fix: streaming tool call parsing, error handling, and fake HA state mutation

- Fix Gemini streaming tool call merge bug: multiple tool calls with same
  index but different IDs are now parsed as separate calls instead of
  concatenating names (e.g. ha_call_serviceha_call_service)
- Handle partial results in voice mode: show error and stop continuous
  mode when agent returns partial/failed results with empty response
- Fix error display during streaming TTS: error messages are shown in
  full response box even when streaming box was already opened
- Add duplicate sentence filter in TTS: skip near-duplicate sentences
  from LLM repetition
- Fix fake HA server state mutation: turn_on/turn_off/set_temperature
  correctly update entity states; temperature sensor simulates change
  when thermostat is adjusted

cli.py

@@ -4238,8 +4238,10 @@ class HermesCLI:
             # Get the final response
             response = result.get("final_response", "") if result else ""
 
-            # Handle failed results (e.g., non-retryable errors like invalid model)
-            if result and result.get("failed") and not response:
+            # Handle failed or partial results (e.g., non-retryable errors, rate limits,
+            # truncated output, invalid tool calls). Both "failed" and "partial" with
+            # an empty final_response mean the agent couldn't produce a usable answer.
+            if result and (result.get("failed") or result.get("partial")) and not response:
                 error_detail = result.get("error", "Unknown error")
                 response = f"Error: {error_detail}"
                 # Stop continuous voice mode on persistent errors (e.g. 429 rate limit)