fix: sync upstream

Author: fighting-u

.claude/settings.local.json

@@ -0,0 +1,14 @@
+{
+  "permissions": {
+    "allow": [
+      "WebFetch(domain:docs.opengauss.org)",
+      "WebSearch",
+      "Bash(ls /d/projects/others/DocsGPT/application/vectorstore/*.py)",
+      "Bash(xargs basename:*)",
+      "Bash(netstat -ano)",
+      "Bash(findstr \":5173\")",
+      "Bash(netsh interface:*)",
+      "Bash(findstr \"5173\")"
+    ]
+  }
+}

application/agents/research_agent.py

@@ -38,7 +38,7 @@
 
 
 def _load_prompt(name: str) -> str:
-    with open(os.path.join(_PROMPTS_DIR, name), "r") as f:
+    with open(os.path.join(_PROMPTS_DIR, name), "r", encoding="utf-8") as f:
         return f.read()
 
 

application/alembic.ini

@@ -1,6 +1,6 @@
 # Alembic configuration for the DocsGPT user-data Postgres database.
 #
-# The SQLAlchemy URL is deliberately NOT set here — env.py reads it from
+# The SQLAlchemy URL is deliberately NOT set here - env.py reads it from
 # ``application.core.settings.settings.POSTGRES_URI`` so the same config
 # source serves the running app and migrations. To run from the project
 # root::
@@ -12,7 +12,7 @@ script_location = %(here)s/alembic
 prepend_sys_path = ..
 version_path_separator = os
 
-# sqlalchemy.url is intentionally left blank — env.py supplies it.
+# sqlalchemy.url is intentionally left blank - env.py supplies it.
 sqlalchemy.url =
 
 [post_write_hooks]

application/api/answer/services/compression/prompt_builder.py

@@ -37,7 +37,7 @@ def _load_prompt(self, version: str) -> str:
         prompt_path = current_dir / "prompts" / "compression" / f"{version}.txt"
 
         try:
-            with open(prompt_path, "r") as f:
+            with open(prompt_path, "r", encoding="utf-8") as f:
                 return f.read()
         except FileNotFoundError:
             logger.error(f"Compression prompt template not found: {prompt_path}")

application/api/answer/services/stream_processor.py

@@ -83,7 +83,7 @@ def get_prompt(prompt_id: str, prompts_collection=None) -> str:
     if prompt_id in preset_mapping:
         file_path = os.path.join(prompts_dir, preset_mapping[prompt_id])
         try:
-            with open(file_path, "r") as f:
+            with open(file_path, "r", encoding="utf-8") as f:
                 return f.read()
         except FileNotFoundError:
             raise FileNotFoundError(f"Prompt file not found: {file_path}")

application/api/user/prompts/routes.py

@@ -113,19 +113,23 @@ def get(self):
                 with open(
                     os.path.join(current_dir, "prompts", "chat_combine_default.txt"),
                     "r",
+                    encoding="utf-8",
                 ) as f:
                     chat_combine_template = f.read()
                 return make_response(jsonify({"content": chat_combine_template}), 200)
             elif prompt_id == "creative":
                 with open(
                     os.path.join(current_dir, "prompts", "chat_combine_creative.txt"),
                     "r",
+                    encoding="utf-8",
                 ) as f:
                     chat_reduce_creative = f.read()
                 return make_response(jsonify({"content": chat_reduce_creative}), 200)
             elif prompt_id == "strict":
                 with open(
-                    os.path.join(current_dir, "prompts", "chat_combine_strict.txt"), "r"
+                    os.path.join(current_dir, "prompts", "chat_combine_strict.txt"),
+                    "r",
+                    encoding="utf-8",
                 ) as f:
                     chat_reduce_strict = f.read()
                 return make_response(jsonify({"content": chat_reduce_strict}), 200)

application/app.py

@@ -87,11 +87,11 @@
 if settings.AUTH_TYPE in ("simple_jwt", "session_jwt", "oidc") and not settings.JWT_SECRET_KEY:
     key_file = ".jwt_secret_key"
     try:
-        with open(key_file, "r") as f:
+        with open(key_file, "r", encoding="utf-8") as f:
             settings.JWT_SECRET_KEY = f.read().strip()
     except FileNotFoundError:
         new_key = os.urandom(32).hex()
-        with open(key_file, "w") as f:
+        with open(key_file, "w", encoding="utf-8") as f:
             f.write(new_key)
         settings.JWT_SECRET_KEY = new_key
     except Exception as e:

application/parser/file/bulk.py

@@ -248,7 +248,7 @@ def load_data(
                 parser_metadata = parser.get_file_metadata(input_file)
             else:
                 # do standard read
-                with open(input_file, "r", errors=self.errors) as f:
+                with open(input_file, "r", encoding="utf-8", errors=self.errors) as f:
                     data = f.read()
 
             # Calculate token count for this file

application/parser/file/markdown_parser.py

@@ -119,7 +119,7 @@ def parse_tups(
             self, filepath: Path, errors: str = "ignore"
     ) -> List[Tuple[Optional[str], str]]:
         """Parse file into tuples."""
-        with open(filepath, "r") as f:
+        with open(filepath, "r", encoding="utf-8", errors=errors) as f:
             content = f.read()
         if self._remove_hyperlinks:
             content = self.remove_hyperlinks(content)

application/parser/file/openapi3_parser.py

@@ -46,6 +46,6 @@ def parse_file(self, file_path):
                 f"parameters: {path.parameters}\nmethods: {info}\n"
             )
             i += 1
-        with open("results.txt", "w") as f:
+        with open("results.txt", "w", encoding="utf-8") as f:
             f.write(results)
         return results