fix(cursor): stop AgentService empty turns and silent tool hangs

Cursor-hosted models (cu/composer-2.5, cu/cursor-grok-*, cu/default) returned
HTTP 200 with an empty turn, or hung, whenever a client sent tools.

- Fold system prompts into the current user message. custom_system_prompt
  (RunRequest field 8) makes AgentService return an empty turn.
- Send ModelDetails (field 3); thinking variants (Composer, Grok, *-thinking)
  return an empty turn when only requested_model (field 9) is set.
- Route tool-call history and declared tool schemas through AgentService:
  encode OpenAI tools into mcp_tools (field 4), decode McpArgs and emit real
  tool_calls with finish_reason tool_calls.
- Map Composer  thinking / Grok thinking_delta (field 4) into visible content
  instead of dropping the answer with the unsigned reasoning.
- Ack request_context without echoing MCP tools (double-advertise stalls the
  HTTP/2 stream) and ack kv_server_message so the run proceeds.
- Reject IDE builtin execs instead of failing the turn, so the model can
  continue with MCP tools or a text answer.
- Add google.protobuf.Value / MCP encoders and a FIXED64 branch to
  encodeField in cursorProtobuf.js.

RTK now compresses the source-format body before translation for cursor only:
its translator rewrites role:tool into user XML, so the post-translate pass
missed those tool results. Every other provider keeps the post-translate pass
unchanged.

open-sse/AGENTS.md

@@ -4,7 +4,7 @@ Provider-agnostic SSE engine: one OpenAI-style request → any provider (LLM cha
 
 ## Request lifecycle (chat)
 
-`handlers/chatCore.js` → `services/model.js` `parseModel` (resolve `provider/model`) → **pre-translate hooks** (`rtk/` tool_result compress, `rtk/headroom.js` proxy compress, `rtk/caveman.js` system inject — all fail-open) → `executors/index.js` `getExecutor(provider)` → `translator/index.js` `translateRequest` (client format → provider format) → `executor.execute()` (streams upstream) → `translateResponse` (provider chunks → client format) → SSE out.
+`handlers/chatCore.js` → `services/model.js` `parseModel` (resolve `provider/model`) → **RTK for `cursor`** (`rtk/` compresses the source-format `tool_result` / `role:tool` in-place — its translator rewrites those shapes, so this one provider must run **before** translate) → `translator/index.js` `translateRequest` (client format → provider format) → **post-translate savers** (`rtk/` compress for every other provider, `rtk/headroom.js` proxy compress, `rtk/caveman.js` / `rtk/ponytail.js` system inject — all fail-open) → `executors/index.js` `getExecutor(provider)` → `executor.execute()` (streams upstream) → `translateResponse` (provider chunks → client format) → SSE out.
 
 ## Directory map