/** * Serialize harness messages into DeepSeek chat completions. User text is joined; assistant text * becomes `content`, tool calls become `tool_calls`, and tool results become separate tool messages. * Assistant reasoning is replayed as `reasoning_content` only on tool-call turns, as required by * thinking-mode passback. Core image blocks are rejected explicitly because this wire route is text-only; * unknown declaration-merged block types retain the adapter's documented extension fallback. * @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 } /** Join the text blocks of a message (used for user/tool-result content). */ function flattenText(blocks: ContentBlock[]): string { return blocks .filter(block => block.type === 'text') .map(block => block.text) .join('') } /** Reject core image content before any text-flattening path can silently erase it. */ function assertTextOnly(blocks: readonly ContentBlock[]): void { for (const block of blocks) { if (block.type === 'image') { throw new LlmError('The DeepSeek chat-completions adapter does not support image content.', 'UNSUPPORTED_CONTENT') } if (block.type === 'tool-result') assertTextOnly(block.content) } } /** Serialize one assistant message (text + reasoning + tool calls). */ function serializeAssistant(message: Message): WireMessage { const text = flattenText(message.content) const reasoning = message.content .filter(block => block.type === 'reasoning') .map(block => block.text) .join('') const toolCalls = message.content .filter(block => block.type === 'tool-call') .map(block => ({ id: block.id, type: 'function' as const, function: { name: block.name, arguments: block.arguments }, })) return { role: 'assistant', // Text-less turns send "" — NEVER null. Pure tool-call turns: the // official samples replay message.content verbatim (which is "") and // some gateways reject null outright. Reasoning-ONLY turns (the model // can answer entirely in the reasoning channel, e.g. a v4-flash // greeting): the live API rejects null-content/no-tool_calls assistant // messages with a 400 ("content or tool_calls must be set"), and since // the message sits durably in the session log, a null here bricks every // later turn of that session. content: text, // Official passback rule (guides/thinking_mode.mdx): reasoning_content // must return on tool-call turns; it is ignored on plain turns, so we // drop it there to save tokens. ...toolCalls.length > 0 && reasoning.length > 0 ? { reasoning_content: reasoning } : {}, ...toolCalls.length > 0 ? { tool_calls: toolCalls } : {}, } } /** * Serialize the conversation. `tool-result` blocks become standalone * `{role: 'tool'}` messages; the harness puts each tool result in its own * user-role message, so a mixed user message contributes its text first and * its tool results as separate wire messages after. * @param messages - the harness conversation, in order. * @returns the wire messages; order preserved, each tool result expanded into its own entry. */ export function serializeMessages(messages: Message[]): WireMessage[] { const wire: WireMessage[] = [] for (const message of messages) { assertTextOnly(message.content) if (message.role === 'system') { wire.push({ role: 'system', content: flattenText(message.content) }) continue } if (message.role === 'assistant') { wire.push(serializeAssistant(message)) continue } // user role: tool results ride in user messages in the harness // vocabulary, but DeepSeek wants them as role:'tool' messages. const toolResults = message.content.filter(block => block.type === 'tool-result') const text = flattenText(message.content) if (text.length > 0 || toolResults.length === 0) { wire.push({ role: 'user', content: text }) } for (const result of toolResults) { wire.push({ role: 'tool', tool_call_id: result.toolCallId, // Empty tool output still needs SOME content on the wire. content: flattenText(result.content) || '(no output)', }) } } return wire } /** * Build the full wire request. Always streaming (`stream: true`, usage * reporting on); optional fields are omitted rather than sent as null, so * provider defaults apply. * @param options - the harness request (model, history, system, tools, sampling). * @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 { const messages: WireMessage[] = [] if (options.system !== undefined) { messages.push({ role: 'system', content: options.system }) } messages.push(...serializeMessages(options.messages)) const tools: WireTool[] | undefined = options.tools?.map(tool => ({ type: 'function', function: { name: tool.name, description: tool.description, parameters: tool.parameters, }, })) 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 } : {}, ...tools !== undefined && tools.length > 0 ? { tools } : {}, ...options.temperature !== undefined ? { temperature: options.temperature } : {}, ...options.maxTokens !== undefined ? { max_tokens: options.maxTokens } : {}, ...options.stop !== undefined ? { stop: options.stop } : {}, } }