Result classifier

from fastmcp_feedback.instrumentation import DEFAULT_RESULT_CLASSIFIER, soft_error_classifier

Contract

A result classifier is (tool: str, result: Any) -> str | None.

• It runs only for calls that did not raise.
• result is the payload the record stores: the tool’s structured content when present, otherwise its content items (texts, or {"type": ...} for other kinds).
• When the tool marked its result as an MCP error (isError) without raising, result arrives as a dict with "isError": True, alongside the payload’s own keys or with the payload under "content".
• None means ok. A string marks a soft error: outcome="soft_error", ok=False, error_type="SoftError", and the string, redacted and cut to max_error_chars, becomes error_message.
• If it raises, the error is logged and the call is recorded as ok.
• It never changes what the client receives.

soft_error_classifier

soft_error_classifier(*, statuses=("error", "failed", "failure"),
                      status_keys=("status", "state"),
                      flag_keys=("ok", "success"),
                      extra_statuses=(),
                      error_keys=("error",)) -> ResultClassifier

Parameter	Description
statuses	Values that mean failure at a status key, compared case-insensitively.
status_keys	Keys holding a status.
flag_keys	Keys holding a success boolean.
extra_statuses	Added to statuses.
error_keys	Keys whose non-empty string value marks a failure on its own. () turns the check off.

Non-dict results are always ok. For a dict, checks run in this order and the first that applies decides:

Order	Condition	Result	Message
1	a status key holds a failing status	soft error	status=failed: <detail>
2	a flag key is exactly False	soft error	ok=False: <detail>
3	isError or is_error is True	soft error	isError: <detail or content text>
4	a flag key is exactly True	ok
5	an error key holds a non-blank string	soft error	error: <string>
6	none of the above	ok

<detail> is the first non-empty value of error, message, detail and reason; a dict there is searched one level down for the same keys. Lists are skipped. A label without a detail is used alone, such as status=failed.

DEFAULT_RESULT_CLASSIFIER is soft_error_classifier() with these defaults.

classify = soft_error_classifier(extra_statuses=("unknown_target",))
assert classify("render", {"status": "unknown_target", "error": "no such object"}) == "status=unknown_target: no such object"
assert classify("render", {"status": "failed", "error": {"code": 7, "message": "disk full"}}) == "status=failed: disk full"
assert classify("render", {"error": {"code": 1}}) is None
assert DEFAULT_RESULT_CLASSIFIER("t", {"isError": True, "content": ["boom"]}) == "isError: boom"

History

Release	Change
2026.09.27.4	Classification added; outcome column.
2026.10.01	error_keys check, on by default.
2026.10.01.1	An explicit True flag wins over an error string.