fix: stop treating empty content as NO_REPLY, detect tool calls

Problems fixed:
1. before_message_write treated empty content (isEmpty) as NO_REPLY.
   Tool-call-only assistant messages (thinking + toolCall, no text)
   had empty extracted text, causing false NO_REPLY detection.
   In single-agent channels this immediately set turn to dormant,
   blocking all subsequent responses for the entire model run.

2. Added explicit toolCall/tool_call/tool_use detection in
   before_message_write — skip turn processing for intermediate
   tool-call messages entirely.

3. no-reply-api/server.mjs: default model name changed from
   'dirigent-no-reply-v1' to 'no-reply' to match the configured
   model id in openclaw.json, fixing model list discovery.

Changes:
- plugin/hooks/before-message-write.ts: toolCall detection + remove isEmpty
- plugin/hooks/message-sent.ts: remove isEmpty from wasNoReply
- no-reply-api/server.mjs: fix default model name
- dist/dirigent/index.ts: same fixes applied to monolithic build
- dist/no-reply-api/server.mjs: same model name fix

no-reply-api/server.mjs

@@ -1,7 +1,7 @@
 import http from "node:http";
 
 const port = Number(process.env.PORT || 8787);
-const modelName = process.env.NO_REPLY_MODEL || "dirigent-no-reply-v1";
+const modelName = process.env.NO_REPLY_MODEL || "no-reply";
 const authToken = process.env.AUTH_TOKEN || "";
 
 function sendJson(res, status, payload) {