From 4b3ed8cccd2ecf71d5daa4e82656012bc0056e31 Mon Sep 17 00:00:00 2001
From: "anthony.wen" <awen01@gmail.com>
Date: Thu, 26 Mar 2026 21:28:27 -0400
Subject: [PATCH] Add per-spec fallback for categorized watcher grouped
 summaries

- update the categorized watcher to fall back to earlier per-spec Run Finished entries when a grouped Cloud Run Finished section is present but does not contain host rows
- broaden duration parsing so colon-form timings like 13:59 and 15:32 from per-spec Cypress summaries are converted into seconds correctly
- make grouped Mattermost posting resilient across categorized batches whose cloud-summary output is incomplete or inconsistent, not just a single distro family
---
 atvm/watcher-service/atvm_run_watcher.py | 65 +++++++++++++++---------
 1 file changed, 42 insertions(+), 23 deletions(-)

diff --git a/atvm/watcher-service/atvm_run_watcher.py b/atvm/watcher-service/atvm_run_watcher.py
index 7aa8f9f..b456b98 100644
--- a/atvm/watcher-service/atvm_run_watcher.py
+++ b/atvm/watcher-service/atvm_run_watcher.py
@@ -265,6 +265,14 @@ def extract_check_xml_timestamp_from_file(xml_path: Path) -> Optional[datetime]:
 
 def parse_duration_seconds(raw: str) -> Optional[float]:
     raw = " ".join(raw.split())
+    if re.fullmatch(r"\d+:\d+(?::\d+)?", raw):
+        parts = [int(part) for part in raw.split(":")]
+        if len(parts) == 2:
+            minutes, seconds = parts
+            return minutes * 60 + seconds
+        if len(parts) == 3:
+            hours, minutes, seconds = parts
+            return hours * 3600 + minutes * 60 + seconds
     match = re.search(r"(?:(\d+)h\s+)?(?:(\d+)m\s+)?(\d+(?:\.\d+)?)(?:s)?", raw)
     if not match:
         return None
@@ -274,6 +282,33 @@ def parse_duration_seconds(raw: str) -> Optional[float]:
     return hours * 3600 + minutes * 60 + seconds
 
 
+def extract_host_results_from_run_finished_segment(segment_text: str, inventory: Dict[str, str]) -> Dict[str, HostResult]:
+    host_results: Dict[str, HostResult] = {}
+    normalized = re.sub(r"\n\s*│\s*s\s*│", "s", segment_text)
+    for host_match in re.finditer(
+        r"✔\s+(atvm[^\s]+)\.ts\s+([0-9:hms.\s]+?)\s+(\d+)\s+(\d+)\s+([-\d]+)\s+([-\d]+)\s+([-\d]+)",
+        normalized,
+        re.S,
+    ):
+        host = host_match.group(1)
+        duration_seconds = parse_duration_seconds(host_match.group(2))
+        tests = int(host_match.group(3))
+        passing = int(host_match.group(4))
+        failing = 0 if host_match.group(5) == "-" else int(host_match.group(5))
+        detail = f"{tests} tests, {failing} failures"
+        status = "FAIL" if failing else "PASS"
+        host_results[host] = HostResult(
+            host=host,
+            kernel=inventory.get(host, "unknown"),
+            status=status,
+            detail=detail,
+            tests=tests,
+            failures=failing,
+            duration_seconds=duration_seconds,
+        )
+    return host_results
+
+
 def extract_completed_subrun_summaries(log_text: str, inventory: Dict[str, str]) -> List[Dict[str, object]]:
     summaries: List[Dict[str, object]] = []
     cloud_blocks = list(
@@ -283,33 +318,16 @@ def extract_completed_subrun_summaries(log_text: str, inventory: Dict[str, str])
             re.S,
         )
     )
+    previous_block_end = 0
     for block in cloud_blocks:
         block_text = block.group(1)
         currents_url = block.group(2)
-        normalized = re.sub(r"\n\s*│\s*s\s*│", "s", block_text)
-        host_results: Dict[str, HostResult] = {}
-        for host_match in re.finditer(
-            r"✔\s+(atvm[^\s]+)\.ts\s+([0-9hms.\s]+?)\s+(\d+)\s+(\d+)\s+([-\d]+)\s+([-\d]+)\s+([-\d]+)",
-            normalized,
-            re.S,
-        ):
-            host = host_match.group(1)
-            duration_seconds = parse_duration_seconds(host_match.group(2))
-            tests = int(host_match.group(3))
-            passing = int(host_match.group(4))
-            failing = 0 if host_match.group(5) == "-" else int(host_match.group(5))
-            detail = f"{tests} tests, {failing} failures"
-            status = "FAIL" if failing else "PASS"
-            host_results[host] = HostResult(
-                host=host,
-                kernel=inventory.get(host, "unknown"),
-                status=status,
-                detail=detail,
-                tests=tests,
-                failures=failing,
-                duration_seconds=duration_seconds,
-            )
+        host_results = extract_host_results_from_run_finished_segment(block_text, inventory)
         if not host_results:
+            prior_segment = log_text[previous_block_end:block.start()]
+            host_results = extract_host_results_from_run_finished_segment(prior_segment, inventory)
+        if not host_results:
+            previous_block_end = block.end()
             continue
         summaries.append(
             {
@@ -317,6 +335,7 @@ def extract_completed_subrun_summaries(log_text: str, inventory: Dict[str, str])
                 "currents_url": currents_url,
             }
         )
+        previous_block_end = block.end()
     return summaries