fix(cli): remove eval export option

.github/workflows/evals.yml

@@ -94,8 +94,7 @@ jobs:
             "${TARGET_FLAG[@]}" \
             --workers 3 \
             --threshold ${{ steps.filter.outputs.threshold }} \
-            --output .agentv/ci-results/artifacts \
-            --export .agentv/ci-results/junit.xml
+            --output .agentv/ci-results/artifacts
           EXIT_CODE=$?
 
           echo "exit_code=$EXIT_CODE" >> "$GITHUB_OUTPUT"
@@ -104,16 +103,6 @@ jobs:
         if: always()
         run: bun run scripts/ci-summary.ts .agentv/ci-results >> "$GITHUB_STEP_SUMMARY"
 
-      - name: Publish JUnit test results
-        if: always()
-        continue-on-error: true
-        uses: dorny/test-reporter@v1
-        with:
-          name: AgentV Eval Results
-          path: .agentv/ci-results/junit.xml
-          reporter: java-junit
-          fail-on-error: false
-
       - name: Upload eval artifacts
         if: always()
         uses: actions/upload-artifact@v4

AGENTS.md

@@ -384,8 +384,7 @@ Unit tests alone are insufficient for grader changes. After implementing or modi
 ```bash
 # 1. Run the eval, writing results to a sibling *.results.jsonl file
 bun apps/cli/src/cli.ts eval examples/path/to/suite.eval.yaml --target azure \
-  --output examples/path/to/suite.run \
-  --export examples/path/to/suite.results.jsonl
+  --output examples/path/to/suite.run
 
 # 2. Assert all expected score ranges pass
 bun scripts/check-grader-scores.ts
@@ -396,7 +395,7 @@ The script auto-discovers `examples/**/*.grader-scores.yaml`, locates the siblin
 **To add score checks for a new eval:**
 1. Create `<eval-stem>.grader-scores.yaml` next to the eval YAML.
 2. Add entries for each `(test_id, grader, range)` you care about — `grader` must match a `scores[].name` value in the JSONL output, and `range.min`/`range.max` default to 0/1 if omitted.
-3. Run the eval with `--output <eval-stem>.run --export <eval-stem>.results.jsonl`, then run the script.
+3. Run the eval with `--output <eval-stem>.run`, then run the script.
 
 See `examples/red-team/archetypes/coding-agent/suites/screenshot-pii-upload.grader-scores.yaml` for a concrete example.
 

README.md

@@ -78,8 +78,7 @@ agentv compare .agentv/results/runs/<timestamp>/index.jsonl
 
 ```bash
 agentv eval evals/my-eval.yaml --output ./run   # writes ./run/index.jsonl
-agentv eval evals/my-eval.yaml --export report.html
-agentv eval evals/my-eval.yaml --export results.xml   # JUnit XML for CI
+cat ./run/index.jsonl                         # JSONL results for scripts/CI
 ```
 
 ## TypeScript SDK

apps/cli/src/commands/eval/commands/run.ts

@@ -46,7 +46,7 @@ export const evalRunCommand = command({
     out: option({
       type: optional(string),
       long: 'out',
-      description: '[Removed: use --output <dir> and --export <file>] Former flat result path',
+      description: '[Removed: use --output <dir>] Former flat result path',
     }),
     output: option({
       type: optional(string),
@@ -58,19 +58,13 @@ export const evalRunCommand = command({
     outputFormat: option({
       type: optional(string),
       long: 'output-format',
-      description: '[Removed: use --export <file>] Run directories always write index.jsonl',
+      description: '[Removed] Run directories always write index.jsonl',
     }),
     experiment: option({
       type: optional(string),
       long: 'experiment',
       description: 'Experiment label for canonical run output (default: default)',
     }),
-    export: multioption({
-      type: array(string),
-      long: 'export',
-      description:
-        'Write additional output file(s). Format inferred from extension: .jsonl, .json, .xml, .yaml, .html (repeatable)',
-    }),
     dryRun: flag({
       long: 'dry-run',
       description: 'Use mock provider responses instead of real LLM calls',
@@ -252,7 +246,6 @@ export const evalRunCommand = command({
       output: args.output,
       outputFormat: args.outputFormat,
       experiment: args.experiment,
-      export: args.export,
       dryRun: args.dryRun,
       dryRunDelay: args.dryRunDelay,
       dryRunDelayMin: args.dryRunDelayMin,

apps/cli/src/commands/eval/output-writer.ts

@@ -1,81 +1,15 @@
-import path from 'node:path';
-
 import type { EvaluationResult } from '@agentv/core';
 
-import { HtmlWriter } from './html-writer.js';
-import { JsonWriter } from './json-writer.js';
 import { JsonlWriter } from './jsonl-writer.js';
-import { JunitWriter } from './junit-writer.js';
-import { YamlWriter } from './yaml-writer.js';
-
-export type OutputFormat = 'jsonl' | 'yaml' | 'html';
 
 export interface OutputWriter {
   append(result: EvaluationResult): Promise<void>;
   close(): Promise<void>;
 }
 
-export interface WriterOptions {
-  readonly threshold?: number;
-}
-
 export async function createOutputWriter(
   filePath: string,
-  format: OutputFormat,
   options?: { append?: boolean },
 ): Promise<OutputWriter> {
-  switch (format) {
-    case 'jsonl':
-      return JsonlWriter.open(filePath, { append: options?.append });
-    case 'yaml':
-      return YamlWriter.open(filePath);
-    case 'html':
-      return HtmlWriter.open(filePath);
-    default: {
-      const exhaustiveCheck: never = format;
-      throw new Error(`Unsupported output format: ${exhaustiveCheck}`);
-    }
-  }
-}
-
-const SUPPORTED_EXTENSIONS = new Set(['.jsonl', '.json', '.xml', '.yaml', '.yml', '.html', '.htm']);
-
-export function createWriterFromPath(
-  filePath: string,
-  options?: WriterOptions,
-): Promise<OutputWriter> {
-  const ext = path.extname(filePath).toLowerCase();
-  switch (ext) {
-    case '.jsonl':
-      return JsonlWriter.open(filePath);
-    case '.json':
-      return JsonWriter.open(filePath);
-    case '.xml':
-      return JunitWriter.open(filePath, { threshold: options?.threshold });
-    case '.yaml':
-    case '.yml':
-      return YamlWriter.open(filePath);
-    case '.html':
-    case '.htm':
-      return HtmlWriter.open(filePath);
-    default:
-      throw new Error(
-        `Unsupported output file extension "${ext}". Supported: ${[...SUPPORTED_EXTENSIONS].join(', ')}`,
-      );
-  }
-}
-
-export async function createMultiWriter(
-  filePaths: readonly string[],
-  options?: WriterOptions,
-): Promise<OutputWriter> {
-  const writers = await Promise.all(filePaths.map((fp) => createWriterFromPath(fp, options)));
-  return {
-    async append(result: EvaluationResult): Promise<void> {
-      await Promise.all(writers.map((w) => w.append(result)));
-    },
-    async close(): Promise<void> {
-      await Promise.all(writers.map((w) => w.close()));
-    },
-  };
+  return JsonlWriter.open(filePath, { append: options?.append });
 }