +82,7 @@ function liveAgent(
}
const api = (ctx: Context) => createApiProxy(ctx, {
provider: 'default-provider',
model: 'default-model',
defaultTarget: () => ({ provider: 'default-provider', model: 'default-model' }),
cwd: '/tmp',
workspaceRoot: '/tmp',
})

View File

@@ -125,7 +125,7 @@ describe('Web session model selection', () => {
model: 'private-preview',
reasoningEffort: ReasoningEffortId('max'),
})
const api = createApiProxy(ctx, { provider: 'deepseek-official', model: 'deepseek-chat', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const catalog = expectValue(await api.sessions.models(request({ sessionId })))
expect(catalog.current).toEqual({
@@ -160,7 +160,7 @@ describe('Web session model selection', () => {
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 api = createApiProxy(ctx, { defaultTarget: () => ({ 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
@@ -225,4 +225,101 @@ describe('Web session model selection', () => {
.toEqual({ provider: 'deepseek-official', model: 'private-preview', reasoningEffort: 'max' })
await ctx.fiber.dispose()
})
it('reads the host default live for a session whose log names no route', async () => {
const { ctx, sessionId } = await harness()
let stored = { provider: 'deepseek-official', model: 'deepseek-chat' }
const api = createApiProxy(ctx, {
defaultTarget: () => stored,
cwd: '/tmp',
workspaceRoot: '/tmp',
})
expect(expectValue(await api.sessions.models(request({ sessionId }))).current)
.toEqual({ provider: 'deepseek-official', model: 'deepseek-chat' })
// The default moving after the session exists still reaches it: New
// Session reuses a blank session rather than minting another, so a seed
// captured at creation would show the superseded model there.
stored = { provider: 'deepseek-official', model: 'deepseek-reasoner' }
expect(expectValue(await api.sessions.models(request({ sessionId }))).current)
.toEqual({ provider: 'deepseek-official', model: 'deepseek-reasoner' })
expect(expectValue(await api.host.describe(request({}))))
.toMatchObject({ provider: 'deepseek-official', model: 'deepseek-reasoner' })
await ctx.fiber.dispose()
})
it('keeps a session that logged a route on it when the host default moves', async () => {
const { ctx, sessionId } = await harness({
provider: 'deepseek-official',
model: 'deepseek-chat',
})
let stored = { provider: 'deepseek-official', model: 'deepseek-chat' }
const api = createApiProxy(ctx, {
defaultTarget: () => stored,
cwd: '/tmp',
workspaceRoot: '/tmp',
})
stored = { provider: 'duplicate', model: 'same' }
expect(expectValue(await api.sessions.models(request({ sessionId }))).current)
.toEqual({ provider: 'deepseek-official', model: 'deepseek-chat' })
await ctx.fiber.dispose()
})
it('saves an accepted selection as the default and survives a storage failure', async () => {
const { ctx, sessionId } = await harness()
const saved: unknown[] = []
let reject = false
const api = createApiProxy(ctx, {
defaultTarget: () => ({ provider: 'deepseek-official', model: 'deepseek-chat' }),
persistDefaultTarget: (target) => {
saved.push(target)
return reject ? Promise.reject(new Error('read-only document')) : Promise.resolve()
},
cwd: '/tmp',
workspaceRoot: '/tmp',
})
expectValue(await api.sessions.selectModel(request({
sessionId, provider: 'deepseek-official', model: 'deepseek-reasoner', reasoningEffort: 'max',
})))
expect(saved).toEqual([
{ provider: 'deepseek-official', model: 'deepseek-reasoner', reasoningEffort: 'max' },
])
// A refused selection never becomes anyone's default.
await api.sessions.selectModel(request({ sessionId, provider: 'missing', model: 'model' }))
expect(saved).toHaveLength(1)
// Storage failing is not the selection failing: the switch already applies
// to this session, so the call still succeeds.
reject = true
const stillAccepted = expectValue(await api.sessions.selectModel(request({
sessionId, provider: 'deepseek-official', model: 'deepseek-chat',
})))
expect(stillAccepted.selected).toEqual({ provider: 'deepseek-official', model: 'deepseek-chat', reasoningEffort: 'high' })
expect(expectValue(await api.sessions.models(request({ sessionId }))).current)
.toEqual({ provider: 'deepseek-official', model: 'deepseek-chat', reasoningEffort: 'high' })
await ctx.fiber.dispose()
})
it('serves a session and its catalog when the stored default names a route that is gone', async () => {
const { ctx, sessionId } = await harness()
const api = createApiProxy(ctx, {
// What a Models-page removal leaves behind: the settings document still
// names the route the user last picked, and nothing serves it.
defaultTarget: () => ({ provider: 'deleted-gateway', model: 'deleted-model' }),
cwd: '/tmp',
workspaceRoot: '/tmp',
})
const catalog = expectValue(await api.sessions.models(request({ sessionId })))
// Passed through rather than repaired: matching no group is precisely what
// makes the composer seat prompt for a selection instead of naming a model
// the deployment cannot reach.
expect(catalog.current).toEqual({ provider: 'deleted-gateway', model: 'deleted-model' })
expect(catalog.groups.flatMap(group => group.models.map(model => `${group.id}/${model.id}`)))
.not.toContain('deleted-gateway/deleted-model')
await ctx.fiber.dispose()
})
})

View File

@@ -68,7 +68,7 @@ function seedMessages(session: Session, count: number): void {
}
}
const api = (ctx: Context) => createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = (ctx: Context) => createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
describe('session.history projections block', () => {
it('serves the unit value on the tail page with asOfSeq = last event seq', async () => {

View File

@@ -13,7 +13,7 @@ async function harness(): Promise<{ ctx: Context; api: ApiProxy }> {
await ctx.plugin(UserInteractionService)
return {
ctx,
api: createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }),
api: createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }),
}
}

View File

@@ -68,7 +68,7 @@ function liveAgent(ctx: Context, id: string, turns: number): Session {
return session
}
const api = (ctx: Context) => createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = (ctx: Context) => createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
describe('sessions.rename', () => {
it('accepts through the composed title service: normalized user-source event, echoed seq', async () => {

View File

@@ -27,7 +27,7 @@ vi.mock('node:fs/promises', async (importOriginal) => {
})
const sid = (value: string): SessionId => value as SessionId
const defaults = { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' }
const defaults = { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' }
function request(query: string): RpcRequest<{ query: string }> {
return { rpcId: RpcId(`search-${query}`), payload: { query } }

View File

@@ -88,7 +88,7 @@ function bench(options: {
ctx.provide('sessionProjections', { snapshot, restore, onChanged: () => () => {} })
ctx.provide('userInteraction', { registerProvider: () => () => {} })
const api = createApiProxy(ctx, {
provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp',
defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp',
})
return { api, getAgent, listChildren, inspect, snapshot, restore, followup, parent }
}

View File

@@ -105,7 +105,7 @@ async function collect(iterable: AsyncIterable<RpcRequest<MuxFrame>>, count: num
describe('mux live view computation', () => {
it('attaches the three standard card views, omits view without a presenter, soft-falls on throw', async () => {
const { ctx } = await harness()
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const abort = new AbortController()
const stream = api.events.mux({ rpcId: RpcId('t-mux'), payload: {} }, abort.signal)
const collected = collect(stream, 9, abort)
@@ -170,7 +170,7 @@ describe('mux live view computation', () => {
it('serves history entries with call/result views, backscan pairing, and soft-falls', async () => {
const { ctx } = await harness()
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const session = ctx.sessions.create()
// history resolves the agent first; a live structural stub is enough (only
// .session is read on this path).
@@ -238,7 +238,7 @@ describe('mux live view computation', () => {
it('counts only append-origin messages toward maxMessages and keeps compaction provenance whole', async () => {
const { ctx } = await harness()
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const session = ctx.sessions.create()
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
session.append('turn/start', { turn: 1 })
@@ -287,7 +287,7 @@ describe('mux live view computation', () => {
it('drops a disposed session from the live open-call table (result after dispose gets no view)', async () => {
const { ctx } = await harness()
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const abort = new AbortController()
const stream = api.events.mux({ rpcId: RpcId('t-mux3'), payload: {} }, abort.signal)
@@ -308,7 +308,7 @@ describe('mux live view computation', () => {
it('pairs a result after turn/end via the in-memory backscan fallback', async () => {
const { ctx } = await harness()
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
const api = createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
const abort = new AbortController()
const stream = api.events.mux({ rpcId: RpcId('t-mux2'), payload: {} }, abort.signal)
const collected = collect(stream, 4, abort)

View File

@@ -100,8 +100,7 @@ async function harness(
// object per harness mirrors the seam's stability contract.
ctx.provide('directoryPicker', { capability: () => picker } as never)
const api = createApiProxy(ctx, {
provider: 'test',
model: 'test-model',
defaultTarget: () => ({ provider: 'test', model: 'test-model' }),
cwd: workspaceRoot,
workspaceRoot,
...extras.openPath === undefined ? {} : { openPath: extras.openPath },

View File

@@ -274,7 +274,7 @@ describe('sessions domain schemas', () => {
describe('host domain schemas', () => {
it('validates describe request/value', () => {
expect(hostDescribeRequestSchema.parse({})).toEqual({})
const value = hostDescribeValueSchema.parse({ version: '1', cwd: '/x', provider: 'p', model: 'm', attachedSessions: 2 })
const value = hostDescribeValueSchema.parse({ version: '1', cwd: '/x', defaultTarget: () => ({ provider: 'p', model: 'm' }), attachedSessions: 2 })
expect(value.attachedSessions).toBe(2)
expect(hostDescribeValueSchema.parse({ version: '1', cwd: '/x', attachedSessions: 0 }).provider).toBeUndefined()
})