sparkforensics-server 0.2.4 → 0.4.0

package/public/docs/assets/{user-guide_mcp-tools.md.DGvolGzt.js → user-guide_mcp-tools.md.dQwIvdTF.js}

@@ -1,11 +1,11 @@
-import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E=JSON.parse('{"title":"MCP tools reference","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/mcp-tools.md","filePath":"user-guide/mcp-tools.md"}'),t={name:"user-guide/mcp-tools.md"};function l(h,s,p,o,k,d){return a(),e("div",null,[...s[0]||(s[0]=[n(`<h1 id="mcp-tools-reference" tabindex="-1">MCP tools reference <a class="header-anchor" href="#mcp-tools-reference" aria-label="Permalink to &quot;MCP tools reference&quot;">​</a></h1><p>SparkForensics has an MCP server with eight tools, so an MCP-aware client (or an AI agent) can diagnose a run without opening the dashboard.</p><p>Five of the eight tools (<code>list_runs</code>, <code>diagnose_run</code>, <code>get_run_summary</code>, <code>compare_runs</code>, <code>get_finding_evidence</code>) accept an optional <code>redact: boolean</code> parameter (default <code>false</code>) that pseudonymizes the app id and any host/IP tokens in the response (<code>app-1</code>, <code>host-1</code>, ...), so a result can be shared outside the environment that produced it. On <code>compare_runs</code>, <code>runIdA</code>/ <code>runIdB</code> are caller-supplied identifiers, not Spark application ids, so there&#39;s no single app-id field to redact; <code>redact</code> instead scans stage names and other free text for embedded app ids and host/IP tokens and pseudonymizes those. <code>list_runs</code> pseudonymizes every run&#39;s app id and name consistently, so two attempts of the same app still redact to the same identity across the list.</p><h2 id="connecting-a-client" tabindex="-1">Connecting a client <a class="header-anchor" href="#connecting-a-client" aria-label="Permalink to &quot;Connecting a client&quot;">​</a></h2><p>Run the server with <code>npx</code>:</p><div class="language- vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang"></span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span>npx sparkforensics-mcp</span></span></code></pre></div><p>Or point an MCP client (Claude Desktop, Claude Code) at it with this config:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
+import{_ as i,o as a,c as e,a5 as t}from"./chunks/framework.DSg0KOwT.js";const c=JSON.parse('{"title":"MCP tools reference","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/mcp-tools.md","filePath":"user-guide/mcp-tools.md"}'),n={name:"user-guide/mcp-tools.md"};function h(l,s,o,p,d,k){return a(),e("div",null,[...s[0]||(s[0]=[t(`<h1 id="mcp-tools-reference" tabindex="-1">MCP tools reference <a class="header-anchor" href="#mcp-tools-reference" aria-label="Permalink to &quot;MCP tools reference&quot;">​</a></h1><p>SparkForensics has an MCP server with eight tools, so an MCP-aware client (or an AI agent) can diagnose a run without opening the dashboard.</p><p>Five of the eight tools (<code>list_runs</code>, <code>diagnose_run</code>, <code>get_run_summary</code>, <code>compare_runs</code>, <code>get_finding_evidence</code>) accept an optional <code>redact: boolean</code> parameter (default <code>false</code>) that pseudonymizes the app id and any host/IP tokens in the response (<code>app-1</code>, <code>host-1</code>, ...), so a result can be shared outside the environment that produced it. On <code>compare_runs</code>, <code>runIdA</code>/ <code>runIdB</code> are caller-supplied identifiers, not Spark application ids, so there&#39;s no single app-id field to redact; <code>redact</code> instead scans stage names and other free text for embedded app ids and host/IP tokens and pseudonymizes those. <code>list_runs</code> pseudonymizes every run&#39;s app id and name consistently, so two attempts of the same app still redact to the same identity across the list.</p><h2 id="connecting-a-client" tabindex="-1">Connecting a client <a class="header-anchor" href="#connecting-a-client" aria-label="Permalink to &quot;Connecting a client&quot;">​</a></h2><p>Run the server with <code>npx</code>:</p><div class="language- vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang"></span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span>npx sparkforensics-mcp</span></span></code></pre></div><p>Or point an MCP client (Claude Desktop, Claude Code) at it with this config:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;mcpServers&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: {</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">    &quot;sparkforensics&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: {</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">      &quot;command&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;npx&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">      &quot;args&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;sparkforensics-mcp&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">]</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    }</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  }</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><h2 id="diagnose-run" tabindex="-1"><code>diagnose_run</code> <a class="header-anchor" href="#diagnose-run" aria-label="Permalink to &quot;\`diagnose_run\`&quot;">​</a></h2><p>Diagnose a Spark run: thresholded findings with remediation text.</p><p>Parameters (all optional: provide either a <code>source</code> to load a fresh run, or a <code>runId</code> for one already loaded in this session):</p><ul><li><code>source</code>: <code>{ path: string }</code> or <code>{ shsBaseUrl: string, appId: string, attemptId?: string }</code></li><li><code>runId</code>: <code>string</code></li><li><code>redact</code>: <code>boolean</code> (default <code>false</code>), pseudonymizes the app id and any host/IP tokens in the response</li><li><code>include</code>: array of <code>&quot;summary&quot; | &quot;evidenceAvailability&quot; | &quot;detectors&quot;</code> (default omitted, i.e. none). Each requested value adds one extra top-level field to the response, on top of the default <code>findings</code>/<code>recommendations</code>/ <code>cleanChecks</code>/<code>runComplete</code>: <ul><li><code>summary</code>: app id/name/Spark version, stage/job/SQL-execution counts, and a finding count broken down by impact band</li><li><code>evidenceAvailability</code>: which event types the log actually contained, so you can tell &quot;this check came back clean&quot; apart from &quot;this check couldn&#39;t run because the log is missing data&quot;</li><li><code>detectors</code>: the full catalog of checks this tool can run: type, version, scope (stage/sql/app/config), current thresholds, and a doc-page anchor This is opt-in because <code>detectors</code> in particular is a large, mostly-static catalog that would bloat a routine &quot;what&#39;s wrong with this run&quot; call.</li></ul></li><li><code>impactBand</code>: array of impact bands (e.g. <code>[&quot;critical&quot;, &quot;warning&quot;]</code>), narrows the <code>findings</code> array to only these bands</li><li><code>type</code>: array of finding <code>type</code> values, narrows <code>findings</code> to only these types</li><li><code>stageId</code>: number, narrows <code>findings</code> to only findings on this stage</li><li><code>format</code>: <code>&quot;json&quot; | &quot;md&quot;</code> (default <code>&quot;json&quot;</code>), switches <code>content[0].text</code> to a rendered Markdown report instead of JSON. <code>structuredContent</code> always stays JSON-shaped, regardless of <code>format</code>.</li></ul><p><code>impactBand</code>/<code>type</code>/<code>stageId</code> only filter the <code>findings</code> array: <code>recommendations</code>, <code>cleanChecks</code>, and the finding counts in <code>summary</code> (when requested via <code>include</code>) always stay computed from the full, unfiltered set, so a narrow filter never hides that other checks passed or other fixes exist.</p><p>A <code>runId</code> expires. Loaded runs are cached in memory, capped at 8 (LRU-evicted) and expired after 15 minutes (override with <code>SPARKFORENSICS_MCP_CACHE_CAP</code> and <code>SPARKFORENSICS_MCP_CACHE_TTL_MS</code>). A <code>runId</code> from an earlier <code>diagnose_run</code> call may not resolve when you pass it to <code>get_finding_evidence</code>, <code>compare_runs</code>, or <code>evaluate_budgets</code>; re-load the run with <code>source</code> if you get <code>run-not-found</code>.</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;diagnose_run&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;source&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;path&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;app-20260101.zstd&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } } }</span></span></code></pre></div><p>Example response (an event log with no <code>ApplicationEnd</code> event):</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>To tune detector thresholds, start the server with <code>--thresholds &lt;file&gt;</code> (add <code>&quot;--thresholds&quot;, &quot;/absolute/path/thresholds.json&quot;</code> to <code>args</code>). The file format is the CLI&#39;s: see <a href="./getting-started.html#tuning-detector-thresholds">Tuning detector thresholds</a>. The overrides apply to every tool for the life of the server; a client can&#39;t change them per call. An unreadable or invalid file stops the server from starting, with the problem on stderr. On a tuned server, <code>diagnose_run</code>, <code>compare_runs</code> and <code>evaluate_budgets</code> add a top-level <code>tunedThresholds</code>, and each finding and clean check from a tuned detector carries its own <code>tunedThresholds</code>, as in the CLI report. The Markdown output of <code>diagnose_run</code> and <code>compare_runs</code> names the tuned thresholds too.</p><h2 id="diagnose-run" tabindex="-1"><code>diagnose_run</code> <a class="header-anchor" href="#diagnose-run" aria-label="Permalink to &quot;\`diagnose_run\`&quot;">​</a></h2><p>Diagnose a Spark run: thresholded findings with remediation text, led by the same verdict the dashboard opens with. <code>verdict</code> gives a title (&quot;Start with Stage 3&quot;, &quot;1 of 3 jobs failed in this run&quot;), summary sentences, the first three places to look in the dashboard&#39;s order (each with its action, what to try, the potential savings and what that figure counts, and the other finding types flagged at the same place), how many more places the full list holds, and <code>copyText</code>, the dashboard&#39;s &quot;Copy next steps&quot; checklist.</p><p>Parameters (all optional: provide either a <code>source</code> to load a fresh run, or a <code>runId</code> for one already loaded in this session):</p><ul><li><code>source</code>: <code>{ path: string }</code> or <code>{ shsBaseUrl: string, appId: string, attemptId?: string }</code></li><li><code>runId</code>: <code>string</code></li><li><code>redact</code>: <code>boolean</code> (default <code>false</code>), pseudonymizes the app id and any host/IP tokens in the response</li><li><code>include</code>: array of <code>&quot;summary&quot; | &quot;evidenceAvailability&quot; | &quot;detectors&quot;</code> (default omitted, i.e. none). Each requested value adds one extra top-level field to the response, on top of the default <code>verdict</code>/<code>findings</code>/<code>recommendations</code>/ <code>cleanChecks</code>/<code>notRunChecks</code>/<code>runComplete</code>: <ul><li><code>summary</code>: app id/name/Spark version, stage/job/SQL-execution counts, a finding count broken down by impact band, the same counts without evidence caveats and the incomplete-run row (<code>actionableFindingCount</code>, <code>actionableImpactBandCounts</code>, what the dashboard counts), and <code>clean</code></li><li><code>evidenceAvailability</code>: which event types the log actually contained, so you can tell &quot;this check came back clean&quot; apart from &quot;this check couldn&#39;t run because the log is missing data&quot;</li><li><code>detectors</code>: the full catalog of checks this tool can run: type, version, scope (stage/sql/app/config), current thresholds, and a doc-page anchor This is opt-in because <code>detectors</code> in particular is a large, mostly-static catalog that would bloat a routine &quot;what&#39;s wrong with this run&quot; call.</li></ul></li><li><code>impactBand</code>: array of impact bands (e.g. <code>[&quot;critical&quot;, &quot;warning&quot;]</code>), narrows the <code>findings</code> array to only these bands</li><li><code>type</code>: array of finding <code>type</code> values, narrows <code>findings</code> to only these types</li><li><code>stageId</code>: number, narrows <code>findings</code> to only findings on this stage, including a SQL plan finding whose only stage it is (the dashboard&#39;s stage details rule)</li><li><code>format</code>: <code>&quot;json&quot; | &quot;md&quot;</code> (default <code>&quot;json&quot;</code>), switches <code>content[0].text</code> to a rendered Markdown report instead of JSON. <code>structuredContent</code> always stays JSON-shaped, regardless of <code>format</code>.</li></ul><p><code>impactBand</code>/<code>type</code>/<code>stageId</code> only filter the <code>findings</code> array: <code>recommendations</code>, <code>cleanChecks</code>, <code>notRunChecks</code>, and the finding counts in <code>summary</code> (when requested via <code>include</code>) always stay computed from the full, unfiltered set, so a narrow filter never hides that other checks passed or other fixes exist.</p><p>A <code>runId</code> expires. Loaded runs are cached in memory, capped at 8 (LRU-evicted) and expired after 15 minutes (override with <code>SPARKFORENSICS_MCP_CACHE_CAP</code> and <code>SPARKFORENSICS_MCP_CACHE_TTL_MS</code>). A <code>runId</code> from an earlier <code>diagnose_run</code> call may not resolve when you pass it to <code>get_finding_evidence</code>, <code>compare_runs</code>, or <code>evaluate_budgets</code>; re-load the run with <code>source</code> if you get <code>run-not-found</code>.</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;diagnose_run&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;source&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;path&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;app-20260101.zstd&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } } }</span></span></code></pre></div><p>Example response (an event log with no <code>ApplicationEnd</code> event):</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runId&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;b8b2c1a4-...&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runComplete&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">false</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;findings&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [</span></span>
@@ -21,7 +21,7 @@ import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">      &quot;evidence&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: {}</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    }</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  ]</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>The <code>evidence</code> shape is detector-specific. The example above is <code>incompleteRun</code>&#39;s, which is empty; other detectors attach the metrics that drove the finding.</p><h2 id="get-run-summary" tabindex="-1"><code>get_run_summary</code> <a class="header-anchor" href="#get-run-summary" aria-label="Permalink to &quot;\`get_run_summary\`&quot;">​</a></h2><p>App/stage/job/sql counts and duration for a run: no findings.</p><p>Parameters: same as <code>diagnose_run</code> (<code>source</code>, <code>runId</code>, <code>redact</code>, all optional).</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;get_run_summary&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;source&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;path&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;app-20260101.zstd&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } } }</span></span></code></pre></div><p>Example response:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>The <code>evidence</code> shape is detector-specific. The example above is <code>incompleteRun</code>&#39;s, which is empty; other detectors attach the metrics that drove the finding.</p><h2 id="get-run-summary" tabindex="-1"><code>get_run_summary</code> <a class="header-anchor" href="#get-run-summary" aria-label="Permalink to &quot;\`get_run_summary\`&quot;">​</a></h2><p>App/stage/job/sql counts, duration, and how the run ended: no findings. <code>failedJobs</code>/<code>totalJobs</code> count only jobs with an end record, and <code>failureReason</code> is the first line of Spark&#39;s own recorded reason when a job failed, the same line the dashboard verdict quotes (<code>failureReasonStageId</code> is the stage it came from, or <code>null</code> when there is no reason or it came from a job&#39;s exception). <code>runShape</code> carries the dashboard&#39;s run-shape figures: <code>wallClockMs</code>, <code>efficiencyPct</code> (the share of the run with a stage running, the Scorecard&#39;s Efficiency), <code>unusedCoreTimePct</code> (driver idle plus executor slack as a share of available core time; <code>minEfficiencyPct</code> checks 100 minus this), <code>etlPhasesMs</code> (<code>extract</code>/<code>transform</code>/<code>load</code> summed stage time, so a phase can exceed the run) and <code>peakBusyCores</code> (busy cores at the peak of Core Usage by Locality). Each is <code>null</code> where the dashboard shows &quot;Not measured&quot; or &quot;Unavailable&quot;.</p><p>Parameters: same as <code>diagnose_run</code> (<code>source</code>, <code>runId</code>, <code>redact</code>, all optional).</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;get_run_summary&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;source&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;path&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;app-20260101.zstd&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } } }</span></span></code></pre></div><p>Example response:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runId&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;3f9c2b7e-...&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;app&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;id&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;app-1&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;t&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;sparkVersion&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;stageCount&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
@@ -29,8 +29,13 @@ import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;sqlExecutionCount&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;executorCount&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;added&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;removed&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;durationMs&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">100</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
-<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runComplete&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">true</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><h2 id="evaluate-budgets" tabindex="-1"><code>evaluate_budgets</code> <a class="header-anchor" href="#evaluate-budgets" aria-label="Permalink to &quot;\`evaluate_budgets\`&quot;">​</a></h2><p>Evaluate a run against pass/fail thresholds: the MCP equivalent of the CLI&#39;s <code>--max-runtime</code>/<code>--max-spill-gb</code>/etc. budget flags, thin-wrapped over the same <code>evaluateBudgets()</code> used by <code>npm run analyze</code>.</p><p>Parameters (all optional):</p><ul><li><code>source</code> / <code>runId</code>: identify the run to evaluate (same shape as <code>diagnose_run</code>)</li><li><code>maxRuntimeMs</code>, <code>maxSpillGb</code>, <code>maxSkewRatio</code>, <code>maxFailedTaskRatePct</code>, <code>minEfficiencyPct</code>: single-run budgets, each evaluated only if provided</li><li><code>runIdB</code> / <code>sourceB</code>: a second run to compare the first against, so regression budgets can be evaluated. Same <code>runId</code>/<code>source</code> shape, resolved the same way. Omit both to skip regression budgets.</li><li><code>maxRegressionPct</code>, <code>regressionMetric</code>: fail if <code>regressionMetric</code> (default <code>wallClock</code>; see the CLI docs for the full metric key list) regressed by more than <code>maxRegressionPct</code>% between the first run (baseline) and the second run (candidate). Requires <code>runIdB</code>/<code>sourceB</code>.</li><li><code>failOnIntroduced</code>: fail if the second run introduces any finding in the given impact band (<code>&quot;all&quot;</code> or one of the impact band names). Requires <code>runIdB</code>/<code>sourceB</code>.</li></ul><p>A budget whose required evidence is missing (e.g. no <code>runIdB</code>/<code>sourceB</code> for a regression budget, or a run with no trustworthy task-level evidence) reports <code>inconclusive</code>, not a false pass.</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runComplete&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">true</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;failedJobs&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;totalJobs&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;failureReason&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;failureReasonStageId&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runShape&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;wallClockMs&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">100</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;efficiencyPct&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">0</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;unusedCoreTimePct&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;etlPhasesMs&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;peakBusyCores&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">null</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }</span></span>
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><h2 id="evaluate-budgets" tabindex="-1"><code>evaluate_budgets</code> <a class="header-anchor" href="#evaluate-budgets" aria-label="Permalink to &quot;\`evaluate_budgets\`&quot;">​</a></h2><p>Evaluate a run against pass/fail thresholds: the MCP equivalent of the CLI&#39;s <code>--max-runtime</code>/<code>--max-spill</code>/etc. budget flags, thin-wrapped over the same <code>evaluateBudgets()</code> the <code>sparkforensics-analyze</code> CLI uses.</p><p>Parameters (all optional):</p><ul><li><code>source</code> / <code>runId</code>: identify the run to evaluate (same shape as <code>diagnose_run</code>). When <code>runIdB</code>/<code>sourceB</code> is also given, this run is the regression baseline instead.</li><li><code>maxRuntimeMs</code>, <code>maxSpillGb</code>, <code>maxSkewRatio</code>, <code>maxFailedTaskRatePct</code>, <code>minEfficiencyPct</code>: absolute budgets, each evaluated only if provided. With two runs they apply to the candidate (<code>runIdB</code>/<code>sourceB</code>), the same as the CLI&#39;s <code>--baseline</code> mode. <code>minEfficiencyPct</code> measures busy core time, the share of executor core time that ran tasks (100 minus the dashboard&#39;s Unused core time), not the dashboard&#39;s Efficiency tile.</li><li><code>runIdB</code> / <code>sourceB</code>: a candidate run to compare against the first, so regression budgets can be evaluated. Same <code>runId</code>/<code>source</code> shape, resolved the same way. Omit both to skip regression budgets.</li><li><code>maxRegressionPct</code>, <code>regressionMetric</code>: fail if <code>regressionMetric</code> (default <code>wallClock</code>; see <a href="./getting-started.html#regression-metric-keys">Regression metric keys</a> for the full list) regressed by more than <code>maxRegressionPct</code>% between the first run (baseline) and the second run (candidate). Requires <code>runIdB</code>/<code>sourceB</code>.</li><li><code>failOnIntroduced</code>: fail if the second run introduces any finding in the given impact band (<code>&quot;all&quot;</code> or one of the impact band names). Requires <code>runIdB</code>/<code>sourceB</code>.</li></ul><p>A budget whose required evidence is missing (e.g. no <code>runIdB</code>/<code>sourceB</code> for a regression budget, or a run with no trustworthy task-level evidence) reports <code>inconclusive</code>, not a false pass. Independent of which budgets you pass, an evaluated run with no ApplicationEnd event adds a <code>run-complete</code> result with status <code>inconclusive</code>, the same check that makes the CLI exit <code>3</code>. With two runs, the check applies to the candidate.</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;evaluate_budgets&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: {</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">    &quot;source&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;path&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;baseline.zstd&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
@@ -54,7 +59,7 @@ import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  ],</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;violated&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">true</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;inconclusive&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">false</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><h2 id="compare-runs" tabindex="-1"><code>compare_runs</code> <a class="header-anchor" href="#compare-runs" aria-label="Permalink to &quot;\`compare_runs\`&quot;">​</a></h2><p>Compare two runs: categorized findings delta and metric deltas.</p><p>Parameters:</p><ul><li><code>runIdA</code> / <code>sourceA</code>: identify run A (same <code>source</code> shape as above)</li><li><code>runIdB</code> / <code>sourceB</code>: identify run B</li><li><code>redact</code>: <code>boolean</code> (default <code>false</code>), pseudonymizes any app id or host/IP tokens embedded in free text (stage names and similar) in the response: see the note at the top of this page</li><li><code>format</code>: <code>&quot;json&quot; | &quot;md&quot;</code> (default <code>&quot;json&quot;</code>), switches <code>content[0].text</code> to a rendered Markdown report instead of JSON. <code>structuredContent</code> always stays JSON-shaped, regardless of <code>format</code>.</li></ul><p>Each side takes either a <code>runId</code> or a <code>source</code>, and you can mix them: a cached run ID for the baseline, a fresh file for the candidate.</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><h2 id="compare-runs" tabindex="-1"><code>compare_runs</code> <a class="header-anchor" href="#compare-runs" aria-label="Permalink to &quot;\`compare_runs\`&quot;">​</a></h2><p>Compare two runs: the comparison page&#39;s verdict, categorized findings delta and metric deltas. <code>verdict</code> is the headline the dashboard&#39;s comparison page opens with (run A is <code>runIdA</code>/<code>sourceA</code>, run B is <code>runIdB</code>/<code>sourceB</code>): a <code>title</code> such as &quot;Run B finished 9.9s faster than run A (37%)&quot;, or a failed-job headline when either run had jobs fail, a <code>tone</code> (<code>better</code>, <code>worse</code>, <code>same</code> or <code>unknown</code>), and <code>sentences</code> naming which cost metrics and finding categories moved each way.</p><p>Parameters:</p><ul><li><code>runIdA</code> / <code>sourceA</code>: identify run A (same <code>source</code> shape as above)</li><li><code>runIdB</code> / <code>sourceB</code>: identify run B</li><li><code>redact</code>: <code>boolean</code> (default <code>false</code>), pseudonymizes any app id or host/IP tokens embedded in free text (stage names and similar) in the response: see the note at the top of this page</li><li><code>format</code>: <code>&quot;json&quot; | &quot;md&quot;</code> (default <code>&quot;json&quot;</code>), switches <code>content[0].text</code> to a rendered Markdown report instead of JSON. <code>structuredContent</code> always stays JSON-shaped, regardless of <code>format</code>.</li></ul><p>Each side takes either a <code>runId</code> or a <code>source</code>, and you can mix them: a cached run ID for the baseline, a fresh file for the candidate.</p><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;compare_runs&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: {</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">    &quot;sourceA&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;path&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;baseline.zstd&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> },</span></span>
@@ -63,6 +68,7 @@ import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>Example response:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runIdA&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;aaaa1111-...&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;runIdB&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;bbbb2222-...&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
+<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;verdict&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;title&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;Run B finished 1.0s faster than run A (50%)&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;tone&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;better&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;sentences&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [] },</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;findingsDelta&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;introduced&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [], </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;resolved&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [] },</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;metricDeltas&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">    {</span></span>
@@ -122,4 +128,4 @@ import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;isError&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">true</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: [{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;type&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;text&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;&lt;error message&gt;&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }],</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;structuredContent&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;code&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;&lt;error-code&gt;&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> }</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>The codes:</p><ul><li><code>run-not-found</code>: no cached run for the <code>runId</code> you passed.</li><li><code>finding-not-found</code>: that <code>findingId</code> isn&#39;t on that run.</li><li><code>invalid-date-filter</code>: <code>list_runs</code>&#39;s <code>minDate</code> or <code>maxDate</code> isn&#39;t a parseable date.</li><li><code>invalid-type</code>: that finding <code>type</code> isn&#39;t one <code>get_finding_documentation</code> recognizes.</li><li><code>invalid-anchor</code>: that <code>anchor</code> doesn&#39;t resolve to a known <code>get_reference_doc</code> page.</li><li><code>invalid-event-log</code>: the file doesn&#39;t exist, or the event log (or History Server archive) couldn&#39;t be decoded.</li><li><code>application-not-found</code>: the History Server returned a 404 for that <code>appId</code>/<code>attemptId</code>.</li><li><code>upstream-unreachable</code>: the History Server response stalled mid-body. Override the idle timeout with <code>SPARKFORENSICS_SHS_TIMEOUT_MS</code>. If the server is unreachable entirely (an SSH-only cluster), see <a href="./alternative-log-retrieval.html">Alternative ways to get the logs</a>.</li><li><code>archive-too-large</code>: the History Server archive blew the byte cap. Override it with <code>SPARKFORENSICS_MAX_ARCHIVE_BYTES</code>.</li><li><code>directory-not-found</code>: <code>list_runs</code>&#39;s <code>dir</code> doesn&#39;t exist or isn&#39;t readable.</li><li><code>invalid-shs-base-url</code>: <code>list_runs</code>&#39;s <code>shsBaseUrl</code> isn&#39;t an absolute HTTP(S) URL without credentials, query, or fragment.</li><li><code>access-or-upstream-failure</code>: the fallback code. Bad parameters, a failed History Server fetch, or any error that carries no more specific code.</li></ul>`,84)])])}const c=i(t,[["render",l]]);export{E as __pageData,c as default};
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p>The codes:</p><ul><li><code>run-not-found</code>: no cached run for the <code>runId</code> you passed.</li><li><code>finding-not-found</code>: that <code>findingId</code> isn&#39;t on that run.</li><li><code>invalid-date-filter</code>: <code>list_runs</code>&#39;s <code>minDate</code> or <code>maxDate</code> isn&#39;t a parseable date.</li><li><code>invalid-type</code>: that finding <code>type</code> isn&#39;t one <code>get_finding_documentation</code> recognizes.</li><li><code>invalid-anchor</code>: that <code>anchor</code> doesn&#39;t resolve to a known <code>get_reference_doc</code> page.</li><li><code>invalid-event-log</code>: the file doesn&#39;t exist, or the event log (or History Server archive) couldn&#39;t be decoded.</li><li><code>application-not-found</code>: the History Server returned a 404 for that <code>appId</code>/<code>attemptId</code>.</li><li><code>upstream-unreachable</code>: the History Server response stalled mid-body. Override the idle timeout with <code>SPARKFORENSICS_SHS_TIMEOUT_MS</code>. If the server is unreachable entirely (an SSH-only cluster), see <a href="./alternative-log-retrieval.html">Alternative ways to get the logs</a>.</li><li><code>archive-too-large</code>: the History Server archive blew the byte cap. Override it with <code>SPARKFORENSICS_MAX_ARCHIVE_BYTES</code>.</li><li><code>directory-not-found</code>: <code>list_runs</code>&#39;s <code>dir</code> doesn&#39;t exist or isn&#39;t readable.</li><li><code>invalid-shs-base-url</code>: <code>list_runs</code>&#39;s <code>shsBaseUrl</code> isn&#39;t an absolute HTTP(S) URL without credentials, query, or fragment.</li><li><code>access-or-upstream-failure</code>: the fallback code. Bad parameters, a failed History Server fetch, or any error that carries no more specific code.</li></ul>`,85)])])}const E=i(n,[["render",h]]);export{c as __pageData,E as default};

package/public/docs/assets/user-guide_mcp-tools.md.dQwIvdTF.lean.js

@@ -0,0 +1 @@
+import{_ as i,o as a,c as e,a5 as t}from"./chunks/framework.DSg0KOwT.js";const c=JSON.parse('{"title":"MCP tools reference","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/mcp-tools.md","filePath":"user-guide/mcp-tools.md"}'),n={name:"user-guide/mcp-tools.md"};function h(l,s,o,p,d,k){return a(),e("div",null,[...s[0]||(s[0]=[t("",85)])])}const E=i(n,[["render",h]]);export{c as __pageData,E as default};

package/public/docs/assets/user-guide_run-comparison.md.ChLI3MK0.js

@@ -0,0 +1 @@
+import{_ as t,o as a,c as o,a5 as n}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Run comparison mode","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/run-comparison.md","filePath":"user-guide/run-comparison.md"}'),r={name:"user-guide/run-comparison.md"};function s(i,e,h,d,c,u){return a(),o("div",null,[...e[0]||(e[0]=[n('<h1 id="run-comparison-mode" tabindex="-1">Run comparison mode <a class="header-anchor" href="#run-comparison-mode" aria-label="Permalink to &quot;Run comparison mode&quot;">​</a></h1><p>Put two runs side by side to see whether a tuning change helped.</p><h2 id="starting-a-comparison" tabindex="-1">Starting a comparison <a class="header-anchor" href="#starting-a-comparison" aria-label="Permalink to &quot;Starting a comparison&quot;">​</a></h2><p>From the landing page, click <strong>Compare two runs</strong>. Two slots appear: <strong>Run A (baseline)</strong> and <strong>Run B (candidate)</strong>.</p><ol><li>Load a file into each slot the same way you&#39;d load a single run (drag and drop, or <strong>Choose file</strong>).</li><li>Click <strong>Compare</strong>.</li></ol><p>The runs parse one after the other through the same background worker. When both finish, the comparison view opens.</p><p>Already looking at a run, for example the one before a change? Click <strong>Compare with another run</strong> in the top bar (or the <strong>More options</strong> menu on a phone). The compare view opens with that run as Run A, so you only load Run B, and the open run is not parsed again. <strong>Back to the run</strong> returns to its dashboard.</p><h2 id="reading-the-comparison" tabindex="-1">Reading the comparison <a class="header-anchor" href="#reading-the-comparison" aria-label="Permalink to &quot;Reading the comparison&quot;">​</a></h2><p>The page opens with a verdict: whether run B finished faster or slower than run A, and by how much (a change under 2% reads as &quot;about as long&quot;). When either run had failed jobs, the verdict leads with that instead, for example &quot;Run B had 2 of 5 jobs fail (run A: none)&quot; or &quot;Run B&#39;s only job failed&quot;, and the run-time line follows. When either log has no end-of-run record (the run was killed or the log cut off), the verdict says how much run time each log covers, in a neutral tone, instead of calling the shorter run faster. It then lists which cost metrics got worse or better in run B (again ignoring changes under 2%), and which finding categories became more or less frequent. Volume and count metrics (input, output, tasks, executors) are left out, since more or less of them is not better or worse on its own. <strong>See where to start in run B</strong> opens run B&#39;s dashboard, whose own verdict names the first thing to fix.</p><p>The <strong>Metrics</strong> table covers the whole run: wall-clock duration, shuffle spill, task skew, failed-task rate, disk spill, GC time, input/output bytes, executor run-time, and task/executor counts, baseline against candidate with the change. <strong>Findings by category</strong> lists which finding types appeared or disappeared between the two runs, with the affected stages for each.</p><p>Stage-level detail depends on matching a stage in the baseline to its counterpart in the candidate, and SparkForensics only does that automatically when a stage&#39;s identity (its position in the SQL plan) resolves to exactly one match on both sides; AQE&#39;s runtime replanning makes a plain stage-ID match unreliable. The <strong>Per-stage task skew</strong> table covers only stages matched this way, and the page states what percentage of stages that was. If matching is uncertain (for example, the two runs came from different application names), a warning banner says so; the metric deltas above it still hold; they don&#39;t depend on stage matching.</p><p>For everything else, matching is manual: the <strong>Pinned per-stage deltas</strong> widget lets you pick one stage from the baseline and one from the candidate yourself and pin the pair, then shows their duration, executor run-time, GC time, memory/disk spill, input/output bytes, task count, and failed tasks side by side. Pin as many pairs as you want to check.</p><p>For either run&#39;s full dashboard, click <strong>View run A dashboard</strong> or <strong>View run B dashboard</strong>. <strong>← Back to comparison</strong> takes you back.</p><h2 id="comparing-without-the-dashboard" tabindex="-1">Comparing without the dashboard <a class="header-anchor" href="#comparing-without-the-dashboard" aria-label="Permalink to &quot;Comparing without the dashboard&quot;">​</a></h2><p>The same comparison runs headlessly, and opens with the same verdict: the positional run is run B, the <code>--baseline</code> run is run A. The CLI&#39;s <code>--baseline</code> flag adds a comparison section to its output (<code>comparison.verdict</code> in JSON) and can gate a build on it (<code>--max-regression-pct</code>, <code>--fail-on-introduced</code>; see <a href="./getting-started.html#ci-and-automation">Getting started</a>). The MCP server&#39;s <code>compare_runs</code> and <code>evaluate_budgets</code> tools do the same for an AI assistant; see <a href="./mcp-tools.html">MCP tools reference</a>.</p>',15)])])}const g=t(r,[["render",s]]);export{p as __pageData,g as default};

package/public/docs/assets/user-guide_run-comparison.md.ChLI3MK0.lean.js

@@ -0,0 +1 @@
+import{_ as t,o as a,c as o,a5 as n}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Run comparison mode","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/run-comparison.md","filePath":"user-guide/run-comparison.md"}'),r={name:"user-guide/run-comparison.md"};function s(i,e,h,d,c,u){return a(),o("div",null,[...e[0]||(e[0]=[n("",15)])])}const g=t(r,[["render",s]]);export{p as __pageData,g as default};

package/public/docs/assets/user-guide_understanding-findings.md.D1ccs60C.js

@@ -0,0 +1 @@
+import{_ as a,o as t,c as o,a5 as r}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Understanding findings","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/understanding-findings.md","filePath":"user-guide/understanding-findings.md"}'),s={name:"user-guide/understanding-findings.md"};function i(n,e,l,d,c,h){return t(),o("div",null,[...e[0]||(e[0]=[r('<h1 id="understanding-findings" tabindex="-1">Understanding findings <a class="header-anchor" href="#understanding-findings" aria-label="Permalink to &quot;Understanding findings&quot;">​</a></h1><p>Every flagged problem carries a short ALL-CAPS tag. This page has one entry per tag: what it means, and what to do about it.</p><p>Turn on <a href="./getting-started.html#advanced-view">Advanced view</a> in the dashboard to see, per finding, the confidence level and a link to the same background reading collected here, opened in an in-app &quot;Reference&quot; panel next to the board. A few tags share that reading with another tag, because the underlying Spark-tuning material overlaps: <code>SFAIL</code> with <code>FAIL</code>, <code>PART</code> with <code>SHFL</code>, <code>SPEC</code> with <code>STRAG</code>, and <code>CACHE</code>/<code>LOCAL</code> with <code>UTIL</code>.</p><h2 id="per-stage" tabindex="-1">Per-stage <a class="header-anchor" href="#per-stage" aria-label="Permalink to &quot;Per-stage&quot;">​</a></h2><h3 id="skew" tabindex="-1"><code>SKEW</code>: Task skew <a class="header-anchor" href="#skew" aria-label="Permalink to &quot;`SKEW`: Task skew {#skew}&quot;">​</a></h3><p>A small number of tasks take much longer than their peers in the same stage. For join-driven skew, enable AQE skew-join handling (<code>spark.sql.adaptive.skewJoin.enabled</code>); otherwise salt the key or repartition on a better key.</p><h3 id="shfl" tabindex="-1"><code>SHFL</code>: Shuffle I/O <a class="header-anchor" href="#shfl" aria-label="Permalink to &quot;`SHFL`: Shuffle I/O {#shfl}&quot;">​</a></h3><p>Tasks move a large amount of intermediate data between stages. Raise <code>spark.sql.shuffle.partitions</code>, or add a broadcast join. Only flagged on stages that take at least 0.5% of the run.</p><h3 id="spill" tabindex="-1"><code>SPILL</code>: Memory and disk spill <a class="header-anchor" href="#spill" aria-label="Permalink to &quot;`SPILL`: Memory and disk spill {#spill}&quot;">​</a></h3><p>Tasks are writing data out of memory, which slows execution. Two spill patterns get flagged differently: skew spill, where a few heavy tasks spill while most don&#39;t (rebalance partitioning), and volume spill, where most tasks spill because the data genuinely exceeds available memory (add partitions). Only flagged on stages that take at least 0.5% of the run.</p><h3 id="gc" tabindex="-1"><code>GC</code>: Garbage collection pressure <a class="header-anchor" href="#gc" aria-label="Permalink to &quot;`GC`: Garbage collection pressure {#gc}&quot;">​</a></h3><p>Tasks spend an unusually large share of time reclaiming memory. Reduce object creation: use primitive types, avoid UDFs, or raise executor memory. A stage with very little GC gets an informational note that executor memory may be over-provisioned, only on stages that take at least 0.5% of the run.</p><h3 id="fail" tabindex="-1"><code>FAIL</code>: Failed tasks <a class="header-anchor" href="#fail" aria-label="Permalink to &quot;`FAIL`: Failed tasks {#fail}&quot;">​</a></h3><p>Tasks fail often enough to affect the stage. Failed tasks point to executor instability or data-driven errors. The finding names the dominant error: the exception class, or the executor loss reason (for example &quot;Container killed by YARN for exceeding memory limits&quot;). It lists up to five distinct failures, each with its message and a short stack excerpt. With redaction on, messages and the message text inside excerpts are replaced, since they can carry file paths and data values; class names and stack frames stay.</p><h3 id="sfail" tabindex="-1"><code>SFAIL</code>: Failed stage <a class="header-anchor" href="#sfail" aria-label="Permalink to &quot;`SFAIL`: Failed stage {#sfail}&quot;">​</a></h3><p>A stage attempt failed outright rather than losing individual tasks within it. Inspect the driver log for the failure reason and the job that triggered it.</p><h3 id="strag" tabindex="-1"><code>STRAG</code>: Straggler tasks <a class="header-anchor" href="#strag" aria-label="Permalink to &quot;`STRAG`: Straggler tasks {#strag}&quot;">​</a></h3><p>A few tasks run much slower than the rest of their stage. Rule out a GC pause or a slow shuffle fetch before assuming a hardware issue; if a skewed key is the real cause, that&#39;s a candidate for AQE&#39;s skew-join handling. Only flagged on stages that take at least 0.5% of the run.</p><h3 id="spec" tabindex="-1"><code>SPEC</code>: Speculation waste <a class="header-anchor" href="#spec" aria-label="Permalink to &quot;`SPEC`: Speculation waste {#spec}&quot;">​</a></h3><p>Speculative task attempts used a lot of executor time without confirming a genuine straggler. Self-flags a confidence that scales with how far the wasted time sits past the threshold: these thresholds are still a design spike, not yet validated against real-world runs. If task durations are just naturally variable rather than genuine stragglers, tune <code>spark.speculation.multiplier</code>/<code>spark.speculation.quantile</code>.</p><h3 id="retry" tabindex="-1"><code>RETRY</code>: Retry waste <a class="header-anchor" href="#retry" aria-label="Permalink to &quot;`RETRY`: Retry waste {#retry}&quot;">​</a></h3><p>Repeated task attempts ate into execution time even though the stage completed. Investigate executor loss or fetch failures.</p><h3 id="tiny" tabindex="-1"><code>TINY</code>: Tiny tasks <a class="header-anchor" href="#tiny" aria-label="Permalink to &quot;`TINY`: Tiny tasks {#tiny}&quot;">​</a></h3><p>Many very short tasks add scheduling overhead out of proportion to the work each one does. Repartition to fewer, larger tasks. Only flagged on stages that take at least 0.5% of the run.</p><h3 id="part" tabindex="-1"><code>PART</code>: Partition sizing <a class="header-anchor" href="#part" aria-label="Permalink to &quot;`PART`: Partition sizing {#part}&quot;">​</a></h3><p>Shuffle partitions are too large, too uneven, or too few for the work. A single shuffle partition over 5 GB, for example, will OOM or spill heavily: repartition to break it up before the stage runs.</p><h3 id="slow" tabindex="-1"><code>SLOW</code>: Stage slowness <a class="header-anchor" href="#slow" aria-label="Permalink to &quot;`SLOW`: Stage slowness {#slow}&quot;">​</a></h3><p>A stage ran long overall without a more specific cause getting flagged. Often a partition-count problem: raise parallelism via <code>spark.sql.shuffle.partitions</code> or <code>spark.default.parallelism</code>, or check for a large per-task data volume driving heavy shuffle and spill.</p><h3 id="shape" tabindex="-1"><code>SHAPE</code>: Stage shape <a class="header-anchor" href="#shape" aria-label="Permalink to &quot;`SHAPE`: Stage shape {#shape}&quot;">​</a></h3><p>The stage has an inefficient task count, output shape, or task-to-stage balance: for example, one straggler task taking a large fraction of the stage&#39;s wall-clock time. A too-low task count is only flagged on stages that take at least 0.5% of the run.</p><h3 id="host" tabindex="-1"><code>HOST</code>: Slow host <a class="header-anchor" href="#host" aria-label="Permalink to &quot;`HOST`: Slow host {#host}&quot;">​</a></h3><p>One executor is much slower than its peers. It may just hold data locality for its tasks or carry one heavy stage, rather than a hardware fault. Enable <code>spark.speculation</code> to relaunch a lagging task automatically. Only flagged on stages that take at least 0.5% of the run.</p><h2 id="app-level" tabindex="-1">App-level <a class="header-anchor" href="#app-level" aria-label="Permalink to &quot;App-level&quot;">​</a></h2><h3 id="cold" tabindex="-1"><code>COLD</code>: Executor cold start <a class="header-anchor" href="#cold" aria-label="Permalink to &quot;`COLD`: Executor cold start {#cold}&quot;">​</a></h3><p>New executors take time to become available for work. Pre-warm the cluster, or use dynamic allocation.</p><h3 id="util" tabindex="-1"><code>UTIL</code>: Low utilization <a class="header-anchor" href="#util" aria-label="Permalink to &quot;`UTIL`: Low utilization {#util}&quot;">​</a></h3><p>Allocated executors sit idle for a large share of the application run. Consider a smaller cluster, or enable dynamic allocation.</p><h3 id="mem" tabindex="-1"><code>MEM</code>: Memory utilization <a class="header-anchor" href="#mem" aria-label="Permalink to &quot;`MEM`: Memory utilization {#mem}&quot;">​</a></h3><p>Executor memory or core capacity may be over- or under-provisioned. Some detail here needs <code>spark.eventLog.logStageExecutorMetrics=true</code> on the run being analyzed; without it, per-executor memory usage can&#39;t be broken down. Review <code>spark.executor.memory</code> and executor count if allocated memory sat largely idle over the run. That idle-memory variant self-flags a confidence that scales with how far the estimated waste sits past a 1.5x buffer: it estimates waste from allocated-versus-used memory-time. Check it against the Spark UI before resizing anything.</p><h3 id="cache" tabindex="-1"><code>CACHE</code>: Caching opportunity <a class="header-anchor" href="#cache" aria-label="Permalink to &quot;`CACHE`: Caching opportunity {#cache}&quot;">​</a></h3><p>A reusable dataset (re-read via the same SQL relation more than once) may be worth persisting between stages. Self-flags a confidence that scales with how many executions reuse the same relation: reuse is only inferred, from plan-scan identity across SQL executions, so confirm the reads really do hit the same data before you cache anything.</p><h3 id="cstor" tabindex="-1"><code>CSTOR</code>: Cache storage <a class="header-anchor" href="#cstor" aria-label="Permalink to &quot;`CSTOR`: Cache storage {#cstor}&quot;">​</a></h3><p>A persisted dataset is not fully cached in memory, or is spilling to disk. Raise executor memory, or shrink the cached dataset.</p><p>The cached-partition counts and sizes come from <code>SparkListenerBlockUpdated</code> events, which Spark writes only when <code>spark.eventLog.logBlockUpdates.enabled=true</code>. Since Spark 2.3 the RDD storage figures in stage-submission events are always 0, and they are used only as a fallback. When a Spark 2.3+ run persists RDDs but its log has neither and block-update logging was off, the check reports that the cache could not be checked instead of passing it: turn <code>spark.eventLog.logBlockUpdates.enabled</code> on and rerun to measure eviction and disk spillover.</p><h3 id="local" tabindex="-1"><code>LOCAL</code>: Core usage locality <a class="header-anchor" href="#local" aria-label="Permalink to &quot;`LOCAL`: Core usage locality {#local}&quot;">​</a></h3><p>Tasks run without process- or node-local data placement more often than expected. Check <code>spark.locality.wait</code> settings and executor/data colocation. Self-flags a confidence that scales with the non-local ratio and sample size: the thresholds are our own noise floor for this metric.</p><h3 id="chrn" tabindex="-1"><code>CHRN</code>: Autoscaling churn <a class="header-anchor" href="#chrn" aria-label="Permalink to &quot;`CHRN`: Autoscaling churn {#chrn}&quot;">​</a></h3><p>Executors are stood up and torn down again before they can do useful work: re-provisioning churn rather than normal scale-down. Raise <code>spark.dynamicAllocation.executorIdleTimeout</code>, or widen the <code>minExecutors</code>/<code>maxExecutors</code> bounds to reduce flapping. Self-flags a confidence that scales with how far the short-lived-executor share sits past the threshold: these thresholds are still a design spike, not yet validated against real-world runs.</p><h3 id="jobs" tabindex="-1"><code>JOBS</code>: Job failure rate <a class="header-anchor" href="#jobs" aria-label="Permalink to &quot;`JOBS`: Job failure rate {#jobs}&quot;">​</a></h3><p>A large share of completed jobs did not succeed. Inspect the driver log for the failed job(s) and the stage failures that triggered them.</p><h3 id="incmp" tabindex="-1"><code>INCMP</code>: Incomplete run <a class="header-anchor" href="#incmp" aria-label="Permalink to &quot;`INCMP`: Incomplete run {#incmp}&quot;">​</a></h3><p>This event log never recorded an <code>ApplicationEnd</code> event: capture stopped before the run finished (an in-flight job, a rotated-away log, or a cut-short capture). Every other finding and metric on the board reflects only what was captured up to that point, not the full run.</p><h2 id="configuration-scope" tabindex="-1">Configuration scope <a class="header-anchor" href="#configuration-scope" aria-label="Permalink to &quot;Configuration scope&quot;">​</a></h2><h3 id="cfg" tabindex="-1"><code>CFG</code>: Configuration audit <a class="header-anchor" href="#cfg" aria-label="Permalink to &quot;`CFG`: Configuration audit {#cfg}&quot;">​</a></h3><p>Flags configuration settings that may cause reliability or efficiency problems, independent of any one stage&#39;s behavior. Four properties are audited today:</p><ul><li><code>spark.shuffle.service.enabled</code>: flagged when dynamic allocation is on but the external shuffle service is off, since shuffle data won&#39;t survive executor removal.</li><li><code>spark.dynamicAllocation.maxExecutors</code>: flagged for inverted bounds or a missing upper bound.</li><li><code>spark.serializer</code>: flagged when still on the default Java serializer; <code>org.apache.spark.serializer.KryoSerializer</code> is faster and produces smaller buffers.</li><li><code>spark.executor.memoryOverhead</code>: flagged when set below a safe floor.</li></ul><h2 id="sql-scope" tabindex="-1">SQL scope <a class="header-anchor" href="#sql-scope" aria-label="Permalink to &quot;SQL scope&quot;">​</a></h2><h3 id="plan" tabindex="-1"><code>PLAN</code>: Plan advisor <a class="header-anchor" href="#plan" aria-label="Permalink to &quot;`PLAN`: Plan advisor {#plan}&quot;">​</a></h3><p>Flags patterns in the SQL execution plan worth reviewing. Four checks share this tag:</p><ul><li>Duplicate plan subtree: the same subtree recomputed more than once in the plan. When the repeats have the same shape but different filters, columns or tables, the finding stays informational and claims no time. Only flagged when the repeat&#39;s stages take at least 0.5% of the run.</li><li>Small files: reading an excessive number of small files.</li><li>Under-broadcast: the smaller side of a Sort Merge Join looks well under the broadcast threshold; consider a <code>broadcast()</code> hint or raising <code>spark.sql.autoBroadcastJoinThreshold</code>.</li><li>Over-broadcast: a broadcast exceeds the 1 GB threshold; check for a misapplied broadcast hint or a misconfigured <code>spark.sql.autoBroadcastJoinThreshold</code>.</li></ul>',60)])])}const f=a(s,[["render",i]]);export{p as __pageData,f as default};

package/public/docs/assets/{user-guide_understanding-findings.md.B29f0ucS.lean.js → user-guide_understanding-findings.md.D1ccs60C.lean.js}

@@ -1 +1 @@
-import{_ as a,o as t,c as o,a5 as r}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Understanding findings","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/understanding-findings.md","filePath":"user-guide/understanding-findings.md"}'),s={name:"user-guide/understanding-findings.md"};function i(n,e,l,d,c,h){return t(),o("div",null,[...e[0]||(e[0]=[r("",59)])])}const f=a(s,[["render",i]]);export{p as __pageData,f as default};
+import{_ as a,o as t,c as o,a5 as r}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Understanding findings","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/understanding-findings.md","filePath":"user-guide/understanding-findings.md"}'),s={name:"user-guide/understanding-findings.md"};function i(n,e,l,d,c,h){return t(),o("div",null,[...e[0]||(e[0]=[r("",60)])])}const f=a(s,[["render",i]]);export{p as __pageData,f as default};