repr-cli 0.2.14__tar.gz → 0.2.16__tar.gz

{repr_cli-0.2.14/repr_cli.egg-info → repr_cli-0.2.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: repr-cli
-Version: 0.2.14
+Version: 0.2.16
 Summary: A beautiful, privacy-first CLI that analyzes your code repositories and generates a compelling developer profile
 Author-email: Repr <hello@repr.dev>
 License: MIT License
@@ -219,6 +219,8 @@ repr generate --since "2 weeks ago" --local
 repr generate --since monday --local
 ```
 
+**Note:** `repr generate` automatically skips commits that have already been processed into stories. You can safely run it multiple times without creating duplicates.
+
 ### Publish your profile (optional)
 
 ```bash

{repr_cli-0.2.14 → repr_cli-0.2.16}/README.md

@@ -161,6 +161,8 @@ repr generate --since "2 weeks ago" --local
 repr generate --since monday --local
 ```
 
+**Note:** `repr generate` automatically skips commits that have already been processed into stories. You can safely run it multiple times without creating duplicates.
+
 ### Publish your profile (optional)
 
 ```bash

{repr_cli-0.2.14 → repr_cli-0.2.16}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "repr-cli"
-version = "0.2.14"
+version = "0.2.16"
 description = "A beautiful, privacy-first CLI that analyzes your code repositories and generates a compelling developer profile"
 readme = "README.md"
 license = {file = "LICENSE"}

{repr_cli-0.2.14 → repr_cli-0.2.16}/repr/cli.py

@@ -491,6 +491,23 @@ def generate(
                 console.print(f"  [{BRAND_MUTED}]No commits found[/]")
             continue
         
+        # Filter out already-processed commits
+        from .storage import get_processed_commit_shas
+        processed_shas = get_processed_commit_shas(repo_name=repo_info.name)
+        
+        original_count = len(commit_list)
+        commit_list = [c for c in commit_list if c["full_sha"] not in processed_shas]
+        
+        if not json_output and processed_shas:
+            skipped_count = original_count - len(commit_list)
+            if skipped_count > 0:
+                console.print(f"  [{BRAND_MUTED}]Skipping {skipped_count} already-processed commits[/]")
+        
+        if not commit_list:
+            if not json_output:
+                console.print(f"  [{BRAND_MUTED}]All commits already processed[/]")
+            continue
+        
         # Dry run: show what would be sent
         if dry_run:
             from .openai_analysis import estimate_tokens, get_batch_size

{repr_cli-0.2.14 → repr_cli-0.2.16}/repr/config.py

@@ -108,7 +108,7 @@ DEFAULT_CONFIG = {
     },
     "generation": {
         "batch_size": 5,  # Commits per story
-        "auto_generate_on_hook": False,  # Auto-generate when hook runs
+        "auto_generate_on_hook": True,  # Auto-generate when hook runs
         "default_template": "resume",  # Default story template
         "token_limit": 100000,  # Max tokens per cloud request
         "max_commits_per_batch": 50,  # Max commits per request

{repr_cli-0.2.14 → repr_cli-0.2.16}/repr/storage.py

@@ -246,6 +246,38 @@ def update_story_metadata(story_id: str, updates: dict[str, Any]) -> bool:
         return False
 
 
+def get_processed_commit_shas(repo_name: str | None = None) -> set[str]:
+    """
+    Get all commit SHAs that have already been processed into stories.
+    
+    Args:
+        repo_name: Optional filter by repository name
+    
+    Returns:
+        Set of commit SHAs that have been processed
+    """
+    ensure_directories()
+    
+    processed_shas = set()
+    
+    for meta_path in STORIES_DIR.glob("*.json"):
+        try:
+            metadata = json.loads(meta_path.read_text())
+            
+            # Filter by repo if specified
+            if repo_name and metadata.get("repo_name") != repo_name:
+                continue
+            
+            # Collect commit SHAs from this story
+            commit_shas = metadata.get("commit_shas", [])
+            processed_shas.update(commit_shas)
+            
+        except (json.JSONDecodeError, IOError):
+            continue
+    
+    return processed_shas
+
+
 def get_unpushed_stories() -> list[dict[str, Any]]:
     """Get stories that haven't been pushed to cloud."""
     stories = list_stories()

{repr_cli-0.2.14 → repr_cli-0.2.16/repr_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: repr-cli
-Version: 0.2.14
+Version: 0.2.16
 Summary: A beautiful, privacy-first CLI that analyzes your code repositories and generates a compelling developer profile
 Author-email: Repr <hello@repr.dev>
 License: MIT License
@@ -219,6 +219,8 @@ repr generate --since "2 weeks ago" --local
 repr generate --since monday --local
 ```
 
+**Note:** `repr generate` automatically skips commits that have already been processed into stories. You can safely run it multiple times without creating duplicates.
+
 ### Publish your profile (optional)
 
 ```bash

{repr_cli-0.2.14 → repr_cli-0.2.16}/repr_cli.egg-info/SOURCES.txt

@@ -28,6 +28,7 @@ repr_cli.egg-info/dependency_links.txt
 repr_cli.egg-info/entry_points.txt
 repr_cli.egg-info/requires.txt
 repr_cli.egg-info/top_level.txt
+tests/test_deduplication.py
 tests/test_environment_variables.py
 tests/test_network_sandboxing.py
 tests/test_privacy_guarantees.py

repr_cli-0.2.16/tests/test_deduplication.py

@@ -0,0 +1,143 @@
+"""
+Test commit deduplication in story generation.
+"""
+
+import json
+import tempfile
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+
+from repr.storage import (
+    get_processed_commit_shas,
+    save_story,
+    STORIES_DIR,
+)
+
+
+@pytest.fixture
+def temp_stories_dir(monkeypatch):
+    """Use a temporary directory for stories during tests."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        stories_dir = Path(tmpdir) / "stories"
+        stories_dir.mkdir()
+        monkeypatch.setattr("repr.storage.STORIES_DIR", stories_dir)
+        yield stories_dir
+
+
+def test_get_processed_commit_shas_empty(temp_stories_dir):
+    """Test getting processed commits when no stories exist."""
+    processed = get_processed_commit_shas()
+    assert processed == set()
+
+
+def test_get_processed_commit_shas_single_story(temp_stories_dir):
+    """Test getting processed commits from a single story."""
+    # Save a story with some commits
+    metadata = {
+        "repo_name": "test-repo",
+        "commit_shas": ["abc123", "def456", "ghi789"],
+    }
+    save_story("Test story content", metadata)
+    
+    # Get processed commits
+    processed = get_processed_commit_shas()
+    assert processed == {"abc123", "def456", "ghi789"}
+
+
+def test_get_processed_commit_shas_multiple_stories(temp_stories_dir):
+    """Test getting processed commits from multiple stories."""
+    # Save multiple stories
+    save_story("Story 1", {
+        "repo_name": "test-repo",
+        "commit_shas": ["abc123", "def456"],
+    })
+    save_story("Story 2", {
+        "repo_name": "test-repo",
+        "commit_shas": ["ghi789", "jkl012"],
+    })
+    save_story("Story 3", {
+        "repo_name": "test-repo",
+        "commit_shas": ["def456", "mno345"],  # def456 is duplicate
+    })
+    
+    # Get all processed commits
+    processed = get_processed_commit_shas()
+    assert processed == {"abc123", "def456", "ghi789", "jkl012", "mno345"}
+
+
+def test_get_processed_commit_shas_filter_by_repo(temp_stories_dir):
+    """Test filtering processed commits by repository."""
+    # Save stories for different repos
+    save_story("Story 1", {
+        "repo_name": "repo-a",
+        "commit_shas": ["abc123", "def456"],
+    })
+    save_story("Story 2", {
+        "repo_name": "repo-b",
+        "commit_shas": ["ghi789", "jkl012"],
+    })
+    save_story("Story 3", {
+        "repo_name": "repo-a",
+        "commit_shas": ["mno345"],
+    })
+    
+    # Get processed commits for repo-a only
+    processed_a = get_processed_commit_shas(repo_name="repo-a")
+    assert processed_a == {"abc123", "def456", "mno345"}
+    
+    # Get processed commits for repo-b only
+    processed_b = get_processed_commit_shas(repo_name="repo-b")
+    assert processed_b == {"ghi789", "jkl012"}
+
+
+def test_get_processed_commit_shas_handles_missing_field(temp_stories_dir):
+    """Test handling stories without commit_shas field."""
+    # Save a story without commit_shas
+    save_story("Story without commits", {
+        "repo_name": "test-repo",
+        "summary": "Test story",
+    })
+    
+    # Should not crash, just return empty set
+    processed = get_processed_commit_shas()
+    assert processed == set()
+
+
+def test_get_processed_commit_shas_handles_corrupt_json(temp_stories_dir):
+    """Test handling corrupt JSON files."""
+    # Create a corrupt JSON file
+    corrupt_file = temp_stories_dir / "corrupt.json"
+    corrupt_file.write_text("{ invalid json }")
+    
+    # Should not crash, just skip the corrupt file
+    processed = get_processed_commit_shas()
+    assert processed == set()
+
+
+def test_commit_filtering_in_generate(temp_stories_dir):
+    """Test that generate command filters out processed commits."""
+    # Save a story with some commits
+    save_story("Existing story", {
+        "repo_name": "test-repo",
+        "commit_shas": ["abc123", "def456"],
+    })
+    
+    # Simulate commit list from git
+    all_commits = [
+        {"full_sha": "abc123", "message": "Already processed 1"},
+        {"full_sha": "def456", "message": "Already processed 2"},
+        {"full_sha": "ghi789", "message": "New commit 1"},
+        {"full_sha": "jkl012", "message": "New commit 2"},
+    ]
+    
+    # Filter out processed commits
+    processed_shas = get_processed_commit_shas(repo_name="test-repo")
+    filtered_commits = [c for c in all_commits if c["full_sha"] not in processed_shas]
+    
+    # Should only have the new commits
+    assert len(filtered_commits) == 2
+    assert filtered_commits[0]["full_sha"] == "ghi789"
+    assert filtered_commits[1]["full_sha"] == "jkl012"
+