Bump version

Author: gltanaka

CHANGELOG.md

@@ -1,15 +1,64 @@
+## v0.0.120 (2026-01-18)
+
+### Feat
+
+- Introduce LLM prompt for generating isolated tests and refactor `test_fix.py` to improve test module isolation.
+- Refine command arguments with default values, add operation logging, and introduce new tests for `fix` and `utility` commands.
+- Recursively ensure all JSON schema properties are marked as required for OpenAI strict mode.
+- Add `promptToCodeScore` and `codeToPromptScore` fields to the LLM prompt output specification and renumber subsequent fields.
+- Introduce standardized operation logging for CLI commands and refactor sync orchestration to use the new `operation_log` module.
+- Implement an operation logging module with state management, fingerprinting, run reports, and a command decorator.
+- add operation_log module prompt for shared PDD logging infrastructure (#277)
+
+### Refactor
+
+- centralize sync orchestration logging to a new operation log module and add new tests for LLM invocation and server prompt routes.
+- introduce structured log entry creation and update functions, rename log loading, and enhance fingerprint metadata storage.
+
+## v0.0.120 (2026-01-17)
+
+### Feat
+
+- allow multiple test files for fix and test commands
+- add test cases for numbered file creation
+- Add VS Code extension PDD CLI installation system
+- add automated theorem proving languages Lean and Agda
+
+### Fix
+
+- prevent `pdd fix` from printing output paths for unmodified files and add reproduction tests for issue #232.
+- pass concatenated test content to fix_error_loop and update PR description
+- update tests for multiple test files
+- update tests for multiple test files
+- move file numbering logic to construct_paths
+- update extension metadata for Cursor marketplace compatibility
+- ignore sqlite cache
+- ignore .pyc files
+- ignore .pyc files
+- add --list-contexts cli test
+- Configure pytest subprocess with project root, PYTHONPATH, and cwd for accurate fix operation test results.
+
+### Refactor
+
+- simplify multi-file test fixing
+
 ## v0.0.119 (2026-01-16)
 
 ### Feat
 
-- Introduce 'hello' example with unit tests covering output, return value, multiple calls, and signature, removing Z3 formal verification.
-- introduce a new `hello.py` example, update `README.md` with a PDD command relationship diagram, and refactor the `hello` example and test files.
-- Add smart port detection and frontend improvements
-- Add a new 'hello' example and update the changelog with recent features, fixes, and documentation.
+- **Smart Port Detection:** `pdd connect` automatically detects when the default port (9876) is in use and finds the next available port in range 9876-9899. User-specified ports (`--port`) show a clear error if unavailable instead of auto-switching.
+- **Audio Notifications:** New `useAudioNotification` hook plays Web Audio API sounds on job completion (ascending chime for success, descending for failure). Toggle via sound icon in header; preference persisted to localStorage.
+- **Command Relationship Diagram:** README now includes a Mermaid flowchart showing how PDD commands interact (entry points → issue-driven commands → sync workflow).
+
+### Fix
+
+- **`pdd fix --loop` Without ERROR_FILE:** Loop mode (`--loop`) no longer requires ERROR_FILE argument; error output is generated during the loop. Non-loop mode still requires ERROR_FILE as the last positional argument. Thanks Serhan Asad for your help with this fix!
+- **Nested Project Test Isolation:** `_execute_tests_and_create_run_report()` now sets `--rootdir`, `PYTHONPATH`, and `cwd` based on the project's `.pddrc` marker, preventing pytest from using parent directory configs and causing infinite fix loops.
+- **Click Exception Handling:** `pdd fix` now properly re-raises Click exceptions (`Abort`, `UsageError`, etc.) instead of swallowing them with generic error handling.
 
 ### Refactor
 
-- Address PR review feedback for audio notifications
+- **PromptSpace Code Panel Layout:** Sidebar hides when code panel is open; commands displayed in vertical bar between prompt and code panels for better space utilization.
 
 ## v0.0.118 (2026-01-16)
 

README.md

@@ -1,6 +1,6 @@
 # PDD (Prompt-Driven Development) Command Line Interface
 
-![PDD-CLI Version](https://img.shields.io/badge/pdd--cli-v0.0.119-blue) [![Discord](https://img.shields.io/badge/Discord-join%20chat-7289DA.svg?logo=discord&logoColor=white)](https://discord.gg/Yp4RTh8bG7)
+![PDD-CLI Version](https://img.shields.io/badge/pdd--cli-v0.0.120-blue) [![Discord](https://img.shields.io/badge/Discord-join%20chat-7289DA.svg?logo=discord&logoColor=white)](https://discord.gg/Yp4RTh8bG7)
 
 ## Introduction
 
@@ -365,7 +365,7 @@ export PDD_TEST_OUTPUT_PATH=/path/to/tests/
 
 ## Version
 
-Current version: 0.0.119
+Current version: 0.0.120
 
 To check your installed version, run:
 ```
@@ -1812,13 +1812,13 @@ After the workflow completes, a PR is automatically created linking to the issue
 
 **Manual Mode (legacy):**
 ```
-pdd [GLOBAL OPTIONS] change --manual [OPTIONS] CHANGE_PROMPT_FILE INPUT_CODE [INPUT_PROMPT_FILE]
+pdd [GLOBAL OPTIONS] change --manual [OPTIONS] CHANGE_PROMPT_FILE INPUT_CODE INPUT_PROMPT_FILE
 ```
 
 Arguments:
 - `CHANGE_PROMPT_FILE`: The filename containing the instructions on how to modify the input prompt file.
 - `INPUT_CODE`: The filename of the code that was generated from the input prompt file, or the directory containing the code files when used with the '--csv' option.
-- `INPUT_PROMPT_FILE`: (Optional) The filename of the prompt file that will be modified. Not required when using the '--csv' option.
+- `INPUT_PROMPT_FILE`: The filename of the prompt file that will be modified. Required in standard mode; not used when using the '--csv' option.
 
 Options:
 - `--budget FLOAT`: Set the maximum cost allowed for the change process (default is $5.0).

context/commands/analysis_example.py

@@ -102,11 +102,14 @@ def main():
         with open(des_out, "w") as f: f.write("6")
 
         # FIX: Use correct arguments for bug command (manual=True, args=tuple)
+        # Added timeout_adder and no_github_state to match function signature
         result = bug.callback(
             manual=True,
             args=(bug_prompt, bug_code, bug_prog, curr_out, des_out),
             output=test_out,
-            language="Python"
+            language="Python",
+            timeout_adder=0.0,
+            no_github_state=False
         )
         print(f"Bug Result: {result}")
 

context/commands/modify_example.py

@@ -526,23 +526,25 @@ def cli(ctx):
 
 def example_change_command():
     """
-    Demonstrate the change command.
-    
+    Demonstrate the change command in manual mode.
+
     The change command modifies an existing prompt based on change instructions.
-    It can operate on a single file or in batch mode using a CSV file.
-    
-    Command signature:
-        pdd change CHANGE_PROMPT INPUT_CODE INPUT_PROMPT [OPTIONS]
-    
-    Arguments:
+    It supports two modes: agentic (default) and manual.
+
+    Command signatures:
+        Agentic mode: pdd change ISSUE_URL [OPTIONS]
+        Manual mode:  pdd change --manual CHANGE_PROMPT INPUT_CODE INPUT_PROMPT [OPTIONS]
+
+    Arguments (manual mode):
         CHANGE_PROMPT: Path to file containing change instructions (must exist)
         INPUT_CODE: Path to existing code file (must exist)
         INPUT_PROMPT: Path to prompt file to modify (must exist)
-    
+
     Options:
+        --manual: Use legacy manual mode instead of agentic mode
         --output: Where to save the modified prompt (default: overwrites input)
-        --csv: Path to CSV file for batch mode (columns: prompt_name, change_instructions)
-    
+        --csv: Enable CSV batch mode (use with --manual)
+
     Returns via @track_cost decorator:
         Tuple[Dict[str, str], float, str]:
             - result_data: Dictionary with keys:
@@ -566,11 +568,12 @@ def cli(ctx):
 
     runner = CliRunner()
 
-    # Run the change command
+    # Run the change command in manual mode
     result = runner.invoke(
         cli,
         [
             "change",
+            "--manual",
             files["change_prompt"],
             files["input_code"],
             files["input_prompt"],
@@ -595,22 +598,27 @@ def cli(ctx):
 
 def example_change_command_csv_batch():
     """
-    Demonstrate the change command in CSV batch mode.
-    
-    When using --csv option, the change command processes multiple prompts
+    Demonstrate the change command in manual CSV batch mode.
+
+    When using --csv with --manual, the change command processes multiple prompts
     based on instructions in a CSV file.
-    
+
     CSV file format:
         prompt_name,change_instructions
         path/to/prompt1.prompt,Instructions for first prompt
         path/to/prompt2.prompt,Instructions for second prompt
-    
+
     Command signature:
-        pdd change --csv CSV_FILE
-    
+        pdd change --manual --csv CSV_FILE CODE_DIRECTORY
+
+    Arguments:
+        CSV_FILE: Path to CSV file with batch change instructions
+        CODE_DIRECTORY: Directory containing code files referenced by prompts
+
     Options:
-        --csv: Path to CSV file with batch change instructions
-    
+        --manual: Required for CSV batch mode
+        --csv: Enable CSV batch processing
+
     Returns via @track_cost decorator:
         Tuple[Dict[str, Any], float, str]:
             - result_data: Dictionary with keys:
@@ -634,12 +642,15 @@ def cli(ctx):
 
     runner = CliRunner()
 
-    # Run the change command in CSV batch mode
+    # Run the change command in manual CSV batch mode
     result = runner.invoke(
         cli,
         [
             "change",
-            "--csv", files["csv_file"],
+            "--manual",
+            "--csv",
+            files["csv_file"],
+            files["code_dir"],
         ],
         catch_exceptions=False,
     )
@@ -654,23 +665,23 @@ def cli(ctx):
 def example_update_command():
     """
     Demonstrate the update command.
-    
+
     The update command updates a prompt based on changes made to the code.
-    It compares the original and modified code to understand what changed,
-    then updates the prompt to reflect those changes.
-    
+    It analyzes the modified code file and updates the corresponding prompt
+    to reflect the changes.
+
     Command signature:
-        pdd update INPUT_PROMPT MODIFIED_CODE [OPTIONS]
-    
+        Repo-wide mode: pdd update [OPTIONS]
+        Single-file mode: pdd update MODIFIED_CODE [OPTIONS]
+
     Arguments:
-        INPUT_PROMPT: Path to the original prompt file (must exist)
-        MODIFIED_CODE: Path to the modified code file (must exist)
-    
+        MODIFIED_CODE: Path to the modified code file (single-file mode)
+
     Options:
-        --original-code: Path to original code for comparison (optional)
+        --git: Use git history for original code comparison
         --output: Where to save the updated prompt (default: overwrites input)
         --simple: Use legacy 2-stage LLM update instead of agentic mode
-    
+
     Returns via @track_cost decorator:
         Tuple[Dict[str, str], float, str]:
             - result_data: Dictionary with keys:
@@ -695,20 +706,19 @@ def cli(ctx):
 
     runner = CliRunner()
 
-    # Run the update command
+    # Run the update command in simple mode (legacy mode without git history)
     result = runner.invoke(
         cli,
         [
             "update",
-            files["input_prompt"],
+            "--simple",
             files["modified_code"],
-            "--original-code", files["original_code"],
             "--output", "./output/modified/greeter_updated_python.prompt",
         ],
         catch_exceptions=False,
     )
-    
-    print(f"\nCommand: pdd update {files['input_prompt']} {files['modified_code']} --original-code {files['original_code']}")
+
+    print(f"\nCommand: pdd update --simple {files['modified_code']}")
     print(f"Exit code: {result.exit_code}")
     print(f"Output:\n{result.output}")