Add bounded GPU-priority automatic model testing and profile export

server.py

@@ -16,6 +16,7 @@ from docker_support import DockerSupport
 from inference import LlamaWorker,Scheduler
 from endpoint import Endpoint
 from chat_test import ChatTests
+from auto_test import AutoTests
 from urllib.parse import urlsplit, parse_qs
 from network.client import NetworkClient
 from network.config import parse_config, ConfigError
@@ -90,6 +91,7 @@ class Server(ThreadingHTTPServer):
             try:self.endpoint.start()
             except ValueError as exc:self.endpoint.error=str(exc)
         self.chat_tests=ChatTests(self.profiles,self.worker,self.scheduler)
+        self.auto_tests=AutoTests(self.catalog.root.parent/'auto-tests.json',self.profiles,self.worker,self.scheduler)
         self.sessions = {}
         self.login_attempts = []
         self.auth_lock = threading.Lock()
@@ -241,7 +243,7 @@ class Handler(BaseHTTPRequestHandler):
             return self.respond({'error':'Anmeldung erforderlich.'},401)
         if not self.authenticated() and self.path == '/':
             return self.respond((ROOT/'login.html').read_bytes(), mime='text/html; charset=utf-8')
-        routes = {'/chat-test-ui.js':('chat-test-ui.js','text/javascript'),'/endpoint-ui.js':('endpoint-ui.js','text/javascript'),'/docker-ui.js': ('docker-ui.js','text/javascript'), '/': ('index.html', 'text/html; charset=utf-8'), '/app.js': ('app.js', 'text/javascript'), '/style.css': ('style.css', 'text/css'), '/network-ui.js': ('network-ui.js', 'text/javascript'), '/access-ui.js': ('access-ui.js', 'text/javascript'), '/studio.js': ('studio.js', 'text/javascript'), '/catalog-ui.js': ('catalog-ui.js','text/javascript'), '/runtime-ui.js': ('runtime-ui.js','text/javascript'), '/profiles-ui.js': ('profiles-ui.js','text/javascript'), '/image-test-ui.js': ('image-test-ui.js','text/javascript')}
+        routes = {'/auto-test-ui.js':('auto-test-ui.js','text/javascript'),'/chat-test-ui.js':('chat-test-ui.js','text/javascript'),'/endpoint-ui.js':('endpoint-ui.js','text/javascript'),'/docker-ui.js': ('docker-ui.js','text/javascript'), '/': ('index.html', 'text/html; charset=utf-8'), '/app.js': ('app.js', 'text/javascript'), '/style.css': ('style.css', 'text/css'), '/network-ui.js': ('network-ui.js', 'text/javascript'), '/access-ui.js': ('access-ui.js', 'text/javascript'), '/studio.js': ('studio.js', 'text/javascript'), '/catalog-ui.js': ('catalog-ui.js','text/javascript'), '/runtime-ui.js': ('runtime-ui.js','text/javascript'), '/profiles-ui.js': ('profiles-ui.js','text/javascript'), '/image-test-ui.js': ('image-test-ui.js','text/javascript')}
         if self.path in routes:
             name, mime = routes[self.path]
             return self.respond((ROOT/name).read_bytes(), mime=mime)
@@ -249,6 +251,7 @@ class Handler(BaseHTTPRequestHandler):
             endpoint=self.server.endpoint.status()
             public_endpoint={key:endpoint[key] for key in ('state','port','counts','active_requests')}
             return self.respond(dict(name='Athena Deck', version='0.7.0', state='ready', uptime_seconds=round(time.time()-self.server.started), mode='isolated', location=os.environ.get('DECK_LOCATION', 'Athena · Debian-Server'), endpoint=public_endpoint))
+        if self.path == '/api/v1/auto-tests':return self.respond(self.server.auto_tests.status())
         if self.path == '/api/v1/chat-tests':return self.respond(self.server.chat_tests.status())
         if self.path == '/api/v1/endpoint':return self.respond(self.server.endpoint.status())
         if self.path == '/api/v1/docker':return self.respond(self.server.docker.status())
@@ -337,6 +340,14 @@ class Handler(BaseHTTPRequestHandler):
                 raise ValueError('Ungültige Laufzeitaktion.')
             except ValueError as exc:return self.respond({'error':str(exc)},400)
             except (OSError, subprocess.SubprocessError):return self.respond({'error':'Laufzeitaktion fehlgeschlagen; Speicher und Werkzeuge prüfen.'},503)
+        if self.path in ('/api/v1/auto-tests/start','/api/v1/auto-tests/cancel','/api/v1/auto-tests/save'):
+            try:
+                data=self.read_json()
+                if self.path.endswith('/start'):return self.respond(self.server.auto_tests.start(data))
+                if self.path.endswith('/save'):return self.respond(self.server.auto_tests.save(data))
+                if data:raise ValueError('Keine Parameter erwartet.')
+                return self.respond(self.server.auto_tests.stop())
+            except ValueError as exc:return self.respond({'error':str(exc)},400)
         if self.path in ('/api/v1/chat-tests/start','/api/v1/chat-tests/cancel','/api/v1/chat-tests/unload'):
             try:
                 data=self.read_json()
@@ -433,6 +444,7 @@ def main():
     try:
         server.serve_forever()
     finally:
+        server.auto_tests.stop()
         server.chat_tests.stop()
         server.endpoint.close()
         server.image_runtime.stop()