weco 0.2.23__tar.gz → 0.2.25__tar.gz

{weco-0.2.23 → weco-0.2.25}/.gitignore

@@ -69,8 +69,10 @@ etc/
 # AI generated files
 digest.txt
 .runs/
+CLAUDE.md
 
 *.pyc
 
 # Repomix
+.repomixignore
 repomix-output.*

{weco-0.2.23 → weco-0.2.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: weco
-Version: 0.2.23
+Version: 0.2.25
 Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
 Author-email: Weco AI Team <contact@weco.ai>
 License: MIT
@@ -16,6 +16,8 @@ Requires-Dist: requests
 Requires-Dist: rich
 Requires-Dist: packaging
 Requires-Dist: gitingest
+Requires-Dist: fastapi
+Requires-Dist: slowapi
 Provides-Extra: dev
 Requires-Dist: ruff; extra == "dev"
 Requires-Dist: build; extra == "dev"
@@ -158,6 +160,7 @@ For more advanced examples, including [Triton](/examples/triton/README.md), [CUD
 | `-M, --model`                  | Model identifier for the LLM to use (e.g., `o4-mini`, `claude-sonnet-4-0`).                                                                                                        | `o4-mini` when `OPENAI_API_KEY` is set; `claude-sonnet-4-0` when `ANTHROPIC_API_KEY` is set; `gemini-2.5-pro` when `GEMINI_API_KEY` is set. | `-M o4-mini`         |
 | `-i, --additional-instructions`| Natural language description of specific instructions **or** path to a file containing detailed instructions to guide the LLM.                                                                                             | `None`                                                                                                                                                  | `-i instructions.md` or `-i "Optimize the model for faster inference"`|
 | `-l, --log-dir`                | Path to the directory to log intermediate steps and final optimization result.                                                                                                                                             | `.runs/`                                                                                                                                               | `-l ./logs/`        |
+| `--eval-timeout`       | Timeout in seconds for each step in evaluation.                                                                                                                                                                             | No timeout (unlimited)                                                                                                                                                  | `--eval-timeout 3600`             |
 
 ---
 
@@ -248,28 +251,38 @@ Final speedup value = 1.5
 
 Weco will parse this output to extract the numerical value (1.5 in this case) associated with the metric name ('speedup').
 
-## Contributing
+## Supported Models
 
-We welcome your contributions! To get started:
+Weco supports the following LLM models:
 
-1.  **Fork & Clone the Repository:**
-    ```bash
-    git clone https://github.com/WecoAI/weco-cli.git
-    cd weco-cli
-    ```
+### OpenAI Models
+- `o3`
+- `o3-mini`
+- `o4-mini`
+- `o1-pro`
+- `o1`
+- `gpt-4.1`
+- `gpt-4.1-mini`
+- `gpt-4.1-nano`
+- `gpt-4o`
+- `gpt-4o-mini`
 
-2.  **Install Dependencies:**
-    ```bash
-    pip install -e ".[dev]"
-    ```
+### Anthropic Models
+- `claude-opus-4-0`
+- `claude-sonnet-4-0`
+- `claude-3-7-sonnet-latest`
 
-3.  **Create a Feature Branch:**
-    ```bash
-    git checkout -b feature/your-feature-name
-    ```
+### Gemini Models
+- `gemini-2.5-pro`
+- `gemini-2.5-flash`
+- `gemini-2.5-flash-lite`
+
+You can specify any of these models using the `-M` or `--model` flag. Ensure you have the corresponding API key set as an environment variable for the model provider you wish to use.
 
-4.  **Make Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
+---
+
+## Contributing
 
-5.  **Commit, Push & Open a PR**: Commit your changes, and open a pull request with a clear description of your enhancements.
+We welcome contributions! Please see [contributing.md](contributing.md) for detailed guidelines on how to contribute to this project.
 
 ---

{weco-0.2.23 → weco-0.2.25}/README.md

@@ -134,6 +134,7 @@ For more advanced examples, including [Triton](/examples/triton/README.md), [CUD
 | `-M, --model`                  | Model identifier for the LLM to use (e.g., `o4-mini`, `claude-sonnet-4-0`).                                                                                                        | `o4-mini` when `OPENAI_API_KEY` is set; `claude-sonnet-4-0` when `ANTHROPIC_API_KEY` is set; `gemini-2.5-pro` when `GEMINI_API_KEY` is set. | `-M o4-mini`         |
 | `-i, --additional-instructions`| Natural language description of specific instructions **or** path to a file containing detailed instructions to guide the LLM.                                                                                             | `None`                                                                                                                                                  | `-i instructions.md` or `-i "Optimize the model for faster inference"`|
 | `-l, --log-dir`                | Path to the directory to log intermediate steps and final optimization result.                                                                                                                                             | `.runs/`                                                                                                                                               | `-l ./logs/`        |
+| `--eval-timeout`       | Timeout in seconds for each step in evaluation.                                                                                                                                                                             | No timeout (unlimited)                                                                                                                                                  | `--eval-timeout 3600`             |
 
 ---
 
@@ -224,28 +225,38 @@ Final speedup value = 1.5
 
 Weco will parse this output to extract the numerical value (1.5 in this case) associated with the metric name ('speedup').
 
-## Contributing
+## Supported Models
 
-We welcome your contributions! To get started:
+Weco supports the following LLM models:
 
-1.  **Fork & Clone the Repository:**
-    ```bash
-    git clone https://github.com/WecoAI/weco-cli.git
-    cd weco-cli
-    ```
+### OpenAI Models
+- `o3`
+- `o3-mini`
+- `o4-mini`
+- `o1-pro`
+- `o1`
+- `gpt-4.1`
+- `gpt-4.1-mini`
+- `gpt-4.1-nano`
+- `gpt-4o`
+- `gpt-4o-mini`
 
-2.  **Install Dependencies:**
-    ```bash
-    pip install -e ".[dev]"
-    ```
+### Anthropic Models
+- `claude-opus-4-0`
+- `claude-sonnet-4-0`
+- `claude-3-7-sonnet-latest`
 
-3.  **Create a Feature Branch:**
-    ```bash
-    git checkout -b feature/your-feature-name
-    ```
+### Gemini Models
+- `gemini-2.5-pro`
+- `gemini-2.5-flash`
+- `gemini-2.5-flash-lite`
+
+You can specify any of these models using the `-M` or `--model` flag. Ensure you have the corresponding API key set as an environment variable for the model provider you wish to use.
 
-4.  **Make Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
+---
+
+## Contributing
 
-5.  **Commit, Push & Open a PR**: Commit your changes, and open a pull request with a clear description of your enhancements.
+We welcome contributions! Please see [contributing.md](contributing.md) for detailed guidelines on how to contribute to this project.
 
 ---

weco-0.2.25/contributing.md

@@ -0,0 +1,23 @@
+# Contributing
+
+We welcome your contributions! To get started:
+
+1.  **Fork & Clone the Repository:**
+    ```bash
+    git clone https://github.com/WecoAI/weco-cli.git
+    cd weco-cli
+    ```
+
+2.  **Install Dependencies:**
+    ```bash
+    pip install -e ".[dev]"
+    ```
+
+3.  **Create a Feature Branch:**
+    ```bash
+    git checkout -b feature/your-feature-name
+    ```
+
+4.  **Make Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
+
+5.  **Commit, Push & Open a PR**: Commit your changes, and open a pull request with a clear description of your enhancements.

{weco-0.2.23 → weco-0.2.25}/pyproject.toml

@@ -8,7 +8,7 @@ name = "weco"
 authors = [{ name = "Weco AI Team", email = "contact@weco.ai" }]
 description = "Documentation for `weco`, a CLI for using Weco AI's code optimizer."
 readme = "README.md"
-version = "0.2.23"
+version = "0.2.25"
 license = { text = "MIT" }
 requires-python = ">=3.8"
 dependencies = [
@@ -16,6 +16,8 @@ dependencies = [
     "rich",
     "packaging",
     "gitingest",
+    "fastapi",
+    "slowapi",
 ]
 keywords = ["AI", "Code Optimization", "Code Generation"]
 classifiers = [

{weco-0.2.23 → weco-0.2.25}/weco/api.py

@@ -4,6 +4,7 @@ import requests
 from rich.console import Console
 
 from weco import __pkg_version__, __base_url__
+from .constants import DEFAULT_API_TIMEOUT
 
 
 def handle_api_error(e: requests.exceptions.HTTPError, console: Console) -> None:
@@ -30,7 +31,7 @@ def start_optimization_run(
     additional_instructions: str = None,
     api_keys: Dict[str, Any] = {},
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 800,
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Dict[str, Any]:
     """Start the optimization run."""
     with console.status("[bold green]Starting Optimization..."):
@@ -53,22 +54,29 @@ def start_optimization_run(
                 timeout=timeout,
             )
             response.raise_for_status()
-            return response.json()
+            result = response.json()
+            # Handle None values for code and plan fields
+            if result.get("plan") is None:
+                result["plan"] = ""
+            if result.get("code") is None:
+                result["code"] = ""
+            return result
         except requests.exceptions.HTTPError as e:
             handle_api_error(e, console)
-            sys.exit(1)
+            raise
         except Exception as e:
             console.print(f"[bold red]Error starting run: {e}[/]")
-            sys.exit(1)
+            raise
 
 
 def evaluate_feedback_then_suggest_next_solution(
+    console: Console,
     run_id: str,
     execution_output: str,
     additional_instructions: str = None,
     api_keys: Dict[str, Any] = {},
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 800,
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Dict[str, Any]:
     """Evaluate the feedback and suggest the next solution."""
     try:
@@ -83,10 +91,17 @@ def evaluate_feedback_then_suggest_next_solution(
             timeout=timeout,
         )
         response.raise_for_status()
-        return response.json()
+        result = response.json()
+        # Handle None values for code and plan fields
+        if result.get("plan") is None:
+            result["plan"] = ""
+        if result.get("code") is None:
+            result["code"] = ""
+
+        return result
     except requests.exceptions.HTTPError as e:
         # Allow caller to handle suggest errors, maybe retry or terminate
-        handle_api_error(e, Console())  # Use default console if none passed
+        handle_api_error(e, console)  # Use default console if none passed
         raise  # Re-raise the exception
     except Exception as e:
         print(f"Error: {e}")  # Use print as console might not be available
@@ -94,7 +109,11 @@ def evaluate_feedback_then_suggest_next_solution(
 
 
 def get_optimization_run_status(
-    run_id: str, include_history: bool = False, auth_headers: dict = {}, timeout: Union[int, Tuple[int, int]] = 800
+    console: Console,
+    run_id: str,
+    include_history: bool = False,
+    auth_headers: dict = {},
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Dict[str, Any]:
     """Get the current status of the optimization run."""
     try:
@@ -102,16 +121,30 @@ def get_optimization_run_status(
             f"{__base_url__}/runs/{run_id}", params={"include_history": include_history}, headers=auth_headers, timeout=timeout
         )
         response.raise_for_status()
-        return response.json()
+        result = response.json()
+        # Handle None values for code and plan fields in best_result and nodes
+        if result.get("best_result"):
+            if result["best_result"].get("code") is None:
+                result["best_result"]["code"] = ""
+            if result["best_result"].get("plan") is None:
+                result["best_result"]["plan"] = ""
+        # Handle None values for code and plan fields in nodes array
+        if result.get("nodes"):
+            for i, node in enumerate(result["nodes"]):
+                if node.get("plan") is None:
+                    result["nodes"][i]["plan"] = ""
+                if node.get("code") is None:
+                    result["nodes"][i]["code"] = ""
+        return result
     except requests.exceptions.HTTPError as e:
-        handle_api_error(e, Console())  # Use default console
+        handle_api_error(e, console)  # Use default console
         raise  # Re-raise
     except Exception as e:
         print(f"Error getting run status: {e}")
         raise  # Re-raise
 
 
-def send_heartbeat(run_id: str, auth_headers: dict = {}, timeout: Union[int, Tuple[int, int]] = 10) -> bool:
+def send_heartbeat(run_id: str, auth_headers: dict = {}, timeout: Union[int, Tuple[int, int]] = (10, 10)) -> bool:
     """Send a heartbeat signal to the backend."""
     try:
         response = requests.put(f"{__base_url__}/runs/{run_id}/heartbeat", headers=auth_headers, timeout=timeout)
@@ -119,9 +152,9 @@ def send_heartbeat(run_id: str, auth_headers: dict = {}, timeout: Union[int, Tup
         return True
     except requests.exceptions.HTTPError as e:
         if e.response.status_code == 409:
-            print(f"Heartbeat ignored: Run {run_id} is not running.", file=sys.stderr)
+            print(f"Polling ignore: Run {run_id} is not running.", file=sys.stderr)
         else:
-            print(f"Heartbeat failed for run {run_id}: HTTP {e.response.status_code}", file=sys.stderr)
+            print(f"Polling failed for run {run_id}: HTTP {e.response.status_code}", file=sys.stderr)
         return False
     except Exception as e:
         print(f"Error sending heartbeat for run {run_id}: {e}", file=sys.stderr)
@@ -134,7 +167,7 @@ def report_termination(
     reason: str,
     details: Optional[str] = None,
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 30,
+    timeout: Union[int, Tuple[int, int]] = (10, 30),
 ) -> bool:
     """Report the termination reason to the backend."""
     try:
@@ -172,22 +205,22 @@ def _determine_model_and_api_key() -> tuple[str, dict[str, str]]:
         api_key_dict = {"GEMINI_API_KEY": llm_api_keys["GEMINI_API_KEY"]}
     else:
         # This should never happen if determine_default_model works correctly
-        raise ValueError(f"Unknown model returned: {model}")
+        raise ValueError(f"Unknown default model choice: {model}")
 
     return model, api_key_dict
 
 
 def get_optimization_suggestions_from_codebase(
+    console: Console,
     gitingest_summary: str,
     gitingest_tree: str,
     gitingest_content_str: str,
-    console: Console,
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 800,
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Optional[List[Dict[str, Any]]]:
     """Analyze codebase and get optimization suggestions using the model-agnostic backend API."""
+    model, api_key_dict = _determine_model_and_api_key()
     try:
-        model, api_key_dict = _determine_model_and_api_key()
         response = requests.post(
             f"{__base_url__}/onboard/analyze-codebase",
             json={
@@ -213,16 +246,16 @@ def get_optimization_suggestions_from_codebase(
 
 
 def generate_evaluation_script_and_metrics(
+    console: Console,
     target_file: str,
     description: str,
     gitingest_content_str: str,
-    console: Console,
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 800,
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Tuple[Optional[str], Optional[str], Optional[str], Optional[str]]:
     """Generate evaluation script and determine metrics using the model-agnostic backend API."""
+    model, api_key_dict = _determine_model_and_api_key()
     try:
-        model, api_key_dict = _determine_model_and_api_key()
         response = requests.post(
             f"{__base_url__}/onboard/generate-script",
             json={
@@ -247,18 +280,18 @@ def generate_evaluation_script_and_metrics(
 
 
 def analyze_evaluation_environment(
+    console: Console,
     target_file: str,
     description: str,
     gitingest_summary: str,
     gitingest_tree: str,
     gitingest_content_str: str,
-    console: Console,
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 800,
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Optional[Dict[str, Any]]:
     """Analyze existing evaluation scripts and environment using the model-agnostic backend API."""
+    model, api_key_dict = _determine_model_and_api_key()
     try:
-        model, api_key_dict = _determine_model_and_api_key()
         response = requests.post(
             f"{__base_url__}/onboard/analyze-environment",
             json={
@@ -285,16 +318,16 @@ def analyze_evaluation_environment(
 
 
 def analyze_script_execution_requirements(
+    console: Console,
     script_content: str,
     script_path: str,
     target_file: str,
-    console: Console,
     auth_headers: dict = {},
-    timeout: Union[int, Tuple[int, int]] = 800,
+    timeout: Union[int, Tuple[int, int]] = DEFAULT_API_TIMEOUT,
 ) -> Optional[str]:
     """Analyze script to determine proper execution command using the model-agnostic backend API."""
+    model, api_key_dict = _determine_model_and_api_key()
     try:
-        model, api_key_dict = _determine_model_and_api_key()
         response = requests.post(
             f"{__base_url__}/onboard/analyze-script",
             json={

{weco-0.2.23 → weco-0.2.25}/weco/auth.py

@@ -35,7 +35,7 @@ def save_api_key(api_key: str):
         # Set file permissions to read/write for owner only (600)
         os.chmod(CREDENTIALS_FILE, stat.S_IRUSR | stat.S_IWUSR)
     except OSError as e:
-        print(f"Error: Could not write credentials file or set permissions on {CREDENTIALS_FILE}: {e}")
+        print(f"Error: Unable to save credentials file or set permissions on {CREDENTIALS_FILE}: {e}")
 
 
 def load_weco_api_key() -> str | None:
@@ -53,7 +53,7 @@ def load_weco_api_key() -> str | None:
             credentials = json.load(f)
             return credentials.get("api_key")
     except (IOError, json.JSONDecodeError, OSError) as e:
-        print(f"Warning: Could not read or parse credentials file at {CREDENTIALS_FILE}: {e}")
+        print(f"Warning: Unable to read credentials file at {CREDENTIALS_FILE}: {e}")
         return None
 
 
@@ -64,7 +64,7 @@ def clear_api_key():
             os.remove(CREDENTIALS_FILE)
             print("Logged out successfully.")
         except OSError as e:
-            print(f"Error: Could not remove credentials file at {CREDENTIALS_FILE}: {e}")
+            print(f"Error: Unable to remove credentials file at {CREDENTIALS_FILE}: {e}")
     else:
         print("Already logged out.")
 
@@ -129,7 +129,9 @@ def perform_login(console: Console):
                             continue  # Continue polling
                         else:
                             # Unexpected 202 response format
-                            console.print(f"\n[bold red]Error:[/] Received unexpected 202 response: {token_data}")
+                            console.print(
+                                f"\n[bold red]Error:[/] Received unexpected response from authentication server: {token_data}"
+                            )
                             return False
                     # Check for standard OAuth2 errors (often 400 Bad Request)
                     elif token_response.status_code == 400:
@@ -146,7 +148,7 @@ def perform_login(console: Console):
                             console.print("\n[bold red]Error:[/] Authorization denied by user.")
                             return False
                         else:  # invalid_grant, etc.
-                            error_desc = token_data.get("error_description", "Unknown error during polling.")
+                            error_desc = token_data.get("error_description", "Unknown authentication error occurred.")
                             console.print(f"\n[bold red]Error:[/] {error_desc} ({error_code})")
                             return False
 

{weco-0.2.23 → weco-0.2.25}/weco/chatbot.py

@@ -50,7 +50,7 @@ class UserInteractionHelper:
 
                 if attempts >= max_retries:
                     self.console.print(f"[red]Maximum retry attempts ({max_retries}) reached. Exiting.[/]")
-                    raise Exception("Maximum retry attempts exceeded")
+                    raise Exception("Maximum retry attempts exceeded. Please try again.")
 
                 # Show available options without the full prompt
                 if choices:
@@ -66,7 +66,7 @@ class UserInteractionHelper:
                 continue
 
         # This should never be reached due to the exception above, but just in case
-        raise Exception("Unexpected error in choice selection")
+        raise Exception("Unexpected error while selecting a choice")
 
     def get_choice_numeric(self, prompt: str, max_number: int, default: int = None, max_retries: int = 5) -> int:
         """Get numeric choice with validation and error handling."""
@@ -87,7 +87,7 @@ class UserInteractionHelper:
 
                 if attempts >= max_retries:
                     self.console.print(f"[red]Maximum retry attempts ({max_retries}) reached. Exiting.[/]")
-                    raise Exception("Maximum retry attempts exceeded")
+                    raise Exception("Maximum retry attempts exceeded. Please try again.")
 
                 # Show valid range
                 self.console.print(f"Please enter a number between [bold]1[/] and [bold]{max_number}[/]")
@@ -115,7 +115,7 @@ class UserInteractionHelper:
 
                 if attempts >= max_retries:
                     self.console.print(f"[red]Maximum retry attempts ({max_retries}) reached. Exiting.[/]")
-                    raise Exception("Maximum retry attempts exceeded")
+                    raise Exception("Maximum retry attempts exceeded. Please try again.")
 
                 self.console.print("Valid options: [bold]y[/] / [bold]n[/]")
                 if default:
@@ -123,7 +123,7 @@ class UserInteractionHelper:
 
                 continue
 
-        raise Exception("Unexpected error in yes/no selection")
+        raise Exception("Unexpected error while selecting an option")
 
     def display_optimization_options_table(self, options: List[Dict[str, str]]) -> None:
         """Display optimization options in a formatted table."""
@@ -215,7 +215,10 @@ class Chatbot:
 
             with self.console.status("[bold green]Generating optimization suggestions...[/]"):
                 result = get_optimization_suggestions_from_codebase(
-                    self.gitingest_summary, self.gitingest_tree, self.gitingest_content_str, self.console
+                    console=self.console,
+                    gitingest_summary=self.gitingest_summary,
+                    gitingest_tree=self.gitingest_tree,
+                    gitingest_content_str=self.gitingest_content_str,
                 )
 
                 if result and isinstance(result, list):
@@ -224,7 +227,7 @@ class Chatbot:
                     options = None
 
             if not options or not isinstance(options, list):
-                self.console.print("[red]Failed to get valid optimization options.[/]")
+                self.console.print("[red]Unable to retrieve valid optimization options from the backend.[/]")
                 return None
 
             if not options:
@@ -324,17 +327,19 @@ class Chatbot:
             elif action == "g" or action == "r":
                 with self.console.status("[bold green]Generating evaluation script and determining metrics...[/]"):
                     result = generate_evaluation_script_and_metrics(
-                        selected_option["target_file"],
-                        selected_option["description"],
-                        self.gitingest_content_str,
-                        self.console,
+                        console=self.console,
+                        target_file=selected_option["target_file"],
+                        description=selected_option["description"],
+                        gitingest_content_str=self.gitingest_content_str,
                     )
                 if result and result[0]:
                     eval_script_content, metric_name, goal, reasoning = result
                     if reasoning:
                         self.console.print(f"[dim]Reasoning: {reasoning}[/]")
                 else:
-                    self.console.print("[red]Failed to generate an evaluation script.[/]")
+                    self.console.print(
+                        "[red]Unable to generate an evaluation script. Please try providing a custom script path instead.[/]"
+                    )
                     eval_script_content = None
                     metric_name = None
                     goal = None
@@ -371,7 +376,10 @@ class Chatbot:
         # Analyze the script to determine the proper execution command
         with self.console.status("[bold green]Analyzing script execution requirements...[/]"):
             eval_command = analyze_script_execution_requirements(
-                eval_script_content, eval_script_path_str, selected_option["target_file"], self.console
+                console=self.console,
+                script_content=eval_script_content,
+                script_path=eval_script_path_str,
+                target_file=selected_option["target_file"],
             )
 
         return {
@@ -386,16 +394,16 @@ class Chatbot:
         """Get or create evaluation script configuration using intelligent conversation-guided approach."""
         with self.console.status("[bold green]Analyzing evaluation environment...[/]"):
             analysis = analyze_evaluation_environment(
-                selected_option["target_file"],
-                selected_option["description"],
-                self.gitingest_summary,
-                self.gitingest_tree,
-                self.gitingest_content_str,
-                self.console,
+                console=self.console,
+                target_file=selected_option["target_file"],
+                description=selected_option["description"],
+                gitingest_summary=self.gitingest_summary,
+                gitingest_tree=self.gitingest_tree,
+                gitingest_content_str=self.gitingest_content_str,
             )
 
         if not analysis:
-            self.console.print("[yellow]Failed to analyze evaluation environment. Falling back to generation.[/]")
+            self.console.print("[yellow]Unable to analyze evaluation environment. Falling back to script generation.[/]")
             return self.handle_script_generation_workflow(selected_option)
 
         self.evaluation_analysis = analysis
@@ -529,7 +537,10 @@ class Chatbot:
             if not eval_command or eval_command == f"python {script_path}":
                 with self.console.status("[bold green]Analyzing script execution requirements...[/]"):
                     eval_command = analyze_script_execution_requirements(
-                        script_content, script_path, selected_option["target_file"], self.console
+                        console=self.console,
+                        script_content=script_content,
+                        script_path=script_path,
+                        target_file=selected_option["target_file"],
                     )
 
             self.current_step = "confirmation"
@@ -711,7 +722,7 @@ class Chatbot:
         """Setup evaluation environment for the selected optimization."""
         eval_config = self.get_evaluation_configuration(selected_option)
         if not eval_config:
-            self.console.print("[red]Evaluation script setup failed.[/]")
+            self.console.print("[red]Evaluation script setup failed. Please check your script configuration and try again.[/]")
             return None
 
         eval_config = self.confirm_and_finalize_evaluation_config(eval_config)
@@ -791,7 +802,7 @@ def run_onboarding_chatbot(
         chatbot = Chatbot(project_path, console, run_parser, model)
         chatbot.start()
     except Exception as e:
-        console.print(f"[bold red]An unexpected error occurred in the chatbot: {e}[/]")
+        console.print(f"[bold red]An unexpected error occurred: {e}[/]")
         import traceback
 
         traceback.print_exc()

{weco-0.2.23 → weco-0.2.25}/weco/cli.py

@@ -61,6 +61,12 @@ def configure_run_parser(run_parser: argparse.ArgumentParser) -> None:
         type=str,
         help="Description of additional instruction or path to a file containing additional instructions. Defaults to None.",
     )
+    run_parser.add_argument(
+        "--eval-timeout",
+        type=int,
+        default=None,
+        help="Timeout in seconds for each evaluation. No timeout by default. Example: --eval-timeout 3600",
+    )
 
 
 def execute_run_command(args: argparse.Namespace) -> None:
@@ -77,6 +83,7 @@ def execute_run_command(args: argparse.Namespace) -> None:
         log_dir=args.log_dir,
         additional_instructions=args.additional_instructions,
         console=console,
+        eval_timeout=args.eval_timeout,
     )
     exit_code = 0 if success else 1
     sys.exit(exit_code)
@@ -177,7 +184,9 @@ def main() -> None:
 
         project_path = pathlib.Path(filtered_args[0]) if filtered_args else pathlib.Path.cwd()
         if not project_path.is_dir():
-            console.print(f"[bold red]Error:[/] Path '{project_path}' is not a valid directory.")
+            console.print(
+                f"[bold red]Error:[/] The path '{project_path}' is not a valid directory. Please provide a valid directory path."
+            )
             sys.exit(1)
 
         # Pass the run_parser and model to the chatbot