Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input
# Conflicts: # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/llm-streaming.i18n.yaml # docs/module-graph.md # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # packages/README.i18n.yaml # packages/client/connection/src/client/fixture.ts # packages/client/connection/src/index.ts # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md # packages/client/runtime/src/client/sessions/conversation.ts # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-conversation/src/client/apply.ts # packages/client/ui-conversation/src/client/chat/ChatView.tsx # packages/client/ui-conversation/src/client/chat/MessageItem.tsx # packages/client/ui-conversation/src/client/contract/slots.ts # packages/client/ui-trajectory/tests/views.spec.tsx # packages/compact/compact-basic/README.i18n.yaml # packages/cordis/tool-cordis/src/api-catalog.ts # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/src/api/sessions.ts # packages/host/apiproxy/src/index.ts # packages/host/apiproxy/tests/fetch-carrier.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-deepseek/tests/adapter.spec.ts # packages/llm/llm-deepseek/tests/serialize.spec.ts # packages/llm/llm-pi-ai/README.i18n.yaml # packages/llm/llm-pi-ai/src/adapter.ts # packages/llm/llm-pi-ai/src/index.ts # packages/llm/llm-pi-ai/tests/adapter.spec.ts # packages/llm/llm/src/types.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/src/index.ts # packages/ui/tui/tests/tui.spec.ts
This commit is contained in:
Yichen Jiang
@@ -8,6 +8,7 @@ import LlmService, {
|
||||
LlmError,
|
||||
ProviderRequestId,
|
||||
QUOTA_EXCEEDED_CODE,
|
||||
ReasoningEffortId,
|
||||
userAgent,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
|
||||
@@ -120,6 +121,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
// The wire request carried the auth header contents we configured.
|
||||
expect(server.requests[0]).toMatchObject({
|
||||
model: 'deepseek-v4-flash',
|
||||
reasoning_effort: 'high',
|
||||
stream: true,
|
||||
stream_options: { include_usage: true },
|
||||
})
|
||||
@@ -173,9 +175,45 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
expect(server.headers[0]?.['x-deepseek-harness-compact']).toBe('1')
|
||||
})
|
||||
|
||||
it('forwards thinking config onto the wire', async () => {
|
||||
it('switches dynamically from the configured high default through off to max', async () => {
|
||||
const server = await mockServer([
|
||||
{ kind: 'sse', events: textEvents },
|
||||
{ kind: 'sse', events: textEvents },
|
||||
{ kind: 'sse', events: textEvents },
|
||||
])
|
||||
const ctx = await harness(server.url, { thinking: 'enabled', reasoningEffort: 'high' })
|
||||
|
||||
await assemble(ctx,{
|
||||
model: 'deepseek-v4-flash',
|
||||
messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
|
||||
})
|
||||
await assemble(ctx,{
|
||||
model: 'deepseek-v4-flash',
|
||||
reasoningEffort: ReasoningEffortId('off'),
|
||||
messages: [{ role: 'user', content: [{ type: 'text', text: 'hi again' }] }],
|
||||
})
|
||||
await assemble(ctx,{
|
||||
model: 'deepseek-v4-flash',
|
||||
reasoningEffort: ReasoningEffortId('max'),
|
||||
messages: [{ role: 'user', content: [{ type: 'text', text: 'one more time' }] }],
|
||||
})
|
||||
expect(server.requests[0]).toMatchObject({
|
||||
thinking: { type: 'enabled' },
|
||||
reasoning_effort: 'high',
|
||||
})
|
||||
expect(server.requests[1]).toMatchObject({
|
||||
thinking: { type: 'disabled' },
|
||||
})
|
||||
expect(server.requests[1]).not.toHaveProperty('reasoning_effort')
|
||||
expect(server.requests[2]).toMatchObject({
|
||||
thinking: { type: 'enabled' },
|
||||
reasoning_effort: 'max',
|
||||
})
|
||||
})
|
||||
|
||||
it('publishes only off and omits the wire effort when thinking is disabled', async () => {
|
||||
const server = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const ctx = await harness(server.url, { thinking: 'disabled', reasoningEffort: 'high' })
|
||||
const ctx = await harness(server.url, { thinking: 'disabled' })
|
||||
|
||||
await assemble(ctx,{
|
||||
model: 'deepseek-v4-flash',
|
||||
@@ -183,10 +221,52 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
})
|
||||
expect(server.requests[0]).toMatchObject({
|
||||
thinking: { type: 'disabled' },
|
||||
reasoning_effort: 'high',
|
||||
})
|
||||
expect(server.requests[0]).not.toHaveProperty('reasoning_effort')
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'deepseek-v4-flash'))
|
||||
.resolves.toMatchObject({
|
||||
reasoning: {
|
||||
efforts: [{ id: ReasoningEffortId('off'), name: 'Off' }],
|
||||
defaultEffort: ReasoningEffortId('off'),
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('rejects a per-request effort before I/O when thinking is disabled', async () => {
|
||||
const server = await mockServer([])
|
||||
const ctx = await harness(server.url, { thinking: 'disabled' })
|
||||
|
||||
await expect(assemble(ctx, {
|
||||
model: 'deepseek-v4-flash',
|
||||
reasoningEffort: ReasoningEffortId('high'),
|
||||
messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
|
||||
})).rejects.toMatchObject({ code: 'UNSUPPORTED_REASONING_EFFORT' })
|
||||
expect(server.requests).toHaveLength(0)
|
||||
})
|
||||
|
||||
it.each(['high', 'max'])(
|
||||
'rejects direct adapter effort %s before I/O when thinking is disabled',
|
||||
async (effort) => {
|
||||
const server = await mockServer([])
|
||||
const adapter = new DeepSeekAdapter({
|
||||
apiKey: 'test-key',
|
||||
baseURL: server.url,
|
||||
defaults: { thinking: 'disabled' },
|
||||
})
|
||||
|
||||
const stream = adapter.stream({
|
||||
provider: 'deepseek',
|
||||
model: 'deepseek-v4-flash',
|
||||
reasoningEffort: ReasoningEffortId(effort),
|
||||
messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }],
|
||||
})
|
||||
await expect(async () => {
|
||||
for await (const _chunk of stream) { /* drain */ }
|
||||
}).rejects.toMatchObject({ code: 'UNSUPPORTED_REASONING_EFFORT' })
|
||||
expect(server.requests).toHaveLength(0)
|
||||
},
|
||||
)
|
||||
|
||||
it.each([
|
||||
[401, 'AUTH'],
|
||||
[403, 'AUTH'],
|
||||
@@ -522,17 +602,129 @@ describe('plugin registration and config', () => {
|
||||
expect(ctx.llm.listProviders()).toEqual([])
|
||||
})
|
||||
|
||||
it('registers retryPolicy from the provider config', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
retryPolicy: {
|
||||
mode: 'always',
|
||||
backoff: { initialDelayMs: 25, maxDelayMs: 100, jitterRatio: 0.2 },
|
||||
},
|
||||
})
|
||||
|
||||
expect(ctx.llm.providerRetryPolicy('deepseek')).toEqual({
|
||||
mode: 'always',
|
||||
initialDelayMs: 25,
|
||||
maxDelayMs: 100,
|
||||
jitterRatio: 0.2,
|
||||
})
|
||||
})
|
||||
|
||||
it('owns the deepseek provider and advertises the default models', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'DeepSeek-V4-Flash', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'DeepSeek-V4-Pro', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
])
|
||||
await expect(ctx.llm.resolveModelContext('deepseek', 'deepseek-v4-flash'))
|
||||
.resolves.toEqual({ contextWindow: 128_000 })
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'deepseek-v4-flash'))
|
||||
.resolves.toMatchObject({
|
||||
provider: 'deepseek',
|
||||
id: 'deepseek-v4-flash',
|
||||
name: 'DeepSeek-V4-Flash',
|
||||
context: { contextWindow: 256_000 },
|
||||
reasoning: {
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('off'), name: 'Off' },
|
||||
{ id: ReasoningEffortId('high'), name: 'High' },
|
||||
{ id: ReasoningEffortId('max'), name: 'Max' },
|
||||
],
|
||||
defaultEffort: ReasoningEffortId('high'),
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it.each(['off', 'max'] as const)('uses the configured %s reasoning default', async (effort) => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
reasoningEffort: effort,
|
||||
})
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'unlisted-pass-through'))
|
||||
.resolves.toMatchObject({
|
||||
reasoning: {
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('off'), name: 'Off' },
|
||||
{ id: ReasoningEffortId('high'), name: 'High' },
|
||||
{ id: ReasoningEffortId('max'), name: 'Max' },
|
||||
],
|
||||
defaultEffort: ReasoningEffortId(effort),
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('accepts off as the default when thinking is deployment-disabled', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
thinking: 'disabled',
|
||||
reasoningEffort: 'off',
|
||||
})
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'unlisted-pass-through'))
|
||||
.resolves.toMatchObject({
|
||||
reasoning: {
|
||||
efforts: [{ id: ReasoningEffortId('off'), name: 'Off' }],
|
||||
defaultEffort: ReasoningEffortId('off'),
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it.each(['high', 'max'] as const)(
|
||||
'rejects configured reasoning effort %s when thinking is disabled',
|
||||
async (reasoningEffort) => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await expect(ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
thinking: 'disabled',
|
||||
reasoningEffort,
|
||||
})).rejects.toThrow(/only reasoningEffort "off"/)
|
||||
expect(ctx.llm.listProviders()).toEqual([])
|
||||
},
|
||||
)
|
||||
|
||||
it.each(['high', 'max'] as const)(
|
||||
'rejects disabled-thinking effort %s at the direct constructor boundary',
|
||||
(reasoningEffort) => {
|
||||
expect(() => new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
defaults: { thinking: 'disabled', reasoningEffort },
|
||||
})).toThrow(/only reasoningEffort "off"/)
|
||||
},
|
||||
)
|
||||
|
||||
it('accepts disabled thinking with off at the direct constructor boundary', async () => {
|
||||
const adapter = new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
defaults: { thinking: 'disabled', reasoningEffort: 'off' },
|
||||
})
|
||||
await expect(adapter.resolveModel('deepseek', 'pass-through')).resolves.toMatchObject({
|
||||
reasoning: {
|
||||
efforts: [{ id: ReasoningEffortId('off'), name: 'Off' }],
|
||||
defaultEffort: ReasoningEffortId('off'),
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('uses the default model catalog when apply is called directly', async () => {
|
||||
@@ -540,8 +732,8 @@ describe('plugin registration and config', () => {
|
||||
await ctx.plugin(LlmService)
|
||||
LlmDeepSeek.apply(ctx, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-flash', name: 'DeepSeek-V4-Flash', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'deepseek-v4-pro', name: 'DeepSeek-V4-Pro', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
])
|
||||
})
|
||||
|
||||
@@ -565,10 +757,15 @@ describe('plugin registration and config', () => {
|
||||
{ provider: 'deepseek', id: 'private-fast', name: 'private-fast', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
{ provider: 'deepseek', id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget', inputModalities: ['text'], outputModalities: ['text'] },
|
||||
])
|
||||
await expect(ctx.llm.resolveModelContext('deepseek', 'private-fast'))
|
||||
.resolves.toEqual({ contextWindow: 32_000 })
|
||||
await expect(ctx.llm.resolveModelContext('deepseek', 'arbitrary-unlisted'))
|
||||
.resolves.toBeUndefined()
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'private-fast'))
|
||||
.resolves.toMatchObject({ context: { contextWindow: 32_000 } })
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'private-reasoner'))
|
||||
.resolves.toMatchObject({
|
||||
name: 'Private Reasoner',
|
||||
description: 'Higher reasoning budget',
|
||||
})
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'arbitrary-unlisted'))
|
||||
.resolves.not.toHaveProperty('context')
|
||||
})
|
||||
|
||||
it('uses exact model capacity before the adapter-wide default', async () => {
|
||||
@@ -584,12 +781,12 @@ describe('plugin registration and config', () => {
|
||||
],
|
||||
})
|
||||
|
||||
await expect(ctx.llm.resolveModelContext('deepseek', 'inherits-default'))
|
||||
.resolves.toEqual({ contextWindow: 256_000 })
|
||||
await expect(ctx.llm.resolveModelContext('deepseek', 'exact-override'))
|
||||
.resolves.toEqual({ contextWindow: 64_000 })
|
||||
await expect(ctx.llm.resolveModelContext('deepseek', 'unlisted-pass-through'))
|
||||
.resolves.toEqual({ contextWindow: 256_000 })
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'inherits-default'))
|
||||
.resolves.toMatchObject({ context: { contextWindow: 256_000 } })
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'exact-override'))
|
||||
.resolves.toMatchObject({ context: { contextWindow: 64_000 } })
|
||||
await expect(ctx.llm.resolveModelInfo('deepseek', 'unlisted-pass-through'))
|
||||
.resolves.toMatchObject({ context: { contextWindow: 256_000 } })
|
||||
})
|
||||
|
||||
it('allows an explicit empty model catalog', async () => {
|
||||
@@ -731,4 +928,16 @@ describe('plugin registration and config', () => {
|
||||
streamIdleTimeoutMs: MAX_TIMER_DELAY_MS + 1,
|
||||
})).rejects.toThrow(/streamIdleTimeoutMs/)
|
||||
})
|
||||
|
||||
it('rejects invalid nested retryPolicy before registering the provider', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
|
||||
await expect(ctx.plugin(LlmDeepSeek, {
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
retryPolicy: { mode: 'normal', maxRetries: -1 },
|
||||
})).rejects.toThrow(/retryPolicy/)
|
||||
expect(ctx.llm.listProviders()).toEqual([])
|
||||
})
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user