[DNM Demo ] :: [TRUNK-17702] Document indefinite monitor muting for flaky tests#463
[DNM Demo ] :: [TRUNK-17702] Document indefinite monitor muting for flaky tests#463samgutentag wants to merge 1 commit intomainfrom
Conversation
Documents the new "Forever" option for muting flaky test monitors, along with all existing timed duration options. Adds Step 3 (Mute monitors) to the managing detected flaky tests guide. TRUNK-17702 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
🚫 This pull request was closed by @samgutentag, so it was removed from the merge queue. See more details here. |
|
Claude finished @samgutentag's task in 1m 17s —— View job Review complete
The new Step 3: Mute monitors section is well-structured and clearly written. The step renumbering (Steps 4–6) is correct and consistent. Two minor issues noted via inline comments:
Neither issue is blocking. The content is accurate, the prose is clear, and the hint block provides useful context. Good to merge after addressing these minor items if desired. |
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
| 3. Click **Mute** and select a duration. | ||
|
|
||
| | Duration | Description | | ||
| |---|---| |
There was a problem hiding this comment.
The table descriptions are inconsistent in depth. The 1 hour row gives a meaningful reason ("transient issues"), while 24 hours, 7 days, and 30 days just restate the duration in different units — readers can already infer "7 days = a week" from the Duration column. Consider making all descriptions equally informative, e.g.:
| Duration | Description |
|---|---|
| 1 hour | Suppress briefly for transient or one-off issues |
| 4 hours | Short-term suppression for issues expected to resolve in a few hours |
| 24 hours | Suppress overnight or across a full workday |
| 7 days | Suppress while waiting for a fix in the current sprint |
| 30 days | Suppress for a longer-running or deprioritized fix |
| Forever | Mute indefinitely until manually unmuted |
| You can unmute a monitor at any time from the test case detail page, regardless of the selected duration. | ||
|
|
||
| {% hint style="info" %} | ||
| Muting suppresses the monitor's contribution to the test's status. If the muted monitor was the only active monitor for a test, the test transitions from flaky to healthy for the duration of the mute. |
There was a problem hiding this comment.
"for the duration of the mute" is slightly ambiguous when the Forever option is selected (there is no duration). Consider rewording to "while the monitor is muted" to cover both timed and indefinite cases:
| Muting suppresses the monitor's contribution to the test's status. If the muted monitor was the only active monitor for a test, the test transitions from flaky to healthy for the duration of the mute. | |
| Muting suppresses the monitor's contribution to the test's status. If the muted monitor was the only active monitor for a test, the test transitions from flaky to healthy while the monitor is muted. |
|
/trunk merge |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
samgutentag
changed the title
|
closing this, was used for demo |
1 participant
Summary
Linear tickets
Related PRs
Files changed
flaky-tests/managing-detected-flaky-tests.md— added Step 3 (Mute monitors), renumbered Steps 4–6Open questions
Conflicts
matt/flake-detection-docs) restructures detection docs and adds a muting section to a newflaky-tests/detection/README.md. That PR lists timed durations only (no Forever). Our changes target a different file (managing-detected-flaky-tests.md) but cover overlapping content. Whichever PR merges second should reconcile the muting documentation.Test plan
🤖 Generated with Claude Code