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.

CHANGELOG.md

@@ -7,6 +7,8 @@
 - **i18n**: integrate Persian (fa) translation
 
 ## Fixes
+- **Cursor**: stop AgentService empty turns (`OUT 0`) and silent hangs — fold system prompts instead of `custom_system_prompt`, send `ModelDetails`, read Composer/Grok `thinking_delta`, ack request-context without echoing MCP tools, and reject IDE execs so the model can continue
+- **RTK**: for Cursor, compress source-format `tool_result` / `role:tool` **before** translation — its translator rewrites those shapes, so post-translate compression missed them. Other providers keep the post-translate pass unchanged
 - **OpenCode / OpenCode Go**: resolve 403 `FreeTierError` and 429 rate limits with canonical session format, valid User-Agent, and stable upstream session reuse; force stream and declare `forceStream` for free-tier SSE aggregation; cloak decoy tools, normalize Muse Free tool choice, and strip prior reasoning items on Responses models; route Union Alpha via Messages API
 - **Kiro**: preserve underscores in tool names (`mcp__server__tool`) and restore client tool names in responses; use neutral placeholder for tool-result-only turns; forward tool-result images
 - **Stream**: report aborts after HTTP 200 in-band (per-format error frames) instead of closing silently