feat(benchmark): print scenario runtime, status and prompt for viewing extended (#152)

## Description

  
Command Rename: status → summary
  - Renamed benchmark-job status to benchmark-job summary
  - File renamed: status.ts → summary.ts

  New -e, --extended Flag for Summary

- By default, rli benchmark-job summary <id> shows only the aggregate
table (agent scores)
- With -e flag, shows individual scenario results underneath each agent

  Watch Command Improvements

  Elapsed time per scenario:
- Each running scenario now shows how long it's been running (e.g.,
running (2m 30s))

  Completion behavior:
  - On job completion, exits full-screen and shows:
    - "Benchmark job completed!" message
    - Total elapsed time
    - Summary table (without individual scenarios)
- Hint: To see full results, run: rli benchmark-job summary -e <job_id>

  Display improvements:
  - Added job ID line under the job name header
  - Added terminal resize handler to prevent display artifacts
- Content now truncates to fit terminal height (header stays visible,
progress truncated from bottom)

## Type of Change

<!-- Mark the relevant option with an 'x' -->

- [ ] Bug fix (non-breaking change which fixes an issue)
- [x] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Test updates

## Related Issues

<!-- Link to related issues using #issue-number -->
Closes #

## Changes Made

<!-- Describe the changes in detail -->

## Testing

<!-- Describe how you tested your changes -->

- [ ] I have tested locally
- [ ] I have added/updated tests
- [ ] All existing tests pass

## Checklist

- [ ] My code follows the code style of this project
- [ ] I have performed a self-review of my own code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have updated the documentation accordingly
- [ ] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged and published

## Screenshots (if applicable)

<!-- Add screenshots to help explain your changes -->

## Additional Notes

<!-- Any additional information that reviewers should know -->

Author: ross-rl

README.md

@@ -185,7 +185,7 @@ rli mcp install                          # Install Runloop MCP server configurat
 
 ```bash
 rli benchmark-job run                    # Run a benchmark job with one or more ...
-rli benchmark-job status <id>            # Get benchmark job status and results
+rli benchmark-job summary <id>           # Get benchmark job summary and results
 rli benchmark-job watch <id>             # Watch benchmark job progress in real-...
 ```
 

src/commands/benchmark-job/status.ts src/commands/benchmark-job/summary.tssrc/commands/benchmark-job/status.ts renamed to src/commands/benchmark-job/summary.ts

@@ -1,5 +1,5 @@
 /**
- * Status benchmark job command
+ * Summary benchmark job command
  */
 
 import chalk from "chalk";
@@ -11,8 +11,9 @@ import {
 } from "../../services/benchmarkJobService.js";
 import { output, outputError } from "../../utils/output.js";
 
-interface StatusOptions {
+interface SummaryOptions {
   output?: string;
+  extended?: boolean;
 }
 
 // Job states that indicate completion
@@ -285,7 +286,7 @@ function calculateCompletedStats(
 }
 
 // Print results table for completed jobs
-function printResultsTable(job: BenchmarkJob): void {
+function printResultsTable(job: BenchmarkJob, extended: boolean = false): void {
   const outcomes = job.benchmark_outcomes || [];
 
   if (outcomes.length === 0) {
@@ -363,55 +364,59 @@ function printResultsTable(job: BenchmarkJob): void {
         chalk.dim(totalColStr),
     );
 
-    // Print individual scenario results underneath (indented)
-    for (const scenario of scenarioOutcomes) {
-      const scenarioName =
-        scenario.scenario_name || scenario.scenario_definition_id || "unknown";
-      const state = scenario.state || "unknown";
-      const score = scenario.score;
-
-      let statusIcon: string;
-      let statusColor: typeof chalk.green;
-
-      if (state.toUpperCase() === "COMPLETED") {
-        if (score === 1.0) {
-          statusIcon = chalk.green("\u2713"); // checkmark
-          statusColor = chalk.green;
+    // Print individual scenario results underneath (indented) when extended
+    if (extended) {
+      for (const scenario of scenarioOutcomes) {
+        const scenarioName =
+          scenario.scenario_name ||
+          scenario.scenario_definition_id ||
+          "unknown";
+        const state = scenario.state || "unknown";
+        const score = scenario.score;
+
+        let statusIcon: string;
+        let statusColor: typeof chalk.green;
+
+        if (state.toUpperCase() === "COMPLETED") {
+          if (score === 1.0) {
+            statusIcon = chalk.green("\u2713"); // checkmark
+            statusColor = chalk.green;
+          } else {
+            statusIcon = chalk.yellow("\u2717"); // X
+            statusColor = chalk.yellow;
+          }
         } else {
-          statusIcon = chalk.yellow("\u2717"); // X
-          statusColor = chalk.yellow;
+          statusIcon = chalk.red("!");
+          statusColor = chalk.red;
         }
-      } else {
-        statusIcon = chalk.red("!");
-        statusColor = chalk.red;
-      }
 
-      const scenarioNameTrunc =
-        scenarioName.length > 50
-          ? scenarioName.slice(0, 47) + "..."
-          : scenarioName;
-
-      const scoreStr =
-        score !== undefined && score !== null
-          ? `score=${score.toFixed(1)}`
-          : state;
-
-      console.log(
-        chalk.dim("  ") +
-          statusIcon +
-          " " +
-          chalk.dim(scenarioNameTrunc.padEnd(52)) +
-          statusColor(scoreStr),
-      );
+        const scenarioNameTrunc =
+          scenarioName.length > 50
+            ? scenarioName.slice(0, 47) + "..."
+            : scenarioName;
+
+        const scoreStr =
+          score !== undefined && score !== null
+            ? `score=${score.toFixed(1)}`
+            : state;
+
+        console.log(
+          chalk.dim("  ") +
+            statusIcon +
+            " " +
+            chalk.dim(scenarioNameTrunc.padEnd(52)) +
+            statusColor(scoreStr),
+        );
+      }
     }
   }
 
   console.log();
 }
 
-export async function statusBenchmarkJob(
+export async function summaryBenchmarkJob(
   id: string,
-  options: StatusOptions = {},
+  options: SummaryOptions = {},
 ) {
   try {
     const job = await getBenchmarkJob(id);
@@ -420,11 +425,11 @@ export async function statusBenchmarkJob(
     if (options.output && options.output !== "text") {
       output(job, { format: options.output, defaultFormat: "json" });
     } else if (isComplete) {
-      printResultsTable(job);
+      printResultsTable(job, options.extended);
     } else {
       await printStatus(job);
     }
   } catch (error) {
-    outputError("Failed to get benchmark job status", error);
+    outputError("Failed to get benchmark job summary", error);
   }
 }

src/commands/benchmark-job/watch.ts

@@ -56,11 +56,13 @@ function exitFullScreen(): void {
   process.stdout.write(ANSI.exitAltScreen);
 }
 
-// Render content at top of screen
+// Render content at top of screen, truncating to fit terminal height
 function renderScreen(lines: string[]): void {
   process.stdout.write(ANSI.moveTo(1, 1));
   process.stdout.write(ANSI.clearScreen);
-  for (const line of lines) {
+  const maxLines = (process.stdout.rows || 24) - 1; // Leave 1 line buffer
+  const truncatedLines = lines.slice(0, maxLines);
+  for (const line of truncatedLines) {
     console.log(line);
   }
 }
@@ -71,10 +73,27 @@ function formatPercent(count: number, total: number): string {
   return ((count / total) * 100).toFixed(1) + "%";
 }
 
+// Format duration in human-readable format
+function formatDuration(ms: number): string {
+  const seconds = Math.floor(ms / 1000);
+  const minutes = Math.floor(seconds / 60);
+  const hours = Math.floor(minutes / 60);
+  const remainingMinutes = minutes % 60;
+  const remainingSeconds = seconds % 60;
+  if (hours > 0) {
+    return `${hours}h ${remainingMinutes}m ${remainingSeconds}s`;
+  }
+  if (minutes > 0) {
+    return `${minutes}m ${remainingSeconds}s`;
+  }
+  return `${seconds}s`;
+}
+
 // In-progress scenario info for display
 interface InProgressScenario {
   name: string;
   state: string;
+  startTimeMs?: number;
 }
 
 // Progress stats for a benchmark run
@@ -141,17 +160,20 @@ function calculateRunProgress(
       inProgressScenarios.push({
         name: scenario.name || scenario.scenario_id || "unknown",
         state: scenarioState,
+        startTimeMs: scenario.start_time_ms,
       });
     } else if (scenarioState === "running") {
       running++;
       inProgressScenarios.push({
         name: scenario.name || scenario.scenario_id || "unknown",
         state: scenarioState,
+        startTimeMs: scenario.start_time_ms,
       });
     } else if (scenarioState && scenarioState !== "pending") {
       inProgressScenarios.push({
         name: scenario.name || scenario.scenario_id || "unknown",
         state: scenarioState,
+        startTimeMs: scenario.start_time_ms,
       });
     }
   }
@@ -311,15 +333,29 @@ function formatScenarioLines(
 ): string[] {
   const limited = scenarios.slice(0, maxScenarios);
   const remaining = scenarios.length - limited.length;
+  const now = Date.now();
 
   const lines: string[] = [];
   for (const scenario of limited) {
     let name = scenario.name;
-    if (name.length > 45) {
-      name = name.slice(0, 42) + "...";
+    if (name.length > 35) {
+      name = name.slice(0, 32) + "...";
     }
     const stateStr = formatScenarioState(scenario.state, tick);
-    lines.push(chalk.dim("      └ ") + chalk.dim(name.padEnd(46)) + stateStr);
+
+    // Calculate elapsed time if start time is available
+    let elapsedStr = "";
+    if (scenario.startTimeMs) {
+      const elapsedMs = now - scenario.startTimeMs;
+      elapsedStr = chalk.dim(` (${formatDuration(elapsedMs)})`);
+    }
+
+    lines.push(
+      chalk.dim("      └ ") +
+        chalk.dim(name.padEnd(36)) +
+        stateStr +
+        elapsedStr,
+    );
   }
 
   if (remaining > 0) {
@@ -457,47 +493,6 @@ function printResultsTable(job: BenchmarkJob): void {
         failedErrorColored +
         chalk.dim(totalColStr),
     );
-
-    for (const scenario of scenarioOutcomes) {
-      const scenarioName =
-        scenario.scenario_name || scenario.scenario_definition_id || "unknown";
-      const state = scenario.state || "unknown";
-      const score = scenario.score;
-
-      let statusIcon: string;
-      let statusColor: typeof chalk.green;
-
-      if (state.toUpperCase() === "COMPLETED") {
-        if (score === 1.0) {
-          statusIcon = chalk.green("\u2713");
-          statusColor = chalk.green;
-        } else {
-          statusIcon = chalk.yellow("\u2717");
-          statusColor = chalk.yellow;
-        }
-      } else {
-        statusIcon = chalk.red("!");
-        statusColor = chalk.red;
-      }
-
-      const scenarioNameTrunc =
-        scenarioName.length > 50
-          ? scenarioName.slice(0, 47) + "..."
-          : scenarioName;
-
-      const scoreStr =
-        score !== undefined && score !== null
-          ? `score=${score.toFixed(1)}`
-          : state;
-
-      console.log(
-        chalk.dim("  ") +
-          statusIcon +
-          " " +
-          chalk.dim(scenarioNameTrunc.padEnd(52)) +
-          statusColor(scoreStr),
-      );
-    }
   }
 
   console.log();
@@ -547,6 +542,13 @@ export async function watchBenchmarkJob(id: string) {
     const SPINNER_INTERVAL_MS = 100;
     const UPDATES_PER_POLL = Math.floor(POLL_INTERVAL_MS / SPINNER_INTERVAL_MS);
 
+    // Handle terminal resize - clear screen to prevent artifacts
+    let needsFullRedraw = false;
+    const handleResize = () => {
+      needsFullRedraw = true;
+    };
+    process.stdout.on("resize", handleResize);
+
     try {
       let tick = 0;
       let progressList = await fetchAllRunsProgress(job);
@@ -572,6 +574,7 @@ export async function watchBenchmarkJob(id: string) {
           chalk.bold.cyan(`Benchmark Job: ${jobName}`) +
             chalk.dim(` (${elapsedStr})`),
         );
+        screenLines.push(chalk.dim(`ID: ${job.id}`));
         screenLines.push(chalk.dim(`State: ${job.state}`));
         screenLines.push("");
 
@@ -585,6 +588,12 @@ export async function watchBenchmarkJob(id: string) {
         screenLines.push("");
         screenLines.push(chalk.dim("Press Ctrl+C to exit"));
 
+        // Force full clear on resize to prevent artifacts
+        if (needsFullRedraw) {
+          process.stdout.write(ANSI.clearScreen);
+          needsFullRedraw = false;
+        }
+
         // Render the screen
         renderScreen(screenLines);
 
@@ -601,11 +610,27 @@ export async function watchBenchmarkJob(id: string) {
         await sleep(SPINNER_INTERVAL_MS);
       }
     } finally {
+      process.stdout.off("resize", handleResize);
       cleanup();
     }
 
-    // Show final results
+    // Calculate total elapsed time
+    const totalElapsed = Date.now() - startTime;
+    const totalElapsedStr = formatDuration(totalElapsed);
+
+    // Show completion message
+    console.log(chalk.green.bold("Benchmark job completed!"));
+    console.log(chalk.dim(`Total time: ${totalElapsedStr}`));
+
+    // Show final results (summary only)
     printResultsTable(job);
+
+    // Show hint for full results
+    console.log(
+      chalk.dim(
+        `To see full results, run: rli benchmark-job summary -e ${job.id}`,
+      ),
+    );
   } catch (error) {
     outputError("Failed to watch benchmark job", error);
   }

src/utils/commands.ts

@@ -1054,16 +1054,17 @@ export function createProgram(): Command {
     });
 
   benchmarkJob
-    .command("status <id>")
-    .description("Get benchmark job status and results")
+    .command("summary <id>")
+    .description("Get benchmark job summary and results")
+    .option("-e, --extended", "Show individual scenario results")
     .option(
       "-o, --output [format]",
       "Output format: text|json|yaml (default: text)",
     )
     .action(async (id, options) => {
-      const { statusBenchmarkJob } =
-        await import("../commands/benchmark-job/status.js");
-      await statusBenchmarkJob(id, options);
+      const { summaryBenchmarkJob } =
+        await import("../commands/benchmark-job/summary.js");
+      await summaryBenchmarkJob(id, options);
     });
 
   benchmarkJob