From fd7ccb53fcdc90d71b33cbff6293298b2c2326aa Mon Sep 17 00:00:00 2001
From: Research Assistant <research@example.com>
Date: Thu, 23 Apr 2026 00:57:48 +0800
Subject: [PATCH] fix: unify PaddleOCR env var names to match pipeline
 expectations (API_TOKEN/JOB_URL)

---
 docs/INSTALLATION.md      |  4 ++--
 scripts/setup.py          |  4 ++--
 scripts/validate_setup.py | 10 +++++-----
 setup_wizard.py           |  9 ++++++---
 4 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/docs/INSTALLATION.md b/docs/INSTALLATION.md
index 31e905cd..648cad8a 100644
--- a/docs/INSTALLATION.md
+++ b/docs/INSTALLATION.md
@@ -72,8 +72,8 @@ ln -s "~/Zotero" "{vault_path}/99_System/Zotero"
 
 创建 `{vault_path}/.env`:
 ```
-PADDLEOCR_API_KEY=your_api_key_here
-PADDLEOCR_API_URL=https://api.paddleocr.baidu.com/api/v1/ocr
+PADDLEOCR_API_TOKEN=your_api_token_here
+PADDLEOCR_JOB_URL=https://paddleocr.aistudio-app.com/api/v2/ocr/jobs
 ```
 
 ### Step 5: 部署脚本
diff --git a/scripts/setup.py b/scripts/setup.py
index 52b5004f..f6e42539 100644
--- a/scripts/setup.py
+++ b/scripts/setup.py
@@ -278,8 +278,8 @@ def create_env_file(vault_path: Path, config: dict, paths: dict) -> None:
         "# PaperForge Configuration",
         f"ZOTERO_DATA_DIR={config['zotero_path']}",
         f"ZOTERO_STORAGE_DIR={config.get('storage_path', config['zotero_path'])}",
-        f"PADDLEOCR_API_KEY={config['ocr_api_key']}",
-        "PADDLEOCR_API_URL=https://paddleocr.baidu.com/api/v1/ocr",
+        f"PADDLEOCR_API_TOKEN={config['ocr_api_key']}",
+        "PADDLEOCR_JOB_URL=https://paddleocr.aistudio-app.com/api/v2/ocr/jobs",
         "",
         "# Agent Configuration",
         f"PAPERFORGE_AGENT={config['agent']}",
diff --git a/scripts/validate_setup.py b/scripts/validate_setup.py
index 77aecfb9..f8a9d672 100644
--- a/scripts/validate_setup.py
+++ b/scripts/validate_setup.py
@@ -89,12 +89,12 @@ def validate_ocr_pipeline(vault_path: str) -> list[tuple[bool, str]]:
     results.append((ok, msg))
     
     if ok:
-        # Check if PADDLEOCR_API_KEY is set
-        env_content = env_path.read_text(encoding="utf-8")
-        if "PADDLEOCR_API_KEY" in env_content:
-            results.append((True, "[OK] PADDLEOCR_API_KEY configured in .env"))
+        # Check if PADDLEOCR_API_TOKEN is set
+        env_content = env_path.read_text(encoding='utf-8')
+        if "PADDLEOCR_API_TOKEN" in env_content:
+            results.append((True, "[OK] PADDLEOCR_API_TOKEN configured in .env"))
         else:
-            results.append((False, "[FAIL] PADDLEOCR_API_KEY not found in .env"))
+            results.append((False, "[FAIL] PADDLEOCR_API_TOKEN not found in .env"))
     
     # Check OCR pipeline directory
     ocr_dir = vault_dir / "99_System" / "LiteraturePipeline" / "worker"
diff --git a/setup_wizard.py b/setup_wizard.py
index 0ef23137..9bd163a2 100644
--- a/setup_wizard.py
+++ b/setup_wizard.py
@@ -922,11 +922,14 @@ class DeployStep(StepScreen):
         
         env_path = vault / ".env"
         env_content = f"""# PaperForge 配置文件
-# PaddleOCR API Key（从 https://paddleocr.baidu.com 获取）
-PADDLEOCR_API_KEY={api_key}
+# PaddleOCR API Token（从 https://paddleocr.baidu.com 获取）
+PADDLEOCR_API_TOKEN={api_key}
 
 # PaddleOCR API 地址
-PADDLEOCR_API_URL={api_url}
+PADDLEOCR_JOB_URL={api_url}
+
+# PaddleOCR 模型（通常不需要修改）
+PADDLEOCR_MODEL=PaddleOCR-VL-1.5
 """
         env_path.write_text(env_content, encoding="utf-8")