From 3ae5eabf9de84e7200af4a486a50276a7b11c7c8 Mon Sep 17 00:00:00 2001
From: Swifty <craigswift13@gmail.com>
Date: Thu, 5 Feb 2026 14:54:39 +0100
Subject: [PATCH] fix(backend/chat): Use latest prompt label in non-production
 environments (#11977)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In non-production environments, the chat service now fetches prompts
with the `latest` label instead of the default production-labeled
prompt. This makes it easier to test and iterate on prompt changes in
dev/staging without needing to promote them to production first.

### Changes 🏗️

- Updated `_get_system_prompt_template()` in chat service to pass
`label="latest"` when `app_env` is not `PRODUCTION`
- Production environments continue using the default behavior
(production-labeled prompts)

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified that in non-production environments, prompts with
`latest` label are fetched
- [x] Verified that production environments still use the default
(production) labeled prompts

Co-authored-by: Otto <otto@agpt.co>
---
 .../backend/backend/api/features/chat/service.py   | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/autogpt_platform/backend/backend/api/features/chat/service.py b/autogpt_platform/backend/backend/api/features/chat/service.py
index bf7dbb6c7e..06da6bdf2b 100644
--- a/autogpt_platform/backend/backend/api/features/chat/service.py
+++ b/autogpt_platform/backend/backend/api/features/chat/service.py
@@ -33,7 +33,7 @@ from backend.data.understanding import (
     get_business_understanding,
 )
 from backend.util.exceptions import NotFoundError
-from backend.util.settings import Settings
+from backend.util.settings import AppEnvironment, Settings
 
 from . import db as chat_db
 from . import stream_registry
@@ -222,8 +222,18 @@ async def _get_system_prompt_template(context: str) -> str:
         try:
             # cache_ttl_seconds=0 disables SDK caching to always get the latest prompt
             # Use asyncio.to_thread to avoid blocking the event loop
+            # In non-production environments, fetch the latest prompt version
+            # instead of the production-labeled version for easier testing
+            label = (
+                None
+                if settings.config.app_env == AppEnvironment.PRODUCTION
+                else "latest"
+            )
             prompt = await asyncio.to_thread(
-                langfuse.get_prompt, config.langfuse_prompt_name, cache_ttl_seconds=0
+                langfuse.get_prompt,
+                config.langfuse_prompt_name,
+                label=label,
+                cache_ttl_seconds=0,
             )
             return prompt.compile(users_information=context)
         except Exception as e: