feat!: Finalize some of the programming_language -> language migration

docs/api-reference/core/Codebase.mdx

@@ -310,8 +310,8 @@ Fetches a codebase from GitHub and returns a Codebase instance.
     defaultValue=""
 />
 <Parameter
-    name="programming_language"
-    type={ <code className="text-sm bg-gray-100 px-2 py-0.5 rounded">ProgrammingLanguage | None</code> }
+    name="language"
+    type={ <code className="text-sm bg-gray-100 px-2 py-0.5 rounded">Literal["python", "typescript"] | ProgrammingLanguage | None</code> }
     description="The programming language of the repo. Defaults to None."
     defaultValue=""
 />

src/codegen/extensions/graph/main.py

@@ -1,7 +1,6 @@
 from codegen import Codebase
 from codegen.extensions.graph.create_graph import create_codebase_graph
 from codegen.extensions.graph.neo4j_exporter import Neo4jExporter
-from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 
 def visualize_codebase(codebase, neo4j_uri: str, username: str, password: str):
@@ -39,5 +38,5 @@ def visualize_codebase(codebase, neo4j_uri: str, username: str, password: str):
 
 if __name__ == "__main__":
     # Initialize codebase
-    codebase = Codebase("../../", programming_language=ProgrammingLanguage.PYTHON)
+    codebase = Codebase("../../", language="python")
     visualize_codebase(codebase, "bolt://localhost:7687", "neo4j", "password")

src/codegen/extensions/mcp/codebase_agent.py

@@ -11,7 +11,8 @@
 
 mcp = FastMCP(
     "codebase-agent-mcp",
-    instructions="Use this server to access any information from your codebase. This tool can provide information ranging from AST Symbol details and information from across the codebase. Use this tool for all questions, queries regarding your codebase.",
+    instructions="""Use this server to access any information from your codebase. This tool can provide information ranging from AST Symbol details and information from across the codebase.
+    Use this tool for all questions, queries regarding your codebase.""",
 )
 
 
@@ -27,7 +28,7 @@ def query_codebase(
     if not os.path.exists(codebase_dir):
         return {"error": f"Codebase directory '{codebase_dir}' does not exist. Please provide a valid directory path."}
     # Initialize codebase
-    codebase = Codebase(repo_path=codebase_dir, programming_language=codebase_language)
+    codebase = Codebase(repo_path=codebase_dir, language=codebase_language)
 
     # Create the agent
     agent = create_codebase_inspector_agent(codebase=codebase, model_name="gpt-4", verbose=True)

src/codegen/extensions/mcp/codebase_mods.py

@@ -21,7 +21,7 @@ def split_files_by_function(
 ):
     if not os.path.exists(codebase_dir):
         return {"error": f"Codebase directory '{codebase_dir}' does not exist. Please provide a valid directory path."}
-    codebase = Codebase(repo_path=codebase_dir, programming_language=codebase_language)
+    codebase = Codebase(repo_path=codebase_dir, language=codebase_language)
     new_files = {}
     file = codebase.get_file(target_file)
     # for each test_function in the file

src/codegen/extensions/mcp/codebase_tools.py

@@ -25,7 +25,7 @@ def reveal_symbol_tool(
     collect_dependencies: Annotated[Optional[bool], "includes dependencies of symbol"],
     collect_usages: Annotated[Optional[bool], "includes usages of symbol"],
 ):
-    codebase = Codebase(repo_path=codebase_dir, programming_language=codebase_language)
+    codebase = Codebase(repo_path=codebase_dir, language=codebase_language)
     result = reveal_symbol(
         codebase=codebase,
         symbol_name=symbol_name,
@@ -45,7 +45,7 @@ def search_codebase_tool(
     codebase_language: Annotated[ProgrammingLanguage, "The language the codebase is written in"],
     use_regex: Annotated[bool, "use regex for the search query"],
 ):
-    codebase = Codebase(repo_path=codebase_dir, programming_language=codebase_language)
+    codebase = Codebase(repo_path=codebase_dir, language=codebase_language)
     result = search(codebase, query, target_directories, use_regex=use_regex)
     return json.dumps(result, indent=2)
 

src/codegen/sdk/core/codebase.py

@@ -141,7 +141,7 @@
         self,
         repo_path: str,
         *,
-        language: Literal["python", "typescript"] | None = None,
+        language: Literal["python", "typescript"] | ProgrammingLanguage | None = None,
         projects: None = None,
         config: CodebaseConfig = DefaultConfig,
         io: IO | None = None,
@@ -180,13 +180,13 @@
             main_project = ProjectConfig.from_path(repo_path, programming_language=ProgrammingLanguage(language.upper()) if language else None)
             projects = [main_project]
         else:
             main_project = projects[0]
 
         # Initialize codebase
         self._op = main_project.repo_operator
         self.viz = VisualizationManager(op=self._op)
         self.repo_path = Path(self._op.repo_path)
         self.ctx = CodebaseContext(projects, config=config, io=io, progress=progress)
         self.console = Console(record=True, soft_wrap=True)
 
     @noapidoc
@@ -202,7 +202,7 @@
         yield "nodes", len(self.ctx.nodes)
         yield "edges", len(self.ctx.edges)
 
     __rich_repr__.angular = ANGULAR_STYLE
 
     @property
     @deprecated("Please do not use the local repo operator directly")
@@ -244,8 +244,8 @@
 
     @noapidoc
     def _symbols(self, symbol_type: SymbolType | None = None) -> list[TSymbol | TClass | TFunction | TGlobalVar]:
         matches: list[Symbol] = self.ctx.get_nodes(NodeType.SYMBOL)
         return [x for x in matches if x.is_top_level and (symbol_type is None or x.symbol_type == symbol_type)]
 
     # =====[ Node Types ]=====
     @overload
@@ -254,7 +254,7 @@
     def files(self, *, extensions: Literal["*"]) -> list[File]: ...
     @overload
     def files(self, *, extensions: None = ...) -> list[TSourceFile]: ...
     @proxy_property
     def files(self, *, extensions: list[str] | Literal["*"] | None = None) -> list[TSourceFile] | list[File]:
         """A list property that returns all files in the codebase.
 
@@ -284,15 +284,15 @@
         return sort_editables(files, alphabetical=True, dedupe=False)
 
     @cached_property
     def codeowners(self) -> list["CodeOwner[TSourceFile]"]:
         """List all CodeOnwers in the codebase.
 
         Returns:
             list[CodeOwners]: A list of CodeOwners objects in the codebase.
         """
         if self.G.codeowners_parser is None:
             return []
         return CodeOwner.from_parser(self.G.codeowners_parser, lambda *args, **kwargs: self.files(*args, **kwargs))
 
     @property
     def directories(self) -> list[TDirectory]:
@@ -304,7 +304,7 @@
         Returns:
             list[TDirectory]: A list of Directory objects in the codebase.
         """
         return list(self.ctx.directories.values())
 
     @property
     def imports(self) -> list[TImport]:
@@ -1251,7 +1251,7 @@
             tmp_dir (Optional[str]): The directory to clone the repo into. Defaults to /tmp/codegen
             commit (Optional[str]): The specific commit hash to clone. Defaults to HEAD
             shallow (bool): Whether to do a shallow clone. Defaults to True
-            language (Literal["python", "typescript"] | None): The programming language of the repo. Defaults to None.
+            language (Literal["python", "typescript"] | ProgrammingLanguage | None): The programming language of the repo. Defaults to None.
             config (CodebaseConfig): Configuration for the codebase. Defaults to DefaultConfig.
 
         Returns:

src/codegen/sdk/system-prompt.txt

@@ -1350,7 +1350,6 @@ Construct a Codebase by passing in a path to a local `git` repository or any sub
 
 ```python
 from codegen import Codebase
-from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 # Parse from a git repository root
 codebase = Codebase("path/to/repository")
@@ -1362,12 +1361,12 @@ codebase = Codebase("path/to/repository/src/subfolder")
 codebase = Codebase("./")
 
 # Specify programming language (instead of inferring from file extensions)
-codebase = Codebase("./", programming_language=ProgrammingLanguage.TYPESCRIPT)
+codebase = Codebase("./", language="typescript")
 ```
 
 <Note>
   By default, Codegen will automatically infer the programming language of the codebase and
-  parse all files in the codebase. You can override this by passing the `programming_language` parameter
+  parse all files in the codebase. You can override this by passing the `language` parameter
   with a value from the `ProgrammingLanguage` enum.
 </Note>
 
@@ -1383,7 +1382,6 @@ To fetch and parse a repository directly from GitHub, use the `from_repo` functi
 
 ```python
 import codegen
-from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 # Fetch and parse a repository (defaults to /tmp/codegen/{repo_name})
 codebase = codegen.from_repo('fastapi/fastapi')
@@ -1394,7 +1392,7 @@ codebase = codegen.from_repo(
     tmp_dir='/custom/temp/dir',  # Optional: custom temp directory
     commit='786a8ada7ed0c7f9d8b04d49f24596865e4b7901',  # Optional: specific commit
     shallow=False,  # Optional: full clone instead of shallow
-    programming_language=ProgrammingLanguage.PYTHON  # Optional: override language detection
+    language="python"  # Optional: override language detection
 )
 ```
 
@@ -1446,7 +1444,6 @@ from codegen import Codebase
 from codegen.git.repo_operator.local_repo_operator import LocalRepoOperator
 from codegen.git.schemas.repo_config import BaseRepoConfig
 from codegen.sdk.codebase.config import ProjectConfig
-from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 codebase = Codebase(
     projects = [
@@ -1456,7 +1453,7 @@ codebase = Codebase(
                 repo_config=BaseRepoConfig(),
                 bot_commit=True
             ),
-            programming_language=ProgrammingLanguage.TYPESCRIPT,
+            language="typescript",
             base_path="src/codegen/sdk/typescript",
             subdirectories=["src/codegen/sdk/typescript"]
         )
@@ -6606,14 +6603,13 @@ First, we initialize the codebase and create a vector index for semantic search:
 ```python
 from codegen import Codebase
 from codegen.extensions import VectorIndex
-from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 def initialize_codebase():
     """Initialize and index the codebase."""
     # Initialize codebase with smart caching
     codebase = Codebase.from_repo(
         "codegen-sh/codegen-sdk",
-        programming_language=ProgrammingLanguage.PYTHON,
+        language="python",
         tmp_dir="/root"
     )
 
@@ -6795,6 +6791,7 @@ While this example demonstrates a simple RAG-based bot, you can extend it to bui
   </Card>
 </CardGroup>
 
+
 ---
 title: "Mining Training Data for LLMs"
 sidebarTitle: "Mining Data"
@@ -10651,7 +10648,7 @@ from codegen.extensions.tools.semantic_search import semantic_search
 
 @mcp.tool('codebase_semantic_search', "search codebase with the provided query")
 def search(query: Annotated[str, "search query to run against codebase"]):
-  codebase = Codebase("provide location to codebase", programming_language="provide codebase Language")
+  codebase = Codebase("provide location to codebase", language="provide codebase Language")
   # use the semantic search tool from codegen.extensions.tools OR write your own
   results = semantic_search(codebase=codebase, query=query)
   return results
@@ -10672,6 +10669,7 @@ If you'd like to integrate this into an IDE checkout out this [setup guide](/int
 And that's a wrap, chime in at our [community
   Slack](https://community.codegen.com) if you have questions or ideas for additional MCP tools/capabilities
 
+
 ---
 title: "Neo4j Graph"
 sidebarTitle: "Neo4j Graph"