Document why HTTP variant doesn't use previous_response_id

Over HTTP, previous_response_id requires store=True (30-day OpenAI-side
conversation storage). The WebSocket variant avoids this via a
connection-local in-memory cache that works with store=False. Add
comments explaining this in both class docstrings, at the store=False
parameter, and in the adapter's previous_response_id note.

src/pipecat/adapters/services/open_ai_responses_adapter.py

@@ -95,12 +95,11 @@ class OpenAIResponsesLLMAdapter(BaseLLMAdapter[OpenAIResponsesLLMInvocationParam
             # If we added support for user-provided explicit
             # `previous_response_id` and/or `conversation_id` (overriding
             # internal management), we'd need to revisit this logic, as it'd
-            # be legit to provide instructions without input items. Worth
-            # noting that OpenAI's docs suggest these parameters are primarily
-            # for development convenience rather than performance (the model
-            # still processes the full context), and come with the tradeoff
-            # of requiring OpenAI-side 30-day conversation storage, which may
-            # not be desirable for many users.
+            # be legit to provide instructions without input items. Note that
+            # over HTTP, `previous_response_id` requires `store=True` (30-day
+            # OpenAI-side storage), which is why the HTTP variant doesn't use
+            # it. The WebSocket variant avoids this via a connection-local
+            # in-memory cache — see the class docstrings in llm.py.
             if not input_items:
                 params["input"] = [{"role": "developer", "content": system_instruction}]
             else:

src/pipecat/services/openai/responses/llm.py

@@ -223,6 +223,10 @@ class _BaseOpenAIResponsesLLMService(LLMService):
         params: Dict[str, Any] = {
             "model": self._settings.model,
             "stream": True,
+            # store=False avoids OpenAI-side 30-day conversation storage.
+            # The WebSocket variant's previous_response_id optimization
+            # still works with store=False because it uses a connection-local
+            # in-memory cache. See the class docstrings for details.
             "store": False,
             "input": invocation_params["input"],
         }
@@ -337,6 +341,13 @@ class OpenAIResponsesLLMService(_BaseOpenAIResponsesLLMService):
     Automatically uses ``previous_response_id`` to send only incremental context when
     possible, and falls back to full context on reconnection or cache miss.
 
+    The ``previous_response_id`` optimization works with ``store=False`` (the default)
+    because WebSocket mode uses a connection-local in-memory cache — no conversations
+    are stored on OpenAI's servers.  This is why the HTTP variant
+    (``OpenAIResponsesHttpLLMService``) does not offer this optimization by default
+    (or at all, yet): over HTTP, ``previous_response_id`` requires ``store=True``,
+    which enables OpenAI-side 30-day conversation storage.
+
     This is the recommended variant for real-time / conversational use.
 
     Example::
@@ -856,6 +867,15 @@ class OpenAIResponsesHttpLLMService(_BaseOpenAIResponsesLLMService):
     Uses server-sent events (SSE) via the OpenAI Python SDK for streaming
     inference. Each ``_process_context`` call opens a new HTTP connection.
 
+    Unlike the WebSocket variant, this service does not use
+    ``previous_response_id`` for incremental context delivery by default
+    (or at all, yet).  Over HTTP, ``previous_response_id`` requires
+    ``store=True``, which enables OpenAI-side 30-day conversation storage
+    — a privacy/compliance tradeoff that many users won't want.  The
+    WebSocket variant avoids this because its ``previous_response_id``
+    uses a connection-local in-memory cache that works with
+    ``store=False`` (nothing is stored long-term).
+
     Example::
 
         llm = OpenAIResponsesHttpLLMService(