Repository navigation
feat(skills): add verify-backwave verification skill - #6
Merged
Merged
Conversation
Add a project skill that launches Sample.Api on a private port with its own SQLite file or Postgres container. The skill drives the dashboard in a private headless Chrome and keeps the evidence in .verify-evidence/. Cleanup stops only what the run started. Seed the feature map with five dashboard features: jobs and job detail, failures and requeue, queue pause and resume, workflows, and the tag filter.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This change adds the project skill
verify-backwaveat.agents/skills/verify-backwave/. The.claude/skillssymlink points to.agents/skills.SKILL.mdhas these sections: Launch, Doctor, Drive, Evidence, Cleanup, Helpers, and Gotchas.scripts/bwvis the run helper, with the commandslaunch,doctor,url,api,wait-job,browser,shot,sql,cleanup, andruns.features/holds the feature map with five dashboard features: jobs and job detail, failures and requeue, queue pause and resume, workflows, and the tag filter..gitignoreadds.verify-evidence/.The primary surface is the dashboard on
Sample.Apiwith real jobs. The skill names the secondary surfaces: the Sample HTTP API and Swagger, the MCP server at/backwave-mcp, theBackWave.Demohost, Recurring Schedules, Observers, and Executing now. These surfaces have no recipe yet.Isolation and cleanup
--store postgres, the run starts its own labeled Postgres container..verify-evidence/<run-id>/.bwv cleanupstops only the PID, the browser session, and the container that the run recorded. It never stops a process by name. It keeps the evidence and copies the final SQLite file intodb/.End-to-end proof
Run
20260927-154937-57901(SQLite, port 55831) drove the queue pause and resume feature through real clicks in the dashboard:bwv launchbuilt the sample and printedREADY.bwv doctorshowedokon every line.criticalreachedSucceeded. The Queues page then showedcriticalandlimitedasClaiming(ui/pause-before-2.png).Pausein thecriticalrow redirected to the Overview. The Overview showedPAUSED QUEUES 1 critical(ui/pause-overview.png).api/pause-stalled-job.json).Resumeredirected to the Overview withPAUSED QUEUES 0(ui/resume-overview.png). The stalled job reachedSucceeded1 s later.db/pause-audit.txthas three rows:startup 5 limited,sample-operator 3 critical(Pause), andsample-operator 4 critical(Resume).bwv cleanupstopped the browser session and app PID 58101, and removed the scratch directory.bwv runsshows the run ascleanedwithapp-live=no. The evidence directory still holds 27 files.The proof found two faults in the first draft of the skill. Both are now corrected in the skill:
limitedon the Queues page. A queue shows only after it holds a job. The recipe now adds a job first.bwv shottakes a snapshot, so it makes the earlier uids stale. A click on a stale uid failed withSTALE_REF, and the page did not change. The Drive rules now say to take the snapshot and click at once.A second run,
20260927-155247-77205, verified the other recipe claims in the browser:charge-paymentis Dead-Lettered, and its dependents are Cancelled.Scheduledattempt-0 row and 3 new attempts, for14 RECORDEDrows.tenant ›, thenacme, then?tk=tenant&tv=acme.That run was cleaned up the same way.
Out of scope
This change has no product code changes.