fix(web): say what actually went wrong instead of "unknown"

src/web_interface/error_handler.py

@@ -4,6 +4,7 @@
 Provides helpers for consistent error responses across API endpoints.
 """
 
+import re
 from typing import Any, Optional
 from flask import jsonify
 
@@ -16,6 +17,78 @@
 logger = get_logger(__name__)
 
 
+# Credentials that turn up inside exception text. A requests error quotes the
+# URL it failed on, and plugins that authenticate by query string put their key
+# there, so echoing an exception verbatim can hand out an API key. Redact the
+# value, keep the parameter name -- knowing *which* credential was involved is
+# part of the diagnosis.
+_REDACT_CREDENTIAL = re.compile(
+    r'((?:api[_-]?key|access[_-]?token|auth|apikey|key|passwd|password|pwd|'
+    r'secret|sig|signature|token)["\']?\s*[=:]\s*["\']?)([^\s&"\'<>,}]+)',
+    re.IGNORECASE,
+)
+
+# `Authorization: <scheme> <credential>`. The scheme name is kept because it
+# says which kind of credential failed; the credential goes. Any scheme
+# matches, not a fixed list: ApiKey, Negotiate, NTLM, AWS4-HMAC-SHA256 and
+# whatever a plugin's API invents next are all credentials, and a list would
+# silently leak the ones nobody thought of. Not covered by the generic pattern
+# above, whose value part stops at whitespace and so would keep the credential
+# once a space follows the scheme.
+_REDACT_AUTH_HEADER = re.compile(
+    r'((?:proxy-)?authorization["\']?\s*[=:]\s*["\']?\s*'
+    r'(?:[A-Za-z][\w.+-]*[ \t]+)?)'          # optional scheme name, kept
+    r'([^\s,"\'<>}]+)',                       # the credential, redacted
+    re.IGNORECASE,
+)
+
+# Credentials embedded in a URL: https://user:password@host. requests quotes
+# the full URL in its exceptions, so this is a realistic leak. The username is
+# kept -- it identifies which account failed without being the secret.
+_REDACT_URL_USERINFO = re.compile(r'([a-z][a-z0-9+.-]*://[^/\s:@]+:)([^/\s@]+)(@)',
+                                  re.IGNORECASE)
+
+# Long enough for an errno string with a path, short enough not to dump a
+# parser's worth of context into a JSON field.
+_MAX_DETAIL_LENGTH = 400
+
+
+def describe_exception(exc: BaseException,
+                       max_length: int = _MAX_DETAIL_LENGTH) -> str:
+    """
+    One-line, safe-to-return description of an exception.
+
+    The generic "an error occurred; see logs for details" tells a user nothing
+    and, when the failure is bad enough, the logs are unreachable too: a device
+    whose storage was failing returned that message from every endpoint
+    *including* the log viewer, because journalctl could not be executed. The
+    underlying `[Errno 5] Input/output error` named the fault immediately.
+
+    Returns "TypeName: message", credentials redacted and length capped. The
+    type alone is worth carrying -- a bare PermissionError says more than any
+    generic sentence.
+
+    Args:
+        exc: The exception to describe
+        max_length: Truncate beyond this many characters
+
+    Returns:
+        A single-line description, never empty
+    """
+    message = str(exc).strip()
+    text = f"{type(exc).__name__}: {message}" if message else type(exc).__name__
+    # Order matters: the URL and header forms are more specific than the
+    # generic key=value pattern, which would otherwise chew the scheme.
+    text = _REDACT_URL_USERINFO.sub(r'\1<redacted>\3', text)
+    text = _REDACT_AUTH_HEADER.sub(r'\1<redacted>', text)
+    text = _REDACT_CREDENTIAL.sub(r'\1<redacted>', text)
+    # Collapse newlines/tabs so the detail stays one line in a JSON field.
+    text = ' '.join(text.split())
+    if len(text) > max_length:
+        text = text[:max_length - 1].rstrip() + '…'
+    return text
+
+
 def create_error_response(
     error_code: ErrorCode,
     message: str,

test/test_web_error_detail.py

@@ -0,0 +1,248 @@
+"""Tests for surfacing the underlying error in web responses.
+
+Regression under test: every failing endpoint returned "An error occurred; see
+logs for details" and nothing else. On a device whose storage was failing that
+sentence came back from the restart action, from /system/status, and from
+/logs -- the log viewer itself -- because journalctl could not be executed. The
+exception underneath said `[Errno 5] Input/output error: 'systemctl'`, which
+names the fault outright, and nine handlers were discarding it entirely rather
+than even logging it.
+"""
+
+import pytest
+
+from src.web_interface.error_handler import describe_exception
+
+
+class TestDescribeException:
+    def test_names_the_type_and_message(self):
+        detail = describe_exception(OSError(5, "Input/output error", "systemctl"))
+        assert detail == "OSError: [Errno 5] Input/output error: 'systemctl'"
+
+    def test_the_reported_failure_is_legible(self):
+        # The whole point: this string is the diagnosis.
+        assert "Input/output error" in describe_exception(
+            OSError(5, "Input/output error", "systemctl"))
+
+    def test_a_bare_exception_still_names_its_type(self):
+        # A PermissionError with no message still says more than "unknown".
+        assert describe_exception(PermissionError()) == "PermissionError"
+        assert describe_exception(Exception()) == "Exception"
+
+    def test_message_is_kept_when_present(self):
+        assert describe_exception(ValueError("bad port")) == "ValueError: bad port"
+
+
+class TestCredentialRedaction:
+    """Exception text quotes URLs, and plugins authenticate by query string."""
+
+    @pytest.mark.parametrize("secret_text,leaked", [
+        ("failed: https://api.x.com/v1?api_key=SEC123&city=Tampa", "SEC123"),
+        ("token=abcdef123456 was rejected", "abcdef123456"),
+        ("connect failed password=hunter2", "hunter2"),
+        ("GET /?access_token=zzz999", "zzz999"),
+        ('{"secret": "topsecret"}', "topsecret"),
+        # requests quotes the URL it failed on, and both of these forms turn
+        # up in real client exceptions.
+        ("401 for https://user:hunter2@example.com/api", "hunter2"),
+        ("headers: {'Authorization': 'Bearer eyJ.SECRET.sig'}", "eyJ.SECRET.sig"),
+        ("Authorization: Basic dXNlcjpwYXNzd29yZA==", "dXNlcjpwYXNzd29yZA=="),
+        ("Proxy-Authorization: Bearer ptok999", "ptok999"),
+        # Any scheme, not a fixed list -- a list silently leaks whatever it
+        # does not name, and plugin APIs invent their own.
+        ("Authorization: ApiKey SECRET123", "SECRET123"),
+        ("Authorization: Negotiate YIIZnegotiateblob", "YIIZnegotiateblob"),
+        ("Authorization: NTLM TlRMTVNTUAAB", "TlRMTVNTUAAB"),
+        ("authorization: barecredential", "barecredential"),
+    ])
+    def test_credentials_never_reach_the_response(self, secret_text, leaked):
+        detail = describe_exception(RuntimeError(secret_text))
+        assert leaked not in detail
+        assert "<redacted>" in detail
+
+    def test_the_parameter_name_survives_redaction(self):
+        # Knowing *which* credential was involved is part of the diagnosis.
+        detail = describe_exception(RuntimeError("https://x/y?api_key=SEC123"))
+        assert "api_key" in detail
+
+    def test_unknown_schemes_keep_their_name(self):
+        for scheme in ("ApiKey", "Negotiate", "NTLM", "AWS4-HMAC-SHA256"):
+            detail = describe_exception(
+                RuntimeError("Authorization: %s SECRETVALUE" % scheme))
+            assert scheme in detail, detail
+            assert "SECRETVALUE" not in detail, detail
+
+    def test_auth_scheme_and_username_survive(self):
+        # Which kind of credential, and whose, without the credential itself.
+        assert "Bearer" in describe_exception(
+            RuntimeError("Authorization: Bearer eyJ.SECRET.sig"))
+        assert "user" in describe_exception(
+            RuntimeError("https://user:hunter2@example.com"))
+
+    def test_non_secret_context_is_preserved(self):
+        detail = describe_exception(RuntimeError("https://api.x.com/v1?city=Tampa"))
+        assert "city=Tampa" in detail
+        assert "<redacted>" not in detail
+
+
+class TestBounds:
+    def test_long_messages_are_truncated(self):
+        detail = describe_exception(ValueError("x" * 5000))
+        assert len(detail) <= 400
+
+    def test_newlines_are_collapsed_to_one_line(self):
+        detail = describe_exception(ValueError("line one\nline two\tthree"))
+        assert "\n" not in detail and "\t" not in detail
+        assert detail == "ValueError: line one line two three"
+
+    def test_custom_length_is_honoured(self):
+        assert len(describe_exception(ValueError("y" * 500), max_length=50)) <= 50
+
+
+class TestHandlersCarryDetail:
+    """The response shape callers actually see."""
+
+    def test_no_api_v3_handler_discards_its_exception(self):
+        """Every generic-message handler must log a traceback and return detail.
+
+        Nine of them bound `e` and never used it, so the promised log entry was
+        never written either. Checking merely that *something* was logged is
+        too weak -- a `logger.info("failed")` would satisfy it while throwing
+        the exception away just as completely, so this asserts the two things
+        that actually make the failure diagnosable: an error-level record with
+        the traceback, and the sanitized detail in the response.
+        """
+        import ast
+
+        src = open("web_interface/blueprints/api_v3.py").read()
+        tree = ast.parse(src)
+        generic = "An error occurred; see logs for details"
+
+        def logs_a_traceback(handler):
+            """An error/exception-level log call carrying exc_info."""
+            for call in [n for n in ast.walk(handler) if isinstance(n, ast.Call)]:
+                func = call.func
+                if not isinstance(func, ast.Attribute):
+                    continue
+                if func.attr == "exception":       # implies exc_info
+                    return True
+                if func.attr not in ("error", "critical"):
+                    continue
+                if any(kw.arg == "exc_info" and getattr(kw.value, "value", False) is True
+                       for kw in call.keywords):
+                    return True
+            return False
+
+        def describes_this_exception(node, bound):
+            """A describe_exception(<bound>) call anywhere under `node`."""
+            for call in [n for n in ast.walk(node) if isinstance(n, ast.Call)]:
+                if not (isinstance(call.func, ast.Name)
+                        and call.func.id == "describe_exception"):
+                    continue
+                if bound is None:
+                    return True     # bare `except:` cannot name it; accept
+                if any(isinstance(a, ast.Name) and a.id == bound
+                       for a in call.args):
+                    return True
+            return False
+
+        def returns_the_detail(handler):
+            """The detail must be inside what the handler actually returns.
+
+            Looking anywhere in the handler is too weak: a handler could
+            compute describe_exception(e), drop it on the floor, and return the
+            generic message with no details field, while still passing. So the
+            call has to appear within a `return` expression.
+            """
+            returns = [n for n in ast.walk(handler) if isinstance(n, ast.Return)]
+            if not returns:
+                return False
+            return all(describes_this_exception(r, handler.name) for r in returns)
+
+        offenders = []
+        for h in [n for n in ast.walk(tree) if isinstance(n, ast.ExceptHandler)]:
+            seg = ast.get_source_segment(src, h) or ""
+            if generic not in seg:
+                continue
+            missing = []
+            if not logs_a_traceback(h):
+                missing.append("error-level log with exc_info")
+            if not returns_the_detail(h):
+                missing.append("describe_exception(e) in the response")
+            if missing:
+                offenders.append((h.lineno, missing))
+
+        assert not offenders, (
+            "handlers returning the generic message without %s: %r"
+            % ("both a traceback log and the detail", offenders))
+
+    def test_client_errors_keep_their_own_status(self):
+        """A 405 must not be reported as a server-side UNKNOWN_ERROR.
+
+        Werkzeug's HTTPExceptions subclass Exception, so the catch-all saw them
+        too: a GET on a POST-only route came back 500 "an error occurred",
+        which tells the caller nothing and blames the wrong side. Found while
+        probing a device whose POST-only config endpoints answered every GET
+        with UNKNOWN_ERROR.
+        """
+        from flask import Flask, jsonify
+        from werkzeug.exceptions import HTTPException
+
+        app = Flask(__name__)
+
+        @app.errorhandler(Exception)
+        def handle(error):
+            if isinstance(error, HTTPException):
+                return jsonify({
+                    "status": "error",
+                    "error_code": (error.name or "HTTP_ERROR").upper().replace(" ", "_"),
+                    "message": error.description,
+                }), error.code or 500
+            return jsonify({
+                "status": "error",
+                "error_code": "UNKNOWN_ERROR",
+                "message": "An error occurred; see logs for details",
+                "details": describe_exception(error),
+            }), 500
+
+        @app.route("/only-post", methods=["POST"])
+        def only_post():
+            return jsonify({"ok": True})
+
+        @app.route("/boom")
+        def boom():
+            raise OSError(5, "Input/output error", "systemctl")
+
+        client = app.test_client()
+
+        resp = client.get("/only-post")
+        assert resp.status_code == 405, "a wrong method must stay a 405"
+        assert resp.get_json()["error_code"] == "METHOD_NOT_ALLOWED"
+
+        # A genuine server fault still reports as one, with its detail.
+        resp = client.get("/boom")
+        assert resp.status_code == 500
+        assert "Input/output error" in resp.get_json()["details"]
+
+    def test_global_handler_reports_the_underlying_error(self):
+        from flask import Flask, jsonify
+
+        app = Flask(__name__)
+
+        @app.errorhandler(Exception)
+        def handle(error):
+            return jsonify({
+                "status": "error",
+                "error_code": "UNKNOWN_ERROR",
+                "message": "An error occurred; see logs for details",
+                "details": describe_exception(error),
+            }), 500
+
+        @app.route("/boom")
+        def boom():
+            raise OSError(5, "Input/output error", "systemctl")
+
+        client = app.test_client()
+        body = client.get("/boom").get_json()
+        assert body["error_code"] == "UNKNOWN_ERROR"
+        assert "Input/output error" in body["details"]

web_interface/app.py

@@ -16,6 +16,8 @@
 sys.path.insert(0, str(Path(__file__).parent.parent))
 
 from src.config_manager import ConfigManager
+from src.web_interface.error_handler import describe_exception
+from werkzeug.exceptions import HTTPException
 from src.exceptions import ConfigError
 from src.plugin_system.plugin_manager import PluginManager
 from src.plugin_system.store_manager import PluginStoreManager
@@ -391,22 +393,50 @@ def internal_error(error):
     import logging
     logger = logging.getLogger('web_interface')
     logger.error("Internal server error", exc_info=True)
-    return jsonify({
+    payload = {
         'status': 'error',
         'error_code': 'INTERNAL_ERROR',
         'message': 'An internal error occurred; see logs for details',
-    }), 500
+    }
+    # Flask hands the original exception over as `error.original_exception`
+    # when propagation is off; without it there is nothing to describe.
+    original = getattr(error, 'original_exception', None) or (
+        error if isinstance(error, BaseException) else None)
+    if original is not None:
+        payload['details'] = describe_exception(original)
+    return jsonify(payload), 500
 
 @app.errorhandler(Exception)
 def handle_exception(error):
-    """Handle all unhandled exceptions."""
+    """Handle all unhandled exceptions.
+
+    Returning only "see logs for details" is fine until the logs are exactly
+    what you cannot reach. A device with failing storage answered every
+    endpoint with that sentence -- including the log viewer, because journalctl
+    could not be executed -- while the exception underneath said
+    `[Errno 5] Input/output error`. Naming the error costs nothing here and is
+    frequently the whole diagnosis, so include it alongside the log pointer.
+    """
+    # Werkzeug's HTTPExceptions subclass Exception, so this catch-all sees
+    # them too and was reporting every 405, 400, 413 and 415 as a server-side
+    # UNKNOWN_ERROR 500. A GET on a POST-only route came back as "an error
+    # occurred" rather than "method not allowed", which tells the caller
+    # nothing and blames the wrong side. Hand those back as themselves.
+    if isinstance(error, HTTPException):
+        return jsonify({
+            'status': 'error',
+            'error_code': (error.name or 'HTTP_ERROR').upper().replace(' ', '_'),
+            'message': error.description,
+        }), error.code or 500
+
     import logging
     logger = logging.getLogger('web_interface')
     logger.error("Unhandled exception", exc_info=True)
     return jsonify({
         'status': 'error',
         'error_code': 'UNKNOWN_ERROR',
         'message': 'An error occurred; see logs for details',
+        'details': describe_exception(error),
     }), 500
 
 # Captive portal redirect middleware