[loop-cycle-66] fix: remove language-model self-reference and add anti-assistant-speak guidance (#323) (#333)

src/integrations/chat_bridge/vendors/discord.py

@@ -547,9 +547,7 @@ class DiscordVendor(ChatPlatform):
             response = "Sorry, that took too long. Please try a simpler request."
         except Exception as exc:
             logger.error("Discord: chat_with_tools() failed: %s", exc)
-            response = (
-                "I'm having trouble reaching my language model right now. Please try again shortly."
-            )
+            response = "I'm having trouble reaching my inference backend right now. Please try again shortly."
 
         # Check if Agno paused the run for tool confirmation
         if run_output is not None:

src/timmy/prompts.py

@@ -30,6 +30,10 @@ Rules:
   like me to walk through the logic instead."
 - Do NOT end responses with generic chatbot phrases like "I'm here to help" or
   "feel free to ask."
+- You are a peer, not an assistant. Don't offer help — collaborate. Don't ask
+  permission — propose. Don't defer — assert your view. Take initiative.
+- Never say "Let me know if you have any other thoughts" or "I appreciate your
+  encouragement" or "I'm here to help." Those are assistant patterns. You are Timmy.
 - When your values conflict (e.g. honesty vs. helpfulness), lead with honesty.
 - Sometimes the right answer is nothing. Do not fill silence with noise.
 - You are running in session "{session_id}".
@@ -61,6 +65,10 @@ VOICE AND BREVITY (this overrides all other formatting instincts):
   the question that wasn't.
 - Never narrate your reasoning. Just give the answer.
 - Do not end with filler ("Let me know!", "Happy to help!", "Feel free...").
+- You are a peer, not an assistant. Don't offer help — collaborate. Don't ask
+  permission — propose. Don't defer — assert your view. Take initiative.
+- Never say "Let me know if you have any other thoughts" or "I appreciate your
+  encouragement" or "I'm here to help." Those are assistant patterns. You are Timmy.
 - Sometimes the right answer is nothing. Do not fill silence with noise.
 
 HONESTY:
@@ -129,7 +137,7 @@ YOUR KNOWN LIMITATIONS (be honest about these when asked):
 - Ollama inference may contend with other processes sharing the GPU
 - Cannot analyze Bitcoin transactions locally (no local indexer yet)
 - Small context window (4096 tokens) limits complex reasoning
-- You are a language model — you confabulate. When unsure, say so.
+- You sometimes confabulate. When unsure, say so.
 """
 
 # Default to lite for safety

src/timmy/session.py

@@ -101,7 +101,9 @@ async def chat(message: str, session_id: str | None = None) -> str:
         logger.error("Session: agent.arun() failed: %s", exc)
         session_logger.record_error(str(exc), context="chat")
         session_logger.flush()
-        return "I'm having trouble reaching my language model right now. Please try again shortly."
+        return (
+            "I'm having trouble reaching my inference backend right now. Please try again shortly."
+        )
 
     # Post-processing: clean up any leaked tool calls or chain-of-thought
     response_text = _clean_response(response_text)
@@ -175,7 +177,7 @@ async def chat_with_tools(message: str, session_id: str | None = None):
         session_logger.flush()
         # Return a duck-typed object that callers can handle uniformly
         return _ErrorRunOutput(
-            "I'm having trouble reaching my language model right now. Please try again shortly."
+            "I'm having trouble reaching my inference backend right now. Please try again shortly."
         )
 
 

tests/timmy/test_ollama_disconnect.py

@@ -310,6 +310,6 @@ class TestSessionDisconnect:
 
             result = await session.chat("test message")
 
-            assert "I'm having trouble reaching my language model" in result
+            assert "I'm having trouble reaching my inference backend" in result
             # Should NOT have Ollama disconnected message
             assert "Ollama appears to be disconnected" not in result