missing re import (#12)

Author: SamWright822

.gitignore

@@ -146,4 +146,4 @@ packages/crow-integration-tests/errors/
 
 
 # Other
-./CLAUDE.md
+./CLAUDE.md

.pre-commit-config.yaml

@@ -40,6 +40,7 @@ repos:
     rev: v0.24.2
     hooks:
       - id: toml-sort-fix
+        exclude: ^uv\.lock$
   - repo: https://github.com/crate-ci/typos
     rev: v1.30.3
     hooks:

README.md

@@ -6,7 +6,7 @@ See our [blog](https://www.futurehouse.org/research-announcements/demonstrating-
 
 - **Python:** Version 3.12 or higher.
 - **API Keys:**
-  - `EDISON_API_KEY`: For accessing Edison platform agents (Crow, Falcon - now called 'Literature'). Obtain from https://platform.edisonscientific.com/profile. You must first create an Edison profile, purchase credits and then create an API key (Account -> Profile -> API Tokens). 
+  - `EDISON_API_KEY`: For accessing Edison platform agents (Crow, Falcon - now called 'Literature'). Obtain from https://platform.edisonscientific.com/profile. You must first create an Edison profile, purchase credits and then create an API key (Account -> Profile -> API Tokens).
   - An API key for your chosen LLM provider (e.g., `OPENAI_API_KEY` if using OpenAI models). Robin uses LiteLLM, so it can support various providers.
   - The data analysis portion of this repo requires access to the Edison platform. Without access, all the hypothesis and experiment generation code can still be run.
 
@@ -19,15 +19,18 @@ Docker is a tool that packages software into a self-contained "container" that r
 For a fully self-contained environment that avoids OS-level dependency conflicts, Docker is the recommended approach:
 
 1. **Build the image:**
+
    ```bash
    docker build -t robin .
    ```
 
 2. **Set up API keys:**
+
    ```bash
    cp .env.example .env
    # Edit .env and fill in your EDISON_API_KEY and OPENAI_API_KEY
    ```
+
    Important: do **not** wrap values in quotes (e.g. `OPENAI_API_KEY=sk-abc123`, not `OPENAI_API_KEY="sk-abc123"`). Docker reads the file differently from Python and will include the quotes as part of the key.
 
 3. **Run Jupyter:**
@@ -159,6 +162,6 @@ These example outputs are provided to help users to understand the depth, format
 
 ## Advanced Usage
 
-A full example trajectory of both the initial therapeutic candidate generation and experimental data analysis can be found in the `robin_full.ipynb` notebook. This notebook includes the parameters and agents used in the paper. 
+A full example trajectory of both the initial therapeutic candidate generation and experimental data analysis can be found in the `robin_full.ipynb` notebook. This notebook includes the parameters and agents used in the paper.
 
 While this guide focuses on the `robin_demo.ipynb` notebook, the `robin` Python module (in the `robin/` directory) can be imported and its functions (`experimental_assay`, `therapeutic_candidates`, `data_analysis`) can be used programmatically in your own Python scripts for more customized workflows.

pyproject.toml

@@ -21,12 +21,12 @@ dependencies = [
     "aiofiles",
     "anthropic",
     "choix",
+    "edison-client>=0.11",
     "fhaviary",
     "fhlmi",
-    "edison-client>=0.11",  
-    "openai>=1", 
-    "pandas>=2",  
-    "pydantic>=2",  
+    "openai>=1",
+    "pandas>=2",
+    "pydantic>=2",
     "python-dotenv",
     "tqdm",
 ]

robin/assays.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import re
 from pathlib import Path
 from typing import cast
 
@@ -113,15 +114,17 @@ async def experimental_assay(configuration: RobinConfiguration) -> str | None:
 
     response_text = cast(str, experimental_assay_ideas.text)
     if not response_text.strip():
-        raise ValueError("LLM returned an empty response during assay proposal generation.")
+        raise ValueError(
+            "LLM returned an empty response during assay proposal generation."
+        )
     try:
         assay_idea_json = json.loads(response_text)
-    except json.JSONDecodeError:
+    except json.JSONDecodeError as err:
         match = re.search(r"\[.*\]", response_text, re.DOTALL)
         if not match:
             raise ValueError(
                 f"LLM response did not contain a JSON array. Response: {response_text[:200]}"
-            )
+            ) from err
         assay_idea_json = json.loads(match.group())
     assay_idea_list = format_assay_ideas(assay_idea_json)
 

robin/configuration.py

@@ -2,14 +2,13 @@
 import os
 import re
 from datetime import datetime
+from typing import Any
 
 from dotenv import load_dotenv
 from edison_client import EdisonClient, JobNames
 from lmi import LiteLLMModel
 from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
-load_dotenv()
-
 from .prompts import (
     ANALYSIS_QUERIES,
     ASSAY_HYPOTHESIS_FORMAT,
@@ -44,6 +43,8 @@
     SYNTHESIZE_USER_CONTENT,
 )
 
+load_dotenv()
+
 _DEFAULT_LLM_CONFIG_DATA = {
     "model_list": [
         {
@@ -58,9 +59,9 @@
 }
 
 
-def get_default_llm_config():
+def get_default_llm_config() -> dict[str, Any]:
     # Key is read on each instantiation so env vars set after import are picked up.
-    data = copy.deepcopy(_DEFAULT_LLM_CONFIG_DATA)
+    data: dict[str, Any] = copy.deepcopy(_DEFAULT_LLM_CONFIG_DATA)
     data["model_list"][0]["litellm_params"]["api_key"] = os.getenv(
         "OPENAI_API_KEY", "insert_openai_key_here"
     )

robin/utils.py

@@ -558,7 +558,7 @@ def parse_custom_tuple_string(s):  # noqa: PLR0911
                 game_scores.append(None)
         else:
             game_scores.append(None)
-    processed_ranking_results["Game Score"] = game_scores
+    processed_ranking_results["Game Score"] = cast(Any, game_scores)
 
     processed_ranking_results = processed_ranking_results.dropna(subset=["Game Score"])