P5: light-tier canary — gadfly-shaped reviewer on executus core
executus CI / test (pull_request) Failing after 1m5s
Adversarial Review (Gadfly) / review (pull_request) Successful in 8m18s

examples/reviewer proves the core is sufficient for a static-binary light host
(gadfly's shape) with NO batteries:
- config.Env + model.Configure  -> env-driven model fleet + tier overrides
- model.ParseModelForContext    -> tier resolution + failover
- fanout.Run (PerKey caps)      -> N models x M lenses swarm, per-provider bound
- model.GenerateWith[T]         -> structured findings per (model, lens) cell
- Consolidate                   -> one verdict-led report section per model

Hermetic test runs the full 2x3 swarm against majordomo's fake provider and
asserts the consolidated verdicts. A go list -deps CI check asserts the canary
imports ZERO batteries (the light-tier invariant) — gadfly's go.sum stays free
of gorm/redis/discordgo/sqlite. README + docs updated.

This is the canary; migrating the LIVE gadfly repo onto executus core is a
follow-up (kept separate to not destabilize the active reviewer).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-27 00:22:02 -04:00
parent dc2d4ec425
commit ea9475da54
7 changed files with 447 additions and 1 deletions
+102
View File
@@ -0,0 +1,102 @@
package main
import (
"context"
"strings"
"testing"
"gitea.stevedudenhoeffer.com/steve/majordomo/provider/fake"
"gitea.stevedudenhoeffer.com/steve/executus/fanout"
)
// TestReviewSwarm proves the light-tier path end-to-end against the fake
// provider: a 2-model × 3-lens swarm runs, structured findings parse, and
// consolidation produces one verdict-led section per model — no batteries, no
// network.
func TestReviewSwarm(t *testing.T) {
fp := fake.New("fakeprov")
// Model "hot" reports a high-severity finding on every lens; "cold" reports
// nothing. Each model is called once per lens (3×), so enqueue 3 each.
hot := `{"findings":[{"severity":"high","title":"SQL injection","detail":"unsanitized id in query"}]}`
cold := `{"findings":[]}`
for i := 0; i < 3; i++ {
fp.Enqueue("hot", fake.Reply(hot))
fp.Enqueue("cold", fake.Reply(cold))
}
hotM, err := fp.Model("hot")
if err != nil {
t.Fatal(err)
}
coldM, err := fp.Model("cold")
if err != nil {
t.Fatal(err)
}
models := []NamedModel{
{Name: "hot", Provider: "fakeprov", Model: hotM},
{Name: "cold", Provider: "fakeprov", Model: coldM},
}
lenses := []Lens{{Name: "security"}, {Name: "correctness"}, {Name: "error-handling"}}
results := Review(context.Background(), models, lenses, "some diff",
fanout.Options[cell]{MaxConcurrent: 6, PerKey: map[string]int{"fakeprov": 3}})
// 2 models × 3 lenses = 6 cells, all successful.
if len(results) != 6 {
t.Fatalf("got %d cells, want 6", len(results))
}
var hotFindings, coldFindings, errs int
for _, r := range results {
if r.Err != nil {
errs++
continue
}
switch r.Model {
case "hot":
hotFindings += len(r.Findings)
case "cold":
coldFindings += len(r.Findings)
}
}
if errs != 0 {
t.Errorf("expected no cell errors, got %d", errs)
}
if hotFindings != 3 { // one per lens
t.Errorf("hot model findings = %d, want 3", hotFindings)
}
if coldFindings != 0 {
t.Errorf("cold model findings = %d, want 0", coldFindings)
}
report := Consolidate(results)
if !strings.Contains(report, "hot — blocking issues found") {
t.Errorf("hot section should lead with a blocking verdict:\n%s", report)
}
if !strings.Contains(report, "cold — no issues found") {
t.Errorf("cold section should report no issues:\n%s", report)
}
if !strings.Contains(report, "SQL injection") {
t.Errorf("report should surface the finding:\n%s", report)
}
}
// TestConsolidateVerdicts checks the worst-severity-led header logic.
func TestConsolidateVerdicts(t *testing.T) {
got := Consolidate([]LensResult{
{Model: "m", Lens: "a", Findings: []Finding{{Severity: SevSmall, Title: "x"}}},
{Model: "m", Lens: "b", Findings: []Finding{{Severity: SevMedium, Title: "y"}}},
})
if !strings.Contains(got, "m — minor issues") {
t.Errorf("medium-max should be 'minor issues', got:\n%s", got)
}
// An errored lens is surfaced in the header.
got = Consolidate([]LensResult{
{Model: "m", Lens: "a", Findings: []Finding{{Severity: SevCritical, Title: "boom"}}},
{Model: "m", Lens: "b", Err: context.DeadlineExceeded},
})
if !strings.Contains(got, "blocking issues found") || !strings.Contains(got, "errored") {
t.Errorf("critical + errored lens header wrong:\n%s", got)
}
}