From c292ff2242594e081656136a2a3a9f623cbde4de Mon Sep 17 00:00:00 2001
From: mARTin-B78 <mail@martin-bierschenk.de>
Date: Tue, 9 Jun 2026 23:30:33 +0200
Subject: [PATCH] fix: probe Prometheus /metrics at server root, not under /v1
 (v2.03.10)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 linux/CHANGELOG.md          |  7 +++++
 linux/blitztext/__init__.py |  2 +-
 linux/blitztext/stt.py      | 55 ++++++++++++++++++++++---------------
 3 files changed, 41 insertions(+), 23 deletions(-)

diff --git a/linux/CHANGELOG.md b/linux/CHANGELOG.md
index eb5f57f..ace7c91 100644
--- a/linux/CHANGELOG.md
+++ b/linux/CHANGELOG.md
@@ -9,6 +9,13 @@ The version is defined in [`blitztext/__init__.py`](blitztext/__init__.py).
 
 ## [Unreleased]
 
+## [2.03.10] - 2026-06-09
+
+### Fixed
+- **Server RAM probe.** Prometheus `/metrics` is almost always at the server
+  root (`http://host:port/metrics`), not under `/v1`. Now tries the root URL
+  first before falling back to the API base path.
+
 ## [2.03.09] - 2026-06-09
 
 ### Added
diff --git a/linux/blitztext/__init__.py b/linux/blitztext/__init__.py
index 55b59df..3993cc4 100644
--- a/linux/blitztext/__init__.py
+++ b/linux/blitztext/__init__.py
@@ -6,4 +6,4 @@ counterpart to the macOS Blitztext menu bar app: it runs natively on the host
 (not in a container) so it can type into any application via xdotool.
 """
 
-__version__ = "2.03.09"
+__version__ = "2.03.10"
diff --git a/linux/blitztext/stt.py b/linux/blitztext/stt.py
index 40d74f5..b5f9e3f 100644
--- a/linux/blitztext/stt.py
+++ b/linux/blitztext/stt.py
@@ -154,34 +154,45 @@ def probe_server_ram_mb(base_url: str, timeout: float = 3.0) -> float | None:
     Returns RSS in MB if the server exposes Prometheus metrics with either
     ``process_resident_memory_bytes`` (standard Python/Go exporter) or
     ``container_memory_rss`` (cAdvisor). Returns None if not available.
+
+    Tries the server root first (http://host:port/metrics) then the api base
+    path (http://host:port/v1/metrics), because Prometheus endpoints are almost
+    always mounted at root even when the API lives under /v1.
     """
     if not base_url:
         return None
-    base = _api_base(base_url)
-    try:
-        req = urllib.request.Request(base + "/metrics")
-        with urllib.request.urlopen(req, timeout=timeout) as resp:
-            text = resp.read().decode("utf-8", "replace")
-    except Exception:
+    p = urlparse(base_url.rstrip("/"))
+    root = f"{p.scheme}://{p.netloc}"
+    candidates = [root + "/metrics"]
+    api_base_metrics = _api_base(base_url) + "/metrics"
+    if api_base_metrics != candidates[0]:
+        candidates.append(api_base_metrics)
+
+    def _parse(text: str) -> float | None:
+        for line in text.splitlines():
+            line = line.strip()
+            if line.startswith("#"):
+                continue
+            for metric in ("process_resident_memory_bytes", "container_memory_rss"):
+                if line.startswith(metric):
+                    parts = line.split()
+                    if len(parts) >= 2:
+                        try:
+                            return float(parts[-1]) / (1024 * 1024)  # bytes → MB
+                        except ValueError:
+                            pass
         return None
 
-    # Parse Prometheus text format — we only need two specific metric names.
-    # Lines look like:  process_resident_memory_bytes 1.23456e+08
-    best: float | None = None
-    for line in text.splitlines():
-        line = line.strip()
-        if line.startswith("#"):
+    for url in candidates:
+        try:
+            req = urllib.request.Request(url)
+            with urllib.request.urlopen(req, timeout=timeout) as resp:
+                result = _parse(resp.read().decode("utf-8", "replace"))
+                if result is not None:
+                    return result
+        except Exception:
             continue
-        for metric in ("process_resident_memory_bytes", "container_memory_rss"):
-            if line.startswith(metric):
-                parts = line.split()
-                if len(parts) >= 2:
-                    try:
-                        best = float(parts[-1]) / (1024 * 1024)  # bytes → MB
-                        return best
-                    except ValueError:
-                        pass
-    return best
+    return None
 
 
 def detect_remote_device(base_url: str, timeout: float = 3.0) -> str: