Remove Langfuse Dependency for Session ID Grouping in Response API

Currently, in the Response API, we derive the session_id from Langfuse by querying it using the previous response_id, as shown below:

if response_id:
    traces = self.langfuse.fetch_traces(tags=response_id).data
    if traces:
        self.session_id = traces[0].session_id

This approach introduces an unnecessary runtime dependency on Langfuse, solely to group related traces under the same session for visualization purposes.

OpenAI does not currently provide a native conversation ID for API responses, which complicates session tracking.
We are in discussions with OpenAI to potentially add support for a conversation_id or similar identifier at their end which we can pass to langfuse as session_id.

Alternative: Maintain the session or conversation-level grouping within the Glific flow context itself, so that Langfuse becomes an observer rather than a source of truth for session identity.

L'issue identifica il percorso della Response API e la ricerca delle trace Langfuse esistente come punto di ingresso; non viene indicato alcun file o test. Per prima cosa individua dove vengono gestiti response_id e session_id, quindi verifica che il raggruppamento delle sessioni rimanga coerente senza una ricerca Langfuse a runtime.