fix(translator): preserve Responses Lite tools across Chat providers
Codex Responses Lite clients routed to a chat-native OpenAI-compatible provider lost tool use in three places: non-streaming Chat responses leaked the raw chat.completion envelope instead of Responses output items, internal reasoning continuity fields leaked into the outbound Chat body causing some upstreams to reject the request, and the Responses to Chat request translator ignored additional_tools, custom_tool_call, and custom_tool_call_output items entirely. Also fixes apiType (chat vs responses) for openai-compatible nodes being resolved from the immutable provider ID instead of the stored node config, so editing a node's API Type had no runtime effect.
This commit is contained in:
nguyenha935
@@ -9,6 +9,7 @@ import { parseSSEToOpenAIResponse } from "./sseToJsonHandler.js";
|
||||
import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine } from "./requestDetail.js";
|
||||
import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
|
||||
import { decloakToolNames } from "../../utils/claudeCloaking.js";
|
||||
import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
|
||||
|
||||
function parseToolArguments(value) {
|
||||
if (!value) return {};
|
||||
@@ -60,11 +61,93 @@ function openAICompletionToClaudeMessage(responseBody) {
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert an OpenAI Chat Completions non-streaming response body into the
|
||||
* OpenAI Responses API shape. Used when a Responses-format client (e.g. Codex)
|
||||
* is routed to a Chat Completions upstream and `stream:false` — the streaming
|
||||
* path already emits Responses events, but the JSON path returned a raw
|
||||
* `chat.completion` body, so tool_calls were invisible to Responses clients.
|
||||
*/
|
||||
function extractCustomToolInput(argumentsValue) {
|
||||
const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
|
||||
try {
|
||||
const parsed = JSON.parse(argumentsText);
|
||||
if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
|
||||
} catch { /* raw freeform input */ }
|
||||
return argumentsText;
|
||||
}
|
||||
|
||||
function openAICompletionToResponses(responseBody, customToolNames = null) {
|
||||
const choice = responseBody?.choices?.[0];
|
||||
if (!choice) return responseBody;
|
||||
|
||||
const message = choice.message || {};
|
||||
const output = [];
|
||||
|
||||
// Reasoning → a reasoning item (summary text), mirroring the streaming path.
|
||||
const reasoning = message.reasoning_content || message.reasoning;
|
||||
if (typeof reasoning === "string" && reasoning.length > 0) {
|
||||
output.push({
|
||||
type: RESPONSES_ITEM.REASONING,
|
||||
summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
|
||||
});
|
||||
}
|
||||
|
||||
// Assistant text → a message item with output_text content.
|
||||
const text = typeof message.content === "string" ? message.content : "";
|
||||
if (text.length > 0) {
|
||||
output.push({
|
||||
type: RESPONSES_ITEM.MESSAGE,
|
||||
role: ROLE.ASSISTANT,
|
||||
content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
|
||||
});
|
||||
}
|
||||
|
||||
// tool_calls → function_call/custom_tool_call items (Responses-native tool shape).
|
||||
for (const tc of message.tool_calls || []) {
|
||||
const fn = tc.function || {};
|
||||
const custom = customToolNames?.has(fn.name);
|
||||
output.push({
|
||||
type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
|
||||
id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
|
||||
call_id: tc.id || "",
|
||||
name: fn.name || "",
|
||||
...(custom
|
||||
? { input: extractCustomToolInput(fn.arguments) }
|
||||
: { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
|
||||
});
|
||||
}
|
||||
|
||||
const usage = responseBody.usage || {};
|
||||
const status = choice.finish_reason === "tool_calls" ? "completed" : (choice.finish_reason === "stop" ? "completed" : (choice.finish_reason || "completed"));
|
||||
|
||||
return {
|
||||
id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
|
||||
object: "response",
|
||||
created_at: responseBody.created || Math.floor(Date.now() / 1000),
|
||||
model: responseBody.model || "unknown",
|
||||
status,
|
||||
background: false,
|
||||
error: null,
|
||||
output,
|
||||
usage: {
|
||||
input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
|
||||
output_tokens: usage.completion_tokens || usage.output_tokens || 0,
|
||||
total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Translate non-streaming response body from provider format → OpenAI format.
|
||||
*/
|
||||
export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat) {
|
||||
export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames = null) {
|
||||
if (targetFormat === sourceFormat) return responseBody;
|
||||
// Provider responded in OpenAI Chat Completions shape but the client speaks
|
||||
// Responses API — convert so tool_calls/text surface as Responses `output`.
|
||||
if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.OPENAI_RESPONSES) {
|
||||
return openAICompletionToResponses(responseBody, customToolNames);
|
||||
}
|
||||
if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.CLAUDE) {
|
||||
return openAICompletionToClaudeMessage(responseBody);
|
||||
}
|
||||
@@ -198,7 +281,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
|
||||
/**
|
||||
* Handle non-streaming response from provider.
|
||||
*/
|
||||
export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog, pxpipe, reqTag, log }) {
|
||||
export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, trackDone, appendLog, pxpipe, reqTag, log }) {
|
||||
trackDone();
|
||||
const contentType = providerResponse.headers.get("content-type") || "";
|
||||
let responseBody;
|
||||
@@ -239,9 +322,12 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
|
||||
if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
|
||||
|
||||
const translatedResponse = needsTranslation(targetFormat, sourceFormat)
|
||||
? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
|
||||
? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames)
|
||||
: responseBody;
|
||||
const isClaudeMessageResponse = sourceFormat === FORMATS.CLAUDE && translatedResponse?.type === "message";
|
||||
// Responses-format translation produces a `object:"response"` body with no
|
||||
// `choices`; skip the Chat-Completions-specific post-processing below for it.
|
||||
const isResponsesResponse = sourceFormat === FORMATS.OPENAI_RESPONSES && translatedResponse?.object === "response";
|
||||
|
||||
// Fix finish_reason for tool_calls: some providers return non-standard values (e.g. "other")
|
||||
if (translatedResponse?.choices?.[0]) {
|
||||
@@ -254,13 +340,13 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
|
||||
}
|
||||
|
||||
// Ensure OpenAI-required fields
|
||||
if (!isClaudeMessageResponse) {
|
||||
if (!isClaudeMessageResponse && !isResponsesResponse) {
|
||||
if (!translatedResponse.object) translatedResponse.object = "chat.completion";
|
||||
if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
|
||||
}
|
||||
|
||||
// Strip Azure-specific fields
|
||||
if (!isClaudeMessageResponse) {
|
||||
if (!isClaudeMessageResponse && !isResponsesResponse) {
|
||||
delete translatedResponse.prompt_filter_results;
|
||||
if (translatedResponse?.choices) {
|
||||
for (const choice of translatedResponse.choices) delete choice.content_filter_results;
|
||||
@@ -274,7 +360,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
|
||||
// Strip reasoning_content only when content is non-empty.
|
||||
// When content is empty (e.g. thinking models that used all tokens for reasoning),
|
||||
// reasoning_content is the only useful output and must be preserved.
|
||||
if (!isClaudeMessageResponse && translatedResponse?.choices) {
|
||||
if (!isClaudeMessageResponse && !isResponsesResponse && translatedResponse?.choices) {
|
||||
for (const choice of translatedResponse.choices) {
|
||||
if (choice?.message?.reasoning_content && choice.message.content) {
|
||||
delete choice.message.reasoning_content;
|
||||
|
||||
@@ -4,6 +4,7 @@ import { HTTP_STATUS } from "../../config/runtimeConfig.js";
|
||||
import { FORMATS } from "../../translator/formats.js";
|
||||
import { PROVIDERS } from "../../config/providers.js";
|
||||
import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
|
||||
import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
|
||||
|
||||
// Responses-API providers (e.g. codex) may emit SSE without content-type + use Responses output shape
|
||||
const isResponsesProvider = (p) => PROVIDERS[p]?.format === FORMATS.OPENAI_RESPONSES;
|
||||
@@ -34,6 +35,76 @@ function pickAssistantMessageForChatCompletion(output) {
|
||||
return { msgItem: last, textContent: textFromResponsesMessageItem(last) };
|
||||
}
|
||||
|
||||
/**
|
||||
* Convert an OpenAI Chat Completions JSON body into the Responses API shape.
|
||||
* Inlined here (not imported from nonStreamingHandler.js) to avoid a circular
|
||||
* import. Mirrors openAICompletionToResponses in nonStreamingHandler.js.
|
||||
*/
|
||||
function extractCustomToolInput(argumentsValue) {
|
||||
const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
|
||||
try {
|
||||
const parsed = JSON.parse(argumentsText);
|
||||
if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
|
||||
} catch { /* raw freeform input */ }
|
||||
return argumentsText;
|
||||
}
|
||||
|
||||
function chatCompletionToResponses(responseBody, customToolNames = null) {
|
||||
const choice = responseBody?.choices?.[0];
|
||||
if (!choice) return responseBody;
|
||||
|
||||
const message = choice.message || {};
|
||||
const output = [];
|
||||
|
||||
const reasoning = message.reasoning_content || message.reasoning;
|
||||
if (typeof reasoning === "string" && reasoning.length > 0) {
|
||||
output.push({
|
||||
type: RESPONSES_ITEM.REASONING,
|
||||
summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
|
||||
});
|
||||
}
|
||||
|
||||
const text = typeof message.content === "string" ? message.content : "";
|
||||
if (text.length > 0) {
|
||||
output.push({
|
||||
type: RESPONSES_ITEM.MESSAGE,
|
||||
role: ROLE.ASSISTANT,
|
||||
content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
|
||||
});
|
||||
}
|
||||
|
||||
for (const tc of message.tool_calls || []) {
|
||||
const fn = tc.function || {};
|
||||
const custom = customToolNames?.has(fn.name);
|
||||
output.push({
|
||||
type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
|
||||
id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
|
||||
call_id: tc.id || "",
|
||||
name: fn.name || "",
|
||||
...(custom
|
||||
? { input: extractCustomToolInput(fn.arguments) }
|
||||
: { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
|
||||
});
|
||||
}
|
||||
|
||||
const usage = responseBody.usage || {};
|
||||
return {
|
||||
id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
|
||||
object: "response",
|
||||
created_at: responseBody.created || Math.floor(Date.now() / 1000),
|
||||
model: responseBody.model || "unknown",
|
||||
status: "completed",
|
||||
background: false,
|
||||
error: null,
|
||||
output,
|
||||
usage: {
|
||||
input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
|
||||
output_tokens: usage.completion_tokens || usage.output_tokens || 0,
|
||||
total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse OpenAI-style SSE text into a single chat completion JSON.
|
||||
* Used when provider forces streaming but client wants non-streaming.
|
||||
@@ -108,7 +179,7 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
|
||||
* Handle case: provider forced streaming but client wants JSON.
|
||||
* Supports both Codex/Responses API SSE and standard Chat Completions SSE.
|
||||
*/
|
||||
export async function handleForcedSSEToJson({ providerResponse, sourceFormat, provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, trackDone, appendLog, reqTag, log }) {
|
||||
export async function handleForcedSSEToJson({ providerResponse, sourceFormat, targetFormat, provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, customToolNames, trackDone, appendLog, reqTag, log }) {
|
||||
const contentType = providerResponse.headers.get("content-type") || "";
|
||||
const isSSE = contentType.includes("text/event-stream") || (contentType === "" && isResponsesProvider(provider));
|
||||
if (!isSSE) return null; // not handled here
|
||||
@@ -122,7 +193,10 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
|
||||
};
|
||||
|
||||
// Codex/Responses API SSE path
|
||||
const isCodexResponsesApi = isResponsesProvider(provider) || sourceFormat === FORMATS.OPENAI_RESPONSES;
|
||||
// Branch on the UPSTREAM format (targetFormat = format we spoke to the provider in),
|
||||
// not the client format: a Responses-API client behind a chat-native forced-streaming
|
||||
// provider still receives chat SSE chunks, which must go through the standard path.
|
||||
const isCodexResponsesApi = isResponsesProvider(provider) || targetFormat === FORMATS.OPENAI_RESPONSES;
|
||||
if (isCodexResponsesApi) {
|
||||
try {
|
||||
const jsonResponse = await convertResponsesStreamToJson(providerResponse.body);
|
||||
@@ -267,7 +341,17 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
|
||||
}
|
||||
}
|
||||
|
||||
return { success: true, response: new Response(JSON.stringify(parsed), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
|
||||
// A Responses-format client (e.g. Codex) forced this provider to stream,
|
||||
// but wants JSON back. parseSSEToOpenAIResponse yields a Chat Completions
|
||||
// body; convert it to the Responses `output` shape so tool_calls are not
|
||||
// lost on the non-streaming return path. Inlined (not imported from
|
||||
// nonStreamingHandler.js) to avoid a circular import: nonStreamingHandler
|
||||
// already imports parseSSEToOpenAIResponse from this module.
|
||||
const finalBody = sourceFormat === FORMATS.OPENAI_RESPONSES
|
||||
? chatCompletionToResponses(parsed, customToolNames)
|
||||
: parsed;
|
||||
|
||||
return { success: true, response: new Response(JSON.stringify(finalBody), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
|
||||
} catch (err) {
|
||||
console.error("[ChatCore] Chat Completions SSE→JSON failed:", err);
|
||||
return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Failed to convert streaming response to JSON");
|
||||
|
||||
@@ -22,7 +22,7 @@ const CODEX_SOURCE_TO_TARGET = {
|
||||
/**
|
||||
* Determine which SSE transform stream to use based on provider/format.
|
||||
*/
|
||||
function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey }) {
|
||||
function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, customToolNames, model, connectionId, body, onStreamComplete, apiKey }) {
|
||||
const isDroidCLI = userAgent?.toLowerCase().includes("droid") || userAgent?.toLowerCase().includes("codex-cli");
|
||||
// Responses-API providers (e.g. codex) emit Responses SSE → translate into client format
|
||||
const isResponsesProvider = PROVIDERS[provider]?.format === FORMATS.OPENAI_RESPONSES;
|
||||
@@ -30,11 +30,11 @@ function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent,
|
||||
|
||||
if (needsCodexTranslation) {
|
||||
const codexTarget = CODEX_SOURCE_TO_TARGET[sourceFormat] || FORMATS.OPENAI;
|
||||
return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
|
||||
return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey, customToolNames);
|
||||
}
|
||||
|
||||
if (needsTranslation(targetFormat, sourceFormat)) {
|
||||
return createSSETransformStreamWithLogger(targetFormat, sourceFormat, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
|
||||
return createSSETransformStreamWithLogger(targetFormat, sourceFormat, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey, customToolNames);
|
||||
}
|
||||
|
||||
return createPassthroughStreamWithLogger(provider, reqLogger, model, connectionId, body, onStreamComplete, apiKey);
|
||||
@@ -43,7 +43,7 @@ function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent,
|
||||
/**
|
||||
* Handle streaming response — pipe provider SSE through transform stream to client.
|
||||
*/
|
||||
export async function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId, pxpipe, reqTag, log }) {
|
||||
export async function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, streamController, onStreamComplete, streamDetailId, pxpipe, reqTag, log }) {
|
||||
if (onRequestSuccess) {
|
||||
Promise.resolve()
|
||||
.then(onRequestSuccess)
|
||||
@@ -79,7 +79,7 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
|
||||
};
|
||||
}
|
||||
|
||||
const transformStream = buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey });
|
||||
const transformStream = buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, customToolNames, model, connectionId, body, onStreamComplete, apiKey });
|
||||
|
||||
// Responses passthrough: synthesize response.failed + [DONE] if the stream aborts/stalls before a terminal event
|
||||
const isResponsesPassthrough = sourceFormat === FORMATS.OPENAI_RESPONSES && targetFormat === FORMATS.OPENAI_RESPONSES;
|
||||
|
||||
Reference in New Issue
Block a user