Python: Fix _deduplicate_messages catch-all branch dropping valid repeated messages (#4716)

* Fix _deduplicate_messages catch-all branch dropping valid repeated messages (#4682)

Remove the catch-all dedup branch that used (role, hash(content_str)) as a
dedup key. This incorrectly treated any two messages with the same role and
identical content as duplicates, dropping valid repeated messages (e.g., a
user saying 'yes' to confirm two separate things).

The tool-specific dedup branches (tool results by call_id, assistant tool
calls by call_id tuple) remain unchanged as they correctly identify true
protocol-level duplicates.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review: consecutive-duplicate detection for non-tool messages (#4682)

- Replace blanket dedup removal with consecutive-duplicate detection:
  only skip a message if the immediately preceding message has the same
  role and content, preserving protection against upstream replays while
  allowing identical messages at different conversation points.
- Strengthen test assertions to verify message identity and order, not
  just list length.
- Add tests for consecutive duplicate skipping, non-consecutive
  preservation, and messages with contents=None.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Apply pre-commit auto-fixes

* Use message_id for deduplication instead of content hashing

Deduplicate general messages by message_id when available, replacing
the consecutive-duplicate content check. Two messages with the same id
are definitively the same message (upstream replay), while identical
content with distinct ids (e.g. repeated "yes" confirmations) is
preserved. Messages without a message_id are always kept.

* Fix message_id dedup: truthy check, content-hash fallback, log safety

- Use truthy check (`if msg.message_id`) instead of `is not None` so
  empty-string IDs fall through to content-hash dedup rather than
  collapsing unrelated messages.
- Add content-hash fallback for messages without message_id, preventing
  false negatives from integrations that don't set IDs.
- Remove raw message_id from log format string (addresses log-injection
  surface with control characters).
- Add tests for empty-string message_id edge cases.
- Update existing tests to reflect content-hash dedup behavior.

Fixes #4682

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

python/packages/ag-ui/agent_framework_ag_ui/_message_adapters.py

@@ -242,8 +242,16 @@ def _deduplicate_messages(messages: list[Message]) -> list[Message]:
             unique_messages.append(msg)
 
         else:
-            content_str = str([str(c) for c in msg.contents]) if msg.contents else ""
-            key = (role_value, hash(content_str))
+            # Use message_id for deduplication when available — two messages with the
+            # same id are definitively the same message (e.g. upstream replays), while
+            # different messages that happen to share identical content (e.g. repeated
+            # "yes" confirmations) will have distinct ids and be preserved.
+            # Fall back to content-hash when message_id is absent or empty.
+            if msg.message_id:
+                key = ("id", msg.message_id)
+            else:
+                content_str = str([str(c) for c in msg.contents]) if msg.contents else ""
+                key = ("content", role_value, hash(content_str))
 
             if key in seen_keys:
                 logger.info(f"Skipping duplicate message at index {idx}: role={role_value}")

python/packages/ag-ui/tests/ag_ui/test_message_adapters.py

@@ -1015,15 +1015,111 @@ def test_deduplicate_assistant_tool_calls():
     assert len(result) == 1
 
 
-def test_deduplicate_general_messages():
-    """Duplicate general user messages are deduplicated."""
+def test_deduplicate_by_message_id():
+    """Messages with the same message_id are deduplicated."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msg1 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg1.message_id = "msg-1"
+    msg2 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg2.message_id = "msg-1"
+
+    result = _deduplicate_messages([msg1, msg2])
+    assert len(result) == 1
+    assert result == [msg1]
+
+
+def test_deduplicate_preserves_repeated_confirmations_with_distinct_ids():
+    """Identical content with different message_ids is preserved."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    assistant = Message(role="assistant", contents=[Content.from_text(text="Are you sure?")])
+    assistant.message_id = "msg-1"
+    confirm1 = Message(role="user", contents=[Content.from_text(text="yes")])
+    confirm1.message_id = "msg-2"
+    confirm2 = Message(role="user", contents=[Content.from_text(text="yes")])
+    confirm2.message_id = "msg-3"
+
+    result = _deduplicate_messages([confirm1, assistant, confirm2])
+    assert result == [confirm1, assistant, confirm2]
+
+
+def test_deduplicate_preserves_repeated_system_messages_with_distinct_ids():
+    """Non-consecutive identical system messages with different ids are preserved."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    sys1 = Message(role="system", contents=[Content.from_text(text="You are a helpful assistant.")])
+    sys1.message_id = "msg-1"
+    user_msg = Message(role="user", contents=[Content.from_text(text="Hi")])
+    user_msg.message_id = "msg-2"
+    sys2 = Message(role="system", contents=[Content.from_text(text="You are a helpful assistant.")])
+    sys2.message_id = "msg-3"
+
+    result = _deduplicate_messages([sys1, user_msg, sys2])
+    assert result == [sys1, user_msg, sys2]
+
+
+def test_deduplicate_skips_replayed_system_messages_with_same_id():
+    """System messages replayed with the same message_id are deduplicated."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msgs = []
+    for _ in range(3):
+        m = Message(role="system", contents=[Content.from_text(text="You are a helpful assistant.")])
+        m.message_id = "msg-1"
+        msgs.append(m)
+
+    result = _deduplicate_messages(msgs)
+    assert len(result) == 1
+
+
+def test_deduplicate_without_message_id_uses_content_hash():
+    """Messages without message_id are deduplicated by content hash."""
     from agent_framework_ag_ui._message_adapters import _deduplicate_messages
 
     msg1 = Message(role="user", contents=[Content.from_text(text="Hello")])
     msg2 = Message(role="user", contents=[Content.from_text(text="Hello")])
 
     result = _deduplicate_messages([msg1, msg2])
-    assert len(result) == 1
+    assert result == [msg1]
+
+
+def test_deduplicate_without_message_id_preserves_different_content():
+    """Messages without message_id but different content are preserved."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msg1 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg2 = Message(role="user", contents=[Content.from_text(text="World")])
+
+    result = _deduplicate_messages([msg1, msg2])
+    assert result == [msg1, msg2]
+
+
+def test_deduplicate_handles_none_contents():
+    """Messages with contents=None pass through without errors; duplicates are deduped."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msg1 = Message(role="user", contents=None)
+    msg2 = Message(role="assistant", contents=[Content.from_text(text="Hello")])
+    msg3 = Message(role="user", contents=None)
+
+    result = _deduplicate_messages([msg1, msg2, msg3])
+    assert result == [msg1, msg2]
+
+
+def test_deduplicate_mixed_id_and_no_id():
+    """Messages with and without message_id coexist correctly."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msg1 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg1.message_id = "msg-1"
+    msg2 = Message(role="user", contents=[Content.from_text(text="Hello")])  # no id
+    msg3 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg3.message_id = "msg-1"  # duplicate of msg1
+
+    result = _deduplicate_messages([msg1, msg2, msg3])
+    assert len(result) == 2
+    assert result == [msg1, msg2]
 
 
 def test_deduplicate_replaces_empty_tool_result():
@@ -1038,7 +1134,30 @@ def test_deduplicate_replaces_empty_tool_result():
     assert result[0].contents[0].result == "actual result"
 
 
-# ── Multimodal & content conversion edge cases ──
+def test_deduplicate_empty_string_message_id_falls_back_to_content_hash():
+    """Empty-string message_id is treated as missing; content-hash dedup is used."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msg1 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg1.message_id = ""
+    msg2 = Message(role="user", contents=[Content.from_text(text="World")])
+    msg2.message_id = ""
+
+    result = _deduplicate_messages([msg1, msg2])
+    assert result == [msg1, msg2], "Different content with empty IDs should both be preserved"
+
+
+def test_deduplicate_empty_string_message_id_deduplicates_same_content():
+    """Empty-string message_id with identical content should be deduplicated."""
+    from agent_framework_ag_ui._message_adapters import _deduplicate_messages
+
+    msg1 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg1.message_id = ""
+    msg2 = Message(role="user", contents=[Content.from_text(text="Hello")])
+    msg2.message_id = ""
+
+    result = _deduplicate_messages([msg1, msg2])
+    assert result == [msg1], "Same content with empty IDs should be deduplicated"
 
 
 def test_convert_agui_content_unknown_source_type_fallback():