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outdated headers, producing HTTP 429 "Update Required".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.

src/app/api/providers/[id]/models/route.js

@@ -10,6 +10,7 @@ import { resolveKimchiModels } from "open-sse/services/kimchiModels.js";
 import { resolveQoderModels } from "open-sse/services/qoderModels.js";
 import { resolveGrokCliModels } from "open-sse/services/grokCliModels.js";
 import { resolveConnectionProxyConfig } from "@/lib/network/connectionProxy";
+import { resolveCursorModels } from "open-sse/services/cursorModels.js";
 
 const GEMINI_CLI_MODELS_URL = "https://cloudcode-pa.googleapis.com/v1internal:fetchAvailableModels";
 
@@ -292,6 +293,19 @@ const PROVIDER_MODELS_CONFIG = {
       };
     }
   },
+  cursor: {
+    customResolver: async (connection) => {
+      const result = await resolveCursorModels({
+        accessToken: connection.accessToken,
+        providerSpecificData: connection.providerSpecificData || {},
+      }, { forceRefresh: true, log: console });
+      if (result?.models?.length) return { models: result.models };
+      return {
+        models: getStaticProviderModels("cursor"),
+        warning: "Cursor returned no live models; falling back to static catalog.",
+      };
+    },
+  },
 
   // Custom resolvers (non-OpenAI-shaped APIs / token-refresh flows)
   kiro: {

src/app/api/v1/models/route.js

@@ -13,6 +13,7 @@ import { resolveQoderModels } from "open-sse/services/qoderModels.js";
 import { resolveCopilotModels } from "open-sse/services/copilotModels.js";
 import { resolveClinepassModels } from "open-sse/services/clinepassModels.js";
 import { resolveGrokCliModels } from "open-sse/services/grokCliModels.js";
+import { resolveCursorModels } from "open-sse/services/cursorModels.js";
 import { updateProviderCredentials } from "@/sse/services/tokenRefresh";
 import { resolveConnectionProxyConfig } from "@/lib/network/connectionProxy";
 import { capabilitiesFromServiceKind, getCapabilitiesForModel } from "open-sse/providers/capabilities.js";
@@ -97,6 +98,13 @@ const LIVE_MODEL_RESOLVERS = {
     });
     return result?.models?.length ? { models: result.models } : null;
   },
+  cursor: async (conn) => {
+    const result = await resolveCursorModels({
+      accessToken: conn.accessToken,
+      providerSpecificData: conn.providerSpecificData || {},
+    }, { log: console });
+    return result?.models?.length ? { models: result.models } : null;
+  }
 };
 
 const parseOpenAIStyleModels = (data) => {