wcgw 2.4.2__py3-none-any.whl → 2.5.0__py3-none-any.whl

wcgw/client/anthropic_client.py

@@ -29,7 +29,7 @@ from ..types_ import (
     FileEdit,
     Keyboard,
     Mouse,
-    ReadFile,
+    ReadFiles,
     ReadImage,
     ResetShell,
     ScreenShot,
@@ -41,12 +41,7 @@ from .common import CostData
 from .tools import ImageData
 from .computer_use import Computer
 
-from .tools import (
-    DoneFlag,
-    get_tool_output,
-    which_tool_name,
-)
-import tiktoken
+from .tools import DoneFlag, get_tool_output, which_tool_name, default_enc
 
 from urllib import parse
 import subprocess
@@ -156,10 +151,6 @@ def loop(
 
     limit = 1
 
-    enc = tiktoken.encoding_for_model(
-        "gpt-4o-2024-08-06",
-    )
-
     tools = [
         ToolParam(
             input_schema=BashCommand.model_json_schema(),
@@ -192,12 +183,11 @@ def loop(
 """,
         ),
         ToolParam(
-            input_schema=ReadFile.model_json_schema(),
-            name="ReadFile",
+            input_schema=ReadFiles.model_json_schema(),
+            name="ReadFiles",
             description="""
-- Read full file content
-- Provide absolute file path only
-- Use this instead of 'cat' from BashCommand
+- Read full file content of one or more files.
+- Provide absolute file paths only
 """,
         ),
         ToolParam(
@@ -451,7 +441,7 @@ System information:
                             try:
                                 output_or_dones, _ = get_tool_output(
                                     tool_parsed,
-                                    enc,
+                                    default_enc,
                                     limit - cost,
                                     loop,
                                     max_tokens=8000,

wcgw/client/common.py

@@ -38,7 +38,9 @@ def discard_input() -> None:
             while True:
                 # Check if there is input to be read
                 if sys.stdin in select.select([sys.stdin], [], [], 0)[0]:
-                    sys.stdin.read(1)  # Read one character at a time to flush the input buffer
+                    sys.stdin.read(
+                        1
+                    )  # Read one character at a time to flush the input buffer
                 else:
                     break
         finally:

wcgw/client/mcp_server/server.py

@@ -21,7 +21,7 @@ from ...types_ import (
     FileEdit,
     Keyboard,
     Mouse,
-    ReadFile,
+    ReadFiles,
     ReadImage,
     ResetShell,
     Initialize,
@@ -76,7 +76,7 @@ async def handle_list_tools() -> list[types.Tool]:
             inputSchema=Initialize.model_json_schema(),
             name="Initialize",
             description="""
-- Always call this at the start of the conversation before anything else.
+- Always call this at the start of the conversation before using any of the shell tools from wcgw.
 """,
         ),
         ToolParam(
@@ -92,6 +92,7 @@ async def handle_list_tools() -> list[types.Tool]:
 - The control will return to you in {SLEEP_TIME_MAX_S} seconds regardless of the status. For heavy commands, keep checking status using BashInteraction till they are finished.
 - Run long running commands in background using screen instead of "&".
 - Use longer wait_for_seconds if the command is expected to run for a long time.
+- Do not use 'cat' to read files, use ReadFiles tool instead.
 """,
         ),
         ToolParam(
@@ -110,12 +111,11 @@ async def handle_list_tools() -> list[types.Tool]:
 """,
         ),
         ToolParam(
-            inputSchema=ReadFile.model_json_schema(),
-            name="ReadFile",
+            inputSchema=ReadFiles.model_json_schema(),
+            name="ReadFiles",
             description="""
-- Read full file content
-- Provide absolute file path only
-- Use this instead of 'cat' from BashCommand
+- Read full file content of one or more files.
+- Provide absolute file paths only
 """,
         ),
         ToolParam(

wcgw/client/openai_client.py

@@ -17,6 +17,7 @@ from openai.types.chat import (
 )
 import rich
 import petname  # type: ignore[import-untyped]
+import tokenizers  # type: ignore[import-untyped]
 from typer import Typer
 import uuid
 
@@ -26,7 +27,7 @@ from ..types_ import (
     WriteIfEmpty,
     FileEdit,
     ReadImage,
-    ReadFile,
+    ReadFiles,
     ResetShell,
 )
 
@@ -40,7 +41,6 @@ from .tools import (
     get_tool_output,
     which_tool,
 )
-import tiktoken
 
 from urllib import parse
 import subprocess
@@ -160,9 +160,7 @@ def loop(
         config.cost_limit = limit
     limit = config.cost_limit
 
-    enc = tiktoken.encoding_for_model(
-        config.model if not config.model.startswith("o1") else "gpt-4o"
-    )
+    enc = tokenizers.Tokenizer.from_pretrained("Xenova/gpt-4o")
 
     tools = [
         openai.pydantic_function_tool(
@@ -188,11 +186,10 @@ def loop(
 - Only one of send_text, send_specials, send_ascii should be provided.""",
         ),
         openai.pydantic_function_tool(
-            ReadFile,
+            ReadFiles,
             description="""
-- Read full file content
-- Provide absolute file path only
-- Use this instead of 'cat' from BashCommand
+- Read full file content of one or more files.
+- Provide absolute file paths only
 """,
         ),
         openai.pydantic_function_tool(

wcgw/client/openai_utils.py

@@ -15,7 +15,7 @@ from openai.types.chat import (
     ParsedChatCompletionMessage,
 )
 import rich
-import tiktoken
+from tokenizers import Tokenizer  # type: ignore[import-untyped]
 from typer import Typer
 import uuid
 
@@ -23,7 +23,7 @@ from .common import CostData, History
 
 
 def get_input_cost(
-    cost_map: CostData, enc: tiktoken.Encoding, history: History
+    cost_map: CostData, enc: Tokenizer, history: History
 ) -> tuple[float, int]:
     input_tokens = 0
     for msg in history:
@@ -31,8 +31,8 @@ def get_input_cost(
         refusal = msg.get("refusal")
         if isinstance(content, list):
             for part in content:
-                if 'text' in part:
-                    input_tokens += len(enc.encode(part['text']))
+                if "text" in part:
+                    input_tokens += len(enc.encode(part["text"]))
         elif content is None:
             if refusal is None:
                 raise ValueError("Expected content or refusal to be present")
@@ -47,7 +47,7 @@ def get_input_cost(
 
 def get_output_cost(
     cost_map: CostData,
-    enc: tiktoken.Encoding,
+    enc: Tokenizer,
     item: ChatCompletionMessage | ChatCompletionMessageParam,
 ) -> tuple[float, int]:
     if isinstance(item, ChatCompletionMessage):

wcgw/client/tools.py

@@ -19,14 +19,14 @@ from typing import (
     TypeVar,
 )
 import uuid
-import humanize
+
 from pydantic import BaseModel, TypeAdapter
 import typer
 from .computer_use import run_computer_tool
 from websockets.sync.client import connect as syncconnect
 
 import os
-import tiktoken
+import tokenizers  # type: ignore
 import pexpect
 from typer import Typer
 import websockets
@@ -47,7 +47,7 @@ from ..types_ import (
     FileEditFindReplace,
     FileEdit,
     Initialize,
-    ReadFile,
+    ReadFiles,
     ReadImage,
     ResetShell,
     Mouse,
@@ -259,9 +259,17 @@ class BashState:
     def get_pending_for(self) -> str:
         if isinstance(self._state, datetime.datetime):
             timedelta = datetime.datetime.now() - self._state
-            return humanize.naturaldelta(
-                timedelta + datetime.timedelta(seconds=TIMEOUT)
+            return (
+                str(
+                    int(
+                        (
+                            timedelta + datetime.timedelta(seconds=TIMEOUT)
+                        ).total_seconds()
+                    )
+                )
+                + " seconds"
             )
+
         return "Not pending"
 
     @property
@@ -279,16 +287,24 @@ class BashState:
 BASH_STATE = BashState()
 
 
-def initial_info() -> str:
+def initialize(workspace_dir: str = "") -> str:
+    reset_shell()
+    if workspace_dir:
+        BASH_STATE.shell.sendline(f"cd {shlex.quote(workspace_dir)}")
+        BASH_STATE.shell.expect(PROMPT, timeout=0.2)
+        BASH_STATE.update_cwd()
+
     uname_sysname = os.uname().sysname
     uname_machine = os.uname().machine
-    return f"""
+
+    output = f"""
 System: {uname_sysname}
 Machine: {uname_machine}
 Current working directory: {BASH_STATE.cwd}
-wcgw version: {importlib.metadata.version("wcgw")}
 """
 
+    return output
+
 
 def reset_shell() -> str:
     BASH_STATE.reset()
@@ -345,29 +361,11 @@ def get_status() -> str:
 T = TypeVar("T")
 
 
-def save_out_of_context(
-    tokens: list[T],
-    max_tokens: int,
-    suffix: str,
-    tokens_converted: Callable[[list[T]], str],
-) -> tuple[str, list[Path]]:
-    file_contents = list[str]()
-    for i in range(0, len(tokens), max_tokens):
-        file_contents.append(tokens_converted(tokens[i : i + max_tokens]))
-
-    if len(file_contents) == 1:
-        return file_contents[0], []
-
-    rest_paths = list[Path]()
-    for i, content in enumerate(file_contents):
-        if i == 0:
-            continue
-        file_path = NamedTemporaryFile(delete=False, suffix=suffix).name
-        with open(file_path, "w") as f:
-            f.write(content)
-        rest_paths.append(Path(file_path))
-
-    return file_contents[0], rest_paths
+def save_out_of_context(content: str, suffix: str) -> str:
+    file_path = NamedTemporaryFile(delete=False, suffix=suffix).name
+    with open(file_path, "w") as f:
+        f.write(content)
+    return file_path
 
 
 def rstrip(lines: list[str]) -> str:
@@ -397,8 +395,14 @@ def _incremental_text(text: str, last_pending_output: str) -> str:
     return rstrip(rendered)
 
 
+def is_status_check(arg: BashInteraction | BashCommand) -> bool:
+    return isinstance(arg, BashInteraction) and (
+        arg.send_specials == ["Enter"] or arg.send_ascii == [10]
+    )
+
+
 def execute_bash(
-    enc: tiktoken.Encoding,
+    enc: tokenizers.Tokenizer,
     bash_arg: BashCommand | BashInteraction,
     max_tokens: Optional[int],
     timeout_s: Optional[float],
@@ -428,7 +432,9 @@ def execute_bash(
                     "Command should not contain newline character in middle. Run only one command at a time."
                 )
 
-            BASH_STATE.shell.sendline(command)
+            for i in range(0, len(command), 128):
+                BASH_STATE.shell.send(command[i : i + 128])
+            BASH_STATE.shell.send(BASH_STATE.shell.linesep)
 
         else:
             if (
@@ -491,7 +497,9 @@ def execute_bash(
                         0,
                     )
                 console.print(f"Interact text: {bash_arg.send_text}")
-                BASH_STATE.shell.sendline(bash_arg.send_text)
+                for i in range(0, len(bash_arg.send_text), 128):
+                    BASH_STATE.shell.send(bash_arg.send_text[i : i + 128])
+                BASH_STATE.shell.send(BASH_STATE.shell.linesep)
 
     except KeyboardInterrupt:
         BASH_STATE.shell.sendintr()
@@ -505,13 +513,14 @@ def execute_bash(
         incremental_text = _incremental_text(text, BASH_STATE.pending_output)
 
         second_wait_success = False
-        if incremental_text and isinstance(bash_arg, BashInteraction):
+        if is_status_check(bash_arg):
             # There's some text in BashInteraction mode wait for TIMEOUT_WHILE_OUTPUT
             remaining = TIMEOUT_WHILE_OUTPUT - wait
             patience = OUTPUT_WAIT_PATIENCE
+            if not incremental_text:
+                patience -= 1
             itext = incremental_text
             while remaining > 0 and patience > 0:
-                print(remaining, TIMEOUT_WHILE_OUTPUT)
                 index = BASH_STATE.shell.expect([PROMPT, pexpect.TIMEOUT], timeout=wait)
                 if index == 0:
                     second_wait_success = True
@@ -538,7 +547,7 @@ def execute_bash(
 
             if max_tokens and len(tokens) >= max_tokens:
                 incremental_text = "(...truncated)\n" + enc.decode(
-                    tokens[-(max_tokens - 1) :]
+                    tokens.ids[-(max_tokens - 1) :]
                 )
 
             if is_interrupt:
@@ -562,12 +571,9 @@ def execute_bash(
     output = _incremental_text(BASH_STATE.shell.before, BASH_STATE.pending_output)
     BASH_STATE.set_repl()
 
-    if is_interrupt:
-        return "Interrupt successful", 0.0
-
     tokens = enc.encode(output)
     if max_tokens and len(tokens) >= max_tokens:
-        output = "(...truncated)\n" + enc.decode(tokens[-(max_tokens - 1) :])
+        output = "(...truncated)\n" + enc.decode(tokens.ids[-(max_tokens - 1) :])
 
     try:
         exit_status = get_status()
@@ -627,6 +633,19 @@ def ensure_no_previous_output(func: Callable[Param, T]) -> Callable[Param, T]:
     return wrapper
 
 
+def truncate_if_over(content: str, max_tokens: Optional[int]) -> str:
+    if max_tokens and max_tokens > 0:
+        tokens = default_enc.encode(content)
+        n_tokens = len(tokens)
+        if n_tokens > max_tokens:
+            content = (
+                default_enc.decode(tokens.ids[: max(0, max_tokens - 100)])
+                + "\n(...truncated)"
+            )
+
+    return content
+
+
 def read_image_from_shell(file_path: str) -> ImageData:
     if not os.path.isabs(file_path):
         file_path = os.path.join(BASH_STATE.cwd, file_path)
@@ -655,7 +674,25 @@ def read_image_from_shell(file_path: str) -> ImageData:
             return ImageData(media_type=image_type, data=image_b64)  # type: ignore
 
 
-def write_file(writefile: WriteIfEmpty, error_on_exist: bool) -> str:
+def get_context_for_errors(
+    errors: list[tuple[int, int]], file_content: str, max_tokens: Optional[int]
+) -> str:
+    file_lines = file_content.split("\n")
+    min_line_num = max(0, min([error[0] for error in errors]) - 10)
+    max_line_num = min(len(file_lines), max([error[0] for error in errors]) + 10)
+    context_lines = file_lines[min_line_num:max_line_num]
+    context = "\n".join(context_lines)
+
+    if max_tokens is not None and max_tokens > 0:
+        ntokens = len(default_enc.encode(context))
+        if ntokens > max_tokens:
+            return "Please re-read the file to understand the context"
+    return f"Here's relevant snippet from the file where the syntax errors occured:\n```\n{context}\n```"
+
+
+def write_file(
+    writefile: WriteIfEmpty, error_on_exist: bool, max_tokens: Optional[int]
+) -> str:
     if not os.path.isabs(writefile.file_path):
         return f"Failure: file_path should be absolute path, current working directory is {BASH_STATE.cwd}"
     else:
@@ -667,9 +704,14 @@ def write_file(writefile: WriteIfEmpty, error_on_exist: bool) -> str:
         if (error_on_exist or error_on_exist_) and os.path.exists(path_):
             content = Path(path_).read_text().strip()
             if content:
+                content = truncate_if_over(content, max_tokens)
+
                 if error_on_exist_:
-                    return f"Error: can't write to existing file {path_}, use other functions to edit the file"
-                elif error_on_exist:
+                    return (
+                        f"Error: can't write to existing file {path_}, use other functions to edit the file"
+                        + f"\nHere's the existing content:\n```\n{content}\n```"
+                    )
+                else:
                     add_overwrite_warning = content
 
         # Since we've already errored once, add this to whitelist
@@ -690,8 +732,13 @@ def write_file(writefile: WriteIfEmpty, error_on_exist: bool) -> str:
                 timeout=TIMEOUT,
             )
             if return_code != 0 and content.strip():
+                content = truncate_if_over(content, max_tokens)
+
                 if error_on_exist_:
-                    return f"Error: can't write to existing file {path_}, use other functions to edit the file"
+                    return (
+                        f"Error: can't write to existing file {path_}, use other functions to edit the file"
+                        + f"\nHere's the existing content:\n```\n{content}\n```"
+                    )
                 else:
                     add_overwrite_warning = content
 
@@ -724,13 +771,19 @@ def write_file(writefile: WriteIfEmpty, error_on_exist: bool) -> str:
     try:
         check = check_syntax(extension, writefile.file_content)
         syntax_errors = check.description
+
         if syntax_errors:
+            context_for_errors = get_context_for_errors(
+                check.errors, writefile.file_content, max_tokens
+            )
             console.print(f"W: Syntax errors encountered: {syntax_errors}")
             warnings.append(f"""
 ---
-Warning: tree-sitter reported syntax errors, please re-read the file and fix if any errors. 
-Errors:
+Warning: tree-sitter reported syntax errors
+Syntax errors:
 {syntax_errors}
+
+{context_for_errors}
 ---
             """)
 
@@ -740,8 +793,10 @@ Errors:
     if add_overwrite_warning:
         warnings.append(
             "\n---\nWarning: a file already existed and it's now overwritten. Was it a mistake? If yes please revert your action."
-            "Here's the previous content:\n```\n" + add_overwrite_warning + "\n```"
             "\n---\n"
+            + "Here's the previous content:\n```\n"
+            + add_overwrite_warning
+            + "\n```"
         )
 
     return "Success" + "".join(warnings)
@@ -867,9 +922,9 @@ def edit_content(content: str, find_lines: str, replace_with_lines: str) -> str:
     )
 
 
-def do_diff_edit(fedit: FileEdit) -> str:
+def do_diff_edit(fedit: FileEdit, max_tokens: Optional[int]) -> str:
     try:
-        return _do_diff_edit(fedit)
+        return _do_diff_edit(fedit, max_tokens)
     except Exception as e:
         # Try replacing \"
         try:
@@ -879,13 +934,13 @@ def do_diff_edit(fedit: FileEdit) -> str:
                     '\\"', '"'
                 ),
             )
-            return _do_diff_edit(fedit)
+            return _do_diff_edit(fedit, max_tokens)
         except Exception:
             pass
         raise e
 
 
-def _do_diff_edit(fedit: FileEdit) -> str:
+def _do_diff_edit(fedit: FileEdit, max_tokens: Optional[int]) -> str:
     console.log(f"Editing file: {fedit.file_path}")
 
     if not os.path.isabs(fedit.file_path):
@@ -984,13 +1039,19 @@ def _do_diff_edit(fedit: FileEdit) -> str:
         check = check_syntax(extension, apply_diff_to)
         syntax_errors = check.description
         if syntax_errors:
+            context_for_errors = get_context_for_errors(
+                check.errors, apply_diff_to, max_tokens
+            )
+
             console.print(f"W: Syntax errors encountered: {syntax_errors}")
             return f"""Wrote file succesfully.
 ---
 However, tree-sitter reported syntax errors, please re-read the file and fix if there are any errors.
-Errors:
+Syntax errors:
 {syntax_errors}
-            """
+
+{context_for_errors}
+"""
     except Exception:
         pass
 
@@ -1030,7 +1091,7 @@ TOOLS = (
     | AIAssistant
     | DoneFlag
     | ReadImage
-    | ReadFile
+    | ReadFiles
     | Initialize
     | Mouse
     | Keyboard
@@ -1065,8 +1126,8 @@ def which_tool_name(name: str) -> Type[TOOLS]:
         return DoneFlag
     elif name == "ReadImage":
         return ReadImage
-    elif name == "ReadFile":
-        return ReadFile
+    elif name == "ReadFiles":
+        return ReadFiles
     elif name == "Initialize":
         return Initialize
     elif name == "Mouse":
@@ -1086,7 +1147,7 @@ TOOL_CALLS: list[TOOLS] = []
 
 def get_tool_output(
     args: dict[object, object] | TOOLS,
-    enc: tiktoken.Encoding,
+    enc: tokenizers.Tokenizer,
     limit: float,
     loop_call: Callable[[str, float], tuple[str, float]],
     max_tokens: Optional[int],
@@ -1107,10 +1168,10 @@ def get_tool_output(
         output = execute_bash(enc, arg, max_tokens, arg.wait_for_seconds)
     elif isinstance(arg, WriteIfEmpty):
         console.print("Calling write file tool")
-        output = write_file(arg, True), 0
+        output = write_file(arg, True, max_tokens), 0
     elif isinstance(arg, FileEdit):
         console.print("Calling full file edit tool")
-        output = do_diff_edit(arg), 0.0
+        output = do_diff_edit(arg, max_tokens), 0.0
     elif isinstance(arg, DoneFlag):
         console.print("Calling mark finish tool")
         output = mark_finish(arg), 0.0
@@ -1120,17 +1181,15 @@ def get_tool_output(
     elif isinstance(arg, ReadImage):
         console.print("Calling read image tool")
         output = read_image_from_shell(arg.file_path), 0.0
-    elif isinstance(arg, ReadFile):
+    elif isinstance(arg, ReadFiles):
         console.print("Calling read file tool")
-        output = read_file(arg, max_tokens), 0.0
+        output = read_files(arg.file_paths, max_tokens), 0.0
     elif isinstance(arg, ResetShell):
         console.print("Calling reset shell tool")
         output = reset_shell(), 0.0
     elif isinstance(arg, Initialize):
         console.print("Calling initial info tool")
-        # First force reset
-        reset_shell()
-        output = initial_info(), 0.0
+        output = initialize(), 0.0
     elif isinstance(arg, (Mouse, Keyboard, ScreenShot, GetScreenInfo)):
         console.print(f"Calling {type(arg).__name__} tool")
         outputs_cost = run_computer_tool(arg), 0.0
@@ -1179,7 +1238,9 @@ def get_tool_output(
 
 History = list[ChatCompletionMessageParam]
 
-default_enc = tiktoken.encoding_for_model("gpt-4o")
+default_enc: tokenizers.Tokenizer = tokenizers.Tokenizer.from_pretrained(
+    "Xenova/claude-tokenizer"
+)
 curr_cost = 0.0
 
 
@@ -1192,7 +1253,7 @@ class Mdata(BaseModel):
         | FileEditFindReplace
         | FileEdit
         | str
-        | ReadFile
+        | ReadFiles
         | Initialize
     )
 
@@ -1265,43 +1326,69 @@ def app(
     register_client(server_url, client_uuid or "")
 
 
-def read_file(readfile: ReadFile, max_tokens: Optional[int]) -> str:
-    console.print(f"Reading file: {readfile.file_path}")
+def read_files(file_paths: list[str], max_tokens: Optional[int]) -> str:
+    message = ""
+    for i, file in enumerate(file_paths):
+        try:
+            content, truncated, tokens = read_file(file, max_tokens)
+        except ValueError as e:
+            message += f"\n{file}: {str(e)}\n"
+            continue
+
+        if max_tokens:
+            max_tokens = max_tokens - tokens
+
+        message += f"\n``` {file}\n{content}\n"
+
+        if truncated or (max_tokens and max_tokens <= 0):
+            not_reading = file_paths[i + 1 :]
+            if not_reading:
+                message += f'\nNot reading the rest of the files: {", ".join(not_reading)} due to token limit, please call again'
+            break
+        else:
+            message += "```"
+
+    return message
 
-    if not os.path.isabs(readfile.file_path):
-        return f"Failure: file_path should be absolute path, current working directory is {BASH_STATE.cwd}"
 
-    BASH_STATE.add_to_whitelist_for_overwrite(readfile.file_path)
+def read_file(file_path: str, max_tokens: Optional[int]) -> tuple[str, bool, int]:
+    console.print(f"Reading file: {file_path}")
+
+    if not os.path.isabs(file_path):
+        raise ValueError(
+            f"Failure: file_path should be absolute path, current working directory is {BASH_STATE.cwd}"
+        )
+
+    BASH_STATE.add_to_whitelist_for_overwrite(file_path)
 
     if not BASH_STATE.is_in_docker:
-        path = Path(readfile.file_path)
+        path = Path(file_path)
         if not path.exists():
-            return f"Error: file {readfile.file_path} does not exist"
+            raise ValueError(f"Error: file {file_path} does not exist")
 
         with path.open("r") as f:
-            content = f.read()
+            content = f.read(10_000_000)
 
     else:
         return_code, content, stderr = command_run(
-            f"docker exec {BASH_STATE.is_in_docker} cat {shlex.quote(readfile.file_path)}",
+            f"docker exec {BASH_STATE.is_in_docker} cat {shlex.quote(file_path)}",
             timeout=TIMEOUT,
         )
         if return_code != 0:
             raise Exception(
-                f"Error: cat {readfile.file_path} failed with code {return_code}\nstdout: {content}\nstderr: {stderr}"
+                f"Error: cat {file_path} failed with code {return_code}\nstdout: {content}\nstderr: {stderr}"
             )
 
+    truncated = False
+    tokens_counts = 0
     if max_tokens is not None:
         tokens = default_enc.encode(content)
+        tokens_counts = len(tokens)
         if len(tokens) > max_tokens:
-            content, rest = save_out_of_context(
-                tokens,
-                max_tokens - 100,
-                Path(readfile.file_path).suffix,
-                default_enc.decode,
+            content = default_enc.decode(tokens.ids[:max_tokens])
+            rest = save_out_of_context(
+                default_enc.decode(tokens.ids[max_tokens:]), Path(file_path).suffix
             )
-            if rest:
-                rest_ = "\n".join(map(str, rest))
-                content += f"\n(...truncated)\n---\nI've split the rest of the file into multiple files. Here are the remaining splits, please read them:\n{rest_}"
-
-    return content
+            content += f"\n(...truncated)\n---\nI've saved the continuation in a new file. Please read: `{rest}`"
+            truncated = True
+    return content, truncated, tokens_counts

wcgw/relay/serve.py

@@ -21,7 +21,7 @@ from ..types_ import (
     FileEditFindReplace,
     FileEdit,
     Initialize,
-    ReadFile,
+    ReadFiles,
     ResetShell,
     Specials,
 )
@@ -35,7 +35,7 @@ class Mdata(BaseModel):
         | ResetShell
         | FileEditFindReplace
         | FileEdit
-        | ReadFile
+        | ReadFiles
         | Initialize
         | str
     )
@@ -259,7 +259,7 @@ async def bash_interaction(bash_interaction: BashInteractionWithUUID) -> str:
     raise fastapi.HTTPException(status_code=500, detail="Timeout error")
 
 
-class ReadFileWithUUID(ReadFile):
+class ReadFileWithUUID(ReadFiles):
     user_id: UUID
 
 

wcgw/types_.py

@@ -31,9 +31,9 @@ class WriteIfEmpty(BaseModel):
     file_content: str
 
 
-class ReadFile(BaseModel):
-    file_path: str  # The path to the file to read
-    type: Literal["ReadFile"]
+class ReadFiles(BaseModel):
+    file_paths: list[str]
+    type: Literal["ReadFiles"]
 
 
 class FileEditFindReplace(BaseModel):

{wcgw-2.4.2.dist-info → wcgw-2.5.0.dist-info}/METADATA

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: wcgw
-Version: 2.4.2
+Version: 2.5.0
 Summary: Shell and coding agent on claude and chatgpt
 Project-URL: Homepage, https://github.com/rusiaaman/wcgw
 Author-email: Aman Rusia <gapypi@arcfu.com>
+License-File: LICENSE
 Requires-Python: <3.13,>=3.11
 Requires-Dist: anthropic>=0.39.0
 Requires-Dist: fastapi>=0.115.0
-Requires-Dist: humanize>=4.11.0
 Requires-Dist: openai>=1.46.0
 Requires-Dist: petname>=2.6
 Requires-Dist: pexpect>=4.9.0
@@ -18,7 +18,7 @@ Requires-Dist: rich>=13.8.1
 Requires-Dist: semantic-version>=2.10.0
 Requires-Dist: shell>=1.0.1
 Requires-Dist: syntax-checker==0.2.10
-Requires-Dist: tiktoken==0.7.0
+Requires-Dist: tokenizers>=0.21.0
 Requires-Dist: toml>=0.10.2
 Requires-Dist: typer>=0.12.5
 Requires-Dist: types-pexpect>=4.9.0.20240806

{wcgw-2.4.2.dist-info → wcgw-2.5.0.dist-info}/RECORD

@@ -1,20 +1,20 @@
 wcgw/__init__.py,sha256=9K2QW7QuSLhMTVbKbBYd9UUp-ZyrfBrxcjuD_xk458k,118
-wcgw/types_.py,sha256=9h0-UKS4emx12eI24VSfgvz8WW0p5hwxFwzq8Wvbk6w,1858
+wcgw/types_.py,sha256=NDWBfzmR89-L7rFuf-9PeCF3jZuQ-WWMLbRVP-qlnJw,1835
 wcgw/client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wcgw/client/__main__.py,sha256=wcCrL4PjG51r5wVKqJhcoJPTLfHW0wNbD31DrUN0MWI,28
-wcgw/client/anthropic_client.py,sha256=ymMi2Kmkcso_6PT8iuwsqLz4Ne6oTvId3OWBB4La3gc,21147
+wcgw/client/anthropic_client.py,sha256=kmS93LEVwXCppfbgCsfWe_SVmTAtsI3x8PrP8DJDYMY,21041
 wcgw/client/cli.py,sha256=-z0kpDAW3mzfQrQeZfaVJhBCAQY3HXnt9GdgQ8s-u0Y,1003
-wcgw/client/common.py,sha256=grH-yV_4tnTQZ29xExn4YicGLxEq98z-HkEZwH0ReSg,1410
+wcgw/client/common.py,sha256=OCH7Tx64jojz3M3iONUrGMadE07W21DiZs5sOxWX1Qc,1456
 wcgw/client/computer_use.py,sha256=35NKAlMrxwD0TBlMMRnbCwz4g8TBRGOlcy-cmS-yJ_A,15247
 wcgw/client/diff-instructions.txt,sha256=s5AJKG23JsjwRYhFZFQVvwDpF67vElawrmdXwvukR1A,1683
-wcgw/client/openai_client.py,sha256=uJ2l9NXsZuipUcJYR_bFcNNmNlfnCvPm6-M-LiVSVts,17942
-wcgw/client/openai_utils.py,sha256=YNwCsA-Wqq7jWrxP0rfQmBTb1dI0s7dWXzQqyTzOZT4,2629
+wcgw/client/openai_client.py,sha256=hAoUF4wcD0LqqX9MjqWZux12_HH0EdVognNcRLG6pew,17903
+wcgw/client/openai_utils.py,sha256=KfMB1-p2zDiA7pPWwAVarochf7-qeL1UMgtlDV9DtKA,2662
 wcgw/client/sys_utils.py,sha256=GajPntKhaTUMn6EOmopENWZNR2G_BJyuVbuot0x6veI,1376
-wcgw/client/tools.py,sha256=ZLUlVDS-G-_UId5nJoeXINlvjvP2DUGLuTAFmHTDUvw,44131
+wcgw/client/tools.py,sha256=HO4xO0D7oxYJGeof0O-GIADc9UkoPwRbmyh9SgAWTMw,47079
 wcgw/client/mcp_server/Readme.md,sha256=I8N4dHkTUVGNQ63BQkBMBhCCBTgqGOSF_pUR6iOEiUk,2495
 wcgw/client/mcp_server/__init__.py,sha256=hyPPwO9cabAJsOMWhKyat9yl7OlSmIobaoAZKHu3DMc,381
-wcgw/client/mcp_server/server.py,sha256=CNUOAd83lCq0Ed_ZRwd66gIjMFN9VBSO4moTLUPTWwM,11956
-wcgw/relay/serve.py,sha256=KLYjTvM9CfqdxgFOfHM8LUkFGZ9kKyyJunpNdEIFQUk,8766
+wcgw/client/mcp_server/server.py,sha256=d8fegYsneGnmzwqCCL1vkHD_DuB2uQGyg24P_KvAK-A,12024
+wcgw/relay/serve.py,sha256=CYY0mAAzR6nXkdGqLA9dXkgBcMCKPXEAmBcDyutUnjQ,8769
 wcgw/relay/static/privacy.txt,sha256=s9qBdbx2SexCpC_z33sg16TptmAwDEehMCLz4L50JLc,529
 mcp_wcgw/__init__.py,sha256=fKCgOdN7cn7gR3YGFaGyV5Goe8A2sEyllLcsRkN0i-g,2601
 mcp_wcgw/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -38,7 +38,8 @@ mcp_wcgw/shared/memory.py,sha256=dBsOghxHz8-tycdSVo9kSujbsC8xb_tYsGmuJobuZnw,281
 mcp_wcgw/shared/progress.py,sha256=ymxOsb8XO5Mhlop7fRfdbmvPodANj7oq6O4dD0iUcnw,1048
 mcp_wcgw/shared/session.py,sha256=e44a0LQOW8gwdLs9_DE9oDsxqW2U8mXG3d5KT95bn5o,10393
 mcp_wcgw/shared/version.py,sha256=d2LZii-mgsPIxpshjkXnOTUmk98i0DT4ff8VpA_kAvE,111
-wcgw-2.4.2.dist-info/METADATA,sha256=hyO0tbDU7FBSsRNcuX8tnbyg_j2pTtdWm7JG9GY-UZQ,7931
-wcgw-2.4.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-wcgw-2.4.2.dist-info/entry_points.txt,sha256=eKo1omwbAggWlQ0l7GKoR7uV1-j16nk9tK0BhC2Oz_E,120
-wcgw-2.4.2.dist-info/RECORD,,
+wcgw-2.5.0.dist-info/METADATA,sha256=D16uxd1XiajjITvdEIdE2b4MI9gYepkor39zOkOQvFI,7924
+wcgw-2.5.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+wcgw-2.5.0.dist-info/entry_points.txt,sha256=eKo1omwbAggWlQ0l7GKoR7uV1-j16nk9tK0BhC2Oz_E,120
+wcgw-2.5.0.dist-info/licenses/LICENSE,sha256=SDdQZzFz8ehsr0m87ZmC3LL82leZdULi2yJ-XGGuqac,13417
+wcgw-2.5.0.dist-info/RECORD,,

wcgw-2.5.0.dist-info/licenses/LICENSE

@@ -0,0 +1,243 @@
+The majority of this software is licensed under the MIT License.
+Portions of this software include code licensed under the Apache License, Version 2.0.
+
+--------------------------------------------------------------------------------
+MIT License (Primary License)
+--------------------------------------------------------------------------------
+
+Copyright (c) 2024 arusia
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+--------------------------------------------------------------------------------
+Third Party Components
+--------------------------------------------------------------------------------
+
+This project includes components from the following third-party projects:
+
+1. The file at src/wcgw/client/diff-instructions.txt is substantially modified from Aider
+   Source: https://github.com/Aider-AI/aider
+   Original Copyright (c) 2023 Aider-AI
+   Licensed under the Apache License, Version 2.0
+   Modified version Copyright (c) 2024 arusia
+
+The full text of the Apache License 2.0 follows:
+
+--------------------------------------------------------------------------------
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.