refactor(memory): reuse _summarize_user_message_for_log instead of forking it

The original fix added agent/memory_manager.py:flatten_message_content, but
that helper was a near-exact duplicate of
agent/codex_responses_adapter.py:_summarize_user_message_for_log — same
None/str/list dispatch, same {text,input_text,output_text}/{image_url,input_image}
part sets, the identical [N image(s)] marker, and the same str() fallback. The
only difference was the join separator (newline for memory vs space for the
log/trajectory previews the existing helper already serves), and that helper is
already imported into agent/turn_finalizer.py — the same file whose call site the
memory fix touches.

Parameterize the existing helper with sep=' ' (default preserves every current
logging/trajectory caller byte-for-byte) and call it with sep='\n' at the memory
boundary; drop the forked flatten_message_content. Repoints the unit tests to the
consolidated helper and adds a case locking the default space-join.

Single source of truth for multimodal-content flattening; no behavior change for
the fix or for existing callers.

agent/codex_responses_adapter.py

@@ -127,14 +127,21 @@ def _chat_content_to_responses_parts(content: Any, *, role: str = "user") -> Lis
     return converted
 
 
-def _summarize_user_message_for_log(content: Any) -> str:
-    """Return a short text summary of a user message for logging/trajectory.
+def _summarize_user_message_for_log(content: Any, *, sep: str = " ") -> str:
+    """Flatten message content to a plain-text summary.
 
     Multimodal messages arrive as a list of ``{type:"text"|"image_url", ...}``
-    parts from the API server.  Logging, spinner previews, and trajectory
-    files all want a plain string — this helper extracts the first chunk of
-    text and notes any attached images.  Returns an empty string for empty
-    lists and ``str(content)`` for unexpected scalar types.
+    parts from the API server.  Several consumers want a plain string:
+
+    - Logging, spinner previews, and trajectory files (the default ``sep=" "``).
+    - External memory providers, which feed the text to regexes
+      (``sanitize_context``) and text APIs — a raw list crashes the sync with
+      ``expected string or bytes-like object, got 'list'`` (use ``sep="\\n"``).
+
+    Text parts are joined with ``sep``; images become a ``[N image(s)]`` marker
+    so the turn isn't recorded as if the attachment never existed.  Returns an
+    empty string for empty lists and ``str(content)`` for unexpected scalar
+    types.
     """
     if content is None:
         return ""
@@ -157,7 +164,7 @@ def _summarize_user_message_for_log(content: Any) -> str:
                     text_bits.append(text)
             elif ptype in {"image_url", "input_image"}:
                 image_count += 1
-        summary = " ".join(text_bits).strip()
+        summary = sep.join(text_bits).strip()
         if image_count:
             note = f"[{image_count} image{'s' if image_count != 1 else ''}]"
             summary = f"{note} {summary}" if summary else note

agent/memory_manager.py

@@ -67,45 +67,6 @@ def sanitize_context(text: str) -> str:
     return text
 
 
-def flatten_message_content(content: Any) -> str:
-    """Flatten message content to plain text for memory providers.
-
-    Multimodal turns carry content as a list of ``{type: "text"|"image_url",
-    ...}`` parts; providers expect a string and feed it to regexes
-    (``sanitize_context``) and text APIs, so a list crashes the sync
-    (``expected string or bytes-like object, got 'list'``). Text parts are
-    joined, images become a ``[N image(s)]`` marker so the turn isn't
-    recorded as if the attachment never existed.
-    """
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        text_bits: List[str] = []
-        image_count = 0
-        for part in content:
-            if isinstance(part, str):
-                if part:
-                    text_bits.append(part)
-                continue
-            if not isinstance(part, dict):
-                continue
-            ptype = str(part.get("type") or "").strip().lower()
-            if ptype in {"text", "input_text", "output_text"}:
-                text = part.get("text")
-                if isinstance(text, str) and text:
-                    text_bits.append(text)
-            elif ptype in {"image_url", "input_image"}:
-                image_count += 1
-        flattened = "\n".join(text_bits).strip()
-        if image_count:
-            note = f"[{image_count} image{'s' if image_count != 1 else ''}]"
-            flattened = f"{note} {flattened}" if flattened else note
-        return flattened
-    return str(content)
-
-
 class StreamingContextScrubber:
     """Stateful scrubber for streaming text that may contain split memory-context spans.