From c3be6ec184e0f17a184eaff1018051b47a89eeb7 Mon Sep 17 00:00:00 2001
From: BarnacleBoy <barnacleboy.jezzahehn@agentmail.to>
Date: Wed, 6 May 2026 15:44:19 +0000
Subject: [PATCH] feat: add transform_llm_output plugin hook

Enables plugins to transform LLM output text after generation,
useful for vocabulary/personality transformation without burning
inference tokens.

Follows same pattern as transform_tool_result and transform_terminal_output:
- First non-empty string result wins
- Fail-open: exceptions logged as warnings, agent continues
- Signature: (response_text, session_id, model, platform)
---
 hermes_cli/plugins.py |  4 ++++
 run_agent.py          | 21 +++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/hermes_cli/plugins.py b/hermes_cli/plugins.py
index 5b30e7e7ca..1267457737 100644
--- a/hermes_cli/plugins.py
+++ b/hermes_cli/plugins.py
@@ -80,6 +80,10 @@ VALID_HOOKS: Set[str] = {
     "post_tool_call",
     "transform_terminal_output",
     "transform_tool_result",
+    # Transform LLM output before it's returned to the user.
+    # Plugins return a string to replace the response text, or None/empty to leave unchanged.
+    # First non-None string wins. Useful for vocabulary/personality transformation.
+    "transform_llm_output",
     "pre_llm_call",
     "post_llm_call",
     "pre_api_request",
diff --git a/run_agent.py b/run_agent.py
index 919a5875b6..54b0ebccb8 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -14035,6 +14035,27 @@ class AIAgent:
         else:
             logger.info(_diag_msg, *_diag_args)
 
+        # Plugin hook: transform_llm_output
+        # Fired once per turn after the tool-calling loop completes.
+        # Plugins can transform the LLM's output text before it's returned.
+        # First hook to return a string wins; None/empty return leaves text unchanged.
+        if final_response and not interrupted:
+            try:
+                from hermes_cli.plugins import invoke_hook as _invoke_hook
+                _transform_results = _invoke_hook(
+                    "transform_llm_output",
+                    response_text=final_response,
+                    session_id=self.session_id or "",
+                    model=self.model,
+                    platform=getattr(self, "platform", None) or "",
+                )
+                for _hook_result in _transform_results:
+                    if isinstance(_hook_result, str) and _hook_result:
+                        final_response = _hook_result
+                        break  # First non-empty string wins
+            except Exception as exc:
+                logger.warning("transform_llm_output hook failed: %s", exc)
+
         # Plugin hook: post_llm_call
         # Fired once per turn after the tool-calling loop completes.
         # Plugins can use this to persist conversation data (e.g. sync