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

# Conflicts:
#	apps/cli/src/web.ts
#	apps/web/tests/smoke-fixture.e2e.ts
#	docs/architecture.i18n.yaml
#	packages/client/connection/src/client/fixture.ts
#	packages/client/runtime/src/client/sessions/conversation.ts
#	packages/client/runtime/src/client/sessions/session.ts
#	packages/client/ui-conversation/package.json
#	packages/client/ui-conversation/src/client/contract/slots.ts
#	packages/client/ui-conversation/src/client/index.ts
#	packages/client/ui-conversation/src/client/service.ts
#	packages/client/ui-conversation/src/client/skeleton/ConversationRoot.tsx
#	packages/client/ui-conversation/tests/apply-inject.spec.tsx
#	packages/client/ui-conversation/tests/service-orchestration.spec.ts
#	packages/host/runtime/src/api-proxy.ts
#	packages/host/runtime/src/boot.ts
#	packages/host/webserver/tests/webserver.spec.ts
#	pnpm-lock.yaml

packages/llm/llm-deepseek/src/adapter.ts

@@ -40,6 +40,8 @@ export interface DeepSeekAdapterOptions {
   baseURL: string
   /** Request defaults applied to every call (thinking mode, effort). */
   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[]
   /** Maximum provider idle time while one stream read is outstanding. */
@@ -96,6 +98,10 @@ export class DeepSeekAdapter extends LlmAdapter {
 
   constructor(private readonly options: DeepSeekAdapterOptions) {
     super()
+    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
@@ -126,6 +132,7 @@ export class DeepSeekAdapter extends LlmAdapter {
     model: string,
   ): Promise<LlmModelContext | undefined> {
     const contextWindow = this.options.models?.find(entry => entry.id === model)?.contextWindow
+      ?? this.options.defaultContextWindow
     return Promise.resolve(contextWindow === undefined ? undefined : { contextWindow })
   }
 

packages/llm/llm-deepseek/src/index.ts

@@ -40,6 +40,8 @@ export interface Config {
   thinking?: 'enabled' | 'disabled'
   /** Thinking effort (only meaningful with thinking enabled). */
   reasoningEffort?: '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. */
   models?: DeepSeekCatalogModel[]
   /** Maximum provider idle time while one stream read is outstanding (default five minutes). */
@@ -58,6 +60,7 @@ export const Config: z<Config> = z.object({
   baseURL: z.string(),
   thinking: z.union(['enabled', 'disabled']),
   reasoningEffort: z.union(['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),
 })
@@ -103,6 +106,9 @@ export function apply(ctx: Context, config: Config): void {
       thinking: config.thinking,
       reasoningEffort: config.reasoningEffort,
     },
+    ...config.defaultContextWindow === undefined
+      ? {}
+      : { defaultContextWindow: config.defaultContextWindow },
     models: resolveModels(config.models),
     streamIdleTimeoutMs: config.streamIdleTimeoutMs ?? DEFAULT_STREAM_IDLE_TIMEOUT_MS,
   }))

packages/llm/llm-deepseek/src/serialize.ts

@@ -131,14 +131,18 @@ export function serializeRequest(options: GenerateOptions, defaults: RequestDefa
       parameters: tool.parameters,
     },
   }))
+  // 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
 
   return {
     model: options.model,
     messages,
     stream: true,
     stream_options: { include_usage: true },
-    ...defaults.thinking !== undefined ? { thinking: { type: defaults.thinking } } : {},
-    ...defaults.reasoningEffort !== undefined ? { reasoning_effort: defaults.reasoningEffort } : {},
+    ...thinking !== undefined ? { thinking: { type: thinking } } : {},
+    ...reasoningEffort !== undefined ? { reasoning_effort: reasoningEffort } : {},
     ...tools !== undefined && tools.length > 0 ? { tools } : {},
     ...options.temperature !== undefined ? { temperature: options.temperature } : {},
     ...options.maxTokens !== undefined ? { max_tokens: options.maxTokens } : {},