feat: add selectable performance history windows

README.md

@@ -16,7 +16,7 @@ Native-like Hermes dashboard plugin for local Ollama model management and chat.
 - Chat uses a conversation rail, central message timeline, and dedicated model/runtime controls
 - Messages support safe Markdown-style emphasis, fenced code blocks, copy, and retry actions
 - Runtime operations and historical performance graphs are restored below chat: CPU usage/load, system memory, GPU usage/VRAM, disk, swap, resident Ollama weights, and resident model count
-- Performance samples are retained locally for the last 120 one-second telemetry snapshots
+- Performance history is stored in minute buckets for up to 24 hours and can be viewed as Last 1 hour, Last 6 hours, Last 9 hours, Last 12 hours, or Last 24 hours
 - The catalog is loaded separately from live status with server-side search, filters, and pagination
 - Natural composer behavior: Enter sends; Shift+Enter creates a new line
 - Paste images directly into the composer and drag/drop images, PDFs, and text files

dashboard/dist/index.js

@@ -10,6 +10,13 @@
   var CHAT_STORAGE_KEY = "hermes.ollama-manager.chat.v1";
   var PLACEMENT_STORAGE_KEY = "hermes.ollama-manager.placement.v1";
   var PERFORMANCE_STORAGE_KEY = "hermes.ollama-manager.performance.v1";
+  var PERFORMANCE_WINDOWS = [
+    { value: "1", label: "Last 1 hour", seconds: 60 * 60 },
+    { value: "6", label: "Last 6 hours", seconds: 6 * 60 * 60 },
+    { value: "9", label: "Last 9 hours", seconds: 9 * 60 * 60 },
+    { value: "12", label: "Last 12 hours", seconds: 12 * 60 * 60 },
+    { value: "24", label: "Last 24 hours", seconds: 24 * 60 * 60 }
+  ];
 
   function readSavedPlacements() {
     try {
@@ -261,21 +268,31 @@
   }
   function PerformanceGraphs(props) {
     var samples = props.samples || [];
+    var rangeState = React.useState("1"), range = rangeState[0], setRange = rangeState[1];
+    var selectedWindow = PERFORMANCE_WINDOWS.find(function (item) { return item.value === range; }) || PERFORMANCE_WINDOWS[0];
+    var cutoff = Date.now() / 1000 - selectedWindow.seconds;
+    var visibleSamples = samples.filter(function (sample) { return Number(sample.captured_at || 0) >= cutoff; });
     function pct(value) { return value == null ? "n/a" : Number(value).toFixed(1) + "%"; }
     function gib(value) { return value == null ? "n/a" : Number(value).toFixed(2) + " GiB"; }
     function count(value) { return value == null ? "n/a" : String(Math.round(value)); }
     return h("section", { className: "ollama-performance-graphs" },
-      h("div", { className: "ollama-performance-graphs-heading" }, h("div", null, h("h3", null, "Performance history"), h("p", null, "CPU, GPU, memory, storage, swap, and Ollama residency over the last ", samples.length, " samples.")), h("span", null, samples.length ? "Live · 1 second" : "Waiting for telemetry")),
+      h("div", { className: "ollama-performance-graphs-heading" },
+        h("div", null, h("h3", null, "Performance history"), h("p", null, "CPU, GPU, memory, storage, swap, and Ollama residency over the selected window. ", visibleSamples.length, " minute samples available.")),
+        h("div", { className: "ollama-performance-controls" },
+          h("label", { className: "ollama-performance-range" }, "History window", h("select", { value: range, onChange: function (event) { setRange(event.target.value); }, "aria-label": "Performance history window" }, PERFORMANCE_WINDOWS.map(function (item) { return h("option", { key: item.value, value: item.value }, item.label); }))),
+          h("span", null, samples.length ? "Live · 1 second" : "Waiting for telemetry")
+        )
+      ),
       h("div", { className: "ollama-performance-grid" },
-        h(PerformanceGraph, { title: "CPU usage", subtitle: "Total processor utilization", valueKey: "cpu_usage_percent", max: 100, range: "100%", format: pct, samples: samples }),
-        h(PerformanceGraph, { title: "CPU load", subtitle: "1-minute load average", valueKey: "cpu_load_1m", range: "dynamic", format: function (value) { return Number(value).toFixed(2); }, samples: samples }),
-        h(PerformanceGraph, { title: "System memory", subtitle: "Used RAM", valueKey: "memory_used_percent", max: 100, range: "100%", format: pct, samples: samples }),
-        h(PerformanceGraph, { title: "GPU usage", subtitle: "Aggregate GPU utilization", valueKey: "gpu_usage_percent", max: 100, range: "100%", format: pct, samples: samples }),
-        h(PerformanceGraph, { title: "GPU VRAM", subtitle: "Used video memory", valueKey: "gpu_vram_used_percent", max: 100, range: "100%", format: pct, samples: samples }),
-        h(PerformanceGraph, { title: "Disk usage", subtitle: "Root filesystem", valueKey: "disk_used_percent", max: 100, range: "100%", format: pct, samples: samples }),
-        h(PerformanceGraph, { title: "Swap usage", subtitle: "Used swap memory", valueKey: "swap_used_percent", max: 100, range: "100%", format: pct, samples: samples }),
-        h(PerformanceGraph, { title: "Ollama model weights", subtitle: "Resident model bytes", valueKey: "ollama_model_gib", range: "dynamic", format: gib, samples: samples }),
-        h(PerformanceGraph, { title: "Resident models", subtitle: "Loaded Ollama model count", valueKey: "resident_model_count", range: "dynamic", format: count, samples: samples })
+        h(PerformanceGraph, { title: "CPU usage", subtitle: "Total processor utilization", valueKey: "cpu_usage_percent", max: 100, range: "100%", format: pct, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "CPU load", subtitle: "1-minute load average", valueKey: "cpu_load_1m", range: "dynamic", format: function (value) { return Number(value).toFixed(2); }, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "System memory", subtitle: "Used RAM", valueKey: "memory_used_percent", max: 100, range: "100%", format: pct, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "GPU usage", subtitle: "Aggregate GPU utilization", valueKey: "gpu_usage_percent", max: 100, range: "100%", format: pct, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "GPU VRAM", subtitle: "Used video memory", valueKey: "gpu_vram_used_percent", max: 100, range: "100%", format: pct, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "Disk usage", subtitle: "Root filesystem", valueKey: "disk_used_percent", max: 100, range: "100%", format: pct, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "Swap usage", subtitle: "Used swap memory", valueKey: "swap_used_percent", max: 100, range: "100%", format: pct, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "Ollama model weights", subtitle: "Resident model bytes", valueKey: "ollama_model_gib", range: "dynamic", format: gib, samples: visibleSamples }),
+        h(PerformanceGraph, { title: "Resident models", subtitle: "Loaded Ollama model count", valueKey: "resident_model_count", range: "dynamic", format: count, samples: visibleSamples })
       )
     );
   }
@@ -387,6 +404,7 @@
     var aggregateState = React.useState(null), aggregate = aggregateState[0], setAggregate = aggregateState[1];
     var runtimeState = React.useState(null), runtime = runtimeState[0], setRuntime = runtimeState[1];
     var samplesState = React.useState(readSavedPerformanceSamples()), samples = samplesState[0], setSamples = samplesState[1];
+    var performanceHistoryAt = React.useRef(0);
     var busyState = React.useState(""), busy = busyState[0], setBusy = busyState[1];
     var noticeState = React.useState(null), notice = noticeState[0], setNotice = noticeState[1];
     var validationState = React.useState(null), validationReports = validationState[0], setValidationReports = validationState[1];
@@ -474,25 +492,19 @@
       refreshConversations();
       setNotice({ ok: "Conversation deleted from shared storage." });
     }
-    function pollRuntime() {
-      fetchJSON(API + "/runtime").then(function (value) {
-        var total = Number(value.memory_total_bytes || 0), used = Number(value.memory_used_bytes || 0), gpu = value.gpu || {}, gpus = gpu.gpus || [], gpuTotal = gpus.reduce(function (sum, item) { return sum + Number(item.total_bytes || 0); }, 0), gpuUsed = gpus.reduce(function (sum, item) { return sum + Number(item.used_bytes || 0); }, 0), swapTotal = Number(value.swap_total_bytes || 0), swapUsed = Number(value.swap_used_bytes || 0);
-        setRuntime(value);
-        setSamples(function (old) { return old.concat([{
-          captured_at: Number(value.captured_at || Date.now() / 1000),
-          cpu_usage_percent: value.cpu && value.cpu.usage_percent,
-          cpu_load_1m: value.cpu && value.cpu.load_average && value.cpu.load_average[0],
-          memory_used_percent: total ? used * 100 / total : null,
-          gpu_usage_percent: gpu.utilization_percent,
-          gpu_vram_used_percent: gpuTotal ? gpuUsed * 100 / gpuTotal : null,
-          disk_used_percent: value.disk && value.disk.used_percent,
-          swap_used_percent: swapTotal ? swapUsed * 100 / swapTotal : null,
-          ollama_model_gib: Number(value.ollama_model_bytes || 0) / (1024 * 1024 * 1024),
-          resident_model_count: Array.isArray(value.model_memory) ? value.model_memory.length : 0
-        }]).slice(-120); });
+    function pollPerformanceHistory() {
+      performanceHistoryAt.current = Date.now();
+      fetchJSON(API + "/runtime/history?hours=24").then(function (value) {
+        setSamples(Array.isArray(value.samples) ? value.samples : []);
       }).catch(function () {});
     }
-    React.useEffect(function () { pollRuntime(); var timer = setInterval(pollRuntime, 1000); return function () { clearInterval(timer); }; }, []);
+    function pollRuntime() {
+      fetchJSON(API + "/runtime").then(function (value) {
+        setRuntime(value);
+        if (Date.now() - performanceHistoryAt.current >= 5000) pollPerformanceHistory();
+      }).catch(function () {});
+    }
+    React.useEffect(function () { pollRuntime(); pollPerformanceHistory(); var timer = setInterval(pollRuntime, 1000); return function () { clearInterval(timer); }; }, []);
     React.useEffect(function () { savePerformanceSamples(samples); }, [samples]);
 
     React.useEffect(function () { savePlacements(placements); }, [placements]);

dashboard/manifest.json

@@ -3,7 +3,7 @@
   "label": "Ollama Models",
   "description": "Inspect, manage, and chat with local Ollama models, including shared persistent conversations, performance metrics, images, PDFs, URLs, and live memory telemetry.",
   "icon": "Cpu",
-  "version": "1.7.7",
+  "version": "1.7.8",
   "tab": {"path": "/ollama-manager", "position": "after:models"},
   "entry": "dist/index.js",
   "css": "dist/style.css",

dashboard/plugin_api.py

@@ -82,6 +82,10 @@ CHAT_HEARTBEAT_INTERVAL = 5.0
 HARNESS_MIN_VALIDATORS = 1
 HARNESS_MAX_DRAFT_CHARS = 24_000
 HARNESS_MAX_VALIDATION_CHARS = 8_000
+PERFORMANCE_HISTORY_FILE = "performance-history.jsonl"
+PERFORMANCE_HISTORY_BUCKET_SECONDS = 60
+PERFORMANCE_HISTORY_MAX_SAMPLES = 24 * 60
+PERFORMANCE_HISTORY_WINDOWS = {1, 6, 9, 12, 24}
 
 _jobs: dict[str, dict[str, Any]] = {}
 _jobs_lock = threading.Lock()
@@ -1003,6 +1007,83 @@ def _runtime_snapshot() -> dict[str, Any]:
     }
 
 
+def _performance_sample(runtime: dict[str, Any]) -> dict[str, Any]:
+    total = int(runtime.get("memory_total_bytes") or 0)
+    used = int(runtime.get("memory_used_bytes") or 0)
+    gpu = runtime.get("gpu") or {}
+    gpus = gpu.get("gpus") or []
+    gpu_total = sum(int(item.get("total_bytes") or 0) for item in gpus)
+    gpu_used = sum(int(item.get("used_bytes") or 0) for item in gpus)
+    swap_total = int(runtime.get("swap_total_bytes") or 0)
+    swap_used = int(runtime.get("swap_used_bytes") or 0)
+    cpu = runtime.get("cpu") or {}
+    disk = runtime.get("disk") or {}
+    load_average = cpu.get("load_average") or []
+    captured_at = float(runtime.get("captured_at") or time.time())
+    bucket = int(captured_at // PERFORMANCE_HISTORY_BUCKET_SECONDS) * PERFORMANCE_HISTORY_BUCKET_SECONDS
+    return {
+        "captured_at": bucket,
+        "cpu_usage_percent": cpu.get("usage_percent"),
+        "cpu_load_1m": load_average[0] if load_average else None,
+        "memory_used_percent": used * 100 / total if total else None,
+        "gpu_usage_percent": gpu.get("utilization_percent"),
+        "gpu_vram_used_percent": gpu_used * 100 / gpu_total if gpu_total else None,
+        "disk_used_percent": disk.get("used_percent"),
+        "swap_used_percent": swap_used * 100 / swap_total if swap_total else None,
+        "ollama_model_gib": int(runtime.get("ollama_model_bytes") or 0) / (1024 * 1024 * 1024),
+        "resident_model_count": len(runtime.get("model_memory") or []),
+    }
+
+
+def _read_performance_history() -> list[dict[str, Any]]:
+    path = _home() / PERFORMANCE_HISTORY_FILE
+    rows: dict[int, dict[str, Any]] = {}
+    try:
+        for line in path.read_text(encoding="utf-8").splitlines():
+            try:
+                sample = json.loads(line)
+                bucket = int(sample.get("captured_at"))
+                if bucket > 0:
+                    rows[bucket] = sample
+            except (TypeError, ValueError, json.JSONDecodeError):
+                continue
+    except OSError:
+        return []
+    return [rows[key] for key in sorted(rows)][-PERFORMANCE_HISTORY_MAX_SAMPLES:]
+
+
+_performance_history_lock = threading.Lock()
+
+
+def _record_performance_sample(runtime: dict[str, Any]) -> list[dict[str, Any]]:
+    sample = _performance_sample(runtime)
+    path = _home() / PERFORMANCE_HISTORY_FILE
+    with _performance_history_lock:
+        rows = {int(item["captured_at"]): item for item in _read_performance_history() if item.get("captured_at")}
+        rows[int(sample["captured_at"])] = sample
+        cutoff = int(time.time()) - 24 * 60 * 60
+        history = [rows[key] for key in sorted(rows) if key >= cutoff][-PERFORMANCE_HISTORY_MAX_SAMPLES:]
+        temporary = path.with_name(f".{path.name}.{os.getpid()}.tmp")
+        temporary.write_text("".join(json.dumps(item, separators=(",", ":")) + "\n" for item in history), encoding="utf-8")
+        temporary.replace(path)
+        return history
+
+
+def _performance_history(hours: int) -> list[dict[str, Any]]:
+    cutoff = time.time() - hours * 60 * 60
+    return [sample for sample in _read_performance_history() if float(sample.get("captured_at") or 0) >= cutoff]
+
+
+def _validate_performance_hours(hours: int) -> int:
+    try:
+        value = int(hours)
+    except (TypeError, ValueError) as exc:
+        raise HTTPException(400, "History window must be 1, 6, 9, 12, or 24 hours") from exc
+    if value not in PERFORMANCE_HISTORY_WINDOWS:
+        raise HTTPException(400, "History window must be 1, 6, 9, 12, or 24 hours")
+    return value
+
+
 def _validate_public_url(value: str) -> str:
     parsed = urlparse(value.strip())
     if parsed.scheme not in {"http", "https"} or not parsed.hostname:
@@ -2300,7 +2381,21 @@ def metrics(limit: int = 100) -> dict[str, Any]:
 
 @router.get("/runtime")
 def runtime() -> dict[str, Any]:
-    return _runtime_snapshot()
+    snapshot = _runtime_snapshot()
+    _record_performance_sample(snapshot)
+    return snapshot
+
+
+@router.get("/runtime/history")
+def runtime_history(hours: int = 24) -> dict[str, Any]:
+    selected_hours = _validate_performance_hours(hours)
+    snapshot = _runtime_snapshot()
+    _record_performance_sample(snapshot)
+    return {
+        "hours": selected_hours,
+        "bucket_seconds": PERFORMANCE_HISTORY_BUCKET_SECONDS,
+        "samples": _performance_history(selected_hours),
+    }
 
 
 @router.post("/chat/load")

plugin.yaml

@@ -1,5 +1,5 @@
 name: ollama-manager
-version: 1.7.7
+version: 1.7.8
 description: Native dashboard manager and chat interface for local Ollama models, attachments, URLs, shared persistent conversations, performance metrics, and live runtime telemetry.
 auto_install_dependencies: true
 python_dependencies:

tests/test_validation_harness.py

@@ -1,4 +1,6 @@
 import threading
+import tempfile
+import time
 import unittest
 from pathlib import Path
 from unittest.mock import patch
@@ -229,6 +231,42 @@ class ValidationHarnessTests(unittest.TestCase):
         self.assertIn("historical performance graphs are shown in Operations / Performance below", bundle)
         self.assertIn("setInterval(pollRuntime, 1000)", bundle)
 
+    def test_performance_sample_uses_minute_bucket_and_runtime_values(self):
+        sample = api._performance_sample({
+            "captured_at": 1700000061,
+            "memory_total_bytes": 200,
+            "memory_used_bytes": 100,
+            "swap_total_bytes": 100,
+            "swap_used_bytes": 25,
+            "ollama_model_bytes": 1024 ** 3,
+            "model_memory": [{"name": "model"}],
+            "cpu": {"usage_percent": 12.5, "load_average": [1.25]},
+            "gpu": {"utilization_percent": 40, "gpus": [{"total_bytes": 100, "used_bytes": 50}]},
+            "disk": {"used_percent": 33.3},
+        })
+        self.assertEqual(sample["captured_at"], 1700000040)
+        self.assertEqual(sample["memory_used_percent"], 50.0)
+        self.assertEqual(sample["gpu_vram_used_percent"], 50.0)
+        self.assertEqual(sample["resident_model_count"], 1)
+
+    def test_performance_history_accepts_only_requested_windows(self):
+        for hours in (1, 6, 9, 12, 24):
+            self.assertEqual(api._validate_performance_hours(hours), hours)
+        with self.assertRaises(api.HTTPException) as context:
+            api._validate_performance_hours(2)
+        self.assertEqual(context.exception.status_code, 400)
+
+    def test_performance_history_deduplicates_minute_buckets(self):
+        with tempfile.TemporaryDirectory() as directory, patch.object(api, "_home", return_value=Path(directory)):
+            base = int(time.time()) - 120
+            runtime = {"captured_at": base + 1, "memory_total_bytes": 1, "memory_used_bytes": 1, "cpu": {}, "gpu": {}, "disk": {}, "model_memory": []}
+            first = api._record_performance_sample(runtime)
+            runtime["captured_at"] = base + 2
+            second = api._record_performance_sample(runtime)
+        self.assertEqual(len(first), 1)
+        self.assertEqual(len(second), 1)
+        self.assertEqual(second[0]["captured_at"], ((base + 2) // 60) * 60)
+
 
 if __name__ == "__main__":
     unittest.main()