harivansh-afk/evaluclaude-harness
1
0
Fork 0
mirror of https://github.com/harivansh-afk/evaluclaude-harness.git synced 2026-04-16 19:04:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ui polish

Browse source
This commit is contained in:
Harivansh Rathi 2026-01-11 20:38:57 -05:00
parent ff5300f4e0
commit 69c08c9d6b
12 changed files with 1430 additions and 308 deletions
Download patch file Download diff file Expand all files Collapse all files

76
src/cli/commands/view.ts
View file

@ -6,6 +6,7 @@ import {
formatTrace,
formatTraceList
} from '../../observability/index.js';
import { style, icons, formatError, nextSteps } from '../theme.js';
export const viewCommand = new Command('view')
.description('View evaluation traces')
@ -19,6 +20,14 @@ export const viewCommand = new Command('view')
.option('--decisions', 'Show decisions made', true)
.option('-n, --limit <count>', 'Limit number of traces listed', '20')
.option('--eval <eval-id>', 'Filter traces by eval ID')
.addHelpText('after', `
${style.bold('Examples:')}
${style.command('evaluclaude view')} ${style.dim('View the most recent trace')}
${style.command('evaluclaude view --list')} ${style.dim('List all available traces')}
${style.command('evaluclaude view abc123')} ${style.dim('View a specific trace by ID')}
${style.command('evaluclaude view --json')} ${style.dim('Output trace as raw JSON')}
${style.command('evaluclaude view -v')} ${style.dim('Verbose output with tool calls')}
`)
.action(async (traceId: string | undefined, options) => {
try {
if (options.list) {
@ -26,16 +35,19 @@ export const viewCommand = new Command('view')
const limited = traces.slice(0, parseInt(options.limit, 10));
if (traces.length === 0) {
console.log('\nNo traces found.');
console.log('Run `evaluclaude run` to generate traces.\n');
console.log(`\n${style.warning(`${icons.warning} No traces found.`)}`);
console.log(nextSteps([
{ command: 'evaluclaude run', description: 'Run evals to generate traces' },
{ command: 'evaluclaude pipeline .', description: 'Run full pipeline from scratch' },
]));
return;
}
console.log(formatTraceList(limited));
if (traces.length > limited.length) {
console.log(`Showing ${limited.length} of ${traces.length} traces.`);
console.log(`Use --limit to see more.\n`);
console.log(style.muted(`Showing ${limited.length} of ${traces.length} traces.`));
console.log(style.muted(`Use ${style.command('--limit')} to see more.\n`));
}
return;
}
@ -45,15 +57,20 @@ export const viewCommand = new Command('view')
if (options.last || !traceId) {
trace = await getLatestTrace();
if (!trace) {
console.log('\nNo traces found.');
console.log('Run `evaluclaude run` to generate traces.\n');
console.log(`\n${style.warning(`${icons.warning} No traces found.`)}`);
console.log(nextSteps([
{ command: 'evaluclaude run', description: 'Run evals to generate traces' },
{ command: 'evaluclaude pipeline .', description: 'Run full pipeline from scratch' },
]));
return;
}
} else {
trace = await loadTrace(traceId);
if (!trace) {
console.error(`\nTrace not found: ${traceId}`);
console.log('Use `evaluclaude view --list` to see available traces.\n');
console.log(formatError(`Trace not found: ${style.path(traceId)}`, [
`Run ${style.command('evaluclaude view --list')} to see available traces`,
`Check that the trace ID is correct`,
]));
process.exit(1);
}
}
@ -68,7 +85,10 @@ export const viewCommand = new Command('view')
console.log(output);
} catch (error) {
console.error('Error viewing trace:', error instanceof Error ? error.message : error);
console.log(formatError(
error instanceof Error ? error.message : String(error),
['Run evaluclaude run first to generate traces']
));
process.exit(1);
}
});
@ -77,14 +97,36 @@ export const tracesCommand = new Command('traces')
.description('List all evaluation traces (alias for view --list)')
.option('-n, --limit <count>', 'Limit number of traces', '20')
.option('--eval <eval-id>', 'Filter by eval ID')
.addHelpText('after', `
${style.bold('Examples:')}
${style.command('evaluclaude traces')} ${style.dim('List all traces')}
${style.command('evaluclaude traces -n 50')} ${style.dim('Show up to 50 traces')}
${style.command('evaluclaude traces --eval X')} ${style.dim('Filter by eval ID')}
`)
.action(async (options) => {
const traces = await listTraces(options.eval);
const limited = traces.slice(0, parseInt(options.limit, 10));
if (traces.length === 0) {
console.log('\nNo traces found.');
return;
try {
const traces = await listTraces(options.eval);
const limited = traces.slice(0, parseInt(options.limit, 10));
if (traces.length === 0) {
console.log(`\n${style.warning(`${icons.warning} No traces found.`)}`);
console.log(nextSteps([
{ command: 'evaluclaude run', description: 'Run evals to generate traces' },
]));
return;
}
console.log(formatTraceList(limited));
if (traces.length > limited.length) {
console.log(style.muted(`Showing ${limited.length} of ${traces.length} traces.`));
console.log(style.muted(`Use ${style.command('--limit')} to see more.\n`));
}
} catch (error) {
console.log(formatError(
error instanceof Error ? error.message : String(error),
['Run evaluclaude run first to generate traces']
));
process.exit(1);
}
console.log(formatTraceList(limited));
});