Merge pull request #49 from plasma-umass/interface-cleanup

Interface cleanup: wrapper mode default

.github/workflows/regression-check.yml

@@ -25,7 +25,7 @@ jobs:
         python3 -m pip install .
 
     - name: Check prompts
-      run: python3 tests/regression.py --platform ubuntu --check
+      run: python3 -m tests.regression --platform ubuntu --check
 
   check-macos:
     runs-on: macos-latest
@@ -39,7 +39,7 @@ jobs:
         python3 -m pip install .
 
     - name: Check prompts
-      run: python3 tests/regression.py --platform macos --check
+      run: python3 -m tests.regression --platform macos --check
 
   check-windows:
     runs-on: windows-latest
@@ -53,4 +53,4 @@ jobs:
         python3 -m pip install .
 
     - name: Check prompts
-      run: python3 tests/regression.py --platform windows --check
+      run: python3 -m tests.regression --platform windows --check

.github/workflows/regression-generate.yml

@@ -31,7 +31,7 @@ jobs:
         python3 -m pip install .
 
     - name: Generate current prompts
-      run: python3 tests/regression.py --platform ubuntu --generate
+      run: python3 -m tests.regression --platform ubuntu --generate
 
     - name: Commit
       run: |
@@ -58,7 +58,7 @@ jobs:
         python3 -m pip install .
 
     - name: Generate current prompts
-      run: python3 tests/regression.py --platform macos --generate
+      run: python3 -m tests.regression --platform macos --generate
 
     - name: Commit
       run: |
@@ -85,7 +85,7 @@ jobs:
         python3 -m pip install .
 
     - name: Generate current prompts
-      run: python3 tests/regression.py --platform windows --generate
+      run: python3 -m tests.regression --platform windows --generate
 
     - name: Commit
       run: |

.github/workflows/sanity.yml

@@ -16,12 +16,18 @@ jobs:
       - name: Update pip
         run: python3 -m pip install --upgrade pip
 
-      - name: Install
-        run: python3 -m pip install .
+      - name: Install dependencies
+        run: python3 -m pip install mypy
 
       - name: Install in editable mode
         run: python3 -m pip install -e .
 
+      - name: Install in development mode
+        run: python3 -m pip install .[dev]
+
+      - name: Run mypy
+        run: python3 -m mypy src/**/*.py tests/*.py
+
       - name: Check version through Python
         run: python3 -m cwhy --version
 

README.md

@@ -30,26 +30,22 @@ python3 -m pip install cwhy
 
 ## Usage
 
-### Compiler wrapper mode
-
-This new mode is recommended as CWhy will then operate in the same context as the compiler, and will do a better job
-finding the right source files.
+The wrapper mode is now default and mandatory, with a slightly modified interface.
+CWhy can either be used standalone by passing the full command after the triple dashes `---`, or as part of a build tool
+by creating a short executable script wrapping the compiler command.
 
 ```bash
 # Invoking the compiler directly.
-% `cwhy --wrapper` mycode.cpp
-
-# Using fix mode.
-% `cwhy --wrapper fix` mycode.cpp
+% cwhy --- g++ mycode.cpp
 
-# Using cwhy with Java.
-% `cwhy --wrapper --wrapper-compiler=javac` mycode.java
+# Using CWhy with Java and an increased timeout.
+% cwhy --timeout 180 --- javac MyCode.java
 
-# Invoking with GNU make, using GPT-4.
-% CXX=`cwhy --llm=gpt-4 --wrapper` make
+# Invoking with GNU Make, using GPT-3.5.
+% CXX=`cwhy --llm=gpt-3.5-turbo --wrapper --- c++` make
 
 # Invoking with CMake, using GPT-4 and clang++.
-% cmake -DCMAKE_CXX_COMPILER=`cwhy --llm=gpt-4 --wrapper --wrapper-compiler=clang++` ...
+% cmake -DCMAKE_CXX_COMPILER=`cwhy --llm=gpt-4 --wrapper --- clang++` ...
 ```
 
 When running a configuration tool such as CMake or Autoconf, this may greatly increase configuration time, as these
@@ -61,14 +57,6 @@ configuration time.
 % CWHY_DISABLE=1 cmake -DCMAKE_CXX_COMPILER=`cwhy --wrapper` ...
 ```
 
-### Original mode
-
-Just pipe your compiler's output to `cwhy`.
-
-```bash
-% clang++ -g mycode.cpp |& cwhy
-```
-
 ### Options
 
 These options can be displayed with `cwhy --help`.
@@ -77,8 +65,6 @@ These options can be displayed with `cwhy --help`.
  -  `--timeout`: pick a different timeout than the default for API calls.
  -  `--show-prompt` (debug): print prompts before calling the API.
 
-The wrapper mode specifically also has a `--wrapper-compiler` option to select the underlying compiler to use.
-
 ## Examples
 
 ### C++

pyproject.toml

@@ -10,7 +10,7 @@ authors = [
   { name="Nicolas van Kempen", email="[email protected]" },
   { name="Bryce Adelstein Lelbach", email="[email protected]" }
 ]
-dependencies = ["llm_utils==0.2.2", "openai>=1.3.6", "PyYAML>=6.0.1"]
+dependencies = ["llm_utils==0.2.3", "openai>=1.3.6", "PyYAML>=6.0.1", "rich>=13.7.0"]
 description = "Explains and proposes fixes for compile-time errors for many programming languages."
 readme = "README.md"
 requires-python = ">=3.7"
@@ -26,3 +26,6 @@ cwhy = "cwhy.__main__:main"
 [project.urls]
 "Homepage" = "https://github.com/plasma-umass/cwhy"
 "Bug Tracker" = "https://github.com/plasma-umass/cwhy/issues"
+
+[project.optional-dependencies]
+dev = ["types-PyYAML>=6.0.1"]

src/cwhy/__main__.py

@@ -6,56 +6,119 @@
 import sys
 import tempfile
 import textwrap
+from typing import Any, Optional
 
 import openai
+from rich.console import Console
 
 from . import cwhy
 
 
 def wrapper(args):
-    return textwrap.dedent(
-        f"""
-        #! {sys.executable}
-        from cwhy import cwhy
-        cwhy.wrapper({args})
+    return (
+        textwrap.dedent(
+            f"""
+            #! {sys.executable}
+            from cwhy import cwhy
+            cwhy.wrapper({vars(args)})
         """
-    ).lstrip()
+        ).strip()
+        + "\n"
+    )
+
+
+class RichArgParser(argparse.ArgumentParser):
+    def __init__(self, *args: Any, **kwargs: Any):
+        self.console = Console(highlight=False)
+        super().__init__(*args, **kwargs)
+
+    def _print_message(self, message: Optional[str], file: Any = None) -> None:
+        if message:
+            self.console.print(message)
+
+
+class CWhyArgumentFormatter(argparse.HelpFormatter):
+    # RawDescriptionHelpFormatter.
+    def _fill_text(self, text, width, indent):
+        return "".join(indent + line for line in text.splitlines(keepends=True))
+
+    # RawTextHelpFormatter.
+    def _split_lines(self, text, width):
+        return text.splitlines()
+
+    # ArgumentDefaultsHelpFormatter.
+    # Ignore if help message is multiline.
+    def _get_help_string(self, action):
+        help = action.help
+        if "\n" not in help and "%(default)" not in action.help:
+            if action.default is not argparse.SUPPRESS:
+                defaulting_nargs = [argparse.OPTIONAL, argparse.ZERO_OR_MORE]
+                if action.option_strings or action.nargs in defaulting_nargs:
+                    help += " (default: %(default)s)"
+        return help
 
 
 def main():
-    parser = argparse.ArgumentParser(
+    description = textwrap.dedent(
+        rf"""
+            [b]CWhy[/b]: Explains and proposes fixes for compile-time errors for many programming languages.
+            [blue][link=https://github.com/plasma-umass/cwhy]https://github.com/plasma-umass/cwhy[/link][/blue]
+
+            usage:
+                [b]cwhy [SUBCOMMAND] \[OPTIONS...] --- COMMAND...[/b]
+            usage (GNU Make):
+                [b]CXX=`cwhy --wrapper \[OPTIONS...] --- c++` make[/b]
+            usage (CMake):
+                [b]cmake -DCMAKE_CXX_COMPILER=`cwhy --wrapper \[OPTIONS...] --- c++`[/b]
+        """
+    ).strip()
+
+    parser = RichArgParser(
         prog="cwhy",
-        description="CWhy explains and fixes compiler diagnostic errors.",
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
-        add_help=False,
+        usage=argparse.SUPPRESS,
+        description=description,
+        formatter_class=CWhyArgumentFormatter,
     )
 
-    parser.add_argument(
-        "--help",
-        "-h",
-        action="help",
-        default=argparse.SUPPRESS,
-        help="Show this help message and exit.",
-    )
     parser.add_argument(
         "--version",
         action="version",
         version=f"%(prog)s v{importlib.metadata.metadata('cwhy')['Version']}",
         default=argparse.SUPPRESS,
-        help="Print the version of CWhy and exit.",
+        help="print the version of CWhy and exit",
+    )
+
+    parser.add_argument(
+        "subcommand",
+        nargs="?",
+        default="explain",
+        choices=["explain", "diff", "converse"],
+        metavar="subcommand",
+        help=textwrap.dedent(
+            """
+                explain:  explain the diagnostic (default)
+                diff:     \[experimental] generate a diff to fix the diagnostic
+                converse: \[experimental] interactively converse with CWhy
+            """
+        ).strip(),
     )
 
     parser.add_argument(
         "--llm",
         type=str,
         default="default",
-        help="The language model to use, e.g., 'gpt-3.5-turbo' or 'gpt-4'. The default mode tries gpt-4 and falls back to gpt-3.5-turbo.",
+        help=textwrap.dedent(
+            """
+                the language model to use, e.g., 'gpt-3.5-turbo' or 'gpt-4'
+                the default mode tries gpt-4 and falls back to gpt-3.5-turbo
+            """
+        ).strip(),
     )
     parser.add_argument(
         "--timeout",
         type=int,
         default=60,
-        help="The timeout for API calls in seconds.",
+        help="the timeout for API calls in seconds",
     )
     # The default maximum context length for `gpt-3.5-turbo` is 4096 tokens.
     # We keep 256 tokens for other parts of the prompt, and split the remainder in two
@@ -64,44 +127,33 @@ def main():
         "--max-error-tokens",
         type=int,
         default=1920,
-        help="The maximum number of tokens from the error message to send in the prompt.",
+        help="the maximum number of tokens from the error message to send in the prompt",
     )
     parser.add_argument(
         "--max-code-tokens",
         type=int,
         default=1920,
-        help="The maximum number of code locations tokens to send in the prompt.",
+        help="the maximum number of code locations tokens to send in the prompt",
     )
 
     parser.add_argument(
         "--show-prompt",
         action="store_true",
-        help="When enabled, only print prompt and exit (for debugging purposes).",
+        help="when enabled, only print prompt and exit (for debugging purposes)",
     )
     parser.add_argument(
         "--wrapper",
         action="store_true",
-        help="Enable compiler wrapper behavior.",
+        help="generate a temporary executable used to wrap to compiler command",
     )
     parser.add_argument(
-        "--wrapper-compiler",
-        metavar="COMPILER",
-        type=str,
-        default="c++",
-        help="The underlying compiler. Only enabled with --wrapper.",
+        "---",
+        dest="command",
+        required=True,
+        help=argparse.SUPPRESS,
+        nargs=argparse.REMAINDER,
     )
 
-    subparsers = parser.add_subparsers(title="subcommands", dest="subcommand")
-
-    subparsers.add_parser("explain", help="Explain the diagnostic. (default)")
-    subparsers.add_parser("fix", help="Propose a fix for the diagnostic.")
-    subparsers.add_parser("diff", help="[experimental] Propose a fix in diff format.")
-    subparsers.add_parser(
-        "converse", help="[experimental] A back-and-forth mode with ChatGPT."
-    )
-
-    parser.set_defaults(subcommand="explain")
-
     args = parser.parse_args()
 
     if args.wrapper:
@@ -112,14 +164,7 @@ def main():
         os.chmod(f.name, 0o755)
         print(f.name)
     else:
-        stdin = sys.stdin.read()
-        if not stdin:
-            return
-        try:
-            print(cwhy.main(args, stdin))
-        except (openai.NotFoundError, openai.RateLimitError, openai.APITimeoutError):
-            # This type of exceptions should have been handled down the stack.
-            pass
+        cwhy.main(args)
 
 
 if __name__ == "__main__":

src/cwhy/conversation/__init__.py

@@ -15,7 +15,7 @@ def converse(client, args, diagnostic):
         f"""
             You are an assistant debugger. The user is having an issue with their code, and you are trying to help them.
             A few functions exist to help with this process, namely: {", ".join(available_functions_names)}.
-            Once you are confident in your answer, explain the diagnostic and possibly provide a way to fix the issue.
+            Once you are confident in your answer, explain the diagnostic and provide a way to fix the issue if you can.
         """
     ).strip()
     user_message = f"Here is my error message:\n\n```\n{fns.get_truncated_error_message()}\n```\n\nWhat's the problem?"