fix(cursor): HTTP/2 AgentService support + version bump to 3.12.17

Real Cursor IDE now uses AgentService at agent.api5.cursor.sh (HTTP/2-only)
while 9router still spoke the retired ChatService at api2.cursor.sh with
outdated headers, producing HTTP 429 "Update Required". Add an executeAgent
path that builds an agent.v1.RunRequest Connect RPC over a raw http2 stream
and fetches the account-specific usable model catalog via GetUsableModels.

Also implement MCP tool calling over AgentService: encode OpenAI tools as
AgentRunRequest.mcp_tools (McpToolDefinition with google.protobuf.Value
input_schema), decode McpArgs tool calls, and forward them to the client as
OpenAI tool_calls so the client runs the tool and resumes in the next turn.
Reply to request_context_args with a non-empty RequestContext, to server
heartbeats with client_heartbeat, and to KV blob get/set with empty results,
so action queries no longer stall the stream. Fold the client system prompt
into the user message (custom_system_prompt makes the server return an empty
turn). Bump clientVersion to 3.12.17 and add the x-cursor-client-commit
header so the gateway identifies as a current Cursor IDE release.
This commit is contained in:
long2ice
2026-07-20 15:39:55 +07:00
committed by decolua
parent 4f48ab8c7f
commit 6994cd1f70
12 changed files with 1106 additions and 13 deletions
+11 -3
View File
@@ -291,12 +291,16 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
// Execute request
let providerResponse, providerUrl, providerHeaders, finalBody;
// Most executors return their registry format. Cursor AgentService is an
// exception: it is decoded by the executor into OpenAI-compatible output.
let providerResponseFormat = targetFormat;
try {
const result = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
providerResponse = result.response;
providerUrl = result.url;
providerHeaders = result.headers;
finalBody = result.transformedBody;
providerResponseFormat = result.responseFormat || targetFormat;
reqLogger.logTargetRequest(providerUrl, providerHeaders, finalBody);
} catch (error) {
trackPendingRequest(model, provider, connectionId, false, true);
@@ -335,7 +339,11 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
}
try {
const retryResult = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
if (retryResult.response.ok) { providerResponse = retryResult.response; providerUrl = retryResult.url; }
if (retryResult.response.ok) {
providerResponse = retryResult.response;
providerUrl = retryResult.url;
providerResponseFormat = retryResult.responseFormat || targetFormat;
}
} catch { log?.warn?.("TOKEN", `${provider.toUpperCase()} | retry after refresh failed`); }
} else {
log?.warn?.("TOKEN", `${provider.toUpperCase()} | refresh failed`);
@@ -382,14 +390,14 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
// True non-streaming response
if (!stream) {
const result = await handleNonStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat, reqLogger, toolNameMap, trackDone, appendLog });
const result = await handleNonStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, reqLogger, toolNameMap, trackDone, appendLog });
streamController.handleComplete();
return result;
}
// Streaming response
const { onStreamComplete, streamDetailId } = buildOnStreamComplete({ ...sharedCtx });
return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId });
return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, userAgent, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId });
}
export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {