feat(tools-pve/asr-pipeline): multi-backend ASR web app with LiteLLM routing

servers/tools-pve/asr-pipeline/asrservice/db.py

@@ -1,14 +1,15 @@
 from __future__ import annotations
 
-import json
 import sqlite3
 import time
 from typing import Any
 
-from .config import DB, ensure_dirs
+from .config import DB, DEFAULT_PROVIDER, ensure_dirs
 
-STATUSES = {"uploading", "queued", "transcribing", "refining", "review",
-            "publishing", "complete", "failed"}
+STATUSES = {
+    "uploading", "queued", "transcribing", "refining", "review",
+    "publishing", "complete", "failed",
+}
 
 
 def connect() -> sqlite3.Connection:
@@ -26,6 +27,8 @@ def connect() -> sqlite3.Connection:
         draft TEXT NOT NULL DEFAULT '', result TEXT NOT NULL DEFAULT '',
         source TEXT NOT NULL DEFAULT 'web', sha256 TEXT NOT NULL DEFAULT '',
         attempts INTEGER NOT NULL DEFAULT 0, error_code TEXT NOT NULL DEFAULT '',
+        asr_provider TEXT NOT NULL DEFAULT 'qwen3cam',
+        asr_model TEXT NOT NULL DEFAULT '',
         created_at REAL NOT NULL, updated_at REAL NOT NULL
       );
       CREATE TABLE IF NOT EXISTS job_event(
@@ -37,9 +40,14 @@ def connect() -> sqlite3.Connection:
     """)
     cols = {r[1] for r in con.execute("PRAGMA table_info(intake_job)")}
     additions = {
-        "draft": "TEXT NOT NULL DEFAULT ''", "result": "TEXT NOT NULL DEFAULT ''",
-        "source": "TEXT NOT NULL DEFAULT 'web'", "sha256": "TEXT NOT NULL DEFAULT ''",
-        "attempts": "INTEGER NOT NULL DEFAULT 0", "error_code": "TEXT NOT NULL DEFAULT ''",
+        "draft": "TEXT NOT NULL DEFAULT ''",
+        "result": "TEXT NOT NULL DEFAULT ''",
+        "source": "TEXT NOT NULL DEFAULT 'web'",
+        "sha256": "TEXT NOT NULL DEFAULT ''",
+        "attempts": "INTEGER NOT NULL DEFAULT 0",
+        "error_code": "TEXT NOT NULL DEFAULT ''",
+        "asr_provider": f"TEXT NOT NULL DEFAULT '{DEFAULT_PROVIDER}'",
+        "asr_model": "TEXT NOT NULL DEFAULT ''",
     }
     for name, ddl in additions.items():
         if name not in cols:
@@ -48,23 +56,40 @@ def connect() -> sqlite3.Connection:
     return con
 
 
-def create_job(job_id: str, original_name: str, stored_name: str, *, title: str = "",
-               context: str = "", size: int = 0, source: str = "web") -> dict[str, Any]:
+def create_job(
+    job_id: str,
+    original_name: str,
+    stored_name: str,
+    *,
+    title: str = "",
+    context: str = "",
+    size: int = 0,
+    source: str = "web",
+    asr_provider: str = "",
+    asr_model: str = "",
+) -> dict[str, Any]:
     now = time.time()
+    prov = (asr_provider or DEFAULT_PROVIDER or "qwen3cam").strip().lower()
     with connect() as con:
-        con.execute("INSERT INTO intake_job(id,original_name,stored_name,title,context,size,"
-                    "status,source,created_at,updated_at) VALUES(?,?,?,?,?,?,?,?,?,?)",
-                    (job_id, original_name, stored_name, title, context, size,
-                     "queued", source, now, now))
-        con.execute("INSERT INTO job_event(job_id,status,detail,created_at) VALUES(?,?,?,?)",
-                    (job_id, "queued", "录音已进入队列", now))
+        con.execute(
+            "INSERT INTO intake_job(id,original_name,stored_name,title,context,size,"
+            "status,source,asr_provider,asr_model,created_at,updated_at) "
+            "VALUES(?,?,?,?,?,?,?,?,?,?,?,?)",
+            (job_id, original_name, stored_name, title, context, size,
+             "queued", source, prov, asr_model, now, now))
+        con.execute(
+            "INSERT INTO job_event(job_id,status,detail,created_at) VALUES(?,?,?,?)",
+            (job_id, "queued", f"录音已进入队列 (ASR: {prov})", now))
     return get_job(job_id) or {}
 
 
 def update_job(job_id: str, status: str, detail: str = "", **fields: Any) -> bool:
     if status not in STATUSES:
         raise ValueError(f"invalid status: {status}")
-    allowed = {"transcript", "draft", "result", "sha256", "attempts", "error_code"}
+    allowed = {
+        "transcript", "draft", "result", "sha256", "attempts",
+        "error_code", "asr_provider", "asr_model",
+    }
     changes = {k: v for k, v in fields.items() if k in allowed and v is not None}
     sets = ["status=?", "updated_at=?", "detail=?"]
     values: list[Any] = [status, time.time(), detail[:1000]]
@@ -75,8 +100,9 @@ def update_job(job_id: str, status: str, detail: str = "", **fields: Any) -> boo
     with connect() as con:
         cur = con.execute(f"UPDATE intake_job SET {','.join(sets)} WHERE id=?", values)
         if cur.rowcount:
-            con.execute("INSERT INTO job_event(job_id,status,detail,created_at) VALUES(?,?,?,?)",
-                        (job_id, status, detail[:1000], time.time()))
+            con.execute(
+                "INSERT INTO job_event(job_id,status,detail,created_at) VALUES(?,?,?,?)",
+                (job_id, status, detail[:1000], time.time()))
     return bool(cur.rowcount)
 
 
@@ -88,8 +114,9 @@ def get_job(job_id: str) -> dict[str, Any] | None:
 
 def find_by_stored(stored_name: str) -> dict[str, Any] | None:
     with connect() as con:
-        row = con.execute("SELECT * FROM intake_job WHERE stored_name=? ORDER BY created_at DESC LIMIT 1",
-                          (stored_name,)).fetchone()
+        row = con.execute(
+            "SELECT * FROM intake_job WHERE stored_name=? ORDER BY created_at DESC LIMIT 1",
+            (stored_name,)).fetchone()
         return dict(row) if row else None