feat(sat): fan ceiling check + topology fan tiles

Repurpose the previously-unwired RunFanStressTest into RunFanCheck, a Load-tier SAT test that drives stressapptest (CPU+memory) and, when a GPU is present, a GPU burn to 100% simultaneously, then watches every fan until none has climbed for ~60s. The observed peak RPM per fan is the "ceiling"; it is persisted through the existing fan-observation store. MSI G4201 / AMI MegaRAC exposes no host-side fan force (every OEM IPMI command returns 0xc1; Redfish Thermal is GET-only), so load-driven ramp is the closest safe equivalent. See bible-local/decisions/2026-09-04-fan-ceiling-check.md. - platform.ResolveFanMaxRPM: per-fan max with fallback (persisted peak -> peer peak -> current RPM), resolved in platform, not the view. - platform.ErrTestNotApplicable: no load source or no fan sensors -> task lands as cancelled ("not applicable"), never failed, so an engineer never sees a false red. executeTaskWithOptions maps the sentinel; finalizeTaskForResult honours a pre-set TaskCancelled. - Verdict FAIL only for a fan at 0 RPM / IPMI cr-nr under load. - /topo: one small spinning square per fan, sized by RPM / resolved max, clickable through to a new "fan" component-detail type; per-fan status recorded to the component-status DB from the fan SAT summary. - Wiring: /api/sat/fan/run route, "fan" task target, Load-page card, stress-mode Run All. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019VHG21rgTUiR1G3qFHTVmN
2026-09-04 10:35:34 +03:00
parent e4f7519ef3
commit bb2a501a28
22 changed files with 798 additions and 222 deletions
@@ -614,9 +614,138 @@ func renderTopoMainDiagram(hw schema.HardwareSnapshot, exportDir string) string
 		}}))
 	}

+	// Cooling fans — one small square per fan (no PCIe/CPU affinity, arbitrary
+	// count, so a wrapping flex row like PSUs rather than SVG boxes). Each
+	// square is sized by rpm / observed-max-rpm and carries a fan glyph that
+	// spins via CSS — faster when the fan is spinning faster.
+	if fans := dedupeFansByName(hw.Sensors); len(fans) > 0 {
+		current := map[string]float64{}
+		for _, f := range fans {
+			if f.RPM != nil {
+				current[strings.TrimSpace(f.Name)] = float64(*f.RPM)
+			}
+		}
+		b.WriteString(renderTopoFanRow(fans, platform.ResolveFanMaxRPM(current)))
+	}
+
 	return topoCard("Topology", b.String())
 }

+// renderTopoFanRow renders the COOLING row: one clickable square per fan,
+// side length scaled by rpm/maxRPM and a fan glyph whose spin rate tracks the
+// same ratio. maxByName comes from platform.ResolveFanMaxRPM — it already has
+// an entry for every fan (persisted peak, else peer peak, else current RPM),
+// so no fallback logic lives here.
+func renderTopoFanRow(fans []schema.HardwareFanSensor, maxByName map[string]float64) string {
+	const (
+		fanTileMin = 30 // px, a stalled / slowest fan
+		fanTileMax = 58 // px, a fan at its ceiling
+	)
+
+	var tally topoStatusTally
+	for _, f := range fans {
+		tally.add(classifyTopoSeverity(f.Status))
+	}
+
+	var b strings.Builder
+	b.WriteString(topoRowHeading("Cooling"))
+	b.WriteString(topoFanSpinStyle())
+	b.WriteString(`<div style="display:flex;flex-wrap:wrap;gap:6px;align-items:flex-end">`)
+	for _, f := range fans {
+		name := strings.TrimSpace(f.Name)
+		fill, stroke, text := topoSeverityColors(classifyTopoSeverity(f.Status))
+
+		denom := maxByName[name]
+		ratio := 0.0
+		title := name
+		if f.RPM != nil {
+			if denom > 0 {
+				ratio = float64(*f.RPM) / denom
+			}
+			if ratio < 0 {
+				ratio = 0
+			}
+			if ratio > 1 {
+				ratio = 1
+			}
+			if denom > float64(*f.RPM) {
+				title = fmt.Sprintf("%s · %d RPM (max %d)", name, *f.RPM, int(denom))
+			} else {
+				title = fmt.Sprintf("%s · %d RPM", name, *f.RPM)
+			}
+		} else {
+			title = name + " · no reading"
+		}
+
+		side := fanTileMin + int(float64(fanTileMax-fanTileMin)*ratio+0.5)
+		// Spin period: 2.6s at rest down to 0.5s at the observed peak. A fan
+		// with no reading doesn't spin.
+		spin := ""
+		if f.RPM != nil && *f.RPM > 0 {
+			period := 2.6 - 2.1*ratio
+			spin = fmt.Sprintf(`<svg class="topo-fan-spin" style="animation-duration:%.2fs" width="%d" height="%d" viewBox="0 0 24 24" fill="currentColor" aria-hidden="true">`,
+				period, side*7/16, side*7/16) + topoFanGlyphPaths() + `</svg>`
+		} else {
+			spin = fmt.Sprintf(`<svg width="%d" height="%d" viewBox="0 0 24 24" fill="currentColor" style="opacity:.4" aria-hidden="true">`,
+				side*7/16, side*7/16) + topoFanGlyphPaths() + `</svg>`
+		}
+
+		fmt.Fprintf(&b, `<div title="%s" onclick="openComponentDetail('fan')" `+
+			`style="width:%dpx;height:%dpx;display:flex;align-items:center;justify-content:center;`+
+			`border-radius:5px;background:%s;border:1px solid %s;color:%s;cursor:pointer">%s</div>`,
+			html.EscapeString(title), side, side, fill, stroke, text, spin)
+	}
+	b.WriteString(`</div>`)
+	fmt.Fprintf(&b, `<div style="font-size:11px;color:var(--muted);margin-top:6px">%d fans · %s · tile size ∝ RPM / observed max</div>`,
+		len(fans), html.EscapeString(tally.line()))
+	return b.String()
+}
+
+// topoFanSpinStyle emits the keyframes + base class for the spinning fan
+// glyph once per row. A repeated identical <style> is harmless.
+func topoFanSpinStyle() string {
+	return `<style>@keyframes topoFanSpin{to{transform:rotate(360deg)}}` +
+		`.topo-fan-spin{transform-box:fill-box;transform-origin:center;` +
+		`animation-name:topoFanSpin;animation-timing-function:linear;animation-iteration-count:infinite}` +
+		`@media (prefers-reduced-motion:reduce){.topo-fan-spin{animation:none}}</style>`
+}
+
+// topoFanGlyphPaths is the fan-blade drawing shared by every fan square,
+// designed on a 24×24 viewBox.
+func topoFanGlyphPaths() string {
+	return `<ellipse cx="12" cy="6.5" rx="3.1" ry="5.2"/>` +
+		`<ellipse cx="12" cy="6.5" rx="3.1" ry="5.2" transform="rotate(120 12 12)"/>` +
+		`<ellipse cx="12" cy="6.5" rx="3.1" ry="5.2" transform="rotate(240 12 12)"/>` +
+		`<circle cx="12" cy="12" r="2.3"/>`
+}
+
+// dedupeFansByName returns the fan sensors from a snapshot with duplicate
+// names collapsed to their first occurrence, matching the ingest contract's
+// "(sensor_type, name) — first wins" rule and skipping unnamed sensors.
+func dedupeFansByName(sensors *schema.HardwareSensors) []schema.HardwareFanSensor {
+	if sensors == nil {
+		return nil
+	}
+	seen := map[string]bool{}
+	var out []schema.HardwareFanSensor
+	for _, f := range sensors.Fans {
+		name := strings.TrimSpace(f.Name)
+		if name == "" || seen[name] {
+			continue
+		}
+		seen[name] = true
+		out = append(out, f)
+	}
+	return out
+}
+
+// topoRowHeading renders the small uppercase section label shared by the
+// flex rows below the SVG diagram (Firmware / Power Supplies / Cooling / ...).
+func topoRowHeading(title string) string {
+	return fmt.Sprintf(`<div style="font-size:11px;color:var(--muted);text-transform:uppercase;letter-spacing:.05em;margin:16px 0 6px">%s</div>`,
+		html.EscapeString(title))
+}
+
 // renderTopoFlexRow renders a labeled, wrapping row of component cards.
 // Returns "" if items is empty (e.g. no PSU data in this audit).
 func renderTopoFlexRow(title string, items []topoCardInfo) string {
@@ -624,8 +753,7 @@ func renderTopoFlexRow(title string, items []topoCardInfo) string {
 		return ""
 	}
 	var b strings.Builder
-	fmt.Fprintf(&b, `<div style="font-size:11px;color:var(--muted);text-transform:uppercase;letter-spacing:.05em;margin:16px 0 6px">%s</div>`,
-		html.EscapeString(title))
+	b.WriteString(topoRowHeading(title))
 	b.WriteString(`<div style="display:flex;flex-wrap:wrap;gap:10px">`)
 	for _, item := range items {
 		onclick := ""
@@ -1064,6 +1192,15 @@ func inventoryFallbackRecords(compType string, opts HandlerOptions) []app.Compon
 			}
 			records = append(records, app.ComponentStatusRecord{ComponentKey: key, Status: topoSeverityStatus(p.Status)})
 		}
+	case "fan":
+		for i, f := range dedupeFansByName(hw.Sensors) {
+			name := strings.TrimSpace(f.Name)
+			key := fmt.Sprintf("fan:%d", i)
+			if name != "" {
+				key = "fan:" + name
+			}
+			records = append(records, app.ComponentStatusRecord{ComponentKey: key, Status: topoSeverityStatus(f.Status)})
+		}
 	case "gpu", "nic", "raid":
 		for i, dev := range hw.PCIeDevices {
 			if pcieDeviceKind(dev) != compType {