wcgw 2.6.3__tar.gz → 2.7.1__tar.gz

{wcgw-2.6.3 → wcgw-2.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wcgw
-Version: 2.6.3
+Version: 2.7.1
 Summary: Shell and coding agent on claude and chatgpt
 Project-URL: Homepage, https://github.com/rusiaaman/wcgw
 Author-email: Aman Rusia <gapypi@arcfu.com>
@@ -33,7 +33,7 @@ Description-Content-Type: text/markdown
 - Chatgpt - Allows custom gpt to talk to your shell via a relay server. (linux or mac)
 
 
-⚠️ Warning: do not use this repo if you aren't scared of "Autonomous shell command execution"
+⚠️ Warning: do not allow BashCommand tool without reviewing the command, it may result in data loss.
 
 [![Tests](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml/badge.svg?branch=main)](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml)
 [![Mypy strict](https://github.com/rusiaaman/wcgw/actions/workflows/python-types.yml/badge.svg?branch=main)](https://github.com/rusiaaman/wcgw/actions/workflows/python-types.yml)
@@ -55,7 +55,18 @@ Description-Content-Type: text/markdown
 - ⚡ **Large file edit**: Supports large file incremental edits to avoid token limit issues. Faster than full file write.
 - ⚡ **Syntax checking on edits**: Reports feedback to the LLM if its edits have any syntax errors, so that it can redo it.
 - ⚡ **Interactive Command Handling**: Supports interactive commands using arrow keys, interrupt, and ansi escape sequences.
-- ⚡ **Full Shell Access**: No restrictions, complete control.
+- ⚡ **File protections**: 
+  - The AI needs to read a file at least once before it's allowed to edit or rewrite it. This avoids accidental overwrites. 
+  - Avoids context filling up while reading very large files. Files get chunked based on token length. 
+  - On initialisation the provided workspace's directory structure is returned after selecting important files (based on .gitignore as well as a statistical approach)
+  - File edit based on search-replace tries to find correct search block if it has multiple matches based on previous search blocks. Fails otherwise (for correctness).
+  - File edit has spacing tolerant matching, with warning on issues like indentation mismatch. If there's no match, the closest match is returned to the AI to fix its mistakes.
+  - Using Aider-like search and replace, which has better performance than tool call based search and replace.
+- ⚡ **Shell optimisations**: 
+  - Only one command is allowed to be run at a time, simplifying management and avoiding rogue processes. There's only single shell instance at any point of time.
+  - Current working directory is always returned after any shell command to prevent AI from getting lost. 
+  - Command polling exits after a quick timeout to avoid slow feedback. However, status checking has wait tolerance based on fresh output streaming from a command. Both of these approach combined provides a good shell interaction experience.
+   
 
 ## Top use cases examples
 

{wcgw-2.6.3 → wcgw-2.7.1}/README.md

@@ -4,7 +4,7 @@
 - Chatgpt - Allows custom gpt to talk to your shell via a relay server. (linux or mac)
 
 
-⚠️ Warning: do not use this repo if you aren't scared of "Autonomous shell command execution"
+⚠️ Warning: do not allow BashCommand tool without reviewing the command, it may result in data loss.
 
 [![Tests](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml/badge.svg?branch=main)](https://github.com/rusiaaman/wcgw/actions/workflows/python-tests.yml)
 [![Mypy strict](https://github.com/rusiaaman/wcgw/actions/workflows/python-types.yml/badge.svg?branch=main)](https://github.com/rusiaaman/wcgw/actions/workflows/python-types.yml)
@@ -26,7 +26,18 @@
 - ⚡ **Large file edit**: Supports large file incremental edits to avoid token limit issues. Faster than full file write.
 - ⚡ **Syntax checking on edits**: Reports feedback to the LLM if its edits have any syntax errors, so that it can redo it.
 - ⚡ **Interactive Command Handling**: Supports interactive commands using arrow keys, interrupt, and ansi escape sequences.
-- ⚡ **Full Shell Access**: No restrictions, complete control.
+- ⚡ **File protections**: 
+  - The AI needs to read a file at least once before it's allowed to edit or rewrite it. This avoids accidental overwrites. 
+  - Avoids context filling up while reading very large files. Files get chunked based on token length. 
+  - On initialisation the provided workspace's directory structure is returned after selecting important files (based on .gitignore as well as a statistical approach)
+  - File edit based on search-replace tries to find correct search block if it has multiple matches based on previous search blocks. Fails otherwise (for correctness).
+  - File edit has spacing tolerant matching, with warning on issues like indentation mismatch. If there's no match, the closest match is returned to the AI to fix its mistakes.
+  - Using Aider-like search and replace, which has better performance than tool call based search and replace.
+- ⚡ **Shell optimisations**: 
+  - Only one command is allowed to be run at a time, simplifying management and avoiding rogue processes. There's only single shell instance at any point of time.
+  - Current working directory is always returned after any shell command to prevent AI from getting lost. 
+  - Command polling exits after a quick timeout to avoid slow feedback. However, status checking has wait tolerance based on fresh output streaming from a command. Both of these approach combined provides a good shell interaction experience.
+   
 
 ## Top use cases examples
 

{wcgw-2.6.3 → wcgw-2.7.1}/gpt_action_json_schema.json

@@ -289,6 +289,46 @@
           }
         }
       }
+    },
+    "/v1/context_save": {
+      "post": {
+        "x-openai-isConsequential": false,
+        "summary": "Context Save",
+        "operationId": "context_save_v1_context_save_post",
+        "requestBody": {
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/ContextSaveWithUUID"
+              }
+            }
+          },
+          "required": true
+        },
+        "responses": {
+          "200": {
+            "description": "Successful Response",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "string",
+                  "title": "Response Context Save V1 Context Save Post"
+                }
+              }
+            }
+          },
+          "422": {
+            "description": "Validation Error",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/HTTPValidationError"
+                }
+              }
+            }
+          }
+        }
+      }
     }
   },
   "components": {
@@ -387,6 +427,44 @@
         ],
         "title": "CommandWithUUID"
       },
+      "ContextSaveWithUUID": {
+        "properties": {
+          "id": {
+            "type": "string",
+            "title": "Id"
+          },
+          "project_root_path": {
+            "type": "string",
+            "title": "Project Root Path"
+          },
+          "description": {
+            "type": "string",
+            "title": "Description"
+          },
+          "relevant_file_globs": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array",
+            "title": "Relevant File Globs"
+          },
+          "user_id": {
+            "type": "string",
+            "format": "uuid",
+            "title": "User Id"
+          }
+        },
+        "additionalProperties": false,
+        "type": "object",
+        "required": [
+          "id",
+          "project_root_path",
+          "description",
+          "relevant_file_globs",
+          "user_id"
+        ],
+        "title": "ContextSaveWithUUID"
+      },
       "FileEditWithUUID": {
         "properties": {
           "file_path": {
@@ -438,6 +516,10 @@
             "type": "array",
             "title": "Initial Files To Read"
           },
+          "task_id_to_resume": {
+            "type": "string",
+            "title": "Task Id To Resume"
+          },
           "user_id": {
             "type": "string",
             "format": "uuid",
@@ -449,6 +531,7 @@
         "required": [
           "any_workspace_path",
           "initial_files_to_read",
+          "task_id_to_resume",
           "user_id"
         ],
         "title": "InitializeWithUUID"

{wcgw-2.6.3 → wcgw-2.7.1}/gpt_instructions.txt

@@ -44,6 +44,11 @@ Instructions for `BashInteraction`
 Instructions for `ResetShell`
 - Resets the shell. Use only if all interrupts and prompt reset attempts have failed repeatedly.
 
+Instructions for `ContextSave`
+- Saves provided description and file contents of all the relevant file paths or globs in a single text file.
+  - Provide random unqiue id or whatever user provided.
+  - Leave project path as empty string if no project path
+
 Instructions for `FileEdit`:
     - Use absolute file path only.
     - Use SEARCH/REPLACE blocks to edit the file.

{wcgw-2.6.3 → wcgw-2.7.1}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 authors = [{ name = "Aman Rusia", email = "gapypi@arcfu.com" }]
 name = "wcgw"
-version = "2.6.3"
+version = "2.7.1"
 description = "Shell and coding agent on claude and chatgpt"
 readme = "README.md"
 requires-python = ">=3.11, <3.13"

{wcgw-2.6.3 → wcgw-2.7.1}/src/wcgw/client/anthropic_client.py

@@ -1,59 +1,51 @@
 import base64
 import json
 import mimetypes
-from pathlib import Path
-import sys
+import os
+import subprocess
+import tempfile
 import traceback
-from typing import Callable, DefaultDict, Optional, cast, Literal
-import anthropic
+import uuid
+from pathlib import Path
+from typing import Literal, Optional, cast
+
+import rich
 from anthropic import Anthropic
 from anthropic.types import (
-    ToolParam,
+    ImageBlockParam,
     MessageParam,
+    TextBlockParam,
+    ToolParam,
     ToolResultBlockParam,
     ToolUseBlockParam,
-    ImageBlockParam,
-    TextBlockParam,
 )
-
-import rich
-import petname  # type: ignore[import-untyped]
+from dotenv import load_dotenv
 from typer import Typer
-import uuid
 
 from ..types_ import (
     BashCommand,
     BashInteraction,
-    WriteIfEmpty,
-    FileEditFindReplace,
+    ContextSave,
     FileEdit,
+    GetScreenInfo,
     Keyboard,
     Mouse,
     ReadFiles,
     ReadImage,
     ResetShell,
     ScreenShot,
-    GetScreenInfo,
+    WriteIfEmpty,
+)
+from .common import discard_input
+from .memory import load_memory
+from .tools import (
+    DoneFlag,
+    ImageData,
+    default_enc,
+    get_tool_output,
+    initialize,
+    which_tool_name,
 )
-
-from .common import Models, discard_input
-from .common import CostData
-from .tools import ImageData
-from .computer_use import Computer
-
-from .tools import DoneFlag, get_tool_output, which_tool_name, default_enc
-
-from urllib import parse
-import subprocess
-import os
-import tempfile
-
-import toml
-from pydantic import BaseModel
-
-
-from dotenv import load_dotenv
-
 
 History = list[MessageParam]
 
@@ -135,19 +127,28 @@ def loop(
 
     history: History = []
     waiting_for_assistant = False
+    memory = None
     if resume:
-        if resume == "latest":
-            resume_path = sorted(Path(".wcgw").iterdir(), key=os.path.getmtime)[-1]
-        else:
-            resume_path = Path(resume)
-        if not resume_path.exists():
-            raise FileNotFoundError(f"File {resume} not found")
-        with resume_path.open() as f:
-            history = json.load(f)
-        if len(history) <= 2:
-            raise ValueError("Invalid history file")
-        first_message = ""
-        waiting_for_assistant = history[-1]["role"] != "assistant"
+        try:
+            _, memory = load_memory(
+                resume,
+                8000,
+                lambda x: default_enc.encode(x).ids,
+                lambda x: default_enc.decode(x),
+            )
+        except OSError:
+            if resume == "latest":
+                resume_path = sorted(Path(".wcgw").iterdir(), key=os.path.getmtime)[-1]
+            else:
+                resume_path = Path(resume)
+            if not resume_path.exists():
+                raise FileNotFoundError(f"File {resume} not found")
+            with resume_path.open() as f:
+                history = json.load(f)
+            if len(history) <= 2:
+                raise ValueError("Invalid history file")
+            first_message = ""
+            waiting_for_assistant = history[-1]["role"] != "assistant"
 
     limit = 1
 
@@ -216,6 +217,15 @@ def loop(
 - Use absolute file path only.
 - Use SEARCH/REPLACE blocks to edit the file.
 - If the edit fails due to block not matching, please retry with correct block till it matches. Re-read the file to ensure you've all the lines correct.
+""",
+        ),
+        ToolParam(
+            input_schema=ContextSave.model_json_schema(),
+            name="ContextSave",
+            description="""
+Saves provided description and file contents of all the relevant file paths or globs in a single text file.
+- Provide random unqiue id or whatever user provided.
+- Leave project path as empty string if no project path
 """,
         ),
     ]
@@ -270,9 +280,10 @@ def loop(
 """,
             ),
         ]
-    uname_sysname = os.uname().sysname
-    uname_machine = os.uname().machine
 
+    initial_info = initialize(
+        os.getcwd(), [], resume if (memory and resume) else "", 8000
+    )
     system = f"""
 You're an expert software engineer with shell and code knowledge.
 
@@ -284,10 +295,7 @@ Instructions:
     - Do not provide code snippets unless asked by the user, instead directly add/edit the code.
     - Do not install new tools/packages before ensuring no such tools/package or an alternative already exists.
 
-System information:
-    - System: {uname_sysname}
-    - Machine: {uname_machine}
-    - Current directory: {os.getcwd()}
+{initial_info}
 """
 
     with open(os.path.join(os.path.dirname(__file__), "diff-instructions.txt")) as f:

{wcgw-2.6.3 → wcgw-2.7.1}/src/wcgw/client/diff-instructions.txt

@@ -47,7 +47,6 @@ Every *SEARCH/REPLACE block* must use this format:
 
 Every "<<<<<<< SEARCH" section must *EXACTLY MATCH* the existing file content, character for character, including all comments, docstrings, whitespaces, etc.
 
-*SEARCH/REPLACE* blocks will *only* replace the first match occurrence.
 Including multiple unique *SEARCH/REPLACE* blocks if needed.
 Include enough lines in each SEARCH section to uniquely match each set of lines that need to change.