fix(gateway): dm catches A2AAccessDeniedError; circuit breakers handle dict errors

Smoke-7 surfaced: be-qa called dm(recipient='qa-all', ...) — 'qa-all'
is a channel slug, not an agent. A2A enforcement raised
A2AAccessDeniedError. It propagated past dm(), past content_actions,
got caught by FastAPI middleware which renders RobocoError.to_dict()
as {'error': {'code': ..., 'message': ..., 'details': ...}} — a
DICT-shaped 'error' field.

do_server's circuit-breaker check (and flow_server's mirror) did
`payload.get('error') in _CIRCUIT_REJECTION_KINDS` — trying to hash
a dict against a frozenset → `TypeError: unhashable type: 'dict'`.
The agent saw "Error executing tool dm: unhashable type: 'dict'"
and got stuck calling dm in a loop.

Two-layer fix:

1. content_actions.dm now catches A2AAccessDeniedError and returns
   Envelope.not_authorized with the original reason + route_hint as
   remediate. This is the right shape — content tools always emit
   Envelopes; RobocoErrors escaping to the middleware is a bug.

2. Defense-in-depth: do_server._record_and_check_circuit and
   flow_server._record_and_check_circuit now guard against non-string
   error fields. Any future RobocoError-leak that bypasses (1) will
   pass through untouched instead of crashing the tool call.

3 new tests pin the contracts:
- dm A2A denial returns Envelope.not_authorized (not propagated)
- do_server circuit-breaker doesn't crash on dict-shaped errors
This commit is contained in:
Renn F
2026-05-15 03:03:53 +02:00
parent b90ce83946
commit 417b8c5f29
5 changed files with 140 additions and 7 deletions
@@ -260,3 +260,30 @@ def test_verb_extracted_from_path(do_module: types.ModuleType) -> None:
do_module.commit(message="[abc12345] test commit message under 20 chars")
sdk_body = next(body for url, body in captured if "test-sdk" in url)
assert sdk_body["verb"] == "commit"
def test_dict_shaped_error_does_not_crash(do_module: types.ModuleType) -> None:
"""A RobocoError.to_dict()-shaped response must pass through without TypeError.
Smoke-7: A2AAccessDeniedError escaped to middleware and was rendered as
{'error': {'code': ..., 'message': ..., 'details': ...}}. The circuit
breaker's `error in frozenset` check then crashed with
`TypeError: unhashable type: 'dict'`.
"""
factory, captured = _make_client(
orchestrator_response={
"error": {
"code": "A2A_ACCESS_DENIED",
"message": "be-qa cannot A2A with qa-all",
"details": {},
}
},
sdk_response=None, # SDK must not be touched
)
# No TypeError; payload passes through untouched.
with patch("httpx.Client", side_effect=factory):
result = do_module.dm(recipient="qa-all", text="x")
assert isinstance(result["error"], dict)
assert result["error"]["code"] == "A2A_ACCESS_DENIED"
# SDK breaker MUST NOT have been called for a non-string error.
assert all("test-sdk" not in url for url, _ in captured)