feat(llm-deepseek): per-request connection resolution over settings + credentials
The adapter takes an options thunk and a per-stream credential resolver instead of frozen construction facts: base URL, catalog, defaults, idle budget, and the API key re-resolve at each operation, so a settings or credential change reaches the very next request while in-flight streams keep the facts they started with. resolveAdapterOptions is the one explicit resolve step (entry config fails loud at load; a live snapshot failing a beyond-schema bound keeps the last good options). The plugin layers its entry config under the optional llm-deepseek settings section and resolves keys literal-first through ctx.credentials with an ambient env fallback; a missing key now registers the route, warns, and fails each request with actionable MISSING_CREDENTIAL instead of failing plugin load. The registration-captured retry policy re-registers the route in place when it changes.
This commit is contained in:
Yichen Jiang
@@ -27,8 +27,10 @@
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-credentials": "^0.0.1",
|
||||
"@deepseek-ai/dsh-invariants": "^0.0.1",
|
||||
"@deepseek-ai/dsh-llm": "^0.0.1",
|
||||
"@deepseek-ai/dsh-settings": "^0.0.1",
|
||||
"@deepseek-ai/dsh-timeout": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
@@ -37,8 +39,10 @@
|
||||
"schemastery": "^3.18.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-credentials": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-settings": "workspace:^",
|
||||
"@deepseek-ai/dsh-timeout": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
|
||||
@@ -1,21 +1,23 @@
|
||||
/**
|
||||
* `DeepSeekAdapter`: fetch + SSE against a DeepSeek (OpenAI-compatible)
|
||||
* chat-completions endpoint, emitting harness StreamChunks.
|
||||
* chat-completions endpoint, emitting harness StreamChunks. The adapter is
|
||||
* transport-only: connection facts arrive through a thunk resolved once per
|
||||
* operation and the bearer token through a per-request resolver, so the
|
||||
* registering plugin owns validation, layering, and credential policy.
|
||||
*
|
||||
* @module dsh-llm-deepseek/adapter
|
||||
*/
|
||||
|
||||
import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, isQuotaExceededError, LlmAdapter, LlmError, ProviderRequestId, QUOTA_EXCEEDED_CODE, ReasoningEffortId, resolveRetryPolicy } from '@deepseek-ai/dsh-llm'
|
||||
import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, isQuotaExceededError, LlmAdapter, LlmError, ProviderRequestId, QUOTA_EXCEEDED_CODE, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
import type {
|
||||
GenerateOptions,
|
||||
LlmModelInfo,
|
||||
LlmProviderInfo,
|
||||
LlmResolvedModelInfo,
|
||||
ResolvedRetryPolicy,
|
||||
RetryPolicyConfig,
|
||||
StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import { idleWatchdog, MAX_TIMER_DELAY_MS, timeoutOf } from '@deepseek-ai/dsh-timeout'
|
||||
import { idleWatchdog, timeoutOf } from '@deepseek-ai/dsh-timeout'
|
||||
import { serializeRequest } from './serialize.ts'
|
||||
import type { RequestDefaults } from './serialize.ts'
|
||||
import { parseSse } from './sse.ts'
|
||||
@@ -34,22 +36,37 @@ export interface DeepSeekCatalogModel {
|
||||
contextWindow?: number
|
||||
}
|
||||
|
||||
/** Constructor options for {@link DeepSeekAdapter}; the plugin's `apply` resolves them from Config + environment. */
|
||||
export interface DeepSeekAdapterOptions {
|
||||
/** Bearer token sent in the `authorization` header on every request. */
|
||||
apiKey: string
|
||||
/**
|
||||
* Validated connection facts for one operation. The plugin's
|
||||
* `resolveAdapterOptions` is the one explicit resolve step producing this
|
||||
* shape; the adapter trusts it and re-reads it per operation, which is what
|
||||
* makes a configuration change reach the next request without re-registration.
|
||||
*/
|
||||
export interface DeepSeekConnectionOptions {
|
||||
/** Endpoint base; `/chat/completions` is appended. */
|
||||
baseURL: string
|
||||
/** Request defaults applied to every call (thinking mode, effort). */
|
||||
defaults?: RequestDefaults
|
||||
defaults: RequestDefaults
|
||||
/** Positive context capacity used when the selected model has no exact value. */
|
||||
defaultContextWindow?: number
|
||||
/** Advisory models exposed to discovery consumers; requests remain unrestricted. */
|
||||
models?: readonly DeepSeekCatalogModel[]
|
||||
models: readonly DeepSeekCatalogModel[]
|
||||
/** Maximum provider idle time while one stream read is outstanding. */
|
||||
streamIdleTimeoutMs?: number
|
||||
/** Provider-owned model-request retry policy; omission uses normal defaults. */
|
||||
retryPolicy?: RetryPolicyConfig
|
||||
streamIdleTimeoutMs: number
|
||||
/** Provider-owned model-request retry policy, already resolved. */
|
||||
retryPolicy: ResolvedRetryPolicy
|
||||
}
|
||||
|
||||
/** Constructor options for {@link DeepSeekAdapter}: the two resolution seams the plugin owns. */
|
||||
export interface DeepSeekAdapterOptions {
|
||||
/** Current validated connection facts; called once per operation. */
|
||||
options: () => DeepSeekConnectionOptions
|
||||
/**
|
||||
* Resolve the bearer token for one request; called once per stream call and
|
||||
* frozen for that call. Throws `LlmError` `MISSING_CREDENTIAL` when no key
|
||||
* is available anywhere.
|
||||
*/
|
||||
resolveApiKey: () => Promise<string>
|
||||
}
|
||||
|
||||
/** Default maximum idle interval while an adapter stream read is outstanding. */
|
||||
@@ -118,29 +135,8 @@ export function httpErrorCode(status: number, error?: WireError['error']): strin
|
||||
* map to `ABORTED`; the configured per-read idle watchdog maps to `TIMEOUT`.
|
||||
*/
|
||||
export class DeepSeekAdapter extends LlmAdapter {
|
||||
private readonly streamIdleTimeoutMs: number
|
||||
private readonly retryPolicy: ResolvedRetryPolicy
|
||||
|
||||
constructor(private readonly options: DeepSeekAdapterOptions) {
|
||||
constructor(private readonly config: DeepSeekAdapterOptions) {
|
||||
super()
|
||||
if (options.defaults?.thinking === 'disabled'
|
||||
&& options.defaults.reasoningEffort !== undefined
|
||||
&& options.defaults.reasoningEffort !== 'off') {
|
||||
throw new Error('llm-deepseek: only reasoningEffort "off" can be configured when thinking is disabled')
|
||||
}
|
||||
if (options.defaultContextWindow !== undefined
|
||||
&& (!Number.isInteger(options.defaultContextWindow) || options.defaultContextWindow <= 0)) {
|
||||
throw new Error('llm-deepseek: defaultContextWindow must be a positive integer')
|
||||
}
|
||||
this.streamIdleTimeoutMs = options.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS
|
||||
if (!Number.isFinite(this.streamIdleTimeoutMs)
|
||||
|| this.streamIdleTimeoutMs <= 0
|
||||
|| this.streamIdleTimeoutMs > MAX_TIMER_DELAY_MS) {
|
||||
throw new Error(
|
||||
`llm-deepseek: streamIdleTimeoutMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`,
|
||||
)
|
||||
}
|
||||
this.retryPolicy = resolveRetryPolicy(options.retryPolicy, 'llm-deepseek: retryPolicy')
|
||||
}
|
||||
|
||||
override providerInfo(provider: string): LlmProviderInfo {
|
||||
@@ -148,11 +144,11 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
}
|
||||
|
||||
override providerRetryPolicy(_provider: string): ResolvedRetryPolicy {
|
||||
return this.retryPolicy
|
||||
return this.config.options().retryPolicy
|
||||
}
|
||||
|
||||
override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
|
||||
return Promise.resolve((this.options.models ?? []).map(model => modelInfo(provider, model)))
|
||||
return Promise.resolve(this.config.options().models.map(model => modelInfo(provider, model)))
|
||||
}
|
||||
|
||||
override resolveModel(
|
||||
@@ -160,15 +156,16 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
model: string,
|
||||
_signal?: AbortSignal,
|
||||
): Promise<LlmResolvedModelInfo> {
|
||||
const configured = this.options.models?.find(entry => entry.id === model)
|
||||
const connection = this.config.options()
|
||||
const configured = connection.models.find(entry => entry.id === model)
|
||||
const contextWindow = configured?.contextWindow
|
||||
?? this.options.defaultContextWindow
|
||||
?? connection.defaultContextWindow
|
||||
return Promise.resolve({
|
||||
...configured === undefined
|
||||
? { provider, id: model, name: model }
|
||||
: modelInfo(provider, configured),
|
||||
...contextWindow === undefined ? {} : { context: { contextWindow } },
|
||||
...this.options.defaults?.thinking === 'disabled'
|
||||
...connection.defaults.thinking === 'disabled'
|
||||
? {
|
||||
reasoning: {
|
||||
efforts: OFF_ONLY_REASONING_EFFORTS,
|
||||
@@ -178,9 +175,9 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
: {
|
||||
reasoning: {
|
||||
efforts: REASONING_EFFORTS,
|
||||
defaultEffort: this.options.defaults?.reasoningEffort === 'off'
|
||||
defaultEffort: connection.defaults.reasoningEffort === 'off'
|
||||
? OFF_REASONING_EFFORT
|
||||
: this.options.defaults?.reasoningEffort === 'max'
|
||||
: connection.defaults.reasoningEffort === 'max'
|
||||
? MAX_REASONING_EFFORT
|
||||
: HIGH_REASONING_EFFORT,
|
||||
},
|
||||
@@ -189,12 +186,17 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
}
|
||||
|
||||
async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
// One resolution per stream call: connection facts and the credential
|
||||
// freeze here and hold for this whole request, so an in-flight stream
|
||||
// never observes a configuration change and the next call re-resolves.
|
||||
const connection = this.config.options()
|
||||
const apiKey = await this.config.resolveApiKey()
|
||||
const consumer = new AbortController()
|
||||
const upstream = options.signal === undefined
|
||||
? consumer.signal
|
||||
: AbortSignal.any([options.signal, consumer.signal])
|
||||
using watchdog = idleWatchdog(upstream, this.streamIdleTimeoutMs, STREAM_IDLE_TIMEOUT_CODE)
|
||||
const iterator = this.request(options, watchdog.signal)[Symbol.asyncIterator]()
|
||||
using watchdog = idleWatchdog(upstream, connection.streamIdleTimeoutMs, STREAM_IDLE_TIMEOUT_CODE)
|
||||
const iterator = this.request(options, watchdog.signal, connection, apiKey)[Symbol.asyncIterator]()
|
||||
let exhausted = false
|
||||
try {
|
||||
while (true) {
|
||||
@@ -208,7 +210,7 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
} catch (error: unknown) {
|
||||
if (timeoutOf(watchdog.signal, STREAM_IDLE_TIMEOUT_CODE) !== undefined) {
|
||||
throw new LlmError(
|
||||
`DeepSeek stream idle timeout after ${this.streamIdleTimeoutMs}ms`,
|
||||
`DeepSeek stream idle timeout after ${connection.streamIdleTimeoutMs}ms`,
|
||||
'TIMEOUT',
|
||||
{ cause: error },
|
||||
)
|
||||
@@ -217,7 +219,7 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
throw new LlmError('DeepSeek request aborted by caller', 'ABORTED', { cause: error })
|
||||
}
|
||||
if (error instanceof LlmError) throw error
|
||||
throw new LlmError(`DeepSeek API stream from ${this.options.baseURL} failed`, 'TRANSPORT', { cause: error })
|
||||
throw new LlmError(`DeepSeek API stream from ${connection.baseURL} failed`, 'TRANSPORT', { cause: error })
|
||||
} finally {
|
||||
consumer.abort('DeepSeek stream consumer stopped')
|
||||
if (!exhausted && iterator.return !== undefined) {
|
||||
@@ -230,13 +232,18 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
}
|
||||
}
|
||||
|
||||
private async * request(options: GenerateOptions, signal: AbortSignal): AsyncIterable<StreamChunk> {
|
||||
const body = serializeRequest(options, this.options.defaults ?? {})
|
||||
private async * request(
|
||||
options: GenerateOptions,
|
||||
signal: AbortSignal,
|
||||
connection: DeepSeekConnectionOptions,
|
||||
apiKey: string,
|
||||
): AsyncIterable<StreamChunk> {
|
||||
const body = serializeRequest(options, connection.defaults)
|
||||
// Prepared outside the try so the TRANSPORT label below covers exactly the
|
||||
// transport boundary, never a serialization failure.
|
||||
const payload = JSON.stringify(body)
|
||||
const headers = {
|
||||
'authorization': `Bearer ${this.options.apiKey}`,
|
||||
'authorization': `Bearer ${apiKey}`,
|
||||
'content-type': 'application/json',
|
||||
'accept': 'text/event-stream',
|
||||
...attributionHeaders(),
|
||||
@@ -252,7 +259,7 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
// outweighs its additional runtime dependencies.
|
||||
let response: Response
|
||||
try {
|
||||
response = await fetch(`${this.options.baseURL}/chat/completions`, {
|
||||
response = await fetch(`${connection.baseURL}/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers,
|
||||
body: payload,
|
||||
@@ -266,7 +273,7 @@ export class DeepSeekAdapter extends LlmAdapter {
|
||||
// lives on `cause`. Wrapping with the endpoint and chaining the cause
|
||||
// lets `errorChain` render the full diagnosis at every reporting seam.
|
||||
throw new LlmError(
|
||||
`DeepSeek API request to ${this.options.baseURL} failed`,
|
||||
`DeepSeek API request to ${connection.baseURL} failed`,
|
||||
'TRANSPORT',
|
||||
{ cause: error },
|
||||
)
|
||||
|
||||
@@ -1,41 +1,56 @@
|
||||
/**
|
||||
* Register a {@link DeepSeekAdapter} for the `deepseek` provider route on `ctx.llm`. Configuration uses
|
||||
* Cordis schemastery; pass secrets from environment variables through `cordis.yml` with `!!js`,
|
||||
* as shown in the package README, rather than reading ad hoc files.
|
||||
* Register a {@link DeepSeekAdapter} for the `deepseek` provider route on
|
||||
* `ctx.llm`, with connection facts resolved per request instead of frozen at
|
||||
* load: the plugin layers its `cordis.yml` entry config under the optional
|
||||
* `llm-deepseek` user-settings section (`ctx.settings`) and resolves the API
|
||||
* key through the optional credential seam (`ctx.credentials`), so a changed
|
||||
* base URL, catalog, or key reaches the very next request without restarting
|
||||
* anything, while an in-flight stream keeps the facts it started with. The
|
||||
* one registration-captured fact — the retry policy — re-registers the route
|
||||
* in place when it changes.
|
||||
* @module @deepseek-ai/dsh-llm-deepseek
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import z from 'schemastery'
|
||||
import { RetryPolicySchema } from '@deepseek-ai/dsh-llm'
|
||||
import { LlmError, resolveRetryPolicy, RetryPolicySchema } from '@deepseek-ai/dsh-llm'
|
||||
import type { RetryPolicyConfig } from '@deepseek-ai/dsh-llm'
|
||||
import { credentialRef } from '@deepseek-ai/dsh-credentials'
|
||||
import type { CredentialRef } from '@deepseek-ai/dsh-credentials'
|
||||
import { deepEqualJson, settingsNamespace } from '@deepseek-ai/dsh-settings'
|
||||
import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
|
||||
import { DEFAULT_STREAM_IDLE_TIMEOUT_MS, DeepSeekAdapter } from './adapter.ts'
|
||||
import type { DeepSeekCatalogModel } from './adapter.ts'
|
||||
import type { DeepSeekCatalogModel, DeepSeekConnectionOptions } from './adapter.ts'
|
||||
|
||||
export { DeepSeekAdapter } from './adapter.ts'
|
||||
export type { DeepSeekAdapterOptions, DeepSeekCatalogModel } from './adapter.ts'
|
||||
export type { DeepSeekAdapterOptions, DeepSeekCatalogModel, DeepSeekConnectionOptions } from './adapter.ts'
|
||||
export type { RequestDefaults } from './serialize.ts'
|
||||
export type * from './types.ts'
|
||||
|
||||
export const name = 'llm-deepseek'
|
||||
export const inject = ['llm']
|
||||
|
||||
const NS = settingsNamespace('llm-deepseek')
|
||||
const DEFAULT_API_KEY_ENV = 'DEEPSEEK_API_KEY'
|
||||
|
||||
const DEFAULT_MODELS: DeepSeekCatalogModel[] = [
|
||||
{ id: 'deepseek-v4-flash', name: 'DeepSeek-V4-Flash', contextWindow: 256_000 },
|
||||
{ id: 'deepseek-v4-pro', name: 'DeepSeek-V4-Pro', contextWindow: 256_000 },
|
||||
]
|
||||
|
||||
/**
|
||||
* Plugin config, validated by the same-named schemastery schema. Every field
|
||||
* is optional in yml: credentials/endpoint fall back to the environment (a
|
||||
* missing API key fails plugin load, not the first call), omitted thinking
|
||||
* mode uses the provider default, and omitted reasoning effort resolves to
|
||||
* `high`.
|
||||
* Plugin config, validated by the same-named schemastery schema and doubling
|
||||
* as the `llm-deepseek` settings-section shape. Every field is optional in
|
||||
* yml: a missing API key resolves through {@link Config.apiKeyEnv} at each
|
||||
* request (a request without any key fails with `MISSING_CREDENTIAL`, not at
|
||||
* plugin load), omitted thinking mode uses the provider default, and omitted
|
||||
* reasoning effort resolves to `high`.
|
||||
*/
|
||||
export interface Config {
|
||||
/** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */
|
||||
/** Literal API key; prefer {@link apiKeyEnv} so no secret enters configuration files. */
|
||||
apiKey?: string
|
||||
/** Credential reference (environment-variable name) resolved per request; defaults to `DEEPSEEK_API_KEY`. */
|
||||
apiKeyEnv?: string
|
||||
/** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */
|
||||
baseURL?: string
|
||||
/** Deployment thinking policy; `disabled` limits every conversation request to `off`. */
|
||||
@@ -60,7 +75,8 @@ const catalogModel: z<DeepSeekCatalogModel> = z.object({
|
||||
})
|
||||
|
||||
export const Config: z<Config> = z.object({
|
||||
apiKey: z.string(),
|
||||
apiKey: z.string().role('secret'),
|
||||
apiKeyEnv: z.string().default(DEFAULT_API_KEY_ENV),
|
||||
baseURL: z.string(),
|
||||
thinking: z.union(['enabled', 'disabled']),
|
||||
reasoningEffort: z.union(['off', 'high', 'max']),
|
||||
@@ -73,6 +89,12 @@ export const Config: z<Config> = z.object({
|
||||
/** Public API default; the internal endpoint comes from $DEEPSEEK_BASE_URL. */
|
||||
export const PUBLIC_BASE_URL = 'https://api.deepseek.com'
|
||||
|
||||
/** Connection facts plus the plugin-consumed credential reference. */
|
||||
export interface ResolvedDeepSeekOptions extends DeepSeekConnectionOptions {
|
||||
/** Reference resolved per request when no literal key is configured. */
|
||||
apiKeyEnv: CredentialRef
|
||||
}
|
||||
|
||||
/** Resolve, validate, and detach the advisory model catalog. */
|
||||
function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): DeepSeekCatalogModel[] {
|
||||
const seen = new Set<string>()
|
||||
@@ -98,20 +120,35 @@ function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): Dee
|
||||
})
|
||||
}
|
||||
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
/**
|
||||
* The one explicit resolve step from raw config to validated connection
|
||||
* facts. Programmatic construction may bypass Schemastery normalization, so
|
||||
* every default and bound is re-judged here — for the composition entry at
|
||||
* load (fail loud) and for each settings snapshot at its first use.
|
||||
* @param config - raw plugin config or resolved settings snapshot.
|
||||
* @returns validated connection facts plus the credential reference.
|
||||
*/
|
||||
export function resolveAdapterOptions(config: Config): ResolvedDeepSeekOptions {
|
||||
if (config.thinking === 'disabled'
|
||||
&& config.reasoningEffort !== undefined
|
||||
&& config.reasoningEffort !== 'off') {
|
||||
throw new Error('llm-deepseek: only reasoningEffort "off" can be configured when thinking is disabled')
|
||||
}
|
||||
const apiKey = config.apiKey ?? process.env.DEEPSEEK_API_KEY
|
||||
if (apiKey === undefined || apiKey.length === 0) {
|
||||
throw new Error('llm-deepseek: an API key is required (Config.apiKey or $DEEPSEEK_API_KEY)')
|
||||
if (config.defaultContextWindow !== undefined
|
||||
&& (!Number.isInteger(config.defaultContextWindow) || config.defaultContextWindow <= 0)) {
|
||||
throw new Error('llm-deepseek: defaultContextWindow must be a positive integer')
|
||||
}
|
||||
const baseURL = config.baseURL ?? process.env.DEEPSEEK_BASE_URL ?? PUBLIC_BASE_URL
|
||||
ctx.llm.registerAdapter(['deepseek'], new DeepSeekAdapter({
|
||||
apiKey,
|
||||
baseURL,
|
||||
const streamIdleTimeoutMs = config.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS
|
||||
if (!Number.isFinite(streamIdleTimeoutMs)
|
||||
|| streamIdleTimeoutMs <= 0
|
||||
|| streamIdleTimeoutMs > MAX_TIMER_DELAY_MS) {
|
||||
throw new Error(
|
||||
`llm-deepseek: streamIdleTimeoutMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`,
|
||||
)
|
||||
}
|
||||
return {
|
||||
apiKeyEnv: credentialRef(config.apiKeyEnv ?? DEFAULT_API_KEY_ENV),
|
||||
baseURL: config.baseURL ?? process.env.DEEPSEEK_BASE_URL ?? PUBLIC_BASE_URL,
|
||||
defaults: {
|
||||
thinking: config.thinking,
|
||||
reasoningEffort: config.reasoningEffort,
|
||||
@@ -120,7 +157,92 @@ export function apply(ctx: Context, config: Config): void {
|
||||
? {}
|
||||
: { defaultContextWindow: config.defaultContextWindow },
|
||||
models: resolveModels(config.models),
|
||||
streamIdleTimeoutMs: config.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS,
|
||||
...config.retryPolicy === undefined ? {} : { retryPolicy: config.retryPolicy },
|
||||
}))
|
||||
streamIdleTimeoutMs,
|
||||
retryPolicy: resolveRetryPolicy(config.retryPolicy, 'llm-deepseek: retryPolicy'),
|
||||
}
|
||||
}
|
||||
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
let current: () => Config = () => config
|
||||
let lastRaw: Config | undefined
|
||||
let lastGood: ResolvedDeepSeekOptions | undefined
|
||||
const options = (): ResolvedDeepSeekOptions => {
|
||||
const raw = current()
|
||||
if (raw === lastRaw && lastGood !== undefined) return lastGood
|
||||
try {
|
||||
const next = resolveAdapterOptions(raw)
|
||||
lastRaw = raw
|
||||
lastGood = next
|
||||
return next
|
||||
} catch (error) {
|
||||
// Static composition resolves before anything registers, so this branch
|
||||
// only sees a live settings snapshot failing a beyond-schema bound:
|
||||
// keep serving the last good facts and say so once per bad snapshot.
|
||||
if (lastGood === undefined) throw error
|
||||
lastRaw = raw
|
||||
ctx.logger.error('llm-deepseek: keeping the last good configuration after an invalid settings section')
|
||||
ctx.logger.error(error)
|
||||
return lastGood
|
||||
}
|
||||
}
|
||||
options()
|
||||
|
||||
const resolveApiKey = async (): Promise<string> => {
|
||||
const raw = current()
|
||||
if (raw.apiKey !== undefined && raw.apiKey.length > 0) return raw.apiKey
|
||||
const ref = options().apiKeyEnv
|
||||
const credentials = ctx.get('credentials')
|
||||
if (credentials !== undefined) {
|
||||
const hit = await credentials.resolve(ref)
|
||||
if (hit !== undefined) return hit.value
|
||||
} else {
|
||||
// Without the seam, keep the historical ambient fallback so a plain
|
||||
// cordis.yml composition works from the environment alone.
|
||||
const ambient = process.env[ref]
|
||||
if (ambient !== undefined && ambient.length > 0) return ambient
|
||||
}
|
||||
throw new LlmError(
|
||||
'llm-deepseek: no API key for provider route "deepseek"; set the llm-deepseek "apiKey" setting,'
|
||||
+ ` store ${ref} with the credentials service, or export ${ref}`,
|
||||
'MISSING_CREDENTIAL',
|
||||
)
|
||||
}
|
||||
|
||||
const adapter = new DeepSeekAdapter({ options, resolveApiKey })
|
||||
// Route effects bind to this apply fiber via the stable `ctx` reference,
|
||||
// even when a swap runs inside the scoped settings callback below.
|
||||
let disposeRoute = ctx.llm.registerAdapter(['deepseek'], adapter)
|
||||
let registeredPolicy = options().retryPolicy
|
||||
const ensureRegistrationFacts = (): void => {
|
||||
const policy = options().retryPolicy
|
||||
if (deepEqualJson(policy, registeredPolicy)) return
|
||||
// The registry captures the retry policy at registration, so it is the one
|
||||
// fact per-request resolution cannot refresh: swap the registration in one
|
||||
// synchronous section (same adapter instance, no NO_ADAPTER window).
|
||||
disposeRoute()
|
||||
disposeRoute = ctx.llm.registerAdapter(['deepseek'], adapter)
|
||||
registeredPolicy = policy
|
||||
}
|
||||
|
||||
void resolveApiKey().then(() => undefined, () => {
|
||||
// Expected on a first boot with dynamic sources: the route stays
|
||||
// registered (the catalog is browsable) and each request fails with the
|
||||
// actionable MISSING_CREDENTIAL message until a key arrives.
|
||||
ctx.logger.warn('llm-deepseek: no API key resolved yet for route "deepseek"; requests will fail until one is configured')
|
||||
})
|
||||
|
||||
ctx.inject(['settings'], (sctx) => {
|
||||
const scope = sctx.settings.register(NS, Config, { base: config })
|
||||
current = () => scope.get()
|
||||
sctx.effect(() => () => {
|
||||
// Settings detached (provider disposed or reloading): fall back to the
|
||||
// composition entry so the plugin keeps working exactly as configured.
|
||||
current = () => config
|
||||
ensureRegistrationFacts()
|
||||
})
|
||||
ensureRegistrationFacts()
|
||||
scope.watch(() => {
|
||||
ensureRegistrationFacts()
|
||||
})
|
||||
})
|
||||
}
|
||||
@@ -1,5 +1,3 @@
|
||||
import { createServer } from 'node:http'
|
||||
import type { IncomingMessage, Server, ServerResponse } from 'node:http'
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService, { createUserMessage,
|
||||
@@ -14,90 +12,18 @@ import LlmService, { createUserMessage,
|
||||
import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { DeepSeekAdapter } from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { DeepSeekAdapter, resolveAdapterOptions } from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { httpErrorCode } from '../src/adapter.ts'
|
||||
import { assemble } from './assemble.ts'
|
||||
|
||||
/** One scripted behavior for the next request the mock server receives. */
|
||||
type Behavior =
|
||||
| { kind: 'sse'; events: string[]; delayMs?: number }
|
||||
| { kind: 'http-error'; status: number; body: string; contentType?: string; headers?: Record<string, string> }
|
||||
| { kind: 'close-early'; events: string[] }
|
||||
|
||||
interface MockServer {
|
||||
url: string
|
||||
/** Bodies of received requests, in order. */
|
||||
requests: unknown[]
|
||||
/** Header bags of received requests, in order (parallel to `requests`). */
|
||||
headers: IncomingMessage['headers'][]
|
||||
script: Behavior[]
|
||||
close(): Promise<void>
|
||||
}
|
||||
|
||||
const servers: Server[] = []
|
||||
import { closeMockServers, mockServer, textEvents } from './mock-server.ts'
|
||||
import type { Behavior } from './mock-server.ts'
|
||||
|
||||
afterEach(async () => {
|
||||
await Promise.all(servers.splice(0).map(server => new Promise(resolve => server.close(resolve))))
|
||||
await closeMockServers()
|
||||
vi.unstubAllEnvs()
|
||||
vi.useRealTimers()
|
||||
})
|
||||
|
||||
/** Local chat-completions stand-in: replays scripted behaviors per request. */
|
||||
async function mockServer(script: Behavior[]): Promise<MockServer> {
|
||||
const requests: unknown[] = []
|
||||
const headers: IncomingMessage['headers'][] = []
|
||||
const server = createServer((request: IncomingMessage, response: ServerResponse) => {
|
||||
let body = ''
|
||||
request.on('data', (chunk: Buffer) => { body += chunk.toString('utf8') })
|
||||
request.on('end', () => {
|
||||
requests.push(JSON.parse(body))
|
||||
headers.push(request.headers)
|
||||
const behavior = script.shift()
|
||||
if (!behavior) {
|
||||
response.writeHead(500).end('mock script exhausted')
|
||||
return
|
||||
}
|
||||
if (behavior.kind === 'http-error') {
|
||||
response.writeHead(behavior.status, {
|
||||
'content-type': behavior.contentType ?? 'application/json',
|
||||
...behavior.headers,
|
||||
})
|
||||
response.end(behavior.body)
|
||||
return
|
||||
}
|
||||
response.writeHead(200, { 'content-type': 'text/event-stream' })
|
||||
const write = (index: number): void => {
|
||||
if (index >= behavior.events.length) {
|
||||
if (behavior.kind === 'sse') response.end()
|
||||
else response.destroy() // close-early: drop the socket mid-stream
|
||||
return
|
||||
}
|
||||
response.write(`data: ${behavior.events[index]}\n\n`)
|
||||
setTimeout(() => { write(index + 1) }, behavior.kind === 'sse' ? behavior.delayMs ?? 0 : 5)
|
||||
}
|
||||
write(0)
|
||||
})
|
||||
})
|
||||
servers.push(server)
|
||||
await new Promise<void>(resolve => server.listen(0, '127.0.0.1', resolve))
|
||||
const address = server.address()
|
||||
if (address === null || typeof address === 'string') throw new Error('no port')
|
||||
return {
|
||||
url: `http://127.0.0.1:${address.port}`,
|
||||
requests,
|
||||
headers,
|
||||
script,
|
||||
close: () => new Promise(resolve => server.close(() => { resolve() })),
|
||||
}
|
||||
}
|
||||
|
||||
const textEvents = [
|
||||
'{"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""}}]}',
|
||||
'{"choices":[{"delta":{"content":"hello"}}]}',
|
||||
'{"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
|
||||
'[DONE]',
|
||||
]
|
||||
|
||||
async function harness(baseURL: string, config: object = {}) {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
@@ -105,6 +31,15 @@ async function harness(baseURL: string, config: object = {}) {
|
||||
return ctx
|
||||
}
|
||||
|
||||
/** Direct adapter over the plugin's real resolve step, with a static key. */
|
||||
function adapterOf(config: Partial<LlmDeepSeek.Config> & { apiKey?: string } = {}): DeepSeekAdapter {
|
||||
const { apiKey, ...rest } = config
|
||||
return new DeepSeekAdapter({
|
||||
options: () => resolveAdapterOptions(rest),
|
||||
resolveApiKey: () => Promise.resolve(apiKey ?? 'k'),
|
||||
})
|
||||
}
|
||||
|
||||
describe('DeepSeekAdapter against a mock server', () => {
|
||||
it('streams a text generation end to end through the assembler', async () => {
|
||||
const server = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
@@ -275,11 +210,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
'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 adapter = adapterOf({ apiKey: 'test-key', baseURL: server.url, thinking: 'disabled' })
|
||||
|
||||
const stream = adapter.stream({
|
||||
provider: 'deepseek',
|
||||
@@ -483,7 +414,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
})
|
||||
|
||||
it('throws EMPTY_RESPONSE when the response has no body', async () => {
|
||||
const adapter = new DeepSeekAdapter({ apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
const adapter = adapterOf({ baseURL: 'http://127.0.0.1:1' })
|
||||
const fetchSpy = vi.spyOn(globalThis, 'fetch').mockResolvedValue(
|
||||
new Response(null, { status: 200 }),
|
||||
)
|
||||
@@ -538,7 +469,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
it('maps connection failures to TRANSPORT without losing the cause', async () => {
|
||||
const cause = new TypeError('connection refused')
|
||||
const fetchSpy = vi.spyOn(globalThis, 'fetch').mockRejectedValue(cause)
|
||||
const adapter = new DeepSeekAdapter({ apiKey: 'k', baseURL: 'https://example.invalid' })
|
||||
const adapter = adapterOf({ baseURL: 'https://example.invalid' })
|
||||
try {
|
||||
const drain = async (): Promise<void> => {
|
||||
for await (const _chunk of adapter.stream({ provider: 'deepseek', model: 'm', messages: [] })) { /* drain */ }
|
||||
@@ -555,7 +486,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
failed.reject('offline')
|
||||
return failed.promise
|
||||
})
|
||||
const adapter = new DeepSeekAdapter({ apiKey: 'k', baseURL: 'https://example.invalid' })
|
||||
const adapter = adapterOf({ baseURL: 'https://example.invalid' })
|
||||
try {
|
||||
const drain = async (): Promise<void> => {
|
||||
for await (const _chunk of adapter.stream({ provider: 'deepseek', model: 'm', messages: [] })) { /* drain */ }
|
||||
@@ -585,11 +516,7 @@ describe('DeepSeekAdapter against a mock server', () => {
|
||||
})
|
||||
return Promise.resolve(new Response(body, { status: 200 }))
|
||||
})
|
||||
const adapter = new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'https://example.invalid',
|
||||
streamIdleTimeoutMs: 100,
|
||||
})
|
||||
const adapter = adapterOf({ baseURL: 'https://example.invalid', streamIdleTimeoutMs: 100 })
|
||||
try {
|
||||
const drain = (async () => {
|
||||
for await (const _chunk of adapter.stream({ provider: 'deepseek', model: 'm', messages: [] })) { /* drain */ }
|
||||
@@ -733,22 +660,15 @@ describe('plugin registration and config', () => {
|
||||
)
|
||||
|
||||
it.each(['high', 'max'] as const)(
|
||||
'rejects disabled-thinking effort %s at the direct constructor boundary',
|
||||
'rejects disabled-thinking effort %s at the resolver boundary',
|
||||
(reasoningEffort) => {
|
||||
expect(() => new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
defaults: { thinking: 'disabled', reasoningEffort },
|
||||
})).toThrow(/only reasoningEffort "off"/)
|
||||
expect(() => resolveAdapterOptions({ 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' },
|
||||
})
|
||||
it('accepts disabled thinking with off at the resolver boundary', async () => {
|
||||
const adapter = adapterOf({ thinking: 'disabled', reasoningEffort: 'off' })
|
||||
await expect(adapter.resolveModel('deepseek', 'pass-through')).resolves.toMatchObject({
|
||||
reasoning: {
|
||||
efforts: [{ id: ReasoningEffortId('off'), name: 'Off' }],
|
||||
@@ -863,11 +783,8 @@ describe('plugin registration and config', () => {
|
||||
it.each([0, 1.5])(
|
||||
'rejects invalid adapter-wide default context capacity %s',
|
||||
async (defaultContextWindow) => {
|
||||
expect(() => new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
defaultContextWindow,
|
||||
})).toThrow(/defaultContextWindow must be a positive integer/)
|
||||
expect(() => resolveAdapterOptions({ defaultContextWindow }))
|
||||
.toThrow(/defaultContextWindow must be a positive integer/)
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
@@ -889,13 +806,19 @@ describe('plugin registration and config', () => {
|
||||
expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
|
||||
})
|
||||
|
||||
it('throws a clear error when no API key is available', async () => {
|
||||
it('loads keyless, keeps the catalog browsable, and fails the request actionably', async () => {
|
||||
vi.stubEnv('DEEPSEEK_API_KEY', '')
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await expect(ctx.plugin(LlmDeepSeek, {}))
|
||||
.rejects.toThrow(/an API key is required/)
|
||||
expect(ctx.llm.listProviders()).toEqual([])
|
||||
await ctx.plugin(LlmDeepSeek, { baseURL: 'http://127.0.0.1:1' })
|
||||
// First-boot onboarding: the route registers so models stay discoverable;
|
||||
// only the request itself needs a key.
|
||||
expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toHaveLength(2)
|
||||
await expect(assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }))
|
||||
.rejects.toMatchObject({ code: 'MISSING_CREDENTIAL' })
|
||||
await expect(assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }))
|
||||
.rejects.toThrow(/store DEEPSEEK_API_KEY with the credentials service, or export DEEPSEEK_API_KEY/)
|
||||
})
|
||||
|
||||
it('prefers explicit config over env for key and base URL', async () => {
|
||||
@@ -927,23 +850,32 @@ describe('plugin registration and config', () => {
|
||||
expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
|
||||
})
|
||||
|
||||
it('adapter is constructible directly for embedding', async () => {
|
||||
const adapter = new DeepSeekAdapter({ apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
it('adapter is constructible directly for embedding over the shared resolver', async () => {
|
||||
const adapter = adapterOf()
|
||||
expect(adapter).toBeInstanceOf(DeepSeekAdapter)
|
||||
await expect(adapter.listModels('deepseek')).resolves.toEqual([])
|
||||
// Direct embedding shares the plugin's one resolve step, so it advertises
|
||||
// the same default catalog instead of a divergent empty one.
|
||||
await expect(adapter.listModels('deepseek')).resolves.toHaveLength(2)
|
||||
})
|
||||
|
||||
it('resolves connection facts and the credential exactly once per stream call', async () => {
|
||||
const server = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const options = vi.fn(() => resolveAdapterOptions({ baseURL: server.url }))
|
||||
const resolveApiKey = vi.fn(() => Promise.resolve('per-request-key'))
|
||||
const adapter = new DeepSeekAdapter({ options, resolveApiKey })
|
||||
|
||||
for await (const _chunk of adapter.stream({ provider: 'deepseek', model: 'm', messages: [] })) { /* drain */ }
|
||||
|
||||
expect(options).toHaveBeenCalledTimes(1)
|
||||
expect(resolveApiKey).toHaveBeenCalledTimes(1)
|
||||
expect(server.headers[0]?.authorization).toBe('Bearer per-request-key')
|
||||
})
|
||||
|
||||
it('rejects invalid idle watchdog bounds for direct and plugin composition', async () => {
|
||||
expect(() => new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
streamIdleTimeoutMs: Number.POSITIVE_INFINITY,
|
||||
})).toThrow(/streamIdleTimeoutMs.*positive finite/)
|
||||
expect(() => new DeepSeekAdapter({
|
||||
apiKey: 'k',
|
||||
baseURL: 'http://127.0.0.1:1',
|
||||
streamIdleTimeoutMs: MAX_TIMER_DELAY_MS + 1,
|
||||
})).toThrow(/streamIdleTimeoutMs.*no greater/)
|
||||
expect(() => resolveAdapterOptions({ streamIdleTimeoutMs: Number.POSITIVE_INFINITY }))
|
||||
.toThrow(/streamIdleTimeoutMs.*positive finite/)
|
||||
expect(() => resolveAdapterOptions({ streamIdleTimeoutMs: MAX_TIMER_DELAY_MS + 1 }))
|
||||
.toThrow(/streamIdleTimeoutMs.*no greater/)
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
|
||||
@@ -0,0 +1,163 @@
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import { credentialRef } from '@deepseek-ai/dsh-credentials'
|
||||
import { CredentialsLocal } from '@deepseek-ai/dsh-credentials-local'
|
||||
import { settingsNamespace } from '@deepseek-ai/dsh-settings'
|
||||
import { SettingsLocal } from '@deepseek-ai/dsh-settings-local'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { assemble } from './assemble.ts'
|
||||
import { closeMockServers, mockServer, textEvents } from './mock-server.ts'
|
||||
|
||||
const NS = settingsNamespace('llm-deepseek')
|
||||
const KEY_REF = credentialRef('DEEPSEEK_API_KEY')
|
||||
|
||||
const cleanups: Array<() => Promise<void>> = []
|
||||
|
||||
afterEach(async () => {
|
||||
while (cleanups.length > 0) await cleanups.pop()!()
|
||||
await closeMockServers()
|
||||
vi.unstubAllEnvs()
|
||||
})
|
||||
|
||||
async function home(): Promise<string> {
|
||||
const dir = await mkdtemp(join(tmpdir(), 'dsh-llm-dynamic-'))
|
||||
cleanups.push(() => rm(dir, { recursive: true, force: true }))
|
||||
return dir
|
||||
}
|
||||
|
||||
interface Harness {
|
||||
ctx: Context
|
||||
settingsFiber: { dispose(): Promise<void> }
|
||||
}
|
||||
|
||||
/**
|
||||
* Real dynamic composition: llm + settings-local + credentials-local +
|
||||
* llm-deepseek over one temp harness home. `watch: false` keeps every change
|
||||
* flowing through the in-process write path, which is deterministic; external
|
||||
* file watching is the providers' own covered concern.
|
||||
*/
|
||||
async function boot(dir: string, config: object): Promise<Harness> {
|
||||
const ctx = new Context()
|
||||
cleanups.push(async () => {
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
await ctx.plugin(LlmService)
|
||||
const settingsFiber = ctx.plugin(SettingsLocal, { path: join(dir, 'settings.yaml'), watch: false })
|
||||
await settingsFiber
|
||||
await ctx.plugin(CredentialsLocal, { path: join(dir, '.env'), watch: false })
|
||||
await ctx.plugin(LlmDeepSeek, config)
|
||||
return { ctx, settingsFiber }
|
||||
}
|
||||
|
||||
function prompt(ctx: Context) {
|
||||
return assemble(ctx, { model: 'deepseek-v4-flash', messages: [] })
|
||||
}
|
||||
|
||||
describe('request-level dynamic configuration', () => {
|
||||
it('routes the next request with the freshly resolved base URL and credential', async () => {
|
||||
vi.stubEnv('DEEPSEEK_API_KEY', '')
|
||||
const dir = await home()
|
||||
await writeFile(join(dir, '.env'), 'DEEPSEEK_API_KEY=first-key\n')
|
||||
const serverA = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const serverB = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const { ctx } = await boot(dir, { baseURL: serverA.url })
|
||||
|
||||
await prompt(ctx)
|
||||
expect(serverA.headers[0]?.authorization).toBe('Bearer first-key')
|
||||
|
||||
await ctx.settings.update(NS, { baseURL: serverB.url })
|
||||
await ctx.credentials.set(KEY_REF, 'second-key')
|
||||
|
||||
await prompt(ctx)
|
||||
// No restart, no re-registration: the next request resolved both facts.
|
||||
expect(serverA.requests).toHaveLength(1)
|
||||
expect(serverB.headers[0]?.authorization).toBe('Bearer second-key')
|
||||
})
|
||||
|
||||
it('prefers a literal settings apiKey over the credential layers', async () => {
|
||||
vi.stubEnv('DEEPSEEK_API_KEY', '')
|
||||
const dir = await home()
|
||||
await writeFile(join(dir, '.env'), 'DEEPSEEK_API_KEY=file-key\n')
|
||||
const server = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const { ctx } = await boot(dir, { baseURL: server.url })
|
||||
|
||||
await ctx.settings.update(NS, { apiKey: 'literal-key' })
|
||||
await prompt(ctx)
|
||||
expect(server.headers[0]?.authorization).toBe('Bearer literal-key')
|
||||
})
|
||||
|
||||
it('starts keyless and serves the next request once the key arrives', async () => {
|
||||
vi.stubEnv('DEEPSEEK_API_KEY', '')
|
||||
const dir = await home()
|
||||
const server = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const { ctx } = await boot(dir, { baseURL: server.url })
|
||||
|
||||
await expect(prompt(ctx)).rejects.toMatchObject({ code: 'MISSING_CREDENTIAL' })
|
||||
await ctx.credentials.set(KEY_REF, 'sk-arrived')
|
||||
await prompt(ctx)
|
||||
expect(server.headers[0]?.authorization).toBe('Bearer sk-arrived')
|
||||
})
|
||||
|
||||
it('advertises a live settings catalog without re-registration', async () => {
|
||||
const dir = await home()
|
||||
const { ctx } = await boot(dir, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toHaveLength(2)
|
||||
await ctx.settings.update(NS, { models: [{ id: 'settings-model', name: 'From Settings' }] })
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
|
||||
{ provider: 'deepseek', id: 'settings-model', name: 'From Settings' },
|
||||
])
|
||||
})
|
||||
|
||||
it('re-registers the route in place when the captured retry policy changes', async () => {
|
||||
const dir = await home()
|
||||
const { ctx } = await boot(dir, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
|
||||
await ctx.settings.update(NS, {
|
||||
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,
|
||||
})
|
||||
expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }])
|
||||
})
|
||||
|
||||
it('keeps the last good options when a settings snapshot fails beyond-schema validation', async () => {
|
||||
const dir = await home()
|
||||
const { ctx } = await boot(dir, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' })
|
||||
|
||||
// Schema-valid but resolver-invalid: duplicate catalog ids pass the array
|
||||
// schema and fail the explicit resolve step.
|
||||
await ctx.settings.update(NS, { models: [{ id: 'dup' }, { id: 'dup' }] })
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toHaveLength(2)
|
||||
await ctx.settings.update(NS, { models: [{ id: 'recovered' }] })
|
||||
await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([
|
||||
{ provider: 'deepseek', id: 'recovered', name: 'recovered' },
|
||||
])
|
||||
})
|
||||
|
||||
it('falls back to the composition entry when settings detach', async () => {
|
||||
vi.stubEnv('DEEPSEEK_API_KEY', '')
|
||||
const dir = await home()
|
||||
await writeFile(join(dir, '.env'), 'DEEPSEEK_API_KEY=steady-key\n')
|
||||
const serverA = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const serverB = await mockServer([{ kind: 'sse', events: textEvents }])
|
||||
const { ctx, settingsFiber } = await boot(dir, { baseURL: serverA.url })
|
||||
|
||||
await ctx.settings.update(NS, { baseURL: serverB.url })
|
||||
await prompt(ctx)
|
||||
expect(serverB.requests).toHaveLength(1)
|
||||
|
||||
await settingsFiber.dispose()
|
||||
await prompt(ctx)
|
||||
expect(serverA.requests).toHaveLength(1)
|
||||
expect(serverA.headers[0]?.authorization).toBe('Bearer steady-key')
|
||||
})
|
||||
})
|
||||
@@ -0,0 +1,82 @@
|
||||
import { createServer } from 'node:http'
|
||||
import type { IncomingMessage, Server, ServerResponse } from 'node:http'
|
||||
|
||||
/** One scripted behavior for the next request the mock server receives. */
|
||||
export type Behavior =
|
||||
| { kind: 'sse'; events: string[]; delayMs?: number }
|
||||
| { kind: 'http-error'; status: number; body: string; contentType?: string; headers?: Record<string, string> }
|
||||
| { kind: 'close-early'; events: string[] }
|
||||
|
||||
export interface MockServer {
|
||||
url: string
|
||||
/** Bodies of received requests, in order. */
|
||||
requests: unknown[]
|
||||
/** Header bags of received requests, in order (parallel to `requests`). */
|
||||
headers: IncomingMessage['headers'][]
|
||||
script: Behavior[]
|
||||
close(): Promise<void>
|
||||
}
|
||||
|
||||
const servers: Server[] = []
|
||||
|
||||
/** Close every server opened since the last call; run from each spec's afterEach. */
|
||||
export async function closeMockServers(): Promise<void> {
|
||||
await Promise.all(servers.splice(0).map(server => new Promise(resolve => server.close(resolve))))
|
||||
}
|
||||
|
||||
/** A minimal complete text generation, reused by request-shape assertions. */
|
||||
export const textEvents = [
|
||||
'{"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""}}]}',
|
||||
'{"choices":[{"delta":{"content":"hello"}}]}',
|
||||
'{"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
|
||||
'[DONE]',
|
||||
]
|
||||
|
||||
/** Local chat-completions stand-in: replays scripted behaviors per request. */
|
||||
export async function mockServer(script: Behavior[]): Promise<MockServer> {
|
||||
const requests: unknown[] = []
|
||||
const headers: IncomingMessage['headers'][] = []
|
||||
const server = createServer((request: IncomingMessage, response: ServerResponse) => {
|
||||
let body = ''
|
||||
request.on('data', (chunk: Buffer) => { body += chunk.toString('utf8') })
|
||||
request.on('end', () => {
|
||||
requests.push(JSON.parse(body))
|
||||
headers.push(request.headers)
|
||||
const behavior = script.shift()
|
||||
if (!behavior) {
|
||||
response.writeHead(500).end('mock script exhausted')
|
||||
return
|
||||
}
|
||||
if (behavior.kind === 'http-error') {
|
||||
response.writeHead(behavior.status, {
|
||||
'content-type': behavior.contentType ?? 'application/json',
|
||||
...behavior.headers,
|
||||
})
|
||||
response.end(behavior.body)
|
||||
return
|
||||
}
|
||||
response.writeHead(200, { 'content-type': 'text/event-stream' })
|
||||
const write = (index: number): void => {
|
||||
if (index >= behavior.events.length) {
|
||||
if (behavior.kind === 'sse') response.end()
|
||||
else response.destroy() // close-early: drop the socket mid-stream
|
||||
return
|
||||
}
|
||||
response.write(`data: ${behavior.events[index]}\n\n`)
|
||||
setTimeout(() => { write(index + 1) }, behavior.kind === 'sse' ? behavior.delayMs ?? 0 : 5)
|
||||
}
|
||||
write(0)
|
||||
})
|
||||
})
|
||||
servers.push(server)
|
||||
await new Promise<void>(resolve => server.listen(0, '127.0.0.1', resolve))
|
||||
const address = server.address()
|
||||
if (address === null || typeof address === 'string') throw new Error('no port')
|
||||
return {
|
||||
url: `http://127.0.0.1:${address.port}`,
|
||||
requests,
|
||||
headers,
|
||||
script,
|
||||
close: () => new Promise(resolve => server.close(() => { resolve() })),
|
||||
}
|
||||
}
|
||||
@@ -20,6 +20,12 @@
|
||||
{
|
||||
"path": "../../llm/llm"
|
||||
},
|
||||
{
|
||||
"path": "../../credentials/credentials"
|
||||
},
|
||||
{
|
||||
"path": "../../settings/settings"
|
||||
},
|
||||
{
|
||||
"path": "../../support/invariants"
|
||||
},
|
||||
|
||||
Generated
+6
@@ -2949,12 +2949,18 @@ importers:
|
||||
specifier: ^3.18.0
|
||||
version: 3.18.0
|
||||
devDependencies:
|
||||
'@deepseek-ai/dsh-credentials':
|
||||
specifier: workspace:^
|
||||
version: link:../../credentials/credentials
|
||||
'@deepseek-ai/dsh-invariants':
|
||||
specifier: workspace:^
|
||||
version: link:../../support/invariants
|
||||
'@deepseek-ai/dsh-llm':
|
||||
specifier: workspace:^
|
||||
version: link:../llm
|
||||
'@deepseek-ai/dsh-settings':
|
||||
specifier: workspace:^
|
||||
version: link:../../settings/settings
|
||||
'@deepseek-ai/dsh-timeout':
|
||||
specifier: workspace:^
|
||||
version: link:../../util/timeout
|
||||
|
||||
Reference in New Issue
Block a user