From 6d48469094a588f0fcea41a5219f03b84bd4f133 Mon Sep 17 00:00:00 2001
From: Christian Boos <christian.boos@bct-technology.com>
Date: Sun, 7 Jun 2026 19:01:16 +0200
Subject: [PATCH] Dedupe "unrecognized message type" warnings per file

These warnings repeat heavily within a transcript (the same type can
appear dozens of times), flooding the output. Emit at most one warning
per distinct unrecognized type per file by tracking which types have
already been warned about.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 claude_code_log/converter.py |  8 +++++++-
 test/test_silent_skip.py     | 26 ++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/claude_code_log/converter.py b/claude_code_log/converter.py
index 86fe6702..f21e2868 100644
--- a/claude_code_log/converter.py
+++ b/claude_code_log/converter.py
@@ -262,6 +262,9 @@ def load_transcript(
     # Parse from source file
     messages: list[TranscriptEntry] = []
     agent_ids: set[str] = set()  # Collect agentId references while parsing
+    # Track unrecognized message types already warned about so we emit at
+    # most one warning per distinct type per file (these tend to repeat a lot).
+    warned_unrecognized_types: set[str | None] = set()
 
     try:
         f = open(jsonl_path, "r", encoding="utf-8", errors="replace")
@@ -347,7 +350,10 @@ def load_transcript(
                         # agent-name). Warn so we notice when Claude Code
                         # introduces new metadata worth supporting — add to
                         # SILENT_SKIP_TYPES once confirmed safe to drop.
-                        if not silent:
+                        # Only warn on the first occurrence of each distinct
+                        # type per file to avoid flooding the output.
+                        if not silent and entry_type not in warned_unrecognized_types:
+                            warned_unrecognized_types.add(entry_type)
                             print(
                                 f"Line {line_no} of {jsonl_path}: unrecognized message type "
                                 f"{entry_type!r} - skipping"
diff --git a/test/test_silent_skip.py b/test/test_silent_skip.py
index f2d66fe8..b892d9de 100644
--- a/test/test_silent_skip.py
+++ b/test/test_silent_skip.py
@@ -180,6 +180,32 @@ def test_unknown_without_uuid_warns(
         assert "unrecognized message type" in captured.out
         assert repr(entry["type"]) in captured.out
 
+    def test_repeated_unknown_type_warns_only_once(
+        self, tmp_path: Path, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """The same unrecognized type repeated within a file warns once,
+        but each distinct type still gets its own first-occurrence warning."""
+        jsonl = tmp_path / "session.jsonl"
+        _write_jsonl(
+            jsonl,
+            [
+                {"type": "mode", "payload": 1},
+                {"type": "pr-link", "url": "x"},
+                {"type": "mode", "payload": 2},
+                {"type": "pr-link", "url": "y"},
+                {"type": "mode", "payload": 3},
+            ],
+        )
+
+        messages = load_transcript(jsonl, silent=False)
+        captured = capsys.readouterr()
+
+        assert messages == []
+        # One warning per distinct type, not per occurrence.
+        assert captured.out.count("unrecognized message type") == 2
+        assert captured.out.count("'mode'") == 1
+        assert captured.out.count("'pr-link'") == 1
+
     def test_silent_mode_suppresses_warning(
         self, tmp_path: Path, capsys: pytest.CaptureFixture[str]
     ) -> None: