feat(atlas): Phase B tail — live namespaces + trim inline fallback

NamespaceSummary (test-first) renders the substrate ns line from live cluster namespaces (system-filtered, sorted, capped). Handler now overlays both node specs and the ns line via a single cached liveOverlay(). Removed the inline SUBSTRATE/STAGES/NS data — /api/atlas.json is the single source; the page shows an error banner on fetch failure instead of stale data. GPU model naming intentionally NOT done: koala's node has no GPU product label (only nvidia.com/gpu count), so "1× GPU" is the API's truth — naming the RTX 5070 would need GPU-feature-discovery, out of scope. Verified: build/vet/lint(0)/test green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-20 00:56:40 +02:00
parent 39fd9b9adc
commit 633ba153f2
5 changed files with 131 additions and 77 deletions
@@ -37,8 +37,12 @@ func NewHandler() http.Handler {
 			http.Error(w, "atlas build failed", http.StatusInternalServerError)
 			return
 		}
-		if live := liveSubstrate(); len(live) > 0 {
-			a.Substrate = atlas.MergeSubstrate(a.Substrate, live)
+		ld := liveOverlay()
+		if len(ld.hosts) > 0 {
+			a.Substrate = atlas.MergeSubstrate(a.Substrate, ld.hosts)
+		}
+		if ld.ns != "" {
+			a.NS = "Tailscale mesh · " + ld.ns
 		}
 		w.Header().Set("Content-Type", "application/json; charset=utf-8")
 		_ = json.NewEncoder(w).Encode(a)
@@ -46,33 +50,41 @@ func NewHandler() http.Handler {
 	return mux
 }

-// substrate cache: query the cluster at most once per TTL; fall back to the
-// authored substrate (returns nil) whenever the cluster is unreachable.
+// liveOverlay holds cluster-sourced substrate facts (node specs + namespace line).
+type liveOverlayData struct {
+	hosts []atlas.Host
+	ns    string
+}
+
+// live cache: query the cluster at most once per TTL; fall back to the authored
+// substrate/ns (zero values) whenever the cluster is unreachable.
 var (
-	subMu    sync.Mutex
-	subCache []atlas.Host
-	subAt    time.Time
+	liveMu    sync.Mutex
+	liveCache liveOverlayData
+	liveAt    time.Time
 )

-const substrateTTL = 30 * time.Second
+const liveTTL = 30 * time.Second

-func liveSubstrate() []atlas.Host {
-	subMu.Lock()
-	defer subMu.Unlock()
-	if !subAt.IsZero() && time.Since(subAt) < substrateTTL {
-		return subCache
+func liveOverlay() liveOverlayData {
+	liveMu.Lock()
+	defer liveMu.Unlock()
+	if !liveAt.IsZero() && time.Since(liveAt) < liveTTL {
+		return liveCache
 	}
-	subAt = time.Now()
-	raw, err := cluster.Nodes()
-	if err != nil {
-		subCache = nil
-		return nil
+	liveAt = time.Now()
+
+	var d liveOverlayData
+	if raw, err := cluster.Nodes(); err == nil {
+		if hosts, err := atlas.HostsFromNodes(raw); err == nil {
+			d.hosts = hosts
+		}
 	}
-	hosts, err := atlas.HostsFromNodes(raw)
-	if err != nil {
-		subCache = nil
-		return nil
+	if raw, err := cluster.Namespaces(); err == nil {
+		if s, err := atlas.NamespaceSummary(raw); err == nil {
+			d.ns = s
+		}
 	}
-	subCache = hosts
-	return hosts
+	liveCache = d
+	return d
 }
@@ -114,7 +114,7 @@
 <body>
 <header>
  <h1><b>CAD</b> Atlas · From Signal to Pod</h1>
-  <span class="sub mono">one human gate · everything up- and downstream is agents · <em>v0.5 · data-driven (CI + substrate from the live cluster)</em></span>
+  <span class="sub mono">one human gate · everything up- and downstream is agents · <em>v0.6 · live cluster (nodes + namespaces) · single-source /api/atlas.json</em></span>
  <div class="controls">
    <button id="replay"><span class="dot"></span> Replay</button>
    <button id="slowmo">Slow-mo · <span id="slowState">off</span></button>
@@ -150,57 +150,11 @@
 </footer>

 <script>
-// Inline data is an offline FALLBACK. Authoritative data is fetched from
-// /api/atlas.json (authored atlas.json + CI stage generated from the real cd.yml).
-let SUBSTRATE=[
-  {n:"koala",  k:"RTX 5070 · k3s control-plane · Gitea · LiteLLM :30401 · llama-swap :31234 · searxng"},
-  {n:"iguana", k:"M2 Ultra · Ollama / mlx"},
-  {n:"flamingo",k:"daily driver · ~/dev"},
-  {n:"piguard",k:"NGINX reverse-proxy · ntfy"},
-];
-let NS="Tailscale mesh · ns: ai-stack · supervisor(→brain) · gitea-mcp · infra-mcp · council";
-
-let STAGES=[
- {no:"STAGE 00",cls:"",title:"Signals",path:"→ mathias/signals",nodes:[
-   {t:"Applied AI Radar",d:"Daily Tier-1 + weekly Tier-2 deep pass. Verified-primary bar (paper/benchmark/code/named-lab).",tags:["cron · daily/weekly","→ signals #1–26+"]},
-   {t:"Manual capture",d:"claude.ai strategic drop · brain capture tool.",tags:["ad-hoc"]},
-   {t:"Aspirational surfaces",pill:"var(--dim)",d:"Telegram / voice / URL → inbox. NOT built.",tags:["gap"]},
- ]},
- {no:"STAGE 01",cls:"telos",title:"TELOS",path:"wiki/telos/",nodes:[
-   {t:"Intention substrate",pill:"var(--violet)",d:"Mission · goals · problems · strategies · status. Every downstream item traces to a goal.",tags:["brain_query wing=telos"]},
- ]},
- {no:"STAGE 02",cls:"",title:"Strategic session",path:"claude.ai frontier + brain MCP",nodes:[
-   {t:"Design · ADRs · specs",d:"Human + frontier model. ISC acceptance criteria written here.",tags:["Define / converge"]},
-   {t:"🏛️ LLM Council",cls:"council",pill:"var(--violet)",d:"fan-out → anonymous cross-review → chairman synth. glm-4.7-flash · qwen36-35b · gemma4-31b (chair).",tags:["hard strategic Q","chat.d-ma.be"]},
-   {t:"Autoresearch Council",cls:"council",pill:"var(--violet)",d:"Sibling pipe — ratifies research before the gate.",tags:["proposed: → standalone svc"]},
- ]},
- {no:"STAGE 03",cls:"",title:"Spec → Gitea issue",path:"agent-ready contract",nodes:[
-   {t:"Contract enforced",d:"Binary ISC · declared risk tier · reg-risk assessment · no open human deps.",tags:["LOW / MED / HIGH"]},
-   {t:"Admission controller",d:"Ed25519-sign issue body at creation (#36). Verify sig + PR alignment at infra boundary.",tags:["chain of custody"]},
-   {t:"⚖️ var-go Oath",cls:"oath",pill:"var(--gold)",d:"Acceptance contract embedded in the issue as a ```var fenced block. Exactly one — zero/multiple fail closed. Prose → typed steps; failures anchored to byte spans.",tags:["swedsl · var-go","defined here → enforced @06"]},
- ]},
- {no:"STAGE 04",cls:"gate",title:"Human dispatch gate",path:"the only checkpoint",nodes:[
-   {t:"Human triggers execution",cls:"gateway",pill:"var(--amber)",d:"Ratify proposed-plan + risk tier, then dispatch.",gate:true},
-   {t:"Session-Dispatch bridge",cls:"bridge",pill:"var(--blue)",d:"claude.ai MCP → gitea:workflow_run_trigger → cad-dispatch.yml → agentsquad. The final design→execution bridge.",tags:["workflow_dispatch"]},
- ]},
- {no:"STAGE 05",cls:"exec",title:"Execute · agentsquad",path:"koala · cmd/agentsquad-serve",nodes:[
-   {t:"Task API",pill:"var(--coral)",d:"POST /tasks → job id · GET /tasks/{id}. taskqueue + serve (v0.12+).",tags:["single agentsquad.yaml"]},
-   {t:"Executor + reviewer loop",cls:"win",pill:"var(--coral)",d:"ADK Go + LiteLLM. Frontier models (local qwen spirals). Reviewer on distinct tier — echo-chamber prevention.",risk:true},
-   {t:"dma-cli · routing + scope",cls:"bridge",pill:"var(--blue)",d:"Harness-config arm: routes agents to the right LLM backend. Three-layer scope policy + confirmation gate = CAD guardrail.",tags:["backend routing","scope guardrail"]},
-   {t:"assessor-loop ledger",d:"Attestation ledger (audit trail) + brain session_log on completion.",tags:["audit package"]},
- ]},
- {no:"STAGE 06",cls:"",title:"PR → CI",path:"Gitea Actions",nodes:[
-   {t:"PR + label",d:"Gitea PR · agent-done / agent-blocked label.",tags:[]},
-   {t:"Mechanical gate",d:"go test · vet · lint · govulncheck. ISC verified mechanically.",tags:["green = proceed"]},
-   {t:"⚖️ var-go/oath gate",cls:"oath",pill:"var(--gold)",d:"cmd/vargo-gate runs in CI → posts commit status context=var-go/oath. Authoritative FLOOR: failed Oath blocks regardless of reviewer approval (#55 anti-rubber-stamp).",tags:["branch-protection req","enforces @03 Oath"]},
- ]},
- {no:"STAGE 07",cls:"cd",title:"CD → pod",path:"Flux GitOps → k3s",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:[
-   {t:"Close the loop",pill:"var(--violet)",d:"session_log + attestation → brain. Score deploy outcome vs originating goal. (arc partly manual — improvement target.)",tags:["continuous"]},
- ]},
-];
+// Single source of truth: /api/atlas.json (Go app — authored atlas.json + CI
+// 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=[];

 const track=document.getElementById('track');
 let stageEls=[];
@@ -279,7 +233,14 @@ 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;
-  }catch(e){ console.warn('atlas: using inline fallback —',e); }
+  }catch(e){
+    console.error('atlas: failed to load /api/atlas.json —',e);
+    document.getElementById('track').insertAdjacentHTML('beforeend',
+      '<div class="stage"><div class="no mono">ERROR</div>'+
+      '<h2 style="color:var(--coral)">Data unavailable</h2>'+
+      '<div class="path mono">/api/atlas.json failed to load</div></div>');
+    return;
+  }
  renderAtlas();
  replay();
 }