Merge remote-tracking branch 'origin/master' into worktree/web-session-model-selector

# Conflicts: # .agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.i18n.yaml # .agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.md # .agents/notes/implemented/architecture/2026-07-20-routed-model-context-and-compaction-policy.zh.md # packages/llm/llm-deepseek/README.i18n.yaml # packages/llm/llm-deepseek/tests/adapter.spec.ts
2026-07-27 15:49:09 +08:00
parent 7da7b182c9 d2edfcca2e
commit 39c60d5d64
106 changed files with 2594 additions and 491 deletions
--- a/packages/llm/llm-deepseek/src/adapter.ts
+++ b/packages/llm/llm-deepseek/src/adapter.ts
@@ -5,12 +5,12 @@
 * @module dsh-llm-deepseek/adapter
 */

-import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, isQuotaExceededError, LlmAdapter, LlmError, ProviderRequestId, QUOTA_EXCEEDED_CODE } 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,
-  LlmModelContext,
  LlmModelInfo,
  LlmProviderInfo,
+  LlmResolvedModelInfo,
  StreamChunk,
 } from '@deepseek-ai/dsh-llm'
 import { idleWatchdog, MAX_TIMER_DELAY_MS, timeoutOf } from '@deepseek-ai/dsh-timeout'
@@ -51,6 +51,26 @@ export interface DeepSeekAdapterOptions {
 /** Default maximum idle interval while an adapter stream read is outstanding. */
 export const DEFAULT_STREAM_IDLE_TIMEOUT_MS = 300_000
 const STREAM_IDLE_TIMEOUT_CODE = 'LLM_STREAM_IDLE_TIMEOUT'
+const OFF_REASONING_EFFORT = ReasoningEffortId('off')
+const HIGH_REASONING_EFFORT = ReasoningEffortId('high')
+const MAX_REASONING_EFFORT = ReasoningEffortId('max')
+const REASONING_EFFORTS = [
+  { id: OFF_REASONING_EFFORT, name: 'Off' },
+  { id: HIGH_REASONING_EFFORT, name: 'High' },
+  { id: MAX_REASONING_EFFORT, name: 'Max' },
+] as const
+const OFF_ONLY_REASONING_EFFORTS = [
+  { id: OFF_REASONING_EFFORT, name: 'Off' },
+] as const
+
+function modelInfo(provider: string, model: DeepSeekCatalogModel): LlmModelInfo {
+  return {
+    provider,
+    id: model.id,
+    name: model.name ?? model.id,
+    ...model.description === undefined ? {} : { description: model.description },
+  }
+}

 function providerRetryAfterMs(value: string | null): number | undefined {
  if (value === null) return undefined
@@ -98,6 +118,11 @@ export class DeepSeekAdapter extends LlmAdapter {

  constructor(private readonly options: 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')
@@ -117,21 +142,40 @@ export class DeepSeekAdapter extends LlmAdapter {
  }

  override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
-    return Promise.resolve((this.options.models ?? []).map(model => ({
-      provider,
-      id: model.id,
-      name: model.name ?? model.id,
-      ...model.description === undefined ? {} : { description: model.description },
-    })))
+    return Promise.resolve((this.options.models ?? []).map(model => modelInfo(provider, model)))
  }

-  override resolveModelContext(
-    _provider: string,
+  override resolveModel(
+    provider: string,
    model: string,
-  ): Promise<LlmModelContext | undefined> {
-    const contextWindow = this.options.models?.find(entry => entry.id === model)?.contextWindow
+    _signal?: AbortSignal,
+  ): Promise<LlmResolvedModelInfo> {
+    const configured = this.options.models?.find(entry => entry.id === model)
+    const contextWindow = configured?.contextWindow
      ?? this.options.defaultContextWindow
-    return Promise.resolve(contextWindow === undefined ? undefined : { contextWindow })
+    return Promise.resolve({
+      ...configured === undefined
+        ? { provider, id: model, name: model }
+        : modelInfo(provider, configured),
+      ...contextWindow === undefined ? {} : { context: { contextWindow } },
+      ...this.options.defaults?.thinking === 'disabled'
+        ? {
+          reasoning: {
+            efforts: OFF_ONLY_REASONING_EFFORTS,
+            defaultEffort: OFF_REASONING_EFFORT,
+          },
+        }
+        : {
+          reasoning: {
+            efforts: REASONING_EFFORTS,
+            defaultEffort: this.options.defaults?.reasoningEffort === 'off'
+              ? OFF_REASONING_EFFORT
+              : this.options.defaults?.reasoningEffort === 'max'
+                ? MAX_REASONING_EFFORT
+                : HIGH_REASONING_EFFORT,
+          },
+        },
+    })
  }

  async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
--- a/packages/llm/llm-deepseek/src/index.ts
+++ b/packages/llm/llm-deepseek/src/index.ts
@@ -28,18 +28,19 @@ const DEFAULT_MODELS: DeepSeekCatalogModel[] = [
 /**
 * 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), and omitted
- * thinking fields send nothing on the wire, so the provider default applies.
+ * missing API key fails plugin load, not the first call), 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. */
  apiKey?: string
  /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */
  baseURL?: string
-  /** Thinking-mode default for every request (provider default: enabled). */
+  /** Deployment thinking policy; `disabled` limits every conversation request to `off`. */
  thinking?: 'enabled' | 'disabled'
-  /** Thinking effort (only meaningful with thinking enabled). */
-  reasoningEffort?: 'high' | 'max'
+  /** 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. */
  defaultContextWindow?: number
  /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */
@@ -59,7 +60,7 @@ export const Config: z<Config> = z.object({
  apiKey: z.string(),
  baseURL: z.string(),
  thinking: z.union(['enabled', 'disabled']),
-  reasoningEffort: z.union(['high', 'max']),
+  reasoningEffort: z.union(['off', 'high', 'max']),
  defaultContextWindow: z.number().step(1).min(1),
  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),
@@ -94,6 +95,11 @@ function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): Dee
 }

 export function apply(ctx: Context, config: Config): void {
+  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)')
--- a/packages/llm/llm-deepseek/src/serialize.ts
+++ b/packages/llm/llm-deepseek/src/serialize.ts
@@ -6,13 +6,49 @@
 * @module dsh-llm-deepseek/serialize
 */

+import { LlmError } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
 import type { WireMessage, WireRequest, WireTool } from './types.ts'

 /** Adapter-level request defaults (from plugin config). */
 export interface RequestDefaults {
  thinking?: 'enabled' | 'disabled' | undefined
-  reasoningEffort?: 'high' | 'max' | undefined
+  reasoningEffort?: 'off' | 'high' | 'max' | undefined
+}
+
+interface ResolvedThinking {
+  thinking?: 'enabled' | 'disabled'
+  reasoningEffort?: 'high' | 'max'
+}
+
+/** Validate the adapter-owned effort before resolving its DeepSeek wire fields. */
+function reasoningEffort(effort: NonNullable<GenerateOptions['reasoningEffort']>): 'off' | 'high' | 'max' {
+  if (effort === 'off' || effort === 'high' || effort === 'max') {
+    return effort as 'off' | 'high' | 'max'
+  }
+  throw new LlmError(
+    `DeepSeek does not support reasoning effort "${effort}"`,
+    'UNSUPPORTED_REASONING_EFFORT',
+  )
+}
+
+/** Resolve one legal thinking/effort pair without exposing `off` as a wire effort. */
+function resolveThinking(options: GenerateOptions, defaults: RequestDefaults): ResolvedThinking {
+  if (options.purpose === 'session-title') return { thinking: 'disabled' }
+  const effort = options.reasoningEffort === undefined
+    ? defaults.reasoningEffort
+    : reasoningEffort(options.reasoningEffort)
+  if (defaults.thinking === 'disabled' && effort !== undefined && effort !== 'off') {
+    throw new LlmError(
+      `DeepSeek deployment does not support reasoning effort "${effort}"`,
+      'UNSUPPORTED_REASONING_EFFORT',
+    )
+  }
+  if (effort === 'off') return { thinking: 'disabled' }
+  if (effort === 'high' || effort === 'max') {
+    return { thinking: 'enabled', reasoningEffort: effort }
+  }
+  return defaults.thinking === undefined ? {} : { thinking: defaults.thinking }
 }

 /** Join the text blocks of a message (used for user/tool-result content). */
@@ -120,16 +156,17 @@ export function serializeRequest(options: GenerateOptions, defaults: RequestDefa
  }))
  // A short title budget must produce visible text; conversation and
  // compaction calls continue to inherit the adapter's thinking defaults.
-  const thinking = options.purpose === 'session-title' ? 'disabled' : defaults.thinking
-  const reasoningEffort = options.purpose === 'session-title' ? undefined : defaults.reasoningEffort
+  const resolvedThinking = resolveThinking(options, defaults)

  return {
    model: options.model,
    messages,
    stream: true,
    stream_options: { include_usage: true },
-    ...thinking !== undefined ? { thinking: { type: thinking } } : {},
-    ...reasoningEffort !== undefined ? { reasoning_effort: reasoningEffort } : {},
+    ...resolvedThinking.thinking !== undefined ? { thinking: { type: resolvedThinking.thinking } } : {},
+    ...resolvedThinking.reasoningEffort !== undefined
+      ? { reasoning_effort: resolvedThinking.reasoningEffort }
+      : {},
    ...tools !== undefined && tools.length > 0 ? { tools } : {},
    ...options.temperature !== undefined ? { temperature: options.temperature } : {},
    ...options.maxTokens !== undefined ? { max_tokens: options.maxTokens } : {},