package host import ( "context" "crypto/sha256" "encoding/hex" "fmt" "os" "path/filepath" "testing" "time" "github.com/carlosframework/platform/internal/registry" "github.com/carlosframework/platform/internal/release" ) func mintAskerFixture(t *testing.T, activeFor time.Duration) (*mintAsker, *int, *time.Time, release.Store, string) { t.Helper() opt, etc := t.TempDir(), t.TempDir() liveTo(t, opt, observedHost, "v1") reg := restartTestRegistry(t) if err := reg.Upsert(registry.Route{Host: observedHost, Kind: "instance", App: "console", Channel: "canary/console", Unit: "console.service", Status: "ready"}); err != nil { t.Fatal(err) } policy := filepath.Join(etc, "proof-policy.json") if err := os.WriteFile(policy, []byte(provePolicy("/etc/carlos/proving.key")), 0o644); err != nil { t.Fatal(err) } t0 := time.Date(2026, 10, 6, 10, 0, 0, 0, time.UTC) clock := t0 asked := 0 store := release.NewDirStore(t.TempDir()) a := &mintAsker{reg: reg, store: store, optDir: opt, policyPath: policy, sys: &fakeUnits{shows: []unitProps{{ActiveState: "active", InvocationID: "i1", MainPID: 7, ActiveEnterTimestamp: t0.Add(-activeFor)}}}, request: func(string, string, error) { asked++ }, now: func() time.Time { return clock }} sha, err := release.FileSHA256(filepath.Join(opt, "versions", "v1", "console")) if err != nil { t.Fatal(err) } return a, &asked, &clock, store, sha } // Review focus 5: the relay can drop a request and a mint write can fail, so // the agent asks every 2 minutes until it sees the proof, then stops. func TestMintAskerReasksUntilTheProofAppears(t *testing.T) { t.Parallel() a, asked, clock, store, sha := mintAskerFixture(t, 20*time.Minute) ctx := context.Background() t0 := *clock at := func(d time.Duration) { *clock = t0.Add(d); a.tick(ctx) } at(0) if *asked != 1 { t.Fatalf("asked %d times at first sight, want 1", *asked) } at(time.Minute) if *asked != 1 { t.Fatalf("asked %d times inside 2 minutes, want 1", *asked) } at(2 * time.Minute) if *asked != 2 { t.Fatalf("asked %d times after 2 minutes, want 2", *asked) } seed, _, err := release.GenerateKey() if err != nil { t.Fatal(err) } key, err := release.ParseSigningKey(seed, "test") if err != nil { t.Fatal(err) } p, err := release.SignProof(key, release.Proof{App: "console", Platform: release.AdoptPlatform(), SHA256: sha, Version: "v1", Prover: "dev", ActiveSince: t0.Add(-20 * time.Minute), ProvenAt: t0}) if err != nil { t.Fatal(err) } if err := release.PutProof(ctx, store, "bab", p); err != nil { t.Fatal(err) } at(4 * time.Minute) at(6 * time.Minute) if *asked != 2 { t.Fatalf("asked %d times after the proof appeared, want 2", *asked) } pend, err := release.GetProofPending(ctx, store, "bab", "console", sha, "dev") if err != nil || !pend.LiveSince.Equal(t0.Add(-20*time.Minute)) { t.Fatalf("pending = %+v, %v", pend, err) } } // putDevProof puts a valid-shaped dev proof for sha in store. func putDevProof(t *testing.T, store release.Store, sha string, at time.Time) { t.Helper() seed, _, err := release.GenerateKey() if err != nil { t.Fatal(err) } key, err := release.ParseSigningKey(seed, "test") if err != nil { t.Fatal(err) } p, err := release.SignProof(key, release.Proof{App: "console", Platform: release.AdoptPlatform(), SHA256: sha, Version: "v1", Prover: "dev", ActiveSince: at.Add(-20 * time.Minute), ProvenAt: at}) if err != nil { t.Fatal(err) } if err := release.PutProof(context.Background(), store, "bab", p); err != nil { t.Fatal(err) } } // Final review H5: dev proves v1, its staged copy is pruned, and the name v1 // is reused for other bytes at the same path. The asker hashes the new file, // finds no proof for it, and asks root again, rather than answering from the // old file's hash and the proof it found for that. func TestMintAskerRehashesAReusedVersionPath(t *testing.T) { t.Parallel() a, asked, clock, store, sha := mintAskerFixture(t, 20*time.Minute) ctx := context.Background() t0 := *clock putDevProof(t, store, sha, t0) a.tick(ctx) if *asked != 0 { t.Fatalf("asked %d times for a proven build, want 0", *asked) } staged := filepath.Join(a.optDir, "versions", "v1", "console") if err := os.Remove(staged); err != nil { t.Fatal(err) } if err := os.WriteFile(staged, []byte("other bytes under the same name"), 0o755); err != nil { t.Fatal(err) } *clock = t0.Add(mintAskEvery) a.tick(ctx) if *asked != 1 { t.Fatalf("asked %d times after the path's bytes changed, want 1: the new bytes have no proof", *asked) } newSHA := sha256Hex("other bytes under the same name") if h := a.shaByPath[staged]; h.sha != newSHA { t.Fatalf("cached sha256 = %q, want the new file's %q", h.sha, newSHA) } } // The same bytes rewritten in place with a new mtime are hashed again too: // size and mtime are part of the file's identity, not only its inode. func TestMintAskerRehashesAFileRewrittenInPlace(t *testing.T) { t.Parallel() a, asked, clock, store, sha := mintAskerFixture(t, 20*time.Minute) ctx := context.Background() t0 := *clock putDevProof(t, store, sha, t0) a.tick(ctx) staged := filepath.Join(a.optDir, "versions", "v1", "console") // liveTo's build is one byte; another byte of the same size, in place. if err := os.WriteFile(staged, []byte("y"), 0o755); err != nil { t.Fatal(err) } later := time.Now().Add(time.Hour) if err := os.Chtimes(staged, later, later); err != nil { t.Fatal(err) } *clock = t0.Add(mintAskEvery) a.tick(ctx) if *asked != 1 { t.Fatalf("asked %d times after an in-place rewrite, want 1", *asked) } } // The proven cache is per proof object: a proof seen for one prover does not // answer for another after the policy changes prover. func TestMintAskerProvenCacheIsPerProver(t *testing.T) { t.Parallel() a, asked, clock, store, sha := mintAskerFixture(t, 20*time.Minute) ctx := context.Background() t0 := *clock putDevProof(t, store, sha, t0) a.tick(ctx) if *asked != 0 { t.Fatalf("asked %d times for a proven build, want 0", *asked) } if err := os.WriteFile(a.policyPath, []byte(`{"schema":1,"prove":{"apps":["console"],"prover":"staging","after":"15m","key_file":"/etc/carlos/proving.key"}}`), 0o644); err != nil { t.Fatal(err) } *clock = t0.Add(mintAskEvery) a.tick(ctx) if *asked != 1 { t.Fatalf("asked %d times once the prover is staging, want 1: dev's proof is not staging's", *asked) } } func TestMintAskerWaitsOutTheBake(t *testing.T) { t.Parallel() a, asked, _, store, sha := mintAskerFixture(t, 5*time.Minute) a.tick(context.Background()) if *asked != 0 { t.Fatalf("asked %d times five minutes into a fifteen-minute bake", *asked) } if _, err := release.GetProofPending(context.Background(), store, "bab", "console", sha, "dev"); err != nil { t.Fatalf("no pending note for a baking build: %v", err) } } // Task 2's carry: a policy file that does not parse is closed. Root mints // nothing until it parses, so the asker has nothing to ask for and stays // quiet rather than reading the broken file as "no prove block" and guessing. func TestMintAskerAsksNothingOnABrokenPolicy(t *testing.T) { t.Parallel() a, asked, _, store, sha := mintAskerFixture(t, 20*time.Minute) if err := os.WriteFile(a.policyPath, []byte(`{"schema":1,"prove":`), 0o644); err != nil { t.Fatal(err) } a.tick(context.Background()) if *asked != 0 { t.Fatalf("asked %d times with a broken policy, want 0", *asked) } if _, err := release.GetProofPending(context.Background(), store, "bab", "console", sha, "dev"); err == nil { t.Fatal("pending note written under a broken policy") } } // Spec §4.5, codex 14: a non-canary listed route with a live version stays in // the fast set while it waits (at the gate's 30 s cadence), and leaves once // it adopts. func TestFastMembersKeepsAWaitingRoute(t *testing.T) { t.Parallel() f := newFastFixture(t) ctx := context.Background() host := "edge.example.com" f.addRoute(t, host, "edge") f.stageLive(t, host, "v1") plat := release.AdoptPlatform() for ver, body := range map[string]string{"v1": "staged build", "v2": "build two"} { m := release.Manifest{App: "fastapp", Version: ver, Kind: "binary", Artifacts: map[string]release.Artifact{plat: {}}} if err := release.Ship(ctx, f.store, "bab", m, map[string][]byte{plat: []byte(body)}); err != nil { t.Fatalf("Ship %s: %v", ver, err) } } if err := release.Promote(ctx, f.store, f.priv, "bab", "fastapp", "edge", "v2"); err != nil { t.Fatal(err) } seed, pubB64, err := release.GenerateKey() if err != nil { t.Fatal(err) } prover, err := release.ParseSigningKey(seed, "test") if err != nil { t.Fatal(err) } policy := filepath.Join(t.TempDir(), "proof-policy.json") if err := os.WriteFile(policy, []byte(fmt.Sprintf(`{"schema":1,"require":[{"app":"fastapp","prover":"dev","key":%q}]}`, pubB64)), 0o644); err != nil { t.Fatal(err) } clock := time.Now() gate := release.NewProofGate(policy, f.dataDir).WithClock(func() time.Time { return clock }) d := f.deps(nil) d.passOpts = append(d.passOpts, release.WithProofGate(gate)) d.proof = gate if got := d.fastMembers(clock); len(got) != 0 { t.Fatalf("members = %v before anything waits", got) } // The serial-triggered full pass sees v2 and finds no proof. if err := release.Pass(ctx, f.reg, f.store, f.pub, f.optDir, d.restart, d.passOpts...); err != nil { t.Fatal(err) } if v, _ := release.LiveVersion(f.optDir, host); v != "v1" { t.Fatalf("live = %q, want v1 while unproven", v) } clock = clock.Add(31 * time.Second) if got := d.fastMembers(clock); len(got) != 1 || got[0] != host { t.Fatalf("members = %v, want the waiting non-canary route", got) } sum := sha256.Sum256([]byte("build two")) p, err := release.SignProof(prover, release.Proof{App: "fastapp", Platform: plat, SHA256: hex.EncodeToString(sum[:]), Version: "v2", Prover: "dev", ActiveSince: clock.Add(-time.Hour).UTC().Truncate(time.Second), ProvenAt: clock.UTC().Truncate(time.Second)}) if err != nil { t.Fatal(err) } if err := release.PutProof(ctx, f.store, "bab", p); err != nil { t.Fatal(err) } fastTick(ctx, d, clock) if v, _ := release.LiveVersion(f.optDir, host); v != "v2" { t.Fatalf("live = %q, want v2 once proven", v) } clock = clock.Add(31 * time.Second) if got := d.fastMembers(clock); len(got) != 0 { t.Fatalf("members = %v after adopting, want none", got) } } // Spec §4.5 for a route with no live link: a new instance of a listed app // whose head is unproven waits like a staged one, and rejoins the sweep each // time its 30 s miss runs out. Its unstaged backoff must not stretch that. func TestFastMembersKeepsAnUnstagedWaitingRouteAtTheMissCadence(t *testing.T) { t.Parallel() f := newFastFixture(t) ctx := context.Background() host := "new.example.com" f.addRoute(t, host, "edge") plat := release.AdoptPlatform() m := release.Manifest{App: "fastapp", Version: "v2", Kind: "binary", Artifacts: map[string]release.Artifact{plat: {}}} if err := release.Ship(ctx, f.store, "bab", m, map[string][]byte{plat: []byte("build two")}); err != nil { t.Fatal(err) } if err := release.Promote(ctx, f.store, f.priv, "bab", "fastapp", "edge", "v2"); err != nil { t.Fatal(err) } _, pubB64, err := release.GenerateKey() if err != nil { t.Fatal(err) } policy := filepath.Join(t.TempDir(), "proof-policy.json") if err := os.WriteFile(policy, []byte(fmt.Sprintf(`{"schema":1,"require":[{"app":"fastapp","prover":"dev","key":%q}]}`, pubB64)), 0o644); err != nil { t.Fatal(err) } clock := time.Now() gate := release.NewProofGate(policy, f.dataDir).WithClock(func() time.Time { return clock }) d := f.deps(nil) d.passOpts = append(d.passOpts, release.WithProofGate(gate)) d.proof = gate for i := 0; i < 8; i++ { if got := d.fastMembers(clock); len(got) != 1 || got[0] != host { t.Fatalf("cycle %d: members = %v, want the waiting unstaged route (step %v)", i, got, d.backoffFor(host)) } fastTick(ctx, d, clock) if w := gate.Waits(); len(w) != 1 || w[0].Host != host { t.Fatalf("cycle %d: waits = %+v, want %s waiting", i, w, host) } if v, _ := release.LiveVersion(f.optDir, host); v != "" { t.Fatalf("cycle %d: live = %q, want nothing while unproven", i, v) } clock = clock.Add(release.ProofMissTTL + time.Second) } } // Ruling 5's purpose, seen from the fast loop: a wait the sweep neither // renews nor clears (here the route moved to a channel with no pointer, so // adoptHost returns before the gate) must not keep its host in the sweep // every tick. It backs off like an unstaged route. func TestFastMembersBacksOffAWaitTheSweepLeftStanding(t *testing.T) { t.Parallel() f := newFastFixture(t) ctx := context.Background() host := "edge.example.com" f.addRoute(t, host, "edge") f.stageLive(t, host, "v1") plat := release.AdoptPlatform() m := release.Manifest{App: "fastapp", Version: "v2", Kind: "binary", Artifacts: map[string]release.Artifact{plat: {}}} if err := release.Ship(ctx, f.store, "bab", m, map[string][]byte{plat: []byte("build two")}); err != nil { t.Fatal(err) } if err := release.Promote(ctx, f.store, f.priv, "bab", "fastapp", "edge", "v2"); err != nil { t.Fatal(err) } _, pubB64, err := release.GenerateKey() if err != nil { t.Fatal(err) } policy := filepath.Join(t.TempDir(), "proof-policy.json") if err := os.WriteFile(policy, []byte(fmt.Sprintf(`{"schema":1,"require":[{"app":"fastapp","prover":"dev","key":%q}]}`, pubB64)), 0o644); err != nil { t.Fatal(err) } clock := time.Now() gate := release.NewProofGate(policy, f.dataDir).WithClock(func() time.Time { return clock }) d := f.deps(nil) d.passOpts = append(d.passOpts, release.WithProofGate(gate)) d.proof = gate if err := release.Pass(ctx, f.reg, f.store, f.pub, f.optDir, d.restart, d.passOpts...); err != nil { t.Fatal(err) } f.addRoute(t, host, "nowhere") // no pointer: the pass never reaches the gate clock = clock.Add(31 * time.Second) if got := d.fastMembers(clock); len(got) != 1 { t.Fatalf("members = %v, want the waiting route", got) } fastTick(ctx, d, clock) if got := d.fastMembers(clock.Add(time.Second)); len(got) != 0 { t.Fatalf("members = %v a second after a sweep that left the wait standing, want none", got) } if d.backoffFor(host) == 0 { t.Fatal("no backoff recorded for the standing wait") } }