Remove request wrapper migration (#64)

* [1/n] migrate inference/chat_completion

* migrate inference/completion

* inference/completion

* inference regenerate openapi spec

* safety api

* migrate agentic system

* migrate apis without implementations

* re-generate openapi spec

* remove hack from openapi generator

* fix inference

* fix inference

* openapi generator rerun

* Simplified Telemetry API and tying it to logger (#57)

* Simplified Telemetry API and tying it to logger

* small update which adds a METRIC type

* move span events one level down into structured log events

---------

Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

* fix api to work with openapi generator

* fix agentic calling inference

* together adapter inference

* update inference adapters

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

llama_toolchain/agentic_system/meta_reference/agent_instance.py

@@ -388,19 +388,17 @@ class ChatAgent(ShieldRunnerMixin):
                 )
             )
 
-            req = ChatCompletionRequest(
-                model=self.agent_config.model,
-                messages=input_messages,
+            tool_calls = []
+            content = ""
+            stop_reason = None
+            async for chunk in self.inference_api.chat_completion(
+                self.agent_config.model,
+                input_messages,
                 tools=self._get_tools(),
                 tool_prompt_format=self.agent_config.tool_prompt_format,
                 stream=True,
                 sampling_params=sampling_params,
-            )
-
-            tool_calls = []
-            content = ""
-            stop_reason = None
-            async for chunk in self.inference_api.chat_completion(req):
+            ):
                 event = chunk.event
                 if event.event_type == ChatCompletionResponseEventType.start:
                     continue