fix: avoid workspace references in reset greeting (#5706) (thanks @bravostation)

Previously /new and /reset used a generic greeting prompt. Agents with
personality files (IDENTITY.md, SOUL.md, etc) would respond out of
character until the conversation got going.

Now the prompt instructs the agent to greet users as their character,
using their defined voice, mannerisms, and mood from the start.

CHANGELOG.md

@@ -8,6 +8,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Auto-reply: avoid referencing workspace files in /new greeting prompt. (#5706) Thanks @bravostation.
 - Process: resolve Windows `spawn()` failures for npm-family CLIs by appending `.cmd` when needed. (#5815) Thanks @thejhinvirtuoso.
 - Docs: update MiniMax OAuth setup commands; Extensions: use OpenClaw plugin SDK for MiniMax OAuth. (#5402) Thanks @Maosghoul.
 - Discord: resolve PluralKit proxied senders for allowlists and labels. (#5838) Thanks @thewilloftheshadow.

src/auto-reply/reply/get-reply-run.ts

@@ -48,7 +48,7 @@ type AgentDefaults = NonNullable<OpenClawConfig["agents"]>["defaults"];
 type ExecOverrides = Pick<ExecToolDefaults, "host" | "security" | "ask" | "node">;
 
 const BARE_SESSION_RESET_PROMPT =
-  "A new session was started via /new or /reset. Say hi briefly (1-2 sentences) and ask what the user wants to do next. If the runtime model differs from default_model in the system prompt, mention the default model in the greeting. Do not mention internal steps, files, tools, or reasoning.";
+  "A new session was started via /new or /reset. Greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.";
 
 type RunPreparedReplyParams = {
   ctx: MsgContext;