Validate post-processed skill output and quote failed JSON in repair
CI / ci (push) Successful in 1m33s
CI / ci (pull_request) Successful in 1m32s

The harness now validates a skill's output again after PostProcess, so
output that post-processing makes invalid (e.g. a whitespace-only echo
trimmed to empty) enters the single repair turn instead of returning as
a success. The repair turn now quotes Response.JSON as the previous
assistant reply whenever structured output was returned, falling back to
Response.Text only when there is none.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-05 07:49:23 -04:00
co-authored by Claude Opus 5.5
parent 9ed5cb1192
commit 7be4879f6d
2 changed files with 65 additions and 12 deletions
+47
View File
@@ -79,6 +79,53 @@ func TestRunInvalidThenValid(t *testing.T) {
}
}
func TestRunPostProcessedOutputIsValidated(t *testing.T) {
var f llm.Fake
f.QueueGenerate(reply(`{"echo":" "}`), reply(`{"echo":"taco"}`))
out, err := run(t, &f)
if err != nil {
t.Fatal(err)
}
if out.Echo != "taco" {
t.Fatalf("Echo = %q", out.Echo)
}
msgs := assertCalls(t, &f, 2)[1].Messages
if len(msgs) != 3 || msgs[1] != (llm.Message{Role: llm.RoleAssistant, Content: `{"echo":" "}`}) ||
!strings.Contains(msgs[2].Content, "echo must not be empty") {
t.Fatalf("repair messages = %+v", msgs)
}
}
func TestRunWhitespaceTwiceIsBadOutput(t *testing.T) {
var f llm.Fake
f.QueueGenerate(reply(`{"echo":" "}`), reply(`{"echo":" "}`))
_, err := run(t, &f)
var bad *BadOutputError
if !errors.Is(err, llm.ErrBadOutput) || !errors.As(err, &bad) {
t.Fatalf("err = %v, want *BadOutputError", err)
}
if !slices.Equal(bad.First, []string{"echo must not be empty"}) ||
!slices.Equal(bad.Repair, []string{"echo must not be empty"}) {
t.Fatalf("BadOutputError = %+v", bad)
}
assertCalls(t, &f, 2)
}
func TestRunRepairQuotesJSONOverText(t *testing.T) {
var f llm.Fake
f.QueueGenerate(
llm.GenerateResult{Response: llm.Response{Text: "Here you go!", JSON: json.RawMessage(`{"echo":"TACO"}`)}},
reply(`{"echo":"taco"}`),
)
if out, err := run(t, &f); err != nil || out.Echo != "taco" {
t.Fatalf("Run = %+v, %v", out, err)
}
msgs := assertCalls(t, &f, 2)[1].Messages
if len(msgs) != 3 || msgs[1] != (llm.Message{Role: llm.RoleAssistant, Content: `{"echo":"TACO"}`}) {
t.Fatalf("repair messages = %+v, want the failed JSON as the assistant reply", msgs)
}
}
func TestRunDecodeFailureIsRepaired(t *testing.T) {
for name, first := range map[string]llm.GenerateResult{
"unknown field": reply(`{"echo":"taco","extra":1}`),