feat: collect agent response per cycle (#46)

Author: ottokruse

README.md

@@ -651,6 +651,7 @@ In the OpenTelemetry Span model, information such as "the model ID used for the
 | `ai.tool.input`                                        | The input parameters provided to the tool                                                                                                                                                         |
 | `ai.tool.output`                                       | The response/output from the tool invocation                                                                                                                                                      |
 | `ai.tool.error`                                        | Error information if tool invocation fails                                                                                                                                                        |
+| `ai.tool.error.traceback`                              | Full Python traceback information when tool invocation fails                                                                                                                                      |
 | `ai.user.input`                                        | The input provided by the user in the conversation                                                                                                                                                |
 | `ai.llm.request.inference.config`                      | Configuration settings for the LLM inference                                                                                                                                                      |
 | `ai.llm.request.messages`                              | Messages being sent to the LLM                                                                                                                                                                    |
@@ -671,6 +672,9 @@ In the OpenTelemetry Span model, information such as "the model ID used for the
 | `ai.llm.response.trace`                                | Trace information                                                                                                                                                                                 |
 | `ai.llm.response.performance.config`                   | The performance config                                                                                                                                                                            |
 | `ai.agent.response`                                    | The final concatenated response from the agent                                                                                                                                                    |
+| `ai.agent.cycle.nr`                                    | The cycle number during agent conversation processing, indicating which iteration of the conversation loop is being executed                                                                      |
+| `ai.agent.cycle.response`                              | The agent's response text for a specific cycle/iteration during conversation processing                                                                                                           |
+| `ai.conversation.aborted`                              | Boolean flag indicating whether the conversation was aborted due to a stop event                                                                                                                  |
 | `service.name`                                         | Name of the service, set to the class name of the agent                                                                                                                                           |
 
 ##### Viewing traces