From 3102862ee99556dbd75c632551e54287dca1bafc Mon Sep 17 00:00:00 2001 From: jenkins Date: Mon, 18 May 2026 21:04:14 -0300 Subject: [PATCH] monitoring(testing): clarify CI run and test history labels --- scripts/dashboards_render_atlas.py | 18 +++++++++--------- .../monitoring/dashboards/atlas-overview.json | 2 +- .../monitoring/dashboards/atlas-testing.json | 10 +++++----- .../monitoring/grafana-dashboard-overview.yaml | 2 +- .../monitoring/grafana-dashboard-testing.yaml | 10 +++++----- 5 files changed, 21 insertions(+), 21 deletions(-) diff --git a/scripts/dashboards_render_atlas.py b/scripts/dashboards_render_atlas.py index 11f91b98..dac81afe 100644 --- a/scripts/dashboards_render_atlas.py +++ b/scripts/dashboards_render_atlas.py @@ -1641,7 +1641,7 @@ OVERVIEW_PANEL_DESCRIPTIONS = { "Enclosure Climate History": "Temperature, humidity, and VPD over time; smooth movement is healthy, sharp swings need attention.", "Fan Intensity History": "Fan levels from Off to 10; warmer colors mean stronger cooling response and more thermal pressure.", "Flux Source": "Git branch Flux is applying; this should normally be the intended production branch.", - "CI Run Success (24h)": "Percent of published quality-gate CI runs that completed successfully in 24h; this is run health, not individual test pass rate.", + "CI Run Success (24h)": "Percent of published quality-gate CI runs that completed successfully in 24h; this is automation health, not raw test pass rate.", "Failed Runs (24h)": "Published quality-gate runs that failed in 24h; zero is good, any value needs a look.", "Suites With Runs (24h)": "Configured suites with at least one published quality-gate run in 24h; full count means the dashboard is fresh.", "Avg Coverage": "Average latest line coverage across suites; higher means code is better protected by tests.", @@ -1683,12 +1683,12 @@ TESTING_PANEL_DESCRIPTIONS = { "CI Runs (24h)": "Selected quality-gate CI run count in 24h; zero means the dashboard may be stale.", "Avg Coverage (%)": "Average latest line coverage for selected suites; higher means better test protection.", "Suites with LOC >500": "Selected suites with oversized source files; zero is good for maintainability.", - "Latest Gate Checks Passing by Suite": "Latest required gate checks passing by suite in the daily freshness window; this includes tests, coverage, LOC, style, and related gates.", + "Latest Gate Checks Passing by Suite": "Latest required gate checks passing by suite; this includes tests plus coverage, LOC, style, and other gates.", "CI Run Success by Suite (24h)": "24h CI run success rate by suite; lower rows mean recent jobs failed, aborted, or could not complete cleanly.", "Coverage by Suite (Latest, gate 95)": "Latest suite coverage; 95%+ is acceptable and 100% is strongest.", "Files <=500 LOC by Suite (Latest)": "Percent of source files within the 500-line limit; higher is easier to maintain.", - "CI Runs And Test History": "Recent CI run, coverage, LOC, and test-category trends for selected suites.", - "CI Run Success by Suite (7d rolling)": "Seven-day rolling CI run success rate by suite; blue lanes mean recent runs are completing cleanly.", + "CI Runs And Test Result History": "Recent CI run, coverage, LOC, and raw test-result trends for selected suites.", + "CI Run Success by Suite (7d rolling)": "Seven-day rolling CI run success rate by suite; this is run completion history, not raw test pass history.", "Test Category Pass Rate History": "Pass rate by test category; use the Suite filter to focus on one project.", "Daily Run Volume (Selected Scope)": "Rolling daily counts of published quality-gate runs; volume explains confidence.", "Coverage History by Suite": "Coverage over time by suite; rising lines mean better test protection.", @@ -4184,7 +4184,7 @@ def build_jobs_dashboard(): ] panels[-1]["description"] = ( "Latest pass percentage across required gate checks in the daily freshness window. " - "100% means tests and supporting gates recently passed; missing means no fresh gate data." + "100% means tests and supporting gates recently passed; raw per-test history is tracked separately." ) reliability_suite_panel = bargauge_panel( 9, @@ -4199,8 +4199,8 @@ def build_jobs_dashboard(): decimals=2, ) reliability_suite_panel["description"] = ( - "24h CI run success rate. This can stay low after failed, aborted, or debug runs even " - "when the latest gate checks are green." + "24h CI run success rate. This is whether automation finished cleanly, so it can stay low " + "after failed or aborted runs even when tests and latest gate checks are green." ) reliability_suite_panel["fieldConfig"]["defaults"]["mappings"] = [ {"type": "value", "options": {"-1": {"text": "no runs"}}} @@ -4214,7 +4214,7 @@ def build_jobs_dashboard(): thresholds=success_thresholds, description=( "Seven-day rolling CI run success rate per suite. Each suite gets its own lane, " - "so failed or aborted runs lower the lane color without creating unreadable 0/100 spikes." + "so failed or aborted runs lower the lane color without implying raw test failures." ), ) panels.append(history_panel) @@ -4680,7 +4680,7 @@ def build_jobs_dashboard(): compact_panels.extend( [ - row_panel(500, "CI Runs And Test History", 11, panels=children([11, 153, 12, 13, 14])), + row_panel(500, "CI Runs And Test Result History", 11, panels=children([11, 153, 12, 13, 14])), row_panel( 501, "Check Failure Rates By Suite", diff --git a/services/monitoring/dashboards/atlas-overview.json b/services/monitoring/dashboards/atlas-overview.json index cdbdd90f..24b24518 100644 --- a/services/monitoring/dashboards/atlas-overview.json +++ b/services/monitoring/dashboards/atlas-overview.json @@ -2195,7 +2195,7 @@ "targetBlank": true } ], - "description": "Percent of published quality-gate CI runs that completed successfully in 24h; this is run health, not individual test pass rate." + "description": "Percent of published quality-gate CI runs that completed successfully in 24h; this is automation health, not raw test pass rate." }, { "id": 152, diff --git a/services/monitoring/dashboards/atlas-testing.json b/services/monitoring/dashboards/atlas-testing.json index 0aa447bb..848ee4b7 100644 --- a/services/monitoring/dashboards/atlas-testing.json +++ b/services/monitoring/dashboards/atlas-testing.json @@ -530,7 +530,7 @@ } } ], - "description": "Latest pass percentage across required gate checks in the daily freshness window. 100% means tests and supporting gates recently passed; missing means no fresh gate data." + "description": "Latest pass percentage across required gate checks in the daily freshness window. 100% means tests and supporting gates recently passed; raw per-test history is tracked separately." }, { "id": 9, @@ -623,7 +623,7 @@ } } ], - "description": "24h CI run success rate. This can stay low after failed, aborted, or debug runs even when the latest gate checks are green." + "description": "24h CI run success rate. This is whether automation finished cleanly, so it can stay low after failed or aborted runs even when tests and latest gate checks are green." }, { "id": 17, @@ -814,7 +814,7 @@ { "id": 500, "type": "row", - "title": "CI Runs And Test History", + "title": "CI Runs And Test Result History", "gridPos": { "h": 1, "w": 24, @@ -827,7 +827,7 @@ "id": 11, "type": "state-timeline", "title": "CI Run Success by Suite (7d rolling)", - "description": "Seven-day rolling CI run success rate per suite. Each suite gets its own lane, so failed or aborted runs lower the lane color without creating unreadable 0/100 spikes.", + "description": "Seven-day rolling CI run success rate per suite. Each suite gets its own lane, so failed or aborted runs lower the lane color without implying raw test failures.", "datasource": { "type": "prometheus", "uid": "atlas-vm" @@ -1299,7 +1299,7 @@ } } ], - "description": "Recent CI run, coverage, LOC, and test-category trends for selected suites." + "description": "Recent CI run, coverage, LOC, and raw test-result trends for selected suites." }, { "id": 501, diff --git a/services/monitoring/grafana-dashboard-overview.yaml b/services/monitoring/grafana-dashboard-overview.yaml index df603bbc..77f49e72 100644 --- a/services/monitoring/grafana-dashboard-overview.yaml +++ b/services/monitoring/grafana-dashboard-overview.yaml @@ -2204,7 +2204,7 @@ data: "targetBlank": true } ], - "description": "Percent of published quality-gate CI runs that completed successfully in 24h; this is run health, not individual test pass rate." + "description": "Percent of published quality-gate CI runs that completed successfully in 24h; this is automation health, not raw test pass rate." }, { "id": 152, diff --git a/services/monitoring/grafana-dashboard-testing.yaml b/services/monitoring/grafana-dashboard-testing.yaml index 6e8498f2..e82ebc0c 100644 --- a/services/monitoring/grafana-dashboard-testing.yaml +++ b/services/monitoring/grafana-dashboard-testing.yaml @@ -539,7 +539,7 @@ data: } } ], - "description": "Latest pass percentage across required gate checks in the daily freshness window. 100% means tests and supporting gates recently passed; missing means no fresh gate data." + "description": "Latest pass percentage across required gate checks in the daily freshness window. 100% means tests and supporting gates recently passed; raw per-test history is tracked separately." }, { "id": 9, @@ -632,7 +632,7 @@ data: } } ], - "description": "24h CI run success rate. This can stay low after failed, aborted, or debug runs even when the latest gate checks are green." + "description": "24h CI run success rate. This is whether automation finished cleanly, so it can stay low after failed or aborted runs even when tests and latest gate checks are green." }, { "id": 17, @@ -823,7 +823,7 @@ data: { "id": 500, "type": "row", - "title": "CI Runs And Test History", + "title": "CI Runs And Test Result History", "gridPos": { "h": 1, "w": 24, @@ -836,7 +836,7 @@ data: "id": 11, "type": "state-timeline", "title": "CI Run Success by Suite (7d rolling)", - "description": "Seven-day rolling CI run success rate per suite. Each suite gets its own lane, so failed or aborted runs lower the lane color without creating unreadable 0/100 spikes.", + "description": "Seven-day rolling CI run success rate per suite. Each suite gets its own lane, so failed or aborted runs lower the lane color without implying raw test failures.", "datasource": { "type": "prometheus", "uid": "atlas-vm" @@ -1308,7 +1308,7 @@ data: } } ], - "description": "Recent CI run, coverage, LOC, and test-category trends for selected suites." + "description": "Recent CI run, coverage, LOC, and raw test-result trends for selected suites." }, { "id": 501,