Find and list your automation runs — use for "how did my tests go", "what failed recently", "show me the runs for suite X", or to locate a run when the user describes it instead of giving an id. Every filter is applied by the SERVER across your whole history, so a suite or a session id from weeks ago is found just as reliably as one from today. total is the true number of matching runs; runs is one page of them, so page with offset rather than assuming the first page is everything. Pass search to hunt for a session id — the short 8-character form shown in the UI and the full id both work. For pass rates and aggregate breakdowns use automation_report instead of tallying these rows. TRIAGE: each FAILED row also carries its already-computed failure analysis — failureKey (the failure signature: runs failing the same way share it), category with categoryConfidence (app_bug / test_script / environment_device / timing / unknown, feedback-aware), flaky (the test passes and fails intermittently), and errorText (first ~200 chars). A failed row with none of these carries analysis: "unanalyzed" instead. To triage a suite or a day, call this once with failedOnly, GROUP the rows by failureKey, and report one line per group (count, category, flaky, errorText, example sessionId). Call automation_session_get only to drill into one group's representative run, never once per failed row. Page with offset if hasMore.