feat: support OpenAI Flex Processing via [litellm] extra_body config

docs/docs/usage-guide/changing_a_model.md

@@ -32,6 +32,16 @@ OPENAI__API_BASE=https://api.openai.com/v1
 OPENAI__KEY=sk-...
 ```
 
+### OpenAI Flex Processing
+
+To reduce costs for non-urgent/background tasks, enable Flex Processing:
+
+```toml
+[litellm]
+extra_body='{"processing_mode": "flex"}'
+```
+
+See [OpenAI Flex Processing docs](https://platform.openai.com/docs/guides/flex-processing) for details.
 
 ### Azure
 

pr_agent/algo/ai_handlers/litellm_ai_handler.py

@@ -364,6 +364,16 @@ class LiteLLMAIHandler(BaseAiHandler):
                     raise ValueError(f"LITELLM.EXTRA_HEADERS contains invalid JSON: {str(e)}")
                 kwargs["extra_headers"] = litellm_extra_headers
 
+            # Support for custom OpenAI body fields (e.g., Flex Processing)
+            if get_settings().get("LITELLM.EXTRA_BODY", None):
+                try:
+                    litellm_extra_body = json.loads(get_settings().litellm.extra_body)
+                    if not isinstance(litellm_extra_body, dict):
+                        raise ValueError("LITELLM.EXTRA_BODY must be a JSON object")
+                    kwargs.update(litellm_extra_body)
+                except json.JSONDecodeError as e:
+                    raise ValueError(f"LITELLM.EXTRA_BODY contains invalid JSON: {str(e)}")
+
             get_logger().debug("Prompts", artifact={"system": system, "user": user})
 
             if get_settings().config.verbosity_level >= 2:

pr_agent/settings/.secrets_template.toml

@@ -16,6 +16,10 @@ key = ""  # Acquire through https://platform.openai.com
 #deployment_id = ""  # The deployment name you chose when you deployed the engine
 #fallback_deployments = []  # For each fallback model specified in configuration.toml in the [config] section, specify the appropriate deployment_id
 
+# OpenAI Flex Processing (optional, for cost savings)
+# [litellm]
+# extra_body='{"processing_mode": "flex"}'
+
 [pinecone]
 api_key = "..."
 environment = "gcp-starter"