Compare commits

...

1 Commits

Author SHA1 Message Date
Codex fb9d5daf2a harness: label provider conformance phases
Harness (E2E) / Harnesses (mock LLM) (push) Has been cancelled
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Has been cancelled
Lint / golangci-lint (push) Has been cancelled
Run Tests / Unit Tests (push) Has been cancelled
Run Tests / Etcd Integration Tests (push) Has been cancelled
2026-07-01 11:45:52 +00:00
3 changed files with 45 additions and 11 deletions
@@ -20,7 +20,11 @@ agent test and the harnesses in `internal/harness`:
preserving run metadata.
The command also emits the registered provider capability matrix so the run shows
which providers advertise model, image, video, and streaming support.
which providers advertise model, image, video, and streaming support. Console output
and summary artifacts label each harness with the phase it is proving (for example,
model call + tool call, workflow event + tool call, or streaming fallback + tool
call), so provider failures identify the failed lifecycle phase instead of only the
provider name.
## Local usage
+28 -7
View File
@@ -36,6 +36,14 @@ import (
const defaultHarnesses = "agent,universe,agent-flow,plan-delegate,a2a-stream-fallback"
var harnessPhases = map[string]string{
"agent": "model call + tool call",
"universe": "service discovery + tool call",
"agent-flow": "workflow event + tool call",
"plan-delegate": "plan persistence + delegation + tool call",
"a2a-stream-fallback": "streaming fallback + tool call",
}
var providerEnv = map[string]string{
"anthropic": "ANTHROPIC_API_KEY",
"openai": "OPENAI_API_KEY",
@@ -92,15 +100,16 @@ func main() {
}
for _, harness := range harnesses {
fmt.Printf("\n==> %s / %s\n", provider, harness)
phase := harnessPhase(harness)
fmt.Printf("\n==> %s / %s (%s)\n", provider, harness, phase)
if err := runHarness(provider, harness, *timeoutFlag); err != nil {
fmt.Printf("FAIL %s / %s: %v\n", provider, harness, err)
fmt.Printf("FAIL %s / %s (%s): %v\n", provider, harness, phase, err)
failed++
results = append(results, conformanceResult{Provider: provider, Harness: harness, Status: statusFailed, Error: err.Error()})
results = append(results, conformanceResult{Provider: provider, Harness: harness, Phase: phase, Status: statusFailed, Error: err.Error()})
continue
}
ran++
results = append(results, conformanceResult{Provider: provider, Harness: harness, Status: statusPassed})
results = append(results, conformanceResult{Provider: provider, Harness: harness, Phase: phase, Status: statusPassed})
}
}
@@ -140,6 +149,7 @@ const (
type conformanceResult struct {
Provider string `json:"provider"`
Harness string `json:"harness,omitempty"`
Phase string `json:"phase,omitempty"`
Status string `json:"status"`
Error string `json:"error,omitempty"`
}
@@ -176,14 +186,18 @@ func writeSummaryMarkdown(path string, summary conformanceSummary) error {
b.WriteString("## Capability matrix\n\n")
b.WriteString(capabilityMarkdown(summary.Capabilities))
b.WriteString("\n## Harness results\n\n")
b.WriteString("| Provider | Harness | Status | Detail |\n")
b.WriteString("| --- | --- | --- | --- |\n")
b.WriteString("| Provider | Harness | Phase | Status | Detail |\n")
b.WriteString("| --- | --- | --- | --- | --- |\n")
for _, result := range summary.Results {
harness := result.Harness
if harness == "" {
harness = "—"
}
fmt.Fprintf(&b, "| %s | %s | %s | %s |\n", result.Provider, harness, result.Status, markdownCell(result.Error))
phase := result.Phase
if phase == "" {
phase = "—"
}
fmt.Fprintf(&b, "| %s | %s | %s | %s | %s |\n", result.Provider, harness, markdownCell(phase), result.Status, markdownCell(result.Error))
}
return os.WriteFile(path, []byte(b.String()), 0o644)
}
@@ -209,6 +223,13 @@ func markdownList(values []string) string {
return strings.Join(escaped, ", ")
}
func harnessPhase(harness string) string {
if phase, ok := harnessPhases[harness]; ok {
return phase
}
return "harness"
}
func markdownCell(s string) string {
if s == "" {
return "—"
@@ -99,7 +99,7 @@ func TestWriteSummaryMarkdown(t *testing.T) {
summary := conformanceSummary{
Capabilities: []ai.CapabilityRow{{Provider: "mock", Capabilities: ai.Capabilities{Model: true}}},
Results: []conformanceResult{
{Provider: "mock", Harness: "agent-flow", Status: statusPassed},
{Provider: "mock", Harness: "agent-flow", Phase: harnessPhase("agent-flow"), Status: statusPassed},
{Provider: "live", Status: statusSkipped, Error: "missing | key"},
},
Passed: 1,
@@ -120,8 +120,8 @@ func TestWriteSummaryMarkdown(t *testing.T) {
"Providers: —.",
"Harnesses: —.",
"| mock | ✅ | — | — | — |",
"| mock | agent-flow | passed | — |",
"| live | — | skipped | missing \\| key |",
"| mock | agent-flow | workflow event + tool call | passed | — |",
"| live | — | — | skipped | missing \\| key |",
} {
if !strings.Contains(got, want) {
t.Fatalf("summary markdown = %q, want %q", got, want)
@@ -129,6 +129,15 @@ func TestWriteSummaryMarkdown(t *testing.T) {
}
}
func TestHarnessPhaseLabelsKnownHarnesses(t *testing.T) {
if got := harnessPhase("a2a-stream-fallback"); got != "streaming fallback + tool call" {
t.Fatalf("harnessPhase() = %q, want streaming fallback phase", got)
}
if got := harnessPhase("custom"); got != "harness" {
t.Fatalf("harnessPhase(custom) = %q, want fallback phase", got)
}
}
func TestMarkdownListEscapesBackticks(t *testing.T) {
got := markdownList([]string{"agent", "bad`name"})
want := "`agent`, `bad\\`name`"