mirror of
https://github.com/Twigpine/zero.git
synced 2026-11-11 23:40:28 -10:00
zzucs
5aa54fe1d2
* fix(agent): mark headless guardrail stops incomplete The empty-turn and repeated-tool-failure guards returned the run as a successful final answer even with RequireCompletionSignal enabled, so zero exec reported exit 0 and a success run_end for work it had just abandoned. Set Result.Incomplete and a reason at both stops when the headless gate is on. Thresholds, stop answers, retry behavior, interactive runs, and --no-completion-gate are unchanged. Fixes #1154 * fix(agent): count consecutive empty turns in stop reason The headless no-output stop reason used result.Turns, which counts every turn in the run, so a run with an earlier tool-call turn claimed "stopped after 4 turns with no output" for a 3-turn empty streak. Use the guard's emptyTurns counter and say "consecutive". Pinned by a case with a successful tool turn before the empty streak.
91 lines
3.3 KiB
Go
91 lines
3.3 KiB
Go
package cli
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"slices"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/Twigpine/zero/internal/config"
|
|
"github.com/Twigpine/zero/internal/zeroruntime"
|
|
)
|
|
|
|
// guardStopExecProvider emits turns with no visible text and no tool calls, so
|
|
// the empty-turn guardrail stops the run after its consecutive-empty-turn cap.
|
|
type guardStopExecProvider struct{}
|
|
|
|
func (guardStopExecProvider) StreamCompletion(ctx context.Context, request zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
|
|
ch := make(chan zeroruntime.StreamEvent, 1)
|
|
select {
|
|
case <-ctx.Done():
|
|
close(ch)
|
|
return ch, ctx.Err()
|
|
case ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventDone}:
|
|
}
|
|
close(ch)
|
|
return ch, nil
|
|
}
|
|
|
|
// A guardrail stop in headless exec must use the existing INCOMPLETE contract
|
|
// (exit 4, error event, run_end status), and --no-completion-gate must keep
|
|
// reporting success. isolateCLIUserState also turns off the models.dev refresh
|
|
// that runExec starts in the background (see the #1152/#1161 flake).
|
|
func TestRunExecGuardrailStopIncompleteContract(t *testing.T) {
|
|
for _, tc := range []struct {
|
|
name string
|
|
args []string
|
|
wantExit int
|
|
wantStatus string
|
|
}{
|
|
{"gate on", []string{"exec", "--output-format", "stream-json", "complete the task"}, exitIncomplete, "incomplete"},
|
|
{"gate off", []string{"exec", "--no-completion-gate", "--output-format", "stream-json", "complete the task"}, exitSuccess, "success"},
|
|
} {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
isolateCLIUserState(t)
|
|
cwd := t.TempDir()
|
|
var stdout, stderr bytes.Buffer
|
|
exitCode := runWithDeps(tc.args, &stdout, &stderr, appDeps{
|
|
getwd: func() (string, error) { return cwd, nil },
|
|
resolveConfig: func(string, config.Overrides) (config.ResolvedConfig, error) {
|
|
return execResolvedConfig(), nil
|
|
},
|
|
newProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
|
|
return guardStopExecProvider{}, nil
|
|
},
|
|
})
|
|
if exitCode != tc.wantExit {
|
|
t.Fatalf("exit code = %d, want %d; stderr=%q", exitCode, tc.wantExit, stderr.String())
|
|
}
|
|
|
|
events := decodeJSONLines(t, stdout.String())
|
|
if len(events) == 0 || events[len(events)-1]["type"] != "run_end" {
|
|
t.Fatalf("expected run_end as the last event, got %#v", events)
|
|
}
|
|
runEnd := events[len(events)-1]
|
|
if runEnd["status"] != tc.wantStatus {
|
|
t.Fatalf("run_end status = %v, want %q", runEnd["status"], tc.wantStatus)
|
|
}
|
|
if runEnd["exitCode"] != float64(tc.wantExit) {
|
|
t.Fatalf("run_end exitCode = %v, want %d", runEnd["exitCode"], tc.wantExit)
|
|
}
|
|
finalEvent := findJSONEvent(t, events, "final")
|
|
if text, _ := finalEvent["text"].(string); !strings.Contains(text, "no output") {
|
|
t.Fatalf("final text = %q, want the guard stop answer", text)
|
|
}
|
|
|
|
if tc.wantStatus == "incomplete" {
|
|
errorEvent := findJSONEvent(t, events, "error")
|
|
if errorEvent["code"] != "incomplete" {
|
|
t.Fatalf("error code = %v, want incomplete", errorEvent["code"])
|
|
}
|
|
if message, _ := errorEvent["message"].(string); !strings.Contains(message, "no output") {
|
|
t.Fatalf("error message = %q, want the guard reason", message)
|
|
}
|
|
} else if slices.Contains(jsonEventTypes(events), "error") {
|
|
t.Fatalf("gate-off run must not emit an error event: %#v", events)
|
|
}
|
|
})
|
|
}
|
|
}
|