fix(langfuse): redact base64 data URIs instead of truncating into invalid base64

The Langfuse SDK treats `data:*;base64,...` strings as media and tries to
decode them. `_truncate_text` was slicing those strings mid-payload, producing
invalid base64 and noisy "Error parsing base64 data URI" logs. Observability
only needs the metadata, not raw image/audio bytes, so redact the whole data
URI (type, media_type, length) before it reaches the SDK.

Salvaged the Langfuse fix from #39682 onto current main as a standalone,
single-concern change (the dashboard `dist/**` and plugin-discovery parts of
that PR already landed separately on main).

Co-authored-by: foras910521-lab <foras910521-lab@users.noreply.github.com>
This commit is contained in:
kshitijk4poor
2026-06-10 10:49:36 +05:30
co-authored by foras910521-lab
parent bf7abc2f73
commit 4642762289
2 changed files with 58 additions and 1 deletions
+34
View File
@@ -171,6 +171,40 @@ class TestHooksInert:
mod.on_post_tool_call(tool_name="read_file", args={}, result="ok", task_id="t", session_id="s")
class TestPayloadSanitization:
def test_safe_value_redacts_base64_data_uri_instead_of_truncating(self):
sys.modules.pop("plugins.observability.langfuse", None)
import importlib
mod = importlib.import_module("plugins.observability.langfuse")
payload = "data:image/png;base64," + ("a" * 20000)
result = mod._safe_value(payload)
assert result == {
"type": "data_uri",
"media_type": "image/png",
"omitted": True,
"length": len(payload),
}
def test_serialize_messages_redacts_data_uri_parts(self):
sys.modules.pop("plugins.observability.langfuse", None)
import importlib
mod = importlib.import_module("plugins.observability.langfuse")
payload = "data:image/jpeg;base64," + ("b" * 20000)
serialized = mod._serialize_messages([
{"role": "user", "content": [{"type": "image_url", "image_url": {"url": payload}}]}
])
assert serialized[0]["content"][0]["image_url"]["url"] == {
"type": "data_uri",
"media_type": "image/jpeg",
"omitted": True,
"length": len(payload),
}
# ---------------------------------------------------------------------------
# Placeholder-credential guard (#23823).
#