Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into worktree/web-multimodal-image-input

Browse Source 
# Conflicts:
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl
#	packages/client/connection/README.i18n.yaml
#	packages/client/connection/README.md
#	packages/client/connection/README.zh.md
#	packages/client/connection/src/client/fixture.ts
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/README.md
#	packages/client/runtime/README.zh.md
#	packages/client/ui-conversation/README.i18n.yaml
#	packages/client/ui-conversation/src/client/chat/AssistantMarkdown.tsx
#	packages/client/ui-conversation/src/client/chat/ChatView.tsx
#	packages/host/apiproxy/README.i18n.yaml
#	packages/host/apiproxy/src/api-proxy.ts
#	packages/llm/llm-deepseek/tests/adapter.spec.ts
#	packages/llm/llm-pi-ai/README.i18n.yaml
#	packages/llm/llm-pi-ai/src/index.ts
#	packages/llm/llm/README.i18n.yaml
#	packages/llm/llm/README.md
#	packages/llm/llm/README.zh.md
#	packages/llm/llm/src/index.ts
#	packages/llm/llm/src/types.ts
This commit is contained in:
creatixchu
2026-07-31 02:14:07 +08:00
parent 451d15429e 085383b145
commit a975eda638
465 changed files with 9284 additions and 1401 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
packages/llm/llm-deepseek/src/adapter.ts
View File

@@ -56,8 +56,10 @@ export interface DeepSeekConnectionOptions {
apiKeyEnv: CredentialRef
/** Request defaults applied to every call (thinking mode, effort). */
defaults: RequestDefaults
/** Default per-request output cap; explicit request values win. */
maxTokens: number
/** Positive context capacity used when the selected model has no exact value. */
defaultContextWindow?: number
defaultContextWindow: number
/** Advisory models exposed to discovery consumers; requests remain unrestricted. */
models: readonly DeepSeekCatalogModel[]
/** Maximum provider idle time while one stream read is outstanding. */
@@ -81,6 +83,10 @@ export interface DeepSeekAdapterOptions {
/** Default maximum idle interval while an adapter stream read is outstanding. */
export const DEFAULT_STREAM_IDLE_TIMEOUT_MS = 300_000
/** Default combined request/response context capacity. */
export const DEFAULT_CONTEXT_WINDOW = 1_000_000
/** Default per-request output-token cap. */
export const DEFAULT_MAX_TOKENS = 256_000
const STREAM_IDLE_TIMEOUT_CODE = 'LLM_STREAM_IDLE_TIMEOUT'
const OFF_REASONING_EFFORT = ReasoningEffortId('off')
const HIGH_REASONING_EFFORT = ReasoningEffortId('high')
@@ -179,7 +185,8 @@ export class DeepSeekAdapter extends LlmAdapter {
...configured === undefined
? { provider, id: model, name: model, inputModalities: ['text' as const] }
: modelInfo(provider, configured),
...contextWindow === undefined ? {} : { context: { contextWindow } },
context: { contextWindow },
defaultMaxTokens: connection.maxTokens,
...connection.defaults.thinking === 'disabled'
? {
reasoning: {

54
packages/llm/llm-deepseek/src/index.ts
View File

@@ -1,5 +1,5 @@
/**
* Register a {@link DeepSeekAdapter} for the `deepseek` provider route on
* Register a {@link DeepSeekAdapter} for the `deepseek-official` 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
@@ -18,10 +18,20 @@ import type { RetryPolicyConfig } from '@deepseek-ai/dsh-llm'
import { credentialRef } from '@deepseek-ai/dsh-credentials'
import { deepEqualJson, installSettingsSection, 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 {
DEFAULT_CONTEXT_WINDOW,
DEFAULT_MAX_TOKENS,
DEFAULT_STREAM_IDLE_TIMEOUT_MS,
DeepSeekAdapter,
} from './adapter.ts'
import type { DeepSeekCatalogModel, DeepSeekConnectionOptions } from './adapter.ts'
export { DeepSeekAdapter } from './adapter.ts'
export {
DEFAULT_CONTEXT_WINDOW,
DEFAULT_MAX_TOKENS,
DEFAULT_STREAM_IDLE_TIMEOUT_MS,
DeepSeekAdapter,
} from './adapter.ts'
export type { DeepSeekAdapterOptions, DeepSeekCatalogModel, DeepSeekConnectionOptions } from './adapter.ts'
export type { RequestDefaults } from './serialize.ts'
export type * from './types.ts'
@@ -32,11 +42,11 @@ export const inject = ['llm']
const NS = settingsNamespace('llm-deepseek')
const DEFAULT_API_KEY_ENV = 'DEEPSEEK_API_KEY'
/** The single provider route this plugin owns. */
const PROVIDER = 'deepseek'
const PROVIDER = 'deepseek-official'
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 },
{ id: 'deepseek-v4-flash', name: 'DeepSeek-V4-Flash', contextWindow: DEFAULT_CONTEXT_WINDOW },
{ id: 'deepseek-v4-pro', name: 'DeepSeek-V4-Pro', contextWindow: DEFAULT_CONTEXT_WINDOW },
]
/**
@@ -58,7 +68,9 @@ export interface Config {
thinking?: 'enabled' | 'disabled'
/** Default thinking effort (default `high`); `off` disables thinking per request. */
reasoningEffort?: 'off' | 'high' | 'max'
/** Positive context capacity used when the selected model has no exact value. */
/** Default per-request output cap (default 256,000); explicit request values win. */
maxTokens?: number
/** Positive context capacity used when the selected model has no exact value (default 1,000,000). */
defaultContextWindow?: number
/** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */
models?: DeepSeekCatalogModel[]
@@ -77,11 +89,12 @@ const catalogModel: z<DeepSeekCatalogModel> = z.object({
export const Config: z<Config> = z.object({
apiKey: z.string().role('secret'),
apiKeyEnv: z.string().default(DEFAULT_API_KEY_ENV),
apiKeyEnv: z.string().role('credential-ref').default(DEFAULT_API_KEY_ENV),
baseURL: z.string(),
thinking: z.union(['enabled', 'disabled']),
reasoningEffort: z.union(['off', 'high', 'max']),
defaultContextWindow: z.number().step(1).min(1),
maxTokens: z.number().step(1).min(1).max(Number.MAX_SAFE_INTEGER).default(DEFAULT_MAX_TOKENS),
defaultContextWindow: z.number().step(1).min(1).default(DEFAULT_CONTEXT_WINDOW),
models: z.array(catalogModel).default(DEFAULT_MODELS),
streamIdleTimeoutMs: z.number().min(Number.MIN_VALUE).max(MAX_TIMER_DELAY_MS).default(DEFAULT_STREAM_IDLE_TIMEOUT_MS),
retryPolicy: RetryPolicySchema,
@@ -141,6 +154,10 @@ export function resolveAdapterOptions(config: Config): ResolvedDeepSeekOptions {
&& (!Number.isInteger(config.defaultContextWindow) || config.defaultContextWindow <= 0)) {
throw new Error('llm-deepseek: defaultContextWindow must be a positive integer')
}
if (config.maxTokens !== undefined
&& (!Number.isSafeInteger(config.maxTokens) || config.maxTokens <= 0)) {
throw new Error('llm-deepseek: maxTokens must be a positive safe integer')
}
const streamIdleTimeoutMs = config.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS
if (!Number.isFinite(streamIdleTimeoutMs)
|| streamIdleTimeoutMs <= 0
@@ -157,9 +174,8 @@ export function resolveAdapterOptions(config: Config): ResolvedDeepSeekOptions {
thinking: config.thinking,
reasoningEffort: config.reasoningEffort,
},
...config.defaultContextWindow === undefined
? {}
: { defaultContextWindow: config.defaultContextWindow },
maxTokens: config.maxTokens ?? DEFAULT_MAX_TOKENS,
defaultContextWindow: config.defaultContextWindow ?? DEFAULT_CONTEXT_WINDOW,
models: resolveModels(config.models),
streamIdleTimeoutMs,
retryPolicy: resolveRetryPolicy(config.retryPolicy, 'llm-deepseek: retryPolicy'),
@@ -215,18 +231,22 @@ export function apply(ctx: Context, config: Config): void {
}
const adapter = new DeepSeekAdapter({ options, resolveApiKey })
ctx.llm.registerConfigurableProviders([
{ provider: PROVIDER, displayName: 'DeepSeek', settingsNs: NS, settingsPath: [] },
])
// 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([PROVIDER], adapter)
const registration = ctx.llm.registerAdapter([PROVIDER], 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([PROVIDER], adapter)
// fact per-request resolution cannot refresh. `replace` re-reads it in one
// synchronous registry section: disposing and re-registering instead would
// publish an empty route set between the two, and an observer that reacted
// to it would see this provider disappear and come back.
registration.replace([PROVIDER])
registeredPolicy = policy
}

7
packages/llm/llm-deepseek/src/serialize.ts
View File

@@ -148,7 +148,10 @@ export function serializeMessages(messages: Message[]): WireMessage[] {
* @param defaults - adapter-level thinking defaults; undefined fields put nothing on the wire.
* @returns the chat-completions request body.
*/
export function serializeRequest(options: GenerateOptions, defaults: RequestDefaults = {}): WireRequest {
export function serializeRequest(
options: GenerateOptions,
defaults: RequestDefaults = {},
): WireRequest {
const messages: WireMessage[] = []
if (options.system !== undefined) {
messages.push({ role: 'system', content: options.system })
@@ -178,7 +181,7 @@ export function serializeRequest(options: GenerateOptions, defaults: RequestDefa
: {},
...tools !== undefined && tools.length > 0 ? { tools } : {},
...options.temperature !== undefined ? { temperature: options.temperature } : {},
...options.maxTokens !== undefined ? { max_tokens: options.maxTokens } : {},
...options.maxTokens === undefined ? {} : { max_tokens: options.maxTokens },
...options.stop !== undefined ? { stop: options.stop } : {},
}
}