fix(atlas): treat skipped jobs as OK in run aggregate

Tag-push runs skip the deploy job (deploy is main-only), so runs with a skipped
job were mislabelled "running" in the timeline. Skipped now counts as completed-
OK; only genuinely in-progress states aggregate to running. Test-first.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

internal/atlas/atlas.json

@@ -36,7 +36,7 @@
       {"t":"assessor-loop ledger","d":"Attestation ledger (audit trail) + brain session_log on completion.","tags":["audit package"]}
     ]},
     {"no":"STAGE 06","title":"PR → CI","path":"Gitea Actions · cd.yml (live)","generate":"ci-jobs","nodes":[]},
-    {"no":"STAGE 07","cls":"cd","title":"CD → pod","path":"Flux GitOps → k3s","nodes":[
+    {"no":"STAGE 07","cls":"cd","title":"CD → pod","path":"Flux GitOps → k3s","generate":"deploy-state","nodes":[
       {"t":"Deploy on green","pill":"var(--green)","d":"Flux reconciles image → k3s pod on koala. Push ≠ deploy: bump tag in mathias/infra.","tags":["ntfy on deploy"]}
     ]},
     {"no":"STAGE 08","cls":"telos","title":"Loop back","path":"→ TELOS (feedback bus)","nodes":[

internal/atlas/cluster.go

@@ -53,6 +53,66 @@ func HostsFromNodes(nodesJSON []byte) ([]Host, error) {
 	return hosts, nil
 }
 
+// Deploy is the live state of a Kubernetes Deployment.
+type Deploy struct {
+	Image   string
+	Ready   int
+	Desired int
+}
+
+// Tag is the image tag (substring after the last ":").
+func (d Deploy) Tag() string {
+	if i := strings.LastIndex(d.Image, ":"); i >= 0 {
+		return d.Image[i+1:]
+	}
+	return d.Image
+}
+
+// DeployState parses a Kubernetes Deployment object into its live state.
+func DeployState(deployJSON []byte) (Deploy, error) {
+	var dep struct {
+		Spec struct {
+			Replicas int `json:"replicas"`
+			Template struct {
+				Spec struct {
+					Containers []struct {
+						Image string `json:"image"`
+					} `json:"containers"`
+				} `json:"spec"`
+			} `json:"template"`
+		} `json:"spec"`
+		Status struct {
+			ReadyReplicas int `json:"readyReplicas"`
+		} `json:"status"`
+	}
+	if err := json.Unmarshal(deployJSON, &dep); err != nil {
+		return Deploy{}, fmt.Errorf("parse deployment: %w", err)
+	}
+	d := Deploy{Ready: dep.Status.ReadyReplicas, Desired: dep.Spec.Replicas}
+	if len(dep.Spec.Template.Spec.Containers) > 0 {
+		d.Image = dep.Spec.Template.Spec.Containers[0].Image
+	}
+	return d, nil
+}
+
+// DeployNode renders the live deploy state as a stage node (green when the
+// rollout is fully ready, amber otherwise).
+func DeployNode(d Deploy) Node {
+	pill := "var(--amber)"
+	if d.Desired > 0 && d.Ready == d.Desired {
+		pill = "var(--green)"
+	}
+	img := d.Image
+	if i := strings.LastIndex(img, "/"); i >= 0 {
+		img = img[i+1:] // drop registry host
+	}
+	return Node{
+		Title: fmt.Sprintf("◆ deployed · %s · %d/%d ready", img, d.Ready, d.Desired),
+		Pill:  pill,
+		Tags:  []string{"live · k8s"},
+	}
+}
+
 // NamespaceSummary parses a Kubernetes `/api/v1/namespaces` list into a compact
 // "ns: a · b · c" line for the substrate, dropping system namespaces, sorting,
 // and capping the count (with "+N more" when it overflows).

internal/atlas/cluster_test.go

@@ -98,6 +98,38 @@ func TestNamespaceSummary_CapsWithMore(t *testing.T) {
 	}
 }
 
+func TestDeployState_ParsesImageAndReplicas(t *testing.T) {
+	dep := []byte(`{"spec":{"replicas":2,"template":{"spec":{"containers":[
+	  {"name":"cad-atlas","image":"localhost:5000/cad-atlas:3ff922a"}]}}},
+	  "status":{"readyReplicas":1,"replicas":2}}`)
+
+	d, err := atlas.DeployState(dep)
+	if err != nil {
+		t.Fatalf("DeployState: %v", err)
+	}
+	if d.Image != "localhost:5000/cad-atlas:3ff922a" || d.Ready != 1 || d.Desired != 2 {
+		t.Fatalf("deploy = %+v", d)
+	}
+	if d.Tag() != "3ff922a" {
+		t.Fatalf("tag = %q, want 3ff922a", d.Tag())
+	}
+}
+
+func TestDeployNode_GreenOnlyWhenFullyReady(t *testing.T) {
+	ready := atlas.DeployNode(atlas.Deploy{Image: "localhost:5000/cad-atlas:abc", Ready: 1, Desired: 1})
+	if ready.Pill != "var(--green)" {
+		t.Fatalf("ready pill = %q, want green", ready.Pill)
+	}
+	if ready.Title != "◆ deployed · cad-atlas:abc · 1/1 ready" {
+		t.Fatalf("title = %q", ready.Title)
+	}
+
+	rolling := atlas.DeployNode(atlas.Deploy{Image: "x/cad-atlas:def", Ready: 0, Desired: 1})
+	if rolling.Pill != "var(--amber)" {
+		t.Fatalf("rolling pill = %q, want amber", rolling.Pill)
+	}
+}
+
 func TestHostsFromNodes_ErrorsOnBadJSON(t *testing.T) {
 	if _, err := atlas.HostsFromNodes([]byte("{not json")); err == nil {
 		t.Fatal("expected error on bad JSON, got nil")

internal/atlas/model.go

@@ -38,6 +38,7 @@ type Atlas struct {
 	Version   string   `json:"version,omitempty"`
 	Substrate []Host   `json:"substrate"`
 	NS        string   `json:"ns,omitempty"`
+	Timeline  []RunDot `json:"timeline,omitempty"`
 	Stages    []Stage  `json:"stages"`
 }
 

internal/atlas/runs.go

@@ -31,21 +31,63 @@ type RunSummary struct {
 // State aggregates the jobs: failure if any failed, running if any not yet
 // succeeded, else success.
 func (s RunSummary) State() string {
-	allSucceeded := true
-	for _, j := range s.Jobs {
+	return aggregateState(s.Jobs)
+}
+
+// RunDot is one run's aggregate outcome for the recent-runs timeline.
+type RunDot struct {
+	Number int    `json:"number"`
+	State  string `json:"state"`
+}
+
+// RecentRuns parses a Gitea `/actions/tasks` response (per-job, newest first)
+// into up to n most-recent runs with their aggregate outcome, newest first.
+func RecentRuns(tasksJSON []byte, n int) ([]RunDot, error) {
+	var resp struct {
+		Tasks []struct {
+			RunNumber  int    `json:"run_number"`
+			Status     string `json:"status"`
+			Conclusion string `json:"conclusion"`
+		} `json:"workflow_runs"`
+	}
+	if err := json.Unmarshal(tasksJSON, &resp); err != nil {
+		return nil, fmt.Errorf("parse tasks: %w", err)
+	}
+	var order []int
+	jobsByRun := map[int][]Job{}
+	for _, t := range resp.Tasks {
+		if _, seen := jobsByRun[t.RunNumber]; !seen {
+			order = append(order, t.RunNumber)
+		}
+		jobsByRun[t.RunNumber] = append(jobsByRun[t.RunNumber], Job{Status: t.Status, Conclusion: t.Conclusion})
+	}
+	dots := make([]RunDot, 0, n)
+	for _, rn := range order {
+		if len(dots) >= n {
+			break
+		}
+		dots = append(dots, RunDot{Number: rn, State: aggregateState(jobsByRun[rn])})
+	}
+	return dots, nil
+}
+
+// aggregateState folds per-job outcomes into a run outcome.
+func aggregateState(jobs []Job) string {
+	pending := false
+	for _, j := range jobs {
 		switch j.State() {
 		case "failure", "cancelled", "error":
 			return "failure"
-		case "success":
+		case "success", "skipped": // completed OK — skipped (e.g. deploy on a tag push) doesn't block
 		default:
-			allSucceeded = false
+			pending = true // running / in_progress / waiting / queued / unknown
 		}
 	}
-	if allSucceeded {
-		return "success"
-	}
+	if pending {
 		return "running"
 	}
+	return "success"
+}
 
 // LatestRunJobs parses a Gitea `/actions/tasks` response (per-job entries,
 // newest first) and returns the newest run with its jobs in pipeline order.

internal/atlas/runs_test.go

@@ -65,6 +65,40 @@ func TestRunNodes_SummaryThenPerJobColoured(t *testing.T) {
 	}
 }
 
+func TestRecentRuns_GroupsRunsNewestFirstWithAggregateState(t *testing.T) {
+	tasks := []byte(`{"workflow_runs":[
+	  {"run_number":28,"name":"Deploy","status":"success"},
+	  {"run_number":28,"name":"Build","status":"success"},
+	  {"run_number":27,"name":"Deploy","status":"completed","conclusion":"failure"},
+	  {"run_number":26,"name":"Build","status":"running"},
+	  {"run_number":25,"name":"Deploy","status":"success"}
+	]}`)
+
+	dots, err := atlas.RecentRuns(tasks, 3)
+	if err != nil {
+		t.Fatalf("RecentRuns: %v", err)
+	}
+	if len(dots) != 3 {
+		t.Fatalf("want 3 dots (capped), got %d: %+v", len(dots), dots)
+	}
+	want := []atlas.RunDot{{28, "success"}, {27, "failure"}, {26, "running"}}
+	for i := range want {
+		if dots[i] != want[i] {
+			t.Fatalf("dot[%d] = %+v, want %+v", i, dots[i], want[i])
+		}
+	}
+}
+
+func TestRunState_SkippedJobsCountAsOK(t *testing.T) {
+	// A tag-push run skips the deploy job; the run still succeeded.
+	s := atlas.RunSummary{Jobs: []atlas.Job{
+		{Status: "skipped"}, {Status: "success"}, {Status: "success"},
+	}}
+	if s.State() != "success" {
+		t.Fatalf("skipped+success run state = %q, want success", s.State())
+	}
+}
+
 func TestLatestRunJobs_ErrorsWhenEmpty(t *testing.T) {
 	if _, err := atlas.LatestRunJobs([]byte(`{"workflow_runs":[]}`)); err == nil {
 		t.Fatal("expected error on empty, got nil")

internal/cluster/client.go

@@ -24,6 +24,11 @@ func Nodes() ([]byte, error) { return get("/api/v1/nodes") }
 // Namespaces returns the raw /api/v1/namespaces JSON from the in-cluster API server.
 func Namespaces() ([]byte, error) { return get("/api/v1/namespaces") }
 
+// Deployment returns the raw JSON for the cad-atlas Deployment (its own live state).
+func Deployment() ([]byte, error) {
+	return get("/apis/apps/v1/namespaces/cad-atlas/deployments/cad-atlas")
+}
+
 func get(path string) ([]byte, error) {
 	host, port := os.Getenv("KUBERNETES_SERVICE_HOST"), os.Getenv("KUBERNETES_SERVICE_PORT")
 	if host == "" || port == "" {

internal/gitea/client.go

@@ -21,7 +21,7 @@ func base() string {
 
 // Runs returns the raw /actions/tasks JSON for mathias/cad-atlas (newest first).
 func Runs() ([]byte, error) {
-	url := base() + "/api/v1/repos/mathias/cad-atlas/actions/tasks?limit=20"
+	url := base() + "/api/v1/repos/mathias/cad-atlas/actions/tasks?limit=50"
 	client := &http.Client{Timeout: 5 * time.Second}
 	resp, err := client.Get(url) //nolint:noctx // short-lived, timeout on the client
 	if err != nil {

internal/web/handler.go

@@ -47,6 +47,7 @@ func NewHandler() http.Handler {
 		if ld.ns != "" {
 			a.NS = "Tailscale mesh · " + ld.ns
 		}
+		a.Timeline = ld.timeline
 		if ld.run != nil {
 			nodes := atlas.RunNodes(*ld.run)
 			for i := range a.Stages {
@@ -55,6 +56,14 @@ func NewHandler() http.Handler {
 				}
 			}
 		}
+		if ld.deploy != nil {
+			node := atlas.DeployNode(*ld.deploy)
+			for i := range a.Stages {
+				if a.Stages[i].Generate == "deploy-state" {
+					a.Stages[i].Nodes = append([]atlas.Node{node}, a.Stages[i].Nodes...)
+				}
+			}
+		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")
 		_ = json.NewEncoder(w).Encode(a)
 	})
@@ -66,6 +75,8 @@ type liveOverlayData struct {
 	hosts    []atlas.Host
 	ns       string
 	run      *atlas.RunSummary
+	deploy   *atlas.Deploy
+	timeline []atlas.RunDot
 }
 
 // live cache: query the cluster at most once per TTL; fall back to the authored
@@ -101,6 +112,14 @@ func liveOverlay() liveOverlayData {
 		if r, err := atlas.LatestRunJobs(raw); err == nil {
 			d.run = &r
 		}
+		if dots, err := atlas.RecentRuns(raw, 12); err == nil {
+			d.timeline = dots
+		}
+	}
+	if raw, err := cluster.Deployment(); err == nil {
+		if dep, err := atlas.DeployState(raw); err == nil {
+			d.deploy = &dep
+		}
 	}
 	liveCache = d
 	return d

internal/web/static/cad-atlas.html

@@ -52,6 +52,13 @@
   .host .k{color:var(--dim);font-size:11px}
   .host.mesh{border-style:dashed;color:var(--dim)}
 
+  .tl{display:none;gap:5px;align-items:center;flex-wrap:wrap;
+    padding:8px 22px;border-bottom:1px solid var(--line);background:var(--panel)}
+  .tl .lbl{color:var(--dim);font-size:11px;letter-spacing:1.5px;margin-right:4px}
+  .rundot{width:22px;height:16px;border-radius:4px;border:1px solid rgba(0,0,0,.35);
+    display:inline-flex;align-items:center;justify-content:center;
+    font-size:9px;color:#08121f;font-weight:600}
+
   .scroll{overflow-x:auto;padding:24px 22px 20px}
   .track{position:relative;display:flex;align-items:flex-start;min-width:max-content}
   svg.spine{position:absolute;left:0;top:0;z-index:0;pointer-events:none;overflow:visible}
@@ -122,6 +129,7 @@
 </header>
 
 <div class="substrate" id="substrate"><span class="lbl mono">SUBSTRATE</span></div>
+<div class="tl mono" id="timeline"></div>
 
 <div class="scroll">
   <div class="track" id="track">
@@ -154,7 +162,7 @@
 // stage from the live cd.yml + substrate from the live cluster). These start
 // empty and are filled by init()'s fetch; on failure the page shows an error
 // banner rather than stale inline data.
-let SUBSTRATE=[], NS="", STAGES=[];
+let SUBSTRATE=[], NS="", STAGES=[], TIMELINE=[];
 
 const track=document.getElementById('track');
 let stageEls=[];
@@ -181,6 +189,20 @@ function renderAtlas(){
   });
 }
 
+function renderTimeline(){
+  const tl=document.getElementById('timeline');
+  if(!TIMELINE.length){tl.style.display='none';return;}
+  tl.innerHTML='<span class="lbl">RECENT RUNS</span>';
+  TIMELINE.forEach(d=>{
+    const c=d.state==='success'?'var(--green)':(d.state==='failure'?'var(--coral)':'var(--amber)');
+    const el=document.createElement('span');
+    el.className='rundot';el.style.background=c;
+    el.title='run #'+d.number+' · '+d.state;el.textContent=d.number;
+    tl.appendChild(el);
+  });
+  tl.style.display='flex';
+}
+
 /* ---- geometry ---- */
 const spine=document.getElementById('spine'), spinePath=document.getElementById('spinePath'),
       loopPath=document.getElementById('loopPath'), loopLbl=document.getElementById('loopLbl'),
@@ -233,6 +255,7 @@ async function init(){
     if(Array.isArray(data.substrate)) SUBSTRATE=data.substrate;
     if(typeof data.ns==='string') NS=data.ns;
     if(Array.isArray(data.stages)) STAGES=data.stages;
+    if(Array.isArray(data.timeline)) TIMELINE=data.timeline;
     if(data.version) document.getElementById('ver').textContent=data.version;
   }catch(e){
     console.error('atlas: failed to load /api/atlas.json —',e);
@@ -243,6 +266,7 @@ async function init(){
     return;
   }
   renderAtlas();
+  renderTimeline();
   replay();
 }
 window.addEventListener('load',init);