fix(logging): redact agent registry exception telemetry

backend/services/agent_registry.py

@@ -20,6 +20,8 @@
 from pathlib import Path
 from typing import Any
 
+from core.safe_logging import redacted_exception_info
+
 logger = logging.getLogger(__name__)
 
 # backend/services/agent_registry.py -> parents[2] is the repository root.
@@ -89,14 +91,20 @@ def _load_json_object(path: Path) -> dict[str, Any]:
     except FileNotFoundError:
         logger.debug("Registration file not found: %s", path)
         return {}
-    except OSError:
-        logger.debug("Could not read registration file: %s", path, exc_info=True)
+    except OSError as exc:
+        logger.debug(
+            "Could not read registration file",
+            exc_info=redacted_exception_info(exc),
+        )
         return {}
 
     try:
         parsed = json.loads(text or "{}")
-    except json.JSONDecodeError:
-        logger.debug("Malformed registration file: %s", path, exc_info=True)
+    except json.JSONDecodeError as exc:
+        logger.debug(
+            "Malformed registration file",
+            exc_info=redacted_exception_info(exc),
+        )
         return {}
 
     return parsed if isinstance(parsed, dict) else {}

backend/tests/test_agent_registry.py

@@ -1,5 +1,9 @@
 """Tests for the workspace agent registry loader."""
 
+import logging
+from pathlib import Path
+
+from services import agent_registry
 from services.agent_registry import (
     clear_registry_cache,
     get_registered_agent,
@@ -45,3 +49,54 @@ def test_task_mapping_resolves_to_noema_agent():
 
 def test_unknown_task_type_resolves_to_none():
     assert resolve_agent_for_task("does-not-exist") is None
+
+
+def test_registry_read_failure_redacts_exception_value_and_path(
+    caplog, monkeypatch, tmp_path
+):
+    secret_path = tmp_path / "OPENAI_API_KEY=sk-test-secret" / "registered_agents.json"
+    secret_error = (
+        "postgresql://operator:password@db.internal/naruon "
+        "OPENAI_API_KEY=sk-test-secret"
+    )
+
+    def raise_read_error(self: Path, *args, **kwargs) -> str:
+        raise OSError(secret_error)
+
+    monkeypatch.setattr(Path, "read_text", raise_read_error)
+
+    with caplog.at_level(logging.DEBUG, logger=agent_registry.__name__):
+        assert agent_registry._load_json_object(secret_path) == {}
+
+    formatter = logging.Formatter("%(levelname)s %(name)s %(message)s")
+    rendered = "\n".join(formatter.format(record) for record in caplog.records)
+
+    assert "Could not read registration file" in rendered
+    assert "OSError" in rendered
+    assert "exception_fingerprint=" in rendered
+    assert secret_error not in rendered
+    assert "sk-test-secret" not in rendered
+    assert "operator:password" not in rendered
+    assert str(secret_path) not in rendered
+
+
+def test_registry_parse_failure_redacts_payload_and_path(caplog, monkeypatch, tmp_path):
+    secret_path = tmp_path / "provider-token-sk-test-secret" / "task_agent_mapping.json"
+    malformed_payload = '{"provider_token":"sk-test-secret",'
+
+    def return_malformed_payload(self: Path, *args, **kwargs) -> str:
+        return malformed_payload
+
+    monkeypatch.setattr(Path, "read_text", return_malformed_payload)
+
+    with caplog.at_level(logging.DEBUG, logger=agent_registry.__name__):
+        assert agent_registry._load_json_object(secret_path) == {}
+
+    formatter = logging.Formatter("%(levelname)s %(name)s %(message)s")
+    rendered = "\n".join(formatter.format(record) for record in caplog.records)
+
+    assert "Malformed registration file" in rendered
+    assert "JSONDecodeError" in rendered
+    assert "exception_fingerprint=" in rendered
+    assert "sk-test-secret" not in rendered
+    assert str(secret_path) not in rendered

docs/doctoring/agent-registry-exception-telemetry.md

@@ -0,0 +1,45 @@
+# Agent registry exception telemetry boundary
+
+## Scope
+
+This document records the sink-specific follow-up to #1698 on the `backend/services/agent_registry.py` registry loader. The shared confidentiality contract is owned by #1700 on top of #1612; this lane only migrates the agent-registry read and JSON-parse failure sinks to that contract.
+
+## Finding
+
+The registry loader previously used ordinary `exc_info=True` for `OSError` and `json.JSONDecodeError`. Python logging can render the original exception value and traceback from that flag. At the same time, the log message included the registry path. A filesystem/provider failure can therefore disclose exception-carried credentials, connection strings, internal paths, or parser context into a normal production log sink.
+
+The `FileNotFoundError` branch is intentionally unchanged. It does not attach exception information and identifies a deterministic missing registration file for operator diagnosis. This repair does not broaden into unrelated registry behavior.
+
+## Decision
+
+The two exception-bearing sinks now call `core.safe_logging.redacted_exception_info(error)`, inherited from #1700. The normal log record preserves:
+
+- a bounded operation label (`Could not read registration file` or `Malformed registration file`);
+- the exception class;
+- the shared one-way failure-site fingerprint.
+
+The record does not carry `str(error)`, `repr(error)`, the raw traceback, or the registry path in these failure cases. The fingerprint remains build-scoped rather than a cross-version durable identifier, matching #1700.
+
+Rejected alternatives:
+
+- keeping `exc_info=True`: retains the original exception value and traceback;
+- interpolating the path while redacting only the exception: still exposes internal path material unnecessarily at this sink;
+- dropping exception correlation entirely: weakens operational RCA without a confidentiality benefit over the shared structured contract;
+- copying or forking the helper: would create a second telemetry contract instead of consuming the #1700 owner path.
+
+## Verification
+
+Focused tests drive the real `logging.Formatter` rather than checking only `LogRecord.getMessage()`. The read-failure case injects an API-key-shaped value, a PostgreSQL connection string, and a secret-bearing path into an `OSError`. The malformed-JSON case injects token-shaped content and a secret-bearing path. Both require the operation label, exception class, and `exception_fingerprint=` while rejecting the injected values and paths from rendered output.
+
+No public/API response contract changes in this slice.
+
+## Traceability
+
+- Naruon issue #1698 — repository exception-log sink inventory and migration acceptance.
+- Naruon PR #1700 — canonical structured exception telemetry helper and confidentiality contract.
+- MITRE. (n.d.). *CWE-532: Insertion of Sensitive Information into Log File*. https://cwe.mitre.org/data/definitions/532.html
+- OWASP Foundation. (n.d.). *Logging Cheat Sheet*. https://cheatsheetseries.owasp.org/cheatsheets/Logging_Cheat_Sheet.html
+
+## Integration gate
+
+This lane remains stacked on #1700. It is not merge authority until the parent security lineage reaches protected ancestry and the final unchanged head obtains every then-live required hosted check plus qualifying independent review. No temporary retarget, copied workflow, synthetic status, dummy commit, force push, destructive rebase, self-approval, or gate weakening is acceptable evidence.