feat: CG-10753: read repo config from local git instance (#424)

# Motivation

<!-- Why is this change necessary? -->

# Content

<!-- Please include a summary of the change -->

# Testing

<!-- How was the change tested? -->

# Please check the following before marking your PR as ready for review

- [x] I have added tests for my changes
- [x] I have updated the documentation or added new documentation as
needed

Author: caroljung-cg

codegen-examples/examples/dict_to_schema/run.py

@@ -1,5 +1,5 @@
 import codegen
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from codegen import Codebase
 
 

codegen-examples/examples/fragment_to_shorthand/run.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 
 @codegen.function("fragment_to_shorthand")

codegen-examples/examples/freezegun_to_timemachine_migration/run.py

@@ -1,5 +1,5 @@
 import codegen
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from codegen import Codebase
 
 

codegen-examples/examples/generate_training_data/run.py

@@ -2,7 +2,7 @@
 
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from codegen.sdk.core.external_module import ExternalModule
 from codegen.sdk.core.import_resolution import Import
 from codegen.sdk.core.symbol import Symbol

codegen-examples/examples/langchain_agent/run.py

@@ -14,7 +14,7 @@
     SemanticEditTool,
     ViewFileTool,
 )
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from langchain import hub
 from langchain.agents import AgentExecutor
 from langchain.agents.openai_functions_agent.base import OpenAIFunctionsAgent

codegen-examples/examples/modules_dependencies/run.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 import networkx as nx
 
 

codegen-examples/examples/openapi_decorators/run.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 
 def analyze_model_fields(method) -> dict:

codegen-examples/examples/reexport_management/run.py

@@ -3,7 +3,7 @@
 
 from codegen.sdk.typescript.file import TSImport
 
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 processed_imports = set()
 

codegen-examples/examples/slack_chatbot/api.py

@@ -6,7 +6,7 @@
 import modal
 from codegen import Codebase
 from codegen.extensions import VectorIndex
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from fastapi import FastAPI, Request
 from openai import OpenAI
 from slack_bolt import App

codegen-examples/examples/sqlalchemy_soft_delete/run.py

@@ -1,7 +1,7 @@
 import codegen
 from codegen import Codebase
 from codegen.sdk.core.detached_symbols.function_call import FunctionCall
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 import shutil
 import subprocess
 from pathlib import Path

codegen-examples/examples/usesuspensequery_to_usesuspensequeries/run.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from codegen.sdk.core.detached_symbols.function_call import FunctionCall
 
 

codegen-examples/examples/visualize_codebases/blast_radius.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 import networkx as nx
 from codegen.sdk.python.symbol import PySymbol
 from codegen.sdk.python.function import PyFunction

codegen-examples/examples/visualize_codebases/call_trace.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 import networkx as nx
 from codegen.sdk.core.detached_symbols.function_call import FunctionCall
 from codegen.sdk.core.function import Function

codegen-examples/examples/visualize_codebases/dependency_trace.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 import networkx as nx
 from codegen.sdk.core.class_definition import Class
 from codegen.sdk.core.symbol import Symbol

codegen-examples/examples/visualize_codebases/method_relationships.py

@@ -1,6 +1,6 @@
 import codegen
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 import networkx as nx
 from codegen.sdk.core.detached_symbols.function_call import FunctionCall
 from codegen.sdk.core.function import Function

docs/conftest.py

@@ -8,7 +8,7 @@
 
 from codegen.sdk.code_generation.current_code_codebase import get_documented_objects
 from codegen.sdk.codebase.factory.get_session import get_codebase_session
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 from codegen.sdk.typescript.class_definition import TSClass
 from codegen.sdk.typescript.file import TSFile
 from codegen.gscli.generate.runner_imports import EXTERNAL_IMPORTS

pyproject.toml

@@ -160,7 +160,7 @@ dev-dependencies = [
 
 
 [tool.uv.workspace]
-members = ["codegen", "codegen-examples"]
+#members = ["codegen", "codegen-examples"]
 exclude = ["codegen-examples"]
 
 [tool.cython-lint]

scripts/profiling/apis.py

@@ -7,7 +7,7 @@
 from tabulate import tabulate
 
 from codegen.sdk.codebase.factory.get_dev_customer_codebase import get_codebase_codegen
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 logging.basicConfig(level=logging.INFO)
 codegen = get_codebase_codegen("../codegen", ".")

src/codegen/cli/api/client.py

@@ -45,8 +45,8 @@
 from codegen.cli.env.global_env import global_env
 from codegen.cli.errors import InvalidTokenError, ServerError
 from codegen.cli.utils.codemods import Codemod
-from codegen.cli.utils.constants import ProgrammingLanguage
 from codegen.cli.utils.function_finder import DecoratedFunction
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 InputT = TypeVar("InputT", bound=BaseModel)
 OutputT = TypeVar("OutputT", bound=BaseModel)

src/codegen/cli/api/schemas.py

@@ -4,8 +4,8 @@
 from pydantic import BaseModel
 from pydantic.fields import Field
 
-from codegen.cli.utils.constants import ProgrammingLanguage
 from codegen.cli.utils.schema import SafeBaseModel
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 T = TypeVar("T")
 

src/codegen/cli/auth/session.py

@@ -8,7 +8,7 @@
 from codegen.cli.errors import AuthError, NoTokenError
 from codegen.cli.git.repo import get_git_repo
 from codegen.cli.utils.config import Config, get_config, write_config
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 
 @dataclass
@@ -39,15 +39,19 @@ class CodegenSession:
     """Represents an authenticated codegen session with user and repository context"""
 
     # =====[ Instance attributes ]=====
-    token: str | None = None
+    _token: str | None = None
 
     # =====[ Lazy instance attributes ]=====
     _config: Config | None = None
     _identity: Identity | None = None
     _profile: UserProfile | None = None
 
-    def __init__(self, token: str | None = None):
-        self.token = token or get_current_token()
+    @property
+    def token(self) -> str | None:
+        """Get the current authentication token"""
+        if self._token:
+            return self._token
+        return get_current_token()
 
     @property
     def config(self) -> Config:

src/codegen/cli/commands/init/main.py

@@ -1,65 +1,84 @@
+import os
 import subprocess
 import sys
 from pathlib import Path
 
 import rich
 import rich_click as click
+from github import BadCredentialsException
+from github.MainClass import Github
 
-from codegen.cli.auth.constants import CODEGEN_DIR
 from codegen.cli.auth.session import CodegenSession
 from codegen.cli.commands.init.render import get_success_message
-from codegen.cli.git.url import get_git_organization_and_repo
 from codegen.cli.rich.codeblocks import format_command
-from codegen.cli.utils.constants import ProgrammingLanguage
 from codegen.cli.workspace.initialize_workspace import initialize_codegen
+from codegen.git.repo_operator.local_git_repo import LocalGitRepo
+from codegen.shared.configs.config import config
+from codegen.shared.configs.constants import CONFIG_PATH
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 
 @click.command(name="init")
-@click.option("--repo-name", type=str, help="The name of the repository")
-@click.option("--organization-name", type=str, help="The name of the organization")
-@click.option("--fetch-docs", is_flag=True, help="Fetch docs and examples (requires auth)")
+@click.option("--path", type=str, help="Path within a git repository. Defaults to the current directory.")
+@click.option("--token", type=str, help="Access token for the git repository. Required for full functionality.")
 @click.option("--language", type=click.Choice(["python", "typescript"], case_sensitive=False), help="Override automatic language detection")
-def init_command(repo_name: str | None = None, organization_name: str | None = None, fetch_docs: bool = False, language: str | None = None):
+@click.option("--fetch-docs", is_flag=True, help="Fetch docs and examples (requires auth)")
+def init_command(path: str | None = None, token: str | None = None, language: str | None = None, fetch_docs: bool = False):
     """Initialize or update the Codegen folder."""
     # Print a message if not in a git repo
+    path = str(Path.cwd()) if path is None else path
     try:
+        os.chdir(path)
         output = subprocess.run(["git", "rev-parse", "--show-toplevel"], capture_output=True, check=True, text=True)
+        local_git = LocalGitRepo(repo_path=output.stdout.strip())
     except (subprocess.CalledProcessError, FileNotFoundError):
-        rich.print("\n[bold red]Error:[/bold red] Not in a git repository")
+        rich.print(f"\n[bold red]Error:[/bold red] Path={path} is not in a git repository")
         rich.print("[white]Please run this command from within a git repository.[/white]")
         rich.print("\n[dim]To initialize a new git repository:[/dim]")
         rich.print(format_command("git init"))
-        rich.print(format_command("git remote add origin <your-repo-url>"))
         rich.print(format_command("codegen init"))
         sys.exit(1)
 
-    # Convert language string to enum if provided
-    programming_language = None
-    if language:
-        programming_language = ProgrammingLanguage[language.upper()]
+    if local_git.origin_remote is None:
+        rich.print("\n[bold red]Error:[/bold red] No remote found for repository")
+        rich.print("[white]Please add a remote to the repository.[/white]")
+        rich.print("\n[dim]To add a remote to the repository:[/dim]")
+        rich.print(format_command("git remote add origin <your-repo-url>"))
+        sys.exit(1)
+
+    if token is None:
+        token = config.secrets.github_token
+    else:
+        config.secrets.github_token = token
 
-    # Only create session if we need to fetch docs
-    session = CodegenSession() if fetch_docs else None
-    codegen_dir = Path.cwd() / CODEGEN_DIR if not session else session.codegen_dir
-    is_update = codegen_dir.exists()
+    if not token:
+        rich.print("\n[bold yellow]Warning:[/bold yellow] GitHub token not found")
+        rich.print("To enable full functionality, please set your GitHub token:")
+        rich.print(format_command("export CODEGEN_SECRETS__GITHUB_TOKEN=<your-token>"))
+        rich.print("Or pass in as a parameter:")
+        rich.print(format_command("codegen init --token <your-token>"))
+    else:
+        # Validate that the token is valid for the repo path.
+        try:
+            Github(login_or_token=token).get_repo(local_git.full_name)
+        except BadCredentialsException:
+            rich.print(format_command(f"\n[bold red]Error:[/bold red] Invalid GitHub token={token} for repo={local_git.full_name}"))
+            rich.print("[white]Please provide a valid GitHub token for this repository.[/white]")
+            sys.exit(1)
 
-    # Only update config if we have a session
-    if session:
-        if organization_name is not None:
-            session.config.organization_name = organization_name
-        if repo_name is not None:
-            session.config.repo_name = repo_name
-        if not session.config.organization_name or not session.config.repo_name:
-            cwd_org, cwd_repo = get_git_organization_and_repo(session.git_repo)
-            session.config.organization_name = session.config.organization_name or cwd_org
-            session.config.repo_name = session.config.repo_name or cwd_repo
-        if programming_language:
-            session.config.programming_language = programming_language
-        session.write_config()
+    # Save repo config
+    config.repository.repo_path = local_git.repo_path
+    config.repository.repo_name = local_git.name
+    config.repository.full_name = local_git.full_name
+    config.repository.user_name = local_git.user_name
+    config.repository.user_email = local_git.user_email
+    config.repository.language = (language or local_git.get_language(access_token=token)).upper()
+    config.save()
 
-    action = "Updating" if is_update else "Initializing"
+    session = CodegenSession()
+    action = "Updating" if CONFIG_PATH.exists() else "Initializing"
     rich.print("")
-    codegen_dir, docs_dir, examples_dir = initialize_codegen(action, session=session, fetch_docs=fetch_docs, programming_language=programming_language)
+    codegen_dir, docs_dir, examples_dir = initialize_codegen(action, session=session, fetch_docs=fetch_docs, programming_language=ProgrammingLanguage(config.repository.language))
 
     # Print success message
     rich.print(f"✅ {action} complete\n")

src/codegen/cli/git/folder.py

@@ -2,6 +2,7 @@
 from pathlib import Path
 
 
+# TODO: move to codegen.git module
 def get_git_folder(path: os.PathLike | None = None) -> Path | None:
     if path is None:
         path = Path.cwd()

src/codegen/cli/git/repo.py

@@ -6,6 +6,7 @@
 from codegen.cli.git.folder import get_git_folder
 
 
+# TODO: move to codegen.git module
 def get_git_repo(path: os.PathLike | None = None) -> Repository | None:
     if path is None:
         path = Path.cwd()

src/codegen/cli/mcp/resources/system_prompt.py

@@ -1327,7 +1327,7 @@ def baz():
 
 ```python
 from codegen import Codebase
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 # Parse from a git repository root
 codebase = Codebase("path/to/repository")
@@ -1360,7 +1360,7 @@ def baz():
 
 ```python
 import codegen
-from codegen.sdk.enums import ProgrammingLanguage
+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')
@@ -1423,7 +1423,7 @@ def baz():
 from codegen.git.repo_operator.local_repo_operator import LocalRepoOperator
 from codegen.git.schemas.repo_config import RepoConfig
 from codegen.sdk.codebase.config import ProjectConfig
-from codegen.sdk.enums import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 codebase = Codebase(
     projects = [

src/codegen/cli/mcp/server.py

@@ -5,7 +5,7 @@
 from codegen.cli.api.client import RestAPI
 from codegen.cli.mcp.resources.system_prompt import SYSTEM_PROMPT
 from codegen.cli.mcp.resources.system_setup_instructions import SETUP_INSTRUCTIONS
-from codegen.cli.utils.constants import ProgrammingLanguage
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 # Initialize FastMCP server
 

src/codegen/cli/workspace/initialize_workspace.py

@@ -14,11 +14,11 @@
 from codegen.cli.git.repo import get_git_repo
 from codegen.cli.git.url import get_git_organization_and_repo
 from codegen.cli.rich.spinners import create_spinner
-from codegen.cli.utils.constants import ProgrammingLanguage
 from codegen.cli.utils.notebooks import create_notebook
 from codegen.cli.workspace.docs_workspace import populate_api_docs
 from codegen.cli.workspace.examples_workspace import populate_examples
 from codegen.cli.workspace.venv_manager import VenvManager
+from codegen.shared.enums.programming_language import ProgrammingLanguage
 
 
 def initialize_codegen(

src/codegen/git/clients/github_client.py

@@ -15,7 +15,7 @@ class GithubClient:
     base_url: str
     _client: Github
 
-    def __init__(self, token: str, base_url: str = Consts.DEFAULT_BASE_URL):
+    def __init__(self, token: str | None = None, base_url: str = Consts.DEFAULT_BASE_URL):
         self.base_url = base_url
         self._client = Github(token, base_url=base_url)