fix: FileTools uses local workspace before API for file content (#6.2)

gitea/tools/file_tools.py

@@ -1,3 +1,5 @@
+import os
+from pathlib import Path
 from typing import Any
 from gitea.client import GiteaClient
 
@@ -5,8 +7,9 @@ from gitea.client import GiteaClient
 class FileTools:
     """Tools for Gitea file/content operations."""
 
-    def __init__(self, client: GiteaClient) -> None:
+    def __init__(self, client: GiteaClient, repo_path: str | None = None) -> None:
         self._client = client
+        self._repo_path: str | None = repo_path
 
     def _paginate_lines(
         self,
@@ -35,6 +38,15 @@ class FileTools:
             )
         return result
 
+    def _resolve_local_path(self, owner: str, repo: str, path: str) -> str | None:
+        """Resolve owner/repo/path to a local filesystem path if the repo is cloned."""
+        if not self._repo_path:
+            return None
+        local_repo: str = os.path.join(self._repo_path, owner, repo)
+        if os.path.isdir(local_repo):
+            return os.path.join(local_repo, path)
+        return None
+
     def get_file_content(
         self,
         owner: str,
@@ -45,10 +57,22 @@ class FileTools:
     ) -> str:
         """Get the content of a file from a Gitea repository with line paging.
 
+        Checks the local workspace first if repo_path is configured, falling
+        back to the remote API when the file is not available locally.
+
         Args:
             offset: 1-indexed line to start from (default 1).
             limit: Maximum number of lines to return (default 250).
         """
+        local_path: str | None = self._resolve_local_path(owner, repo, path)
+        if local_path and os.path.isfile(local_path):
+            try:
+                with open(local_path, 'r', encoding='utf-8', errors='replace') as f:
+                    raw: str = f.read()
+                return self._paginate_lines(raw, offset, limit)
+            except Exception:
+                pass
+
         try:
             content = self._client.files.get_file_content(owner, repo, path)
             raw: str = "\n".join(content) if isinstance(content, list) else content
@@ -67,11 +91,28 @@ class FileTools:
     ) -> str:
         """Get file content at a specific git ref with line paging.
 
+        Checks the local workspace first using ``git show`` if the repo is
+        cloned locally, falling back to the remote API.
+
         Args:
             ref: Branch, tag, or commit SHA (default 'master').
             offset: 1-indexed line to start from (default 1).
             limit: Maximum number of lines to return (default 250).
         """
+        if self._repo_path:
+            local_repo: str = os.path.join(self._repo_path, owner, repo)
+            if os.path.isdir(local_repo):
+                try:
+                    import subprocess
+                    result = subprocess.run(
+                        ["git", "-C", local_repo, "show", f"{ref}:{path}"],
+                        capture_output=True, text=True, timeout=15,
+                    )
+                    if result.returncode == 0:
+                        return self._paginate_lines(result.stdout, offset, limit)
+                except Exception:
+                    pass
+
         try:
             content = self._client.files.get_file_content(owner, repo, path, ref)
             raw: str = "\n".join(content) if isinstance(content, list) else content

main.py

@@ -11,7 +11,7 @@ from gitea.tools.issue_tools import IssueTools
 from gitea.tools.pr_tools import PRTools
 from gitea.tools.file_tools import FileTools
 from gitea.tools.git_tools import GitTools
-from gitea.config import AGENT_MODEL_ID, AGENT_MAX_RETRIES
+from gitea.config import AGENT_MODEL_ID, AGENT_MAX_RETRIES, GITEA_REPOS_ROOT
 from core.orchestrator import AgentOrchestrator
 
 import json
@@ -73,7 +73,7 @@ async def main() -> None:
 
     issue_tools: IssueTools = IssueTools(client)
     pr_tools: PRTools = PRTools(client)
-    file_tools: FileTools = FileTools(client)
+    file_tools: FileTools = FileTools(client, GITEA_REPOS_ROOT)
     git_tools: GitTools = GitTools(client)
     model_name: str = AGENT_MODEL_ID
 

tests/test_file_tools.py

@@ -124,3 +124,31 @@ def test_update_file_failure() -> None:
         "owner", "repo", "path/to/file", "msg", "content", "branch"
     )
     assert "Error updating file: API Error" in res
+
+
+def test_get_file_content_uses_local_file_when_available(tmp_path: str) -> None:
+    import os
+    mock_client = _create_mock_client()
+
+    repo_dir = tmp_path / "owner" / "repo"
+    repo_dir.mkdir(parents=True)
+    file_path = repo_dir / "path" / "to" / "file"
+    file_path.parent.mkdir(parents=True)
+    file_path.write_text("local file content")
+
+    file_tools = FileTools(mock_client, str(tmp_path))
+    res = file_tools.get_file_content("owner", "repo", "path/to/file")
+    assert res == "1: local file content"
+    mock_client.files.get_file_content.assert_not_called()
+
+
+def test_get_file_content_falls_back_to_api_when_no_local(tmp_path: str) -> None:
+    mock_client = _create_mock_client()
+    mock_client.files.get_file_content.return_value = "api content"
+
+    file_tools = FileTools(mock_client, str(tmp_path))
+    res = file_tools.get_file_content("owner", "repo", "path/to/file")
+    assert res == "1: api content"
+    mock_client.files.get_file_content.assert_called_once_with(
+        "owner", "repo", "path/to/file"
+    )