merge: integrate remote speech capabilities into feature/N7Web

src/cognitive_agent/server.py

@@ -13,28 +13,28 @@ import socket
 import threading
 import time
 from copy import deepcopy
-from http.cookies import CookieError, SimpleCookie
 from http import HTTPStatus
+from http.cookies import CookieError, SimpleCookie
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from urllib.parse import ParseResult, parse_qs, quote, unquote, urlparse
 
 from cognitive_agent.config_loader import load_local_env
 
-
 REPOSITORY_ROOT = Path(__file__).resolve().parents[2]
 # Repository-local launch configuration is deliberate and must not be shadowed
 # by stale variables inherited from an IDE or an earlier model experiment.
 load_local_env(REPOSITORY_ROOT / ".env", override=True)
 load_local_env(REPOSITORY_ROOT / ".env.auth", override=True)
 
-from cognitive_agent.auth import AuthConfig, AuthRuntime, verify_password  # noqa: E402
-from cognitive_agent.application.seat_service import SeatDemoService  # noqa: E402
-from cognitive_agent.application.gesture_bridge import GestureCapabilityBridge  # noqa: E402
 from cognitive_agent.application.calibration.service import (  # noqa: E402
     ApiError as CalibrationApiError,
+)
+from cognitive_agent.application.calibration.service import (
     CalibrationService,
 )
+from cognitive_agent.application.gesture_bridge import GestureCapabilityBridge  # noqa: E402
+from cognitive_agent.application.seat_service import SeatDemoService  # noqa: E402
 from cognitive_agent.application.self_extension import (  # noqa: E402
     ExtensionIntegrationError,
     GatewayError,
@@ -44,17 +44,21 @@ from cognitive_agent.application.self_extension import (  # noqa: E402
     resolve_active_peripheral_command,
 )
 from cognitive_agent.application.self_repair import SelfRepairService  # noqa: E402
+from cognitive_agent.auth import AuthConfig, AuthRuntime, verify_password  # noqa: E402
+from cognitive_agent.infrastructure.can.access import (  # noqa: E402
+    HardwareAccessRequiredError,
+)
 from cognitive_agent.infrastructure.can.hardware import (  # noqa: E402
     HardwareBusyError,
     HardwareSafetyError,
 )
 from cognitive_agent.infrastructure.can.gateway import CanGatewayError  # noqa: E402
-from cognitive_agent.infrastructure.can.access import (  # noqa: E402
-    HardwareAccessRequiredError,
-)
 from cognitive_agent.infrastructure.llm.openai_responses import OpenAIIntentError  # noqa: E402
 from cognitive_agent.infrastructure.nfc import NfcReaderService  # noqa: E402
-
+from cognitive_agent.infrastructure.speech import (  # noqa: E402
+    SpeechRecognitionError,
+    SpeechTranscriber,
+)
 
 STATIC_ROOT = REPOSITORY_ROOT / "apps" / "web-console"
 mimetypes.add_type("application/manifest+json", ".webmanifest")
@@ -179,6 +183,7 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
         repository_root=REPOSITORY_ROOT,
     )
     repair = SelfRepairService()
+    speech = SpeechTranscriber(REPOSITORY_ROOT)
     auth = AuthRuntime(AuthConfig.from_env())
     vehicle_display_sync = VehicleDisplaySync()
     server_version = "CognitiveAgentCabinDemo/2.0"
@@ -374,6 +379,9 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
                 return
             self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
             return
+        if path == "/api/speech/status":
+            self._json(self.speech.status())
+            return
         if path.startswith("/api/requests/"):
             self._serve_request(path.removeprefix("/api/requests/"))
             return
@@ -389,6 +397,9 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
             return
         if not self._authorize(path):
             return
+        if path == "/api/speech/transcribe":
+            self._handle_speech_transcription()
+            return
         if path in {
             "/api/hardware/access/request",
             "/api/hardware/access/release",
@@ -518,6 +529,32 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
                     payload.get("control_transport", "wired_can")
                 ),
             }
+            speech_utterance_id = str(
+                payload.get("speech_utterance_id", "")
+            ).strip()
+            if speech_utterance_id:
+                if path != "/api/requests":
+                    raise ValueError(
+                        "speech semantic execution is only accepted by /api/requests"
+                    )
+                speech_understanding = self.speech.cached_result(
+                    speech_utterance_id
+                )
+                if str(speech_understanding.get("clean_text", "")).strip() != utterance:
+                    raise SpeechRecognitionError(
+                        "speech_text_changed",
+                        "语音文本已被修改，请确认修改后的内容再执行。",
+                        status=409,
+                    )
+                if speech_understanding.get("execution_eligible") is not True:
+                    raise SpeechRecognitionError(
+                        "speech_not_executable",
+                        "语音意图尚未通过能力或参数校验，已拒绝执行。",
+                        status=422,
+                    )
+                provider = "local"
+                common_arguments["provider"] = provider
+                common_arguments["_speech_understanding"] = speech_understanding
             if (
                 path != "/api/can/commands"
                 and "application/x-ndjson" in self.headers.get("Accept", "")
@@ -646,6 +683,12 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
                 {"error": "extension_request_ambiguous", "message": str(exc)},
                 HTTPStatus.UNPROCESSABLE_ENTITY,
             )
+        except SpeechRecognitionError as exc:
+            fail_display_sync(exc.code, exc)
+            self._json(
+                {"error": exc.code, "message": str(exc)},
+                HTTPStatus(exc.status),
+            )
         except (ValueError, json.JSONDecodeError) as exc:
             fail_display_sync("invalid_request", exc)
             self._json(
@@ -2135,6 +2178,41 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
             raise ValueError("request body must be a JSON object")
         return payload
 
+    def _handle_speech_transcription(self) -> None:
+        content_type = self.headers.get("Content-Type", "").split(";", 1)[0].strip().lower()
+        if content_type not in {"audio/wav", "audio/wave", "audio/x-wav"}:
+            self._json(
+                {
+                    "error": "unsupported_media_type",
+                    "message": "语音听写接口仅接受 16 位 PCM WAV 音频。",
+                },
+                HTTPStatus.UNSUPPORTED_MEDIA_TYPE,
+            )
+            return
+        try:
+            content_length = int(self.headers.get("Content-Length", "0"))
+            if content_length <= 0 or content_length > 2 * 1024 * 1024:
+                raise SpeechRecognitionError(
+                    "invalid_audio_size",
+                    "录音数据为空或超过大小限制。",
+                    status=413,
+                )
+            result = self.speech.transcribe_wav(
+                self.rfile.read(content_length),
+                utterance_id=self.headers.get("X-Speech-Utterance-Id"),
+            )
+            self._json(result)
+        except SpeechRecognitionError as exc:
+            self._json(
+                {"error": exc.code, "message": str(exc)},
+                HTTPStatus(exc.status),
+            )
+        except (TypeError, ValueError):
+            self._json(
+                {"error": "invalid_audio", "message": "录音请求格式无效。"},
+                HTTPStatus.BAD_REQUEST,
+            )
+
     def _authorize(self, path: str) -> bool:
         if not self.auth.config.enabled or path in PUBLIC_AUTH_PATHS:
             return True
@@ -2407,7 +2485,7 @@ class SeatDemoHandler(BaseHTTPRequestHandler):
         self.send_header("Referrer-Policy", "no-referrer")
         self.send_header(
             "Permissions-Policy",
-            "camera=(self), microphone=(), geolocation=(), payment=(), usb=()",
+            "camera=(self), microphone=(self), geolocation=(), payment=(), usb=()",
         )
         self.send_header(
             "Content-Security-Policy",