Fix Git source sync failures

backend/Dockerfile

@@ -6,6 +6,7 @@ WORKDIR /app
 # Install system dependencies for PDF parsing and embeddings
 RUN apt-get update && apt-get install -y --no-install-recommends \
     curl \
+    git \
     libgl1 \
     libglib2.0-0 \
     && rm -rf /var/lib/apt/lists/*

backend/app/git_source.py

@@ -1,6 +1,7 @@
 # Git Source Operations for Repository Cloning and File Discovery
 import os
 import shutil
+from subprocess import run
 from pathlib import Path
 from typing import List, Optional, Dict, Any
 
@@ -27,6 +28,13 @@ class GitCloneError(Exception):
     pass
 
 
+def run_git(command: List[str]) -> None:
+    result = run(command, capture_output=True, text=True)
+    if result.returncode != 0:
+        error = (result.stderr or result.stdout or "unknown git error").strip()
+        raise GitCloneError(error)
+
+
 def clone_or_update_repo(
     repo_id: str,
     repo_url: str,
@@ -56,36 +64,25 @@ def clone_or_update_repo(
             # Update existing clone
             print(f"  [Git] Updating existing clone at {repo_path}")
 
-            from subprocess import run, CalledProcessError
-            import subprocess
-            
             # Fetch latest changes
-            result = run(
+            run_git(["git", "-C", str(repo_path), "fetch", "origin"])
-                ["git", "-C", str(repo_path), "fetch", "origin"],
-                capture_output=True,
-                text=True
-            )
-            
-            if result.returncode != 0:
-                raise GitCloneError(f"Failed to fetch: {result.stderr}")
 
             # Reset to branch
-            run(
+            run_git(["git", "-C", str(repo_path), "reset", "--hard", "origin/" + branch])
-                ["git", "-C", str(repo_path), "reset", "--hard", "origin/" + branch],
-                capture_output=True,
-                text=True
-            )
         else:
             # Clone new repository
             print(f"  [Git] Cloning {repo_url} to {repo_path}")
 
-            run(
+            run_git(
-                ["git", "-C", str(repo_path.parent), "clone", 
+                [
-                 "--branch", branch, 
+                    "git",
-                 "--single-branch",
+                    "clone",
-                 repo_url, "."],
+                    "--branch",
-                capture_output=True,
+                    branch,
-                text=True
+                    "--single-branch",
+                    repo_url,
+                    str(repo_path),
+                ]
             )
         
         print(f"  [Git] Checked out branch: {branch}")
@@ -97,8 +94,8 @@ def clone_or_update_repo(
             "branch": branch
         }
         
-    except CalledProcessError as e:
+    except GitCloneError:
-        raise GitCloneError(f"Git command failed: {e.stderr}") from e
+        raise
     except Exception as e:
         raise GitCloneError(f"Failed to clone/update repo: {e}") from e
 

backend/app/main.py

@@ -432,15 +432,24 @@ async def sync_sources_api(payload: Optional[SyncSourcesRequest] = None):
     results = []
 
     for source in sources:
-        result = await ingest_git_source(
+        library_id = source.get("library_id", "unknown")
-            library_id=source["library_id"],
+        try:
-            name=source.get("name") or source["library_id"],
+            result = await ingest_git_source(
-            description=source.get("description"),
+                library_id=library_id,
-            repo_url=source["repo_url"],
+                name=source.get("name") or library_id,
-            branch=source.get("branch", "main"),
+                description=source.get("description"),
-            include_paths=source.get("include_paths"),
+                repo_url=source["repo_url"],
-            exclude_paths=source.get("exclude_paths"),
+                branch=source.get("branch", "main"),
-        )
+                include_paths=source.get("include_paths"),
+                exclude_paths=source.get("exclude_paths"),
+            )
+        except Exception as exc:
+            result = {
+                "success": False,
+                "library_id": library_id,
+                "repo_url": source.get("repo_url"),
+                "error": str(exc),
+            }
         results.append(result)
 
     successful = len([r for r in results if r.get("success")])

tests/test_git_sources.py

@@ -0,0 +1,66 @@
+import pytest
+
+from backend.app import git_source, main
+
+
+def test_clone_or_update_repo_clones_into_repo_path(monkeypatch, tmp_path):
+    commands = []
+
+    def fake_run(command, capture_output=True, text=True):
+        commands.append(command)
+
+        class Result:
+            returncode = 0
+            stdout = ""
+            stderr = ""
+
+        return Result()
+
+    monkeypatch.setattr(git_source, "run", fake_run)
+
+    result = git_source.clone_or_update_repo(
+        repo_id="neoforge-git",
+        repo_url="https://github.com/neoforged/Documentation.git",
+        branch="main",
+        repos_base=tmp_path,
+    )
+
+    assert result["success"] is True
+    assert commands == [
+        [
+            "git",
+            "clone",
+            "--branch",
+            "main",
+            "--single-branch",
+            "https://github.com/neoforged/Documentation.git",
+            str(tmp_path / "neoforge-git"),
+        ]
+    ]
+
+
+@pytest.mark.asyncio
+async def test_sync_sources_returns_failed_result_for_source_exception(monkeypatch):
+    async def fake_list_sources():
+        return {
+            "sources": [
+                {
+                    "library_id": "neoforge",
+                    "repo_url": "https://github.com/neoforged/Documentation.git",
+                    "branch": "main",
+                }
+            ]
+        }
+
+    async def fake_ingest_git_source(**kwargs):
+        raise RuntimeError("git is unavailable")
+
+    monkeypatch.setattr(main, "api_list_sources", fake_list_sources)
+    monkeypatch.setattr(main, "ingest_git_source", fake_ingest_git_source)
+
+    result = await main.sync_sources_api()
+
+    assert result["success"] is False
+    assert result["failed"] == 1
+    assert result["results"][0]["library_id"] == "neoforge"
+    assert result["results"][0]["error"] == "git is unavailable"