p100
This commit is contained in:
team 1
75
patch_history/RETRIEX_PATCH_100_ADMIN_EVAL_UX_README.md
Normal file
75
patch_history/RETRIEX_PATCH_100_ADMIN_EVAL_UX_README.md
Normal file
@@ -0,0 +1,75 @@
|
||||
# RetrieX Patch p100 - Admin Eval UX
|
||||
|
||||
Status: patch-only candidate
|
||||
Basis: confirmed v1.6.2 + p99/p99b/p99c green eval suite
|
||||
|
||||
## Ziel
|
||||
|
||||
p100 macht die mit p99 eingeführte Eval-Suite im Admin sichtbar und bedienbar, ohne die produktive RAG-, Shop-, Prompt-, Scoring- oder Antwortlogik fachlich zu ändern.
|
||||
|
||||
## Enthalten
|
||||
|
||||
- Neuer Admin-Bereich `/admin/evals/`
|
||||
- Übersicht über die Eval-Typen:
|
||||
- `retrieval`
|
||||
- `shop_query`
|
||||
- `followup`
|
||||
- `answer_guard`
|
||||
- Anzeige der Case-Anzahl pro Typ
|
||||
- Anzeige typspezifischer letzter Reports aus `tests/evals/reports/<type>-last-run.json`
|
||||
- Run-Buttons pro Eval-Typ
|
||||
- Formular zum Ausführen eines kompletten Typs oder einer einzelnen Case-ID
|
||||
- Detailansicht für PASS/FAIL, Fehler und Result-Details
|
||||
- CLI-Referenz im Admin
|
||||
- Sidebar-Link unter KI-Endpunkte
|
||||
- Link von der KI-/LLM-Setup-Seite zur Eval Suite
|
||||
|
||||
## Report-Verhalten
|
||||
|
||||
Admin-Runs schreiben zwei Reports:
|
||||
|
||||
- `tests/evals/reports/<type>-last-run.json`
|
||||
- `tests/evals/reports/last-run.json`
|
||||
|
||||
Die CLI bleibt unverändert und schreibt weiterhin den bekannten `last-run.json`.
|
||||
|
||||
## Rollen
|
||||
|
||||
Der neue Bereich ist auf Controller-Ebene durch `ROLE_KNOWLEDGE_ADMIN` geschützt.
|
||||
|
||||
## Nicht geändert
|
||||
|
||||
- keine Retrieval-Gewichte
|
||||
- keine Shopquery-Erzeugungslogik
|
||||
- keine Follow-up-Logik
|
||||
- keine Answer-Guard-Logik
|
||||
- keine Prompt-Änderung
|
||||
- keine YAML-Vokabularänderung
|
||||
- keine Modellparameteränderung
|
||||
- keine Datenbankmigration
|
||||
|
||||
## Geänderte Dateien
|
||||
|
||||
- `src/Controller/Admin/AdminEvalController.php`
|
||||
- `src/Service/Admin/EvalAdminService.php`
|
||||
- `templates/admin/evals/index.html.twig`
|
||||
- `templates/admin/base.html.twig`
|
||||
- `templates/admin/model_config/list.html.twig`
|
||||
- `patch_history/RETRIEX_PATCH_100_ADMIN_EVAL_UX_README.md`
|
||||
|
||||
## Prüfung nach Einspielen
|
||||
|
||||
```bash
|
||||
php bin/console mto:agent:config:validate
|
||||
php bin/console mto:agent:eval:run retrieval
|
||||
php bin/console mto:agent:eval:run shop_query
|
||||
php bin/console mto:agent:eval:run followup
|
||||
php bin/console mto:agent:eval:run answer_guard
|
||||
```
|
||||
|
||||
Zusätzlich im Browser prüfen:
|
||||
|
||||
- `/admin/evals/`
|
||||
- Eval-Typ ausführen
|
||||
- Detailreport öffnen
|
||||
- Sidebar-Link sichtbar für Knowledge Admins
|
||||
68
src/Controller/Admin/AdminEvalController.php
Normal file
68
src/Controller/Admin/AdminEvalController.php
Normal file
@@ -0,0 +1,68 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
namespace App\Controller\Admin;
|
||||
|
||||
use App\Security\ApplicationRoles;
|
||||
use App\Service\Admin\EvalAdminService;
|
||||
use Symfony\Bundle\FrameworkBundle\Controller\AbstractController;
|
||||
use Symfony\Component\HttpFoundation\Request;
|
||||
use Symfony\Component\HttpFoundation\Response;
|
||||
use Symfony\Component\Routing\Attribute\Route;
|
||||
|
||||
#[Route('/admin/evals')]
|
||||
final class AdminEvalController extends AbstractController
|
||||
{
|
||||
#[Route('/', name: 'admin_evals_index', methods: ['GET'])]
|
||||
public function index(Request $request, EvalAdminService $evals): Response
|
||||
{
|
||||
$this->denyAccessUnlessGranted(ApplicationRoles::ROLE_KNOWLEDGE_ADMIN);
|
||||
|
||||
$selectedType = trim((string) $request->query->get('type', ''));
|
||||
if ($selectedType === '' || !in_array($selectedType, $evals->supportedTypeNames(), true)) {
|
||||
$selectedType = 'retrieval';
|
||||
}
|
||||
|
||||
return $this->render('admin/evals/index.html.twig', [
|
||||
'types' => $evals->supportedTypes(),
|
||||
'overview' => $evals->overview(),
|
||||
'cases_by_type' => $evals->casesByType(),
|
||||
'selected_type' => $selectedType,
|
||||
'selected_report' => $evals->readTypeReport($selectedType),
|
||||
'last_report' => $evals->readLastReport(),
|
||||
]);
|
||||
}
|
||||
|
||||
#[Route('/run', name: 'admin_evals_run', methods: ['POST'])]
|
||||
public function run(Request $request, EvalAdminService $evals): Response
|
||||
{
|
||||
$this->denyAccessUnlessGranted(ApplicationRoles::ROLE_KNOWLEDGE_ADMIN);
|
||||
|
||||
if (!$this->isCsrfTokenValid('admin_eval_run', (string) $request->request->get('_token'))) {
|
||||
throw $this->createAccessDeniedException();
|
||||
}
|
||||
|
||||
$type = trim((string) $request->request->get('type', 'retrieval'));
|
||||
$caseId = trim((string) $request->request->get('case_id', ''));
|
||||
|
||||
try {
|
||||
$report = $evals->run($type, $caseId !== '' ? $caseId : null);
|
||||
$this->addFlash(
|
||||
((int) ($report['failed'] ?? 0)) === 0 ? 'success' : 'danger',
|
||||
sprintf(
|
||||
'Eval %s abgeschlossen: %d/%d bestanden.',
|
||||
$type,
|
||||
(int) ($report['passed'] ?? 0),
|
||||
(int) ($report['total'] ?? 0)
|
||||
)
|
||||
);
|
||||
} catch (\Throwable $e) {
|
||||
$this->addFlash('danger', $e->getMessage());
|
||||
}
|
||||
|
||||
return $this->redirectToRoute('admin_evals_index', [
|
||||
'type' => $type,
|
||||
]);
|
||||
}
|
||||
}
|
||||
227
src/Service/Admin/EvalAdminService.php
Normal file
227
src/Service/Admin/EvalAdminService.php
Normal file
@@ -0,0 +1,227 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
namespace App\Service\Admin;
|
||||
|
||||
use App\Eval\AgentEvalRunner;
|
||||
use App\Eval\Dto\EvalCase;
|
||||
use App\Eval\Dto\EvalResult;
|
||||
use App\Eval\EvalCaseLoader;
|
||||
use App\Eval\EvalReportWriter;
|
||||
|
||||
final readonly class EvalAdminService
|
||||
{
|
||||
/**
|
||||
* @var array<string, string>
|
||||
*/
|
||||
private const TYPES = [
|
||||
'retrieval' => 'Retrieval',
|
||||
'shop_query' => 'Shopquery',
|
||||
'followup' => 'Follow-up',
|
||||
'answer_guard' => 'Answer-Guard',
|
||||
];
|
||||
|
||||
public function __construct(
|
||||
private EvalCaseLoader $caseLoader,
|
||||
private AgentEvalRunner $runner,
|
||||
private EvalReportWriter $reportWriter,
|
||||
private string $projectDir,
|
||||
) {
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<string, string>
|
||||
*/
|
||||
public function supportedTypes(): array
|
||||
{
|
||||
return self::TYPES;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<int, string>
|
||||
*/
|
||||
public function supportedTypeNames(): array
|
||||
{
|
||||
return array_keys(self::TYPES);
|
||||
}
|
||||
|
||||
public function assertSupportedType(string $type): string
|
||||
{
|
||||
$type = trim($type);
|
||||
|
||||
if (!array_key_exists($type, self::TYPES)) {
|
||||
throw new \InvalidArgumentException(sprintf('Unsupported eval type: %s', $type));
|
||||
}
|
||||
|
||||
return $type;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<string, array<int, array{id:string,prompt:string,type:string}>>
|
||||
*/
|
||||
public function casesByType(): array
|
||||
{
|
||||
$casesByType = [];
|
||||
|
||||
foreach (array_keys(self::TYPES) as $type) {
|
||||
$casesByType[$type] = array_map(
|
||||
static fn (EvalCase $case): array => [
|
||||
'id' => $case->id,
|
||||
'type' => $case->type,
|
||||
'prompt' => $case->prompt,
|
||||
],
|
||||
$this->loadCases($type)
|
||||
);
|
||||
}
|
||||
|
||||
return $casesByType;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<int, array<string, mixed>>
|
||||
*/
|
||||
public function overview(): array
|
||||
{
|
||||
$overview = [];
|
||||
|
||||
foreach (self::TYPES as $type => $label) {
|
||||
$cases = $this->loadCases($type);
|
||||
$report = $this->readTypeReport($type);
|
||||
|
||||
$overview[] = [
|
||||
'type' => $type,
|
||||
'label' => $label,
|
||||
'case_count' => count($cases),
|
||||
'report' => $report,
|
||||
'status' => $this->statusFromReport($report),
|
||||
];
|
||||
}
|
||||
|
||||
return $overview;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<string, mixed>
|
||||
*/
|
||||
public function run(string $type, ?string $caseId = null): array
|
||||
{
|
||||
$type = $this->assertSupportedType($type);
|
||||
$caseId = trim((string) $caseId);
|
||||
$cases = $this->loadCases($type);
|
||||
|
||||
if ($caseId !== '') {
|
||||
$cases = array_values(array_filter(
|
||||
$cases,
|
||||
static fn (EvalCase $case): bool => $case->id === $caseId
|
||||
));
|
||||
}
|
||||
|
||||
if ($cases === []) {
|
||||
throw new \RuntimeException('No eval cases selected.');
|
||||
}
|
||||
|
||||
$results = $this->runner->runAll($cases);
|
||||
$report = $this->buildReport($type, $caseId !== '' ? $caseId : null, $results);
|
||||
|
||||
$typeReportPath = $this->reportWriter->write($report, sprintf('%s-last-run.json', $type));
|
||||
$lastReportPath = $this->reportWriter->write($report);
|
||||
|
||||
$report['written_to'] = $typeReportPath;
|
||||
$report['last_run_written_to'] = $lastReportPath;
|
||||
|
||||
return $report;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<string, mixed>|null
|
||||
*/
|
||||
public function readTypeReport(string $type): ?array
|
||||
{
|
||||
$type = $this->assertSupportedType($type);
|
||||
|
||||
return $this->readReportFile(sprintf('%s/tests/evals/reports/%s-last-run.json', $this->projectDir, $type));
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<string, mixed>|null
|
||||
*/
|
||||
public function readLastReport(): ?array
|
||||
{
|
||||
return $this->readReportFile(sprintf('%s/tests/evals/reports/last-run.json', $this->projectDir));
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<int, EvalCase>
|
||||
*/
|
||||
private function loadCases(string $type): array
|
||||
{
|
||||
return $this->caseLoader->load($this->assertSupportedType($type));
|
||||
}
|
||||
|
||||
/**
|
||||
* @param array<int, EvalResult> $results
|
||||
* @return array<string, mixed>
|
||||
*/
|
||||
private function buildReport(string $type, ?string $caseId, array $results): array
|
||||
{
|
||||
$passed = count(array_filter(
|
||||
$results,
|
||||
static fn (EvalResult $result): bool => $result->passed
|
||||
));
|
||||
$failed = count($results) - $passed;
|
||||
|
||||
return [
|
||||
'type' => $type,
|
||||
'case_filter' => $caseId,
|
||||
'total' => count($results),
|
||||
'passed' => $passed,
|
||||
'failed' => $failed,
|
||||
'generated_at' => (new \DateTimeImmutable())->format(\DateTimeInterface::ATOM),
|
||||
'results' => array_map(
|
||||
static fn (EvalResult $result): array => $result->toArray(),
|
||||
$results
|
||||
),
|
||||
];
|
||||
}
|
||||
|
||||
/**
|
||||
* @return array<string, mixed>|null
|
||||
*/
|
||||
private function readReportFile(string $path): ?array
|
||||
{
|
||||
if (!is_file($path)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
$raw = file_get_contents($path);
|
||||
|
||||
if (!is_string($raw) || trim($raw) === '') {
|
||||
return null;
|
||||
}
|
||||
|
||||
$decoded = json_decode($raw, true);
|
||||
|
||||
if (!is_array($decoded)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return $decoded;
|
||||
}
|
||||
|
||||
private function statusFromReport(?array $report): string
|
||||
{
|
||||
if ($report === null) {
|
||||
return 'not_run';
|
||||
}
|
||||
|
||||
$failed = (int) ($report['failed'] ?? 0);
|
||||
$total = (int) ($report['total'] ?? 0);
|
||||
|
||||
if ($total <= 0) {
|
||||
return 'empty';
|
||||
}
|
||||
|
||||
return $failed === 0 ? 'green' : 'red';
|
||||
}
|
||||
}
|
||||
@@ -134,6 +134,10 @@
|
||||
href="{{ path('admin_model_config_list') }}#agentLiveTest">
|
||||
<i class="bi bi-rocket-takeoff-fill"></i> KI-Agent Live-Test
|
||||
</a>
|
||||
<a class="nav-link text-light {% if route starts with 'admin_evals' %}active fw-bold{% endif %}"
|
||||
href="{{ path('admin_evals_index') }}">
|
||||
<i class="bi bi-clipboard2-check"></i> Eval Suite
|
||||
</a>
|
||||
{% endif %}
|
||||
<hr class="border-secondary">
|
||||
<div class="text-info text-uppercase small mb-2">
|
||||
|
||||
379
templates/admin/evals/index.html.twig
Normal file
379
templates/admin/evals/index.html.twig
Normal file
@@ -0,0 +1,379 @@
|
||||
{% extends 'admin/base.html.twig' %}
|
||||
|
||||
{% block title %}RetrieX Eval Suite{% endblock %}
|
||||
|
||||
{% block body %}
|
||||
|
||||
<div class="d-flex justify-content-between align-items-center mb-4 flex-wrap gap-2">
|
||||
<div>
|
||||
<h1 class="h3 mb-1">
|
||||
<i class="bi bi-clipboard2-check"></i> RetrieX Eval Suite
|
||||
</h1>
|
||||
<div class="small text-secondary">
|
||||
Regressionen für Retrieval, Shopquery, Follow-up und Answer-Guard direkt im Admin prüfen.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<a href="{{ path('admin_model_config_list') }}"
|
||||
class="btn btn-sm btn-outline-secondary">
|
||||
Zurück zum KI-/LLM-Setup
|
||||
</a>
|
||||
</div>
|
||||
|
||||
{% for label in ['success', 'danger', 'warning', 'info'] %}
|
||||
{% for message in app.flashes(label) %}
|
||||
<div class="alert alert-{{ label }} shadow-sm">
|
||||
{{ message }}
|
||||
</div>
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
|
||||
|
||||
|
||||
<div id="adminEvalRunOverlay"
|
||||
class="position-fixed top-0 start-0 w-100 h-100 d-none"
|
||||
style="background: rgba(0, 0, 0, .72); z-index: 1080;">
|
||||
<div class="h-100 d-flex align-items-center justify-content-center px-3">
|
||||
<div class="card bg-black border-warning text-light shadow-lg" style="max-width: 520px; width: 100%;">
|
||||
<div class="card-body text-center py-5">
|
||||
<div class="spinner-border text-warning mb-3" role="status" aria-hidden="true"></div>
|
||||
<h5 class="text-warning mb-2" id="adminEvalRunOverlayLabel">Eval läuft ...</h5>
|
||||
<div class="small text-secondary">
|
||||
Die Regressionstests werden ausgeführt. Bitte die Seite nicht neu laden.
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="row g-4 mb-4">
|
||||
{% for item in overview %}
|
||||
{% set report = item.report %}
|
||||
{% set status = item.status %}
|
||||
{% set badgeClass = status == 'green'
|
||||
? 'bg-success'
|
||||
: (status == 'red' ? 'bg-danger' : 'bg-secondary')
|
||||
%}
|
||||
<div class="col-md-6 col-xl-3">
|
||||
<div class="card bg-black border-secondary text-light h-100 shadow-sm">
|
||||
<div class="card-body">
|
||||
<div class="d-flex justify-content-between align-items-start gap-2 mb-2">
|
||||
<h5 class="text-info mb-0">{{ item.label }}</h5>
|
||||
<span class="badge {{ badgeClass }}">
|
||||
{% if status == 'green' %}
|
||||
grün
|
||||
{% elseif status == 'red' %}
|
||||
rot
|
||||
{% elseif status == 'empty' %}
|
||||
leer
|
||||
{% else %}
|
||||
nicht gelaufen
|
||||
{% endif %}
|
||||
</span>
|
||||
</div>
|
||||
|
||||
<div class="small text-secondary mb-3">
|
||||
{{ item.case_count }} Cases
|
||||
</div>
|
||||
|
||||
{% if report %}
|
||||
<div class="small">
|
||||
<div><strong>Total:</strong> {{ report.total|default(0) }}</div>
|
||||
<div><strong>Passed:</strong> {{ report.passed|default(0) }}</div>
|
||||
<div><strong>Failed:</strong> {{ report.failed|default(0) }}</div>
|
||||
<div class="text-secondary mt-2">
|
||||
{{ report.generated_at|default('') }}
|
||||
</div>
|
||||
</div>
|
||||
{% else %}
|
||||
<div class="small text-secondary">
|
||||
Für diesen Typ liegt noch kein Admin-Report vor.
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
<div class="d-flex flex-wrap gap-2 mt-3">
|
||||
<form method="post"
|
||||
action="{{ path('admin_evals_run') }}"
|
||||
class="d-inline js-admin-eval-run-form"
|
||||
data-eval-type-label="{{ item.label|e('html_attr') }}">
|
||||
<input type="hidden" name="_token" value="{{ csrf_token('admin_eval_run') }}">
|
||||
<input type="hidden" name="type" value="{{ item.type }}">
|
||||
<button type="submit" class="btn btn-sm btn-outline-warning js-admin-eval-run-button">
|
||||
<span class="js-admin-eval-button-label">Run</span>
|
||||
<span class="spinner-border spinner-border-sm ms-2 d-none js-admin-eval-button-spinner"
|
||||
role="status"
|
||||
aria-hidden="true"></span>
|
||||
</button>
|
||||
</form>
|
||||
|
||||
<a class="btn btn-sm btn-outline-info"
|
||||
href="{{ path('admin_evals_index', {type: item.type}) }}">
|
||||
Details
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
{% endfor %}
|
||||
</div>
|
||||
|
||||
<div class="row g-4 mb-4">
|
||||
<div class="col-xl-5">
|
||||
<div class="card bg-black border-secondary text-light h-100 shadow-sm">
|
||||
<div class="card-body">
|
||||
<h5 class="text-warning mb-3">
|
||||
<i class="bi bi-play-circle"></i> Eval ausführen
|
||||
</h5>
|
||||
|
||||
<form method="post"
|
||||
action="{{ path('admin_evals_run') }}"
|
||||
class="js-admin-eval-run-form"
|
||||
data-eval-type-label="Ausgewählter Eval">
|
||||
<input type="hidden" name="_token" value="{{ csrf_token('admin_eval_run') }}">
|
||||
|
||||
<div class="mb-3">
|
||||
<label class="form-label">Eval-Typ</label>
|
||||
<select name="type" class="form-select bg-dark text-light border-secondary js-admin-eval-type-select">
|
||||
{% for type, label in types %}
|
||||
<option value="{{ type }}" {% if type == selected_type %}selected{% endif %}>
|
||||
{{ label }}
|
||||
</option>
|
||||
{% endfor %}
|
||||
</select>
|
||||
<div class="form-text text-secondary">
|
||||
Ohne Case-ID wird der komplette Typ ausgeführt.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="mb-3">
|
||||
<label class="form-label">Optional: Case-ID</label>
|
||||
<input name="case_id"
|
||||
list="evalCaseIds"
|
||||
class="form-control bg-dark text-light border-secondary"
|
||||
placeholder="z. B. followup_indicator_price_001">
|
||||
<datalist id="evalCaseIds">
|
||||
{% for type, cases in cases_by_type %}
|
||||
{% for case in cases %}
|
||||
<option value="{{ case.id }}">{{ type }} - {{ case.prompt }}</option>
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
</datalist>
|
||||
</div>
|
||||
|
||||
<button type="submit" class="btn btn-outline-warning js-admin-eval-run-button">
|
||||
<span class="js-admin-eval-button-label">Eval starten</span>
|
||||
<span class="spinner-border spinner-border-sm ms-2 d-none js-admin-eval-button-spinner"
|
||||
role="status"
|
||||
aria-hidden="true"></span>
|
||||
</button>
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="col-xl-7">
|
||||
<div class="card bg-black border-secondary text-light h-100 shadow-sm">
|
||||
<div class="card-body">
|
||||
<h5 class="text-info mb-3">
|
||||
<i class="bi bi-terminal"></i> CLI-Referenz
|
||||
</h5>
|
||||
|
||||
<p class="small text-secondary mb-3">
|
||||
Die Admin-Runs schreiben typspezifische Reports nach
|
||||
<code>tests/evals/reports/<type>-last-run.json</code>
|
||||
und zusätzlich den bekannten <code>last-run.json</code>.
|
||||
</p>
|
||||
|
||||
<div class="small">
|
||||
{% for type, label in types %}
|
||||
<div class="mb-2">
|
||||
<span class="text-info">{{ label }}</span><br>
|
||||
<code>php bin/console mto:agent:eval:run {{ type }}</code>
|
||||
</div>
|
||||
{% endfor %}
|
||||
</div>
|
||||
|
||||
{% if last_report %}
|
||||
<hr class="border-secondary">
|
||||
<div class="small text-secondary">
|
||||
Letzter generischer Report:
|
||||
<span class="text-light">{{ last_report.type|default('unknown') }}</span>,
|
||||
{{ last_report.passed|default(0) }}/{{ last_report.total|default(0) }} bestanden,
|
||||
{{ last_report.generated_at|default('') }}
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="card bg-black border-secondary text-light shadow-sm">
|
||||
<div class="card-body">
|
||||
<div class="d-flex justify-content-between align-items-center flex-wrap gap-2 mb-3">
|
||||
<h5 class="text-warning mb-0">
|
||||
<i class="bi bi-list-check"></i>
|
||||
Report-Details: {{ types[selected_type]|default(selected_type) }}
|
||||
</h5>
|
||||
|
||||
<div class="btn-group btn-group-sm" role="group" aria-label="Eval report types">
|
||||
{% for type, label in types %}
|
||||
<a class="btn {{ type == selected_type ? 'btn-info' : 'btn-outline-info' }}"
|
||||
href="{{ path('admin_evals_index', {type: type}) }}">
|
||||
{{ label }}
|
||||
</a>
|
||||
{% endfor %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{% if selected_report %}
|
||||
{% set selectedFailed = selected_report.failed|default(0) %}
|
||||
<div class="row g-3 mb-3 small">
|
||||
<div class="col-md-3">
|
||||
<div class="border border-secondary rounded p-3 h-100">
|
||||
<div class="text-secondary">Total</div>
|
||||
<div class="h5 mb-0">{{ selected_report.total|default(0) }}</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="col-md-3">
|
||||
<div class="border border-secondary rounded p-3 h-100">
|
||||
<div class="text-secondary">Passed</div>
|
||||
<div class="h5 text-success mb-0">{{ selected_report.passed|default(0) }}</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="col-md-3">
|
||||
<div class="border border-secondary rounded p-3 h-100">
|
||||
<div class="text-secondary">Failed</div>
|
||||
<div class="h5 {{ selectedFailed == 0 ? 'text-success' : 'text-danger' }} mb-0">
|
||||
{{ selectedFailed }}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="col-md-3">
|
||||
<div class="border border-secondary rounded p-3 h-100">
|
||||
<div class="text-secondary">Generated</div>
|
||||
<div class="small text-light">{{ selected_report.generated_at|default('') }}</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="table-responsive">
|
||||
<table class="table table-dark table-striped table-hover align-middle mb-0">
|
||||
<thead class="table-secondary text-dark">
|
||||
<tr>
|
||||
<th>Status</th>
|
||||
<th>Case</th>
|
||||
<th>Dauer</th>
|
||||
<th>Failures / Details</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
{% for result in selected_report.results|default([]) %}
|
||||
<tr>
|
||||
<td style="width: 110px;">
|
||||
{% if result.passed|default(false) %}
|
||||
<span class="badge bg-success">PASS</span>
|
||||
{% else %}
|
||||
<span class="badge bg-danger">FAIL</span>
|
||||
{% endif %}
|
||||
</td>
|
||||
<td>
|
||||
<code>{{ result.case_id|default('') }}</code>
|
||||
<div class="small text-secondary">{{ result.type|default('') }}</div>
|
||||
</td>
|
||||
<td style="width: 120px;">
|
||||
{{ result.duration_ms|default(0) }} ms
|
||||
</td>
|
||||
<td>
|
||||
{% if result.failures|default([]) is not empty %}
|
||||
<ul class="mb-2 small text-danger">
|
||||
{% for failure in result.failures %}
|
||||
<li>{{ failure }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
{% else %}
|
||||
<div class="small text-success mb-2">Keine Fehler.</div>
|
||||
{% endif %}
|
||||
|
||||
<details>
|
||||
<summary class="small text-info" style="cursor:pointer;">
|
||||
Details anzeigen
|
||||
</summary>
|
||||
<pre class="bg-dark border border-secondary rounded p-2 mt-2 small text-light" style="white-space: pre-wrap; max-height: 260px; overflow: auto;">{{ result.details|default({})|json_encode(constant('JSON_PRETTY_PRINT')) }}</pre>
|
||||
</details>
|
||||
</td>
|
||||
</tr>
|
||||
{% else %}
|
||||
<tr>
|
||||
<td colspan="4" class="text-center text-secondary py-4">
|
||||
Dieser Report enthält keine Resultate.
|
||||
</td>
|
||||
</tr>
|
||||
{% endfor %}
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
{% else %}
|
||||
<div class="alert alert-secondary mb-0">
|
||||
Für {{ types[selected_type]|default(selected_type) }} liegt noch kein typspezifischer Admin-Report vor.
|
||||
Starte den Eval oben oder per CLI.
|
||||
</div>
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
<script>
|
||||
document.addEventListener('DOMContentLoaded', function () {
|
||||
const forms = Array.from(document.querySelectorAll('.js-admin-eval-run-form'));
|
||||
const overlay = document.getElementById('adminEvalRunOverlay');
|
||||
const overlayLabel = document.getElementById('adminEvalRunOverlayLabel');
|
||||
|
||||
function resolveEvalLabel(form) {
|
||||
const select = form.querySelector('.js-admin-eval-type-select');
|
||||
if (select && select.selectedOptions.length > 0) {
|
||||
return select.selectedOptions[0].textContent.trim();
|
||||
}
|
||||
|
||||
return (form.dataset.evalTypeLabel || 'Eval').trim();
|
||||
}
|
||||
|
||||
function setAllRunButtonsDisabled() {
|
||||
document.querySelectorAll('.js-admin-eval-run-button').forEach(function (button) {
|
||||
button.disabled = true;
|
||||
button.classList.add('disabled');
|
||||
});
|
||||
}
|
||||
|
||||
forms.forEach(function (form) {
|
||||
form.addEventListener('submit', function (event) {
|
||||
const button = event.submitter && event.submitter.classList.contains('js-admin-eval-run-button')
|
||||
? event.submitter
|
||||
: form.querySelector('.js-admin-eval-run-button');
|
||||
const label = resolveEvalLabel(form);
|
||||
|
||||
if (overlay && overlayLabel) {
|
||||
overlayLabel.textContent = label + ' läuft ...';
|
||||
overlay.classList.remove('d-none');
|
||||
}
|
||||
|
||||
if (button) {
|
||||
const buttonLabel = button.querySelector('.js-admin-eval-button-label');
|
||||
const spinner = button.querySelector('.js-admin-eval-button-spinner');
|
||||
|
||||
if (buttonLabel) {
|
||||
buttonLabel.textContent = 'Läuft ...';
|
||||
}
|
||||
|
||||
if (spinner) {
|
||||
spinner.classList.remove('d-none');
|
||||
}
|
||||
}
|
||||
|
||||
setAllRunButtonsDisabled();
|
||||
document.body.style.cursor = 'progress';
|
||||
});
|
||||
});
|
||||
});
|
||||
</script>
|
||||
|
||||
{% endblock %}
|
||||
@@ -4,9 +4,17 @@
|
||||
|
||||
{% block body %}
|
||||
|
||||
<div class="d-flex justify-content-between align-items-center mb-4">
|
||||
<div class="d-flex justify-content-between align-items-center mb-4 flex-wrap gap-2">
|
||||
<h1 class="h3 mb-0"><i class="bi bi-rocket-takeoff-fill"></i> KI Modell-Generierung</h1>
|
||||
|
||||
<div class="d-flex flex-wrap gap-2">
|
||||
{% if is_granted('ROLE_KNOWLEDGE_ADMIN') %}
|
||||
<a href="{{ path('admin_evals_index') }}"
|
||||
class="btn btn-sm btn-outline-warning">
|
||||
Eval Suite
|
||||
</a>
|
||||
{% endif %}
|
||||
|
||||
{% if is_granted('ROLE_SUPER_ADMIN') %}
|
||||
<a href="{{ path('admin_model_config_create') }}"
|
||||
class="btn btn-sm btn-outline-info">
|
||||
@@ -14,6 +22,7 @@
|
||||
</a>
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{# ========================================================= #}
|
||||
{# MODEL CONFIG DESCRIPTION #}
|
||||
|
||||
Reference in New Issue
Block a user