bioguider 0.2.20__py3-none-any.whl → 0.2.22__py3-none-any.whl

bioguider/utils/utils.py

@@ -2,6 +2,7 @@ import logging
 import re
 import subprocess
 from typing import Optional
+from pydantic import BaseModel
 import tiktoken
 
 from bioguider.utils.constants import DEFAULT_TOKEN_USAGE
@@ -68,4 +69,36 @@ def increase_token_usage(
 
     return token_usage
 
-    
+def clean_action_input(action_input: str) -> str:
+    replaced_input = ""
+
+    while (True):
+        replaced_input = action_input.strip()
+        replaced_input = replaced_input.strip("`")
+        replaced_input = replaced_input.strip('"')
+        replaced_input = replaced_input.strip()
+        replaced_input = replaced_input.strip("`")
+        replaced_input = replaced_input.strip('"')
+        replaced_input = replaced_input.strip()
+        if (replaced_input == action_input):
+            break
+        action_input = replaced_input
+    
+    action_input = action_input.replace("'", '"')
+    action_input = action_input.replace("`", '"')
+    return action_input
+
+# Convert BaseModel objects to dictionaries for JSON serialization
+def convert_to_serializable(obj):
+    if isinstance(obj, BaseModel):
+        return obj.model_dump()
+    elif hasattr(obj, 'model_dump'):
+        return obj.model_dump()
+    elif isinstance(obj, dict):
+        return {k: convert_to_serializable(v) for k, v in obj.items()}
+    elif isinstance(obj, list):
+        return [convert_to_serializable(item) for item in obj]
+    elif isinstance(obj, tuple):
+        return [convert_to_serializable(item) for item in obj]
+    else:
+        return obj

{bioguider-0.2.20.dist-info → bioguider-0.2.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: bioguider
-Version: 0.2.20
+Version: 0.2.22
 Summary: An AI-Powered package to help biomedical developers to generate clear documentation
 License: MIT
 Author: Cankun Wang

{bioguider-0.2.20.dist-info → bioguider-0.2.22.dist-info}/RECORD

@@ -2,21 +2,21 @@ bioguider/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bioguider/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bioguider/agents/agent_task.py,sha256=TL0Zx8zOmiAVslmNbfMPQ38qTQ73QospY6Dwrwf8POg,2890
 bioguider/agents/agent_tools.py,sha256=r21wHV6a-Ic2T0dk4YzA-_d7PodHPM3GzRxJqv-llSw,7286
-bioguider/agents/agent_utils.py,sha256=SoYFc5oZGY2QqTDHR1DCgBPiwQpigUOANHmlUCUPzu4,14683
+bioguider/agents/agent_utils.py,sha256=Mj6yr_2y4veWokXrXlAsaP38Ez9sdnZruM8ZnnpjxQ4,14825
 bioguider/agents/collection_execute_step.py,sha256=jE_oSQZI5WDaz0bJjUWoAfqWfVbGUqN--cvITSWCGiI,5614
-bioguider/agents/collection_observe_step.py,sha256=n863HrbVANQVeltffjS2zXv-AfVErC8ZEMfb_78hafk,5140
+bioguider/agents/collection_observe_step.py,sha256=1xOw6N3uIoyh4h4_vcULAc5x5KZ9G-zZo42AhRidyn8,5373
 bioguider/agents/collection_plan_step.py,sha256=Nn0f8AOkEDCDtnhaqE7yCQoi7PVpsHmiUcsIqC0T0dQ,5956
 bioguider/agents/collection_task.py,sha256=MjpTYiQQYUpmQf2UOn-dOCZU3kxypc4uOnzd15wb1Ow,7882
-bioguider/agents/collection_task_utils.py,sha256=_e2EebYhl-UYjZ0rHNf2-p32YlstBSffv32suiuT9LI,5386
+bioguider/agents/collection_task_utils.py,sha256=mCmjHFD4HY1mSwkfqPaJbZ8sm6ijjdhnNKj40xudE98,5424
 bioguider/agents/common_agent.py,sha256=TpfxbYskwuwWrjs1g9RaG7sdA5rOLdiVac7If7uK2sg,4558
 bioguider/agents/common_agent_2step.py,sha256=rGiDzUkmmUIFnmJJxzXK5M5BfIyINHXLZ0pmPRUVqQg,7911
 bioguider/agents/common_conversation.py,sha256=_9l6SunRmOZ_3R4Q8CTO9oE_qmP7aYYKFX1EiFBIrm8,2589
 bioguider/agents/common_step.py,sha256=GdOCbmj1pwh4etg-futVFYVDQuoUG89DnIrw-B6QbzM,2594
-bioguider/agents/consistency_collection_execute_step.py,sha256=SBZjdaIc4AX6ljedd8TsJC-1GoYeI16jaqIcfDnTezs,4938
-bioguider/agents/consistency_collection_observe_step.py,sha256=XghjlSMBpq1Va68jRP8_-ZG0O7UlZy1Qhwai9c0LNoo,5029
-bioguider/agents/consistency_collection_plan_step.py,sha256=NUl0Nl39O5EFibJQQB1oMIVY_Tikh75YNVbyt7ryw6s,5389
-bioguider/agents/consistency_collection_task.py,sha256=WP3GL4iPJ38b5F1zZMHmJALx0pRDcF-9JAmz3OHqi6o,5261
-bioguider/agents/consistency_collection_task_utils.py,sha256=BnpBXmpxmmr8NRaBw5sACipP0mMtj1Qpe2AvcMlX_cg,6143
+bioguider/agents/consistency_collection_step.py,sha256=evgb0W3PD5pXfViuP_0T5LqLnNxQCuvP14oY0KEtwSc,3424
+bioguider/agents/consistency_evaluation_task.py,sha256=_nYPEs3xhj1jraQWMRML_Y6vZJD_zydY4BstQYXmXJk,1908
+bioguider/agents/consistency_evaluation_task_utils.py,sha256=8PC4KS14ek9NJy3bLuhZNmpOUKFx3_06nKXzuTWb0tE,444
+bioguider/agents/consistency_observe_step.py,sha256=0FEtNpkaGcuL30wb2d43uTlSyHJ9Pxttn9r3NzPD0oo,4409
+bioguider/agents/consistency_query_step.py,sha256=uYE_V_e74kqoDSxmIkMpZpBjoZRKRsJPmiqs1xHhRF8,3674
 bioguider/agents/dockergeneration_execute_step.py,sha256=F92jDlkc6KjAvTkX7q1FsCYP8J15SCaNgmwh3YPqfDo,6500
 bioguider/agents/dockergeneration_observe_step.py,sha256=Bo5Td0fzMYLbLki0FvwamzqRFOy4eu3AvIUa8oFApE4,6131
 bioguider/agents/dockergeneration_plan_step.py,sha256=SB8tQM9PkIKsD2o1DFD7bedcxz6r6hSy8n_EVK60Fz0,7235
@@ -25,21 +25,23 @@ bioguider/agents/dockergeneration_task_utils.py,sha256=v7emqrJlVW-A5ZdLmPSdiaMSK
 bioguider/agents/evaluation_installation_task.py,sha256=0RNH5NV7YKwn_we_d3IjnFf_ee9IPCEQ_olebq2y8Ng,12130
 bioguider/agents/evaluation_readme_task.py,sha256=pi3oAGJgZhJgJG1xLgiobrk3Uy2a_JIarD5QSPBkmHA,30647
 bioguider/agents/evaluation_submission_requirements_task.py,sha256=J_6C-M2AfYue2C-gWBHl7KqGrTBuFBn9zmMV5vSRk-U,7834
-bioguider/agents/evaluation_task.py,sha256=c3kvc3xgzGbT0C2KpkE-zHBvaxx9zKdmpLzeKHddrds,12690
+bioguider/agents/evaluation_task.py,sha256=uu0BjalctF9hQjGtT53whbeJHv2RVvs8_2woVUmOLRE,8132
+bioguider/agents/evaluation_tutorial_task.py,sha256=n4eElsGEW38JV7pKtOyoATe1K-pSJZfMr8DdMIAhkyY,8332
+bioguider/agents/evaluation_tutorial_task_prompts.py,sha256=WTqIKBI3JErYaiQfLcPNj_hb3D-hSZrae50uJ7526zw,5996
 bioguider/agents/evaluation_userguide_prompts.py,sha256=eyJUx5nUr8v9k0B5GpKDaX2dBxSLVZGA0fwOWS4Uiow,7154
-bioguider/agents/evaluation_userguide_task.py,sha256=AJ7y5WSMs4EqXpQzyAu_5NPmWK0jl3AeHhRXxdZgpz0,8266
+bioguider/agents/evaluation_userguide_task.py,sha256=ONdempCOyn_N-LGV35diKciBbnjDSItXchcLV738XTw,6456
 bioguider/agents/identification_execute_step.py,sha256=w3IjL8f2WiHCyiLjVSoySnIAXpi1-hK1DLKCnXbAN2Y,5587
 bioguider/agents/identification_observe_step.py,sha256=Me5mhEM4e7FGnVFcluNtqfhIxzng6guGIu39xi1TrS8,4341
 bioguider/agents/identification_plan_step.py,sha256=owsTK1NZIuiZL7QPVknJyp9TBRK-mhnuf2RwK4YzaxU,5442
 bioguider/agents/identification_task.py,sha256=bTbovxxQVpO1TcdcQAxDxwPISuAcXndO7zsvHpJSb64,10147
 bioguider/agents/identification_task_utils.py,sha256=Lf0Rj0L0KSiyJmPAgeSz0vLUFQr6TSFuzgufimEN4H0,630
 bioguider/agents/peo_common_step.py,sha256=iw2c1h7X11WJzSE2tSRg0UAoXH0QOlQDxW9CCzSVMOY,2677
-bioguider/agents/prompt_utils.py,sha256=kTeK0LOsxpEIpQ5PMXY0DOHXJ5Z6ryu0UuJIO4ga9Rg,17743
+bioguider/agents/prompt_utils.py,sha256=T7ec7DbdGacIMOE4GAnlzHjuNzbzPDeSVWHvmWt1UGk,19427
 bioguider/agents/python_ast_repl_tool.py,sha256=o7-4P1h8jS8ikhGSA4CI_OWQ2a0Eg5tEdmuAp_qrO-0,2519
 bioguider/agents/rag_collection_task.py,sha256=r_jPAMjQcC7dIydKxX77UuMqjJ3MiVKswNZ-yNw7yx8,5199
 bioguider/conversation.py,sha256=DIvk_d7pz_guuORByK1eaaF09FAK-8shcNTrbSUHz9Y,1779
-bioguider/database/code_structure_db.py,sha256=drYkoQa7mDexCpulG3885Gwcnu92lnHNRlWT8byjF-A,16630
-bioguider/database/summarized_file_db.py,sha256=gGubM5vH3SN_1vouKO0LemvE_EfyjinAScRhlvxJsi0,4654
+bioguider/database/code_structure_db.py,sha256=q9tGZLWrjPi7a3u1b2iUnMO30lNWKbeMOkpDRffev2M,16973
+bioguider/database/summarized_file_db.py,sha256=U60c62e2Bx7PwsTAcCQgljNxD5u5awjpj5qpHEgJbac,4801
 bioguider/generation/__init__.py,sha256=esV02QgCsY67-HBwSHDbA5AcbKzNRIT3wDwwh6N4OFM,945
 bioguider/generation/change_planner.py,sha256=1u_1tcVwggVw6QebXvPJVULYnRAIkKMteFxbnf42aAw,6964
 bioguider/generation/document_renderer.py,sha256=67-XGFGNe8WgHJpqkHLMecgk2OeV8a5cJRAeDTLsXG4,1806
@@ -53,24 +55,26 @@ bioguider/generation/report_loader.py,sha256=KtJ6JHGPDL-PQoucU8hkVzMSz-B0bHbF2WS
 bioguider/generation/style_analyzer.py,sha256=Vn9FAK1qJBNLolLC1tz362k4UBaPl107BlvkQc8pV2I,983
 bioguider/generation/suggestion_extractor.py,sha256=tfkyWtdbAo-maLCF_wqwBXyh93yjulvDY17FuvTnTjk,7611
 bioguider/generation/test_metrics.py,sha256=fG6H1jVikHEx1YvN5Ds4QbVinudJ5OEYkzrV760oLLQ,3766
-bioguider/managers/evaluation_manager.py,sha256=obsesQdEgxBzTd1Re00kanH1d5_4_vxzXI_ndICgedg,5834
+bioguider/managers/evaluation_manager.py,sha256=2RRlVWu3kxBYrK0DRsX1k82LLFKJaNZ1i4HuCYxwJPw,6447
 bioguider/managers/generation_manager.py,sha256=EbAJSvUz-SIriVlozuJ6wa5_1aIbbFfpgg3c9Vcz34g,7615
 bioguider/managers/generation_test_manager.py,sha256=0ty8IibdfN90Oj6M6lkYbxASnQxHYb9I3w9eG7hvEsQ,3270
 bioguider/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 bioguider/rag/config.py,sha256=5g4IqTzgyfZfax9Af9CTkXShgItPOt4_9TEMSekCPik,4602
-bioguider/rag/data_pipeline.py,sha256=bkJ2IUCgPx_OL2uZtPd6cIBor2VFZEIfGd5kVlmiPjw,27292
+bioguider/rag/data_pipeline.py,sha256=hyBmjOpP1ka_y_4X0lUwlNKEBjmPNOmETEfQf-s86ZY,27316
 bioguider/rag/embedder.py,sha256=jofR8hOj3Aj2IyBQ9y6FeAc84tgq5agbIfCGyFxYpJ8,650
 bioguider/rag/rag.py,sha256=JFPwrJlKDSyd3U3Gce_NSxI5343eNUbqPG9Fs5Pfoq0,4696
 bioguider/settings.py,sha256=BD_iz9aYarxmWUl0XaKl4-D4oTXMhFzljsXLNn2phis,3143
-bioguider/utils/code_structure_builder.py,sha256=TBrsmlUPEwqpi5bSVLrOEwFK1dQ49goYJ1EGYmRrtZ8,1607
-bioguider/utils/constants.py,sha256=Yzo9oFG4P4C83vKl22RsWkIDa4dcitvcCIceusNPIRQ,8928
+bioguider/utils/code_structure_builder.py,sha256=PVeooVKxkiBEkX_VEu8h1ACGs-ynrgk_ce2FKJfeeZc,1947
+bioguider/utils/constants.py,sha256=NGmqEgxNDL1fe-htJbtHGcU94EVUK28YAupxGYOJO_c,9012
 bioguider/utils/default.gitignore,sha256=XjPdyO2KV8z8iyuqluaNR_70tBQftMpyKL8HboVNyeI,1605
-bioguider/utils/file_handler.py,sha256=xTrJBQ7VY5baIJPpX7YJP0oniPO3y9ltzayqUOQXJ5g,2644
 bioguider/utils/file_utils.py,sha256=9VfAHsz1UkFPtzAmvWZvPl1TMaKIYNjNlLgsfB8tNjg,3683
 bioguider/utils/gitignore_checker.py,sha256=pOYUwsS9D5014LxcZb0cj3s2CAYaD2uF_pYJpaNKcho,6532
+bioguider/utils/notebook_utils.py,sha256=SfU1iLuwgbDzNN-TUh_qbnfUSgn-PI6NrK6QfmdpMqQ,4009
 bioguider/utils/pyphen_utils.py,sha256=cdZc3qphkvMDeL5NiZ8Xou13M_uVNP7ifJ-FwxO-0BE,2680
-bioguider/utils/utils.py,sha256=aWtgdvB04gEiJTfQNK4aQPO1mxv2zRZTbDaGUBy9DFc,2275
-bioguider-0.2.20.dist-info/LICENSE,sha256=qzkvZcKwwA5DuSuhXMOm2LcO6BdEr4V7jwFZVL2-jL4,1065
-bioguider-0.2.20.dist-info/METADATA,sha256=jAGUMMHuLYW5_lyvc0tYcvKGYlB9YUG1hqT3Kjaqii0,1868
-bioguider-0.2.20.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-bioguider-0.2.20.dist-info/RECORD,,
+bioguider/utils/python_file_handler.py,sha256=BERiE2RHxpu3gAzv26jr8ZQetkrtnMZOv9SjpQ7WIdg,2650
+bioguider/utils/r_file_handler.py,sha256=8HpFaYKP8N1nItwr9tOx49m99pcLSt8EUtTNTJ7xNoE,19564
+bioguider/utils/utils.py,sha256=1N7Wv_i9spTBQ_FbZnlxsjC8mszbBzaegrmvuKGUISg,3531
+bioguider-0.2.22.dist-info/LICENSE,sha256=qzkvZcKwwA5DuSuhXMOm2LcO6BdEr4V7jwFZVL2-jL4,1065
+bioguider-0.2.22.dist-info/METADATA,sha256=khsXgvUKBtkO4HOo1dCqVsw8vgk7zwOh9KdZFP4DtSc,1868
+bioguider-0.2.22.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+bioguider-0.2.22.dist-info/RECORD,,

bioguider/agents/consistency_collection_execute_step.py

@@ -1,152 +0,0 @@
-import logging
-
-from langchain_openai.chat_models.base import BaseChatOpenAI
-from langchain.tools import BaseTool, StructuredTool
-from langchain.agents import AgentExecutor, create_react_agent
-from langchain_community.callbacks.openai_info import OpenAICallbackHandler
-
-from bioguider.agents.consistency_collection_task_utils import ConsistencyCollectionWorkflowState
-from bioguider.agents.consistency_collection_task_utils import ConsistencyCollectionWorkflowState
-from bioguider.database.code_structure_db import CodeStructureDb
-from bioguider.utils.constants import DEFAULT_TOKEN_USAGE
-from bioguider.agents.agent_utils import CustomOutputParser, CustomPromptTemplate
-from bioguider.agents.peo_common_step import ( 
-    PEOCommonStep,
-)
-
-logger = logging.getLogger(__name__)
-
-CONSISTENCY_EVAL_EXECUTION_SYSTEM_PROMPT = """You are an expert developer specializing in the biomedical domain.
-
-You are given a **plan** and are expected to complete it using the available tools.
-
----
-
-### **Available Tools**
-{tools}
-
----
-
-### **Your Task**
-
-Your job is to **execute the given plan step by step**, using the tools available to you.
-
----
-
-### **Output Format (Strict Order Required)**
-
-For **each step**, follow the **exact format** below and **do not change the order of the fields** under any circumstances:
-
-```
-Thought: Describe what you are thinking or planning to do next.  
-Action: The tool you are going to use (must be one of: {tool_names})  
-Action Input: The input provided to the selected action  
-Observation: The result returned by the action
-```
-
----
-
-### **Important Instructions**
-1. You may repeat the **Thought → Action → Action Input → Observation** loop as needed.  
-2. Once all steps in the plan have been executed, output all the results using this format:
-3. For each step, **only execute one tool**.
-
-```
-Thought: I have completed the plan.
-Final Answer:
-Action: <tool_name>
-Action Input: <input>
-Action Observation: <Observation1>
----
-Action: <tool_name>
-Action Input: <input>
-Action Observation: <Observation2>
----
-...
-```
-
----
-
-### **Plan**
-{plan_actions}
-
-### **Actions Already Taken**
-{agent_scratchpad}
-
----
-
-{input}
-"""
-
-class ConsistencyCollectionExecuteStep(PEOCommonStep):
-    def __init__(
-        self, 
-        llm: BaseChatOpenAI, 
-        code_structure_db: CodeStructureDb,
-        custom_tools: list[BaseTool] | None = None,
-    ):
-        self.llm = llm
-        self.code_structure_db = code_structure_db
-        self.step_name = "Consistency Collection Execute Step"
-        self.custom_tools = custom_tools if custom_tools is not None else []
-
-    def _execute_directly(self, state: ConsistencyCollectionWorkflowState):
-        plan_actions = state["plan_actions"]
-        prompt = CustomPromptTemplate(
-            template=CONSISTENCY_EVAL_EXECUTION_SYSTEM_PROMPT,
-            tools=self.custom_tools,
-            plan_actions=plan_actions,
-            input_variables=[
-                "tools", "tool_names", "agent_scratchpad",
-                "intermediate_steps", "plan_actions",
-            ],
-        )
-        output_parser = CustomOutputParser()
-        agent = create_react_agent(
-            llm=self.llm,
-            tools=self.custom_tools,
-            prompt=prompt,
-            output_parser=output_parser,
-            stop_sequence=["\nObservation:"],
-        )
-        callback_handler = OpenAICallbackHandler()
-        agent_executor = AgentExecutor(
-            agent=agent,
-            tools=self.custom_tools,
-            max_iterations=30,
-        )
-        response = agent_executor.invoke(
-            input={
-                "plan_actions": plan_actions,
-                "input": "Now, let's begin."
-            },
-            config={
-                "callbacks": [callback_handler],
-                "recursion_limit": 20,
-            },
-        )
-        if "output" in response:
-            output = response["output"]
-            self._print_step(state, step_output=f"**Execute Output:** \n{output}")
-            if "**Final Answer**" in output:
-                final_answer = output.split("**Final Answer:**")[-1].strip().strip(":")
-                step_output = final_answer
-            elif "Final Answer" in output:
-                final_answer = output.split("Final Answer")[-1].strip().strip(":")
-                step_output = final_answer
-            else:
-                step_output = output
-            self._print_step(state, step_output=step_output)
-            state["step_output"] = step_output
-        else:
-            logger.error("No output found in the response.")
-            self._print_step(
-                state,
-                step_output="Error: No output found in the response.",
-            )
-            state["step_output"] = "Error: No output found in the response."
-        
-        token_usage = vars(callback_handler)
-        token_usage = {**DEFAULT_TOKEN_USAGE, **token_usage}
-            
-        return state, token_usage

bioguider/agents/consistency_collection_observe_step.py

@@ -1,128 +0,0 @@
-from typing import Callable
-
-from langchain_openai.chat_models.base import BaseChatOpenAI
-from langchain_core.prompts import ChatPromptTemplate
-from bioguider.agents.agent_utils import ObservationResult
-from bioguider.agents.common_agent_2step import CommonAgentTwoSteps
-from bioguider.agents.consistency_collection_task_utils import ConsistencyCollectionWorkflowState
-from bioguider.agents.peo_common_step import PEOCommonStep
-
-CONSISTENCY_EVAL_OBSERVE_SYSTEM_PROMPT = """You are an expert developer specializing in the biomedical domain.
-
-### **Goal**
-Your task is to collect the function, class, and method definitions and docstrings for a given user guide/API documentation.
-
----
-
-### **Intermediate Steps**  
-Here are the results from previous steps:  
-{intermediate_steps}
-
----
-
-### **Instructions**
-1. Your goal is if you have enough information to evaluate the consistency of the user guide/API documentation.
-2. Carefully review the **Goal**, **User Guide/API Documentation**, and **Intermediate Output**.
-3. If you believe you have enough information to evaluate the consistency of the user guide/API documentation:
-
-* Proceed with the following format:
-
-  * Provide your reasoning under **Analysis**
-  * Then give your final answer under **FinalAnswer**
-  * **FinalAnswer** format must exactly match this format:
-    **FinalAnswer**: {{"final_answer": "yes" or "no"}}
-  * Your answer **must exactly match the follwing format** (note: no JSON code block, no additional comments), **do not** make up anything:
-
-  ```
-  **Analysis**: your analysis here 
-  **FinalAnswer**: {{"final_answer": "yes" or "no"}}
-  ```
-4. If you believe you do not have enough information to evaluate the consistency of the user guide/API documentation:
-
-* Provide your reasoning under **Thoughts**:
-
-  ```
-  **Thoughts**: your thoughts here
-  ```
-
-Be precise and support your reasoning with evidence from the input.
-
----
-
-### **Notes**
-We are collecting information over multiple rounds, your thoughts and the output of this step will be persisted, so please **do not rush to provide a Final Answer**.  
-If you find the current information insufficient, share your reasoning or thoughts instead—we’ll continue with the next round accordingly.
-
----
-
-### **Input User Guide/API Documentation**
-{user_guide_api_documentation}
-
----
-
-"""
-
-
-class ConsistencyCollectionObserveStep(PEOCommonStep):
-    def __init__(
-        self,
-        llm: BaseChatOpenAI,
-    ):
-        super().__init__(llm=llm)
-        self.step_name = "Consistency Collection Observe Step"
-
-    def _build_prompt(self, state):
-        user_guide_api_documentation = state["user_guide_api_documentation"]
-        intermediate_steps = self._build_intermediate_steps(state)
-        prompt = ChatPromptTemplate.from_template(CONSISTENCY_EVAL_OBSERVE_SYSTEM_PROMPT)
-        return prompt.format(
-            user_guide_api_documentation=user_guide_api_documentation,
-            intermediate_steps=intermediate_steps,
-        )
-
-    def _collect_final_answer(self, state: ConsistencyCollectionWorkflowState):
-        if not ("final_answer" in state and state["final_answer"] is not None and
-            state["final_answer"].strip().lower() == "yes"):
-            return None
-        
-        final_result = ""
-        if "intermediate_steps" in state and state["intermediate_steps"] is not None:
-            for i in range(len(state["intermediate_steps"])):
-                final_result += state["intermediate_steps"][i]
-                final_result += "\n\n"
-        if "step_output" in state and state["step_output"] is not None:
-            final_result += state["step_output"]
-            final_result += "\n\n"
-        
-        return final_result
-
-            
-    def _execute_directly(self, state: ConsistencyCollectionWorkflowState):
-        system_prompt = self._build_prompt(state)
-        agent = CommonAgentTwoSteps(llm=self.llm)
-        res, _, token_usage, reasoning_process = agent.go(
-            system_prompt=system_prompt,
-            instruction_prompt="Now, let's begin the consistency collection observe step.",
-            schema=ObservationResult,
-        )
-        state["final_answer"] = res.FinalAnswer
-        analysis = res.Analysis
-        thoughts = res.Thoughts
-        state["step_analysis"] = analysis
-        state["step_thoughts"] = thoughts
-        state["step_count"] += 1
-        state["final_assembly_result"] = self._collect_final_answer(state)
-        self._print_step(
-            state,
-            step_output=f"**Observation Reasoning Process {state['step_count']}**\n{reasoning_process}"
-        )
-        self._print_step(
-            state,
-            step_output=f"Final Answer: {res.FinalAnswer if res.FinalAnswer else None}\nAnalysis: {analysis}\nThoughts: {thoughts}",
-        )
-        if state["final_assembly_result"] is not None:
-            self._print_step(
-                state,
-                step_output=f"Final Assembly Result: {state['final_assembly_result']}",
-            )
-        return state, token_usage

bioguider/agents/consistency_collection_plan_step.py

@@ -1,128 +0,0 @@
-from langchain_openai.chat_models.base import BaseChatOpenAI
-
-from langchain.tools import BaseTool
-from langchain_core.prompts import ChatPromptTemplate, StringPromptTemplate
-from bioguider.agents.agent_utils import (
-    convert_plan_to_string, 
-    get_tool_names_and_descriptions,
-    PlanAgentResultJsonSchema,
-    PlanAgentResult,
-)
-from bioguider.agents.common_agent_2step import CommonAgentTwoChainSteps, CommonAgentTwoSteps
-from bioguider.agents.consistency_collection_task_utils import ConsistencyCollectionWorkflowState
-from bioguider.agents.peo_common_step import PEOCommonStep
-
-CONSISTANCE_EVAL_PLAN_SYSTEM_PROMPT = ChatPromptTemplate.from_template("""### **Goal**  
-You are an expert developer specializing in the biomedical domain. 
-Your task is to collect the function, class, and method definitions and docstrings for a given user guide/API documentation.
-
----
-
-### **Function Tools**  
-You have access to the following function tools:  
-{tools}
-
----
-
-### **Intermediate Steps**  
-Here are the results from previous steps:  
-{intermediate_steps}
-
----
-
-### **Intermediate Thoughts**  
-- **Analysis**: {intermediate_analysis}  
-- **Thoughts**: {intermediate_thoughts}
-
----
-
-### **Instructions**
-1. We will iterate through multiple **Plan -> Execution -> Observation** loops as needed.  
-   - All variables and tool outputs are **persisted across rounds**, so you can build on prior results.  
-   - Develop your plan **incrementally**, and reflect on intermediate observations before proceeding.  
-   - Limit each step to **one or two actions** — avoid trying to complete everything in a single step.
-
-2. Your task is to evaluate the consistency of the user guide/API documentation.
-
-3. You may use 
-   - the `retrieve_function_definition_and_docstring` tool to get the function definition and docstring or,
-   - the `retrieve_class_definition_and_docstring` to get the class definition and docstring or,
-   - the `retrieve_class_and_method_definition_and_docstring` to get the class and method definition and docstring.
-
-4. Your plan can only use the above tools, **do not** make up any tools not in the above tools list.
-
-5. If no function, class, or method is found in the given user guide/API documentation, you should return "N/A" as an empty plan.
-   Our tools can only retrieve the **function**, **class**, **method** definition and docstring, **do not** make up any function, class, or method name.
-    
-    
-### **Input User Guide/API Documentation**
-{user_guide_api_documentation}
-
-### **Output Format**
-Your plan **must exactly match** a sequence of steps in the following format, **do not** make up anything:
-
-Step: <tool name>   # Tool name **must be one** of {tool_names}  
-Step Input: <function/class/method name>
-Step Input: <file path, if not sure, just put "N/A">
-
-Step: <tool name>  # Tool name **must be one** of {tool_names}  
-Step Input: <function/class/method name>
-Step Input: <file path, if not sure, just put "N/A">
-...
-
-...
-""")
-
-class ConsistencyCollectionPlanStep(PEOCommonStep):
-    """
-    ConsistencyCollectionPlanStep is a step in the consistency collection plan process.
-    It is responsible for initializing the tools and compiling the step.
-    """
-    
-    def __init__(
-        self, 
-        llm: BaseChatOpenAI,
-        custom_tools: list[BaseTool] | None = None,
-    ):
-        super().__init__(llm)
-        self.step_name = "Consistency Collection Plan Step"
-        self.custom_tools = custom_tools if custom_tools is not None else []
-    
-    def _prepare_system_prompt(self, state: ConsistencyCollectionWorkflowState) -> str:
-        user_guide_api_documentation = state["user_guide_api_documentation"]
-        intermediate_steps = self._build_intermediate_steps(state)
-        step_analysis, step_thoughts = self._build_intermediate_analysis_and_thoughts(state)
-        tool_names, tools_desc = get_tool_names_and_descriptions(self.custom_tools)
-        system_prompt = CONSISTANCE_EVAL_PLAN_SYSTEM_PROMPT.format(
-            tools=tools_desc,
-            intermediate_steps=intermediate_steps,
-            intermediate_analysis=step_analysis,
-            intermediate_thoughts=step_thoughts,
-            tool_names=tool_names,
-            user_guide_api_documentation=user_guide_api_documentation,
-        )
-        self._print_step(
-            state,
-            step_output="**Intermediate Step Output**\n" + intermediate_steps
-        )
-        self._print_step(
-            state,
-            step_output="**Intermediate Step Analysis**\n{step_analysis}\n**Intermediate Step Thoughts**\n{step_thoughts}",
-        )
-        return system_prompt
-
-    def _execute_directly(self, state: ConsistencyCollectionWorkflowState):
-        system_prompt = self._prepare_system_prompt(state)
-        agent = CommonAgentTwoSteps(llm=self.llm)
-        res, _, token_usage, reasoning_process = agent.go(
-            system_prompt=system_prompt,
-            instruction_prompt="Now, let's begin the consistency collection plan step.",
-            schema=PlanAgentResultJsonSchema,
-        )
-        PEOCommonStep._reset_step_state(state)
-        res = PlanAgentResult(**res)
-        self._print_step(state, step_output=f"**Reasoning Process**\n{reasoning_process}")
-        self._print_step(state, step_output=f"**Plan**\n{str(res.actions)}")
-        state["plan_actions"] = convert_plan_to_string(res)
-
-        return state, token_usage

bioguider/agents/consistency_collection_task.py

@@ -1,109 +0,0 @@
-import os
-from typing import Callable, Optional, TypedDict
-from langchain.prompts import ChatPromptTemplate
-from langchain_openai.chat_models.base import BaseChatOpenAI
-from langchain_core.messages import AIMessage
-from langchain.tools import StructuredTool
-from pydantic import BaseModel, Field
-import logging
-from langgraph.graph import StateGraph, START, END
-
-from bioguider.agents.agent_task import AgentTask
-from bioguider.agents.agent_tools import agent_tool
-from bioguider.agents.agent_utils import read_file, summarize_file
-from bioguider.agents.peo_common_step import PEOWorkflowState
-from bioguider.agents.common_agent import CommonAgent
-from bioguider.agents.common_agent_2step import CommonAgentTwoSteps
-from bioguider.agents.consistency_collection_task_utils import (
-    ConsistencyCollectionWorkflowState,
-    retrieve_function_definition_and_docstring_tool,
-    retrieve_class_definition_and_docstring_tool,
-    retrieve_class_and_method_definition_and_docstring_tool,
-    retrieve_method_definition_and_docstring_tool,
-)
-from bioguider.agents.consistency_collection_plan_step import ConsistencyCollectionPlanStep
-from bioguider.agents.consistency_collection_observe_step import ConsistencyCollectionObserveStep
-from bioguider.agents.consistency_collection_execute_step import ConsistencyCollectionExecuteStep
-from bioguider.database.code_structure_db import CodeStructureDb
-
-logger = logging.getLogger(__name__)
-
-class ConsistencyCollectionTask(AgentTask):
-    def __init__(
-        self, 
-        llm: BaseChatOpenAI,
-        code_structure_db: CodeStructureDb,
-        step_callback: Callable | None = None,
-    ):
-        super().__init__(llm=llm, step_callback=step_callback)
-        self.llm = llm
-        self.code_structure_db = code_structure_db
-        
-        func_tool = retrieve_function_definition_and_docstring_tool(llm=llm, code_structure_db=code_structure_db)
-        class_tool = retrieve_class_definition_and_docstring_tool(llm=llm, code_structure_db=code_structure_db)
-        class_and_method_tool = retrieve_class_and_method_definition_and_docstring_tool(llm=llm, code_structure_db=code_structure_db)
-        method_tool = retrieve_method_definition_and_docstring_tool(llm=llm, code_structure_db=code_structure_db)
-        self.tools = [func_tool, class_tool, class_and_method_tool, method_tool]
-        self.custom_tools = [            
-            StructuredTool.from_function(
-                func_tool.run,
-                description=func_tool.__class__.__doc__,
-                name=func_tool.__class__.__name__,
-            ),            
-            StructuredTool.from_function(
-                class_tool.run,
-                description=class_tool.__class__.__doc__,
-                name=class_tool.__class__.__name__,
-            ),            
-            StructuredTool.from_function(
-                class_and_method_tool.run,
-                description=class_and_method_tool.__class__.__doc__,
-                name=class_and_method_tool.__class__.__name__,
-            ),
-            StructuredTool.from_function(
-                method_tool.run,
-                description=method_tool.__class__.__doc__,
-                name=method_tool.__class__.__name__,
-            ),
-        ]
-
-        self.steps = [
-            ConsistencyCollectionPlanStep(llm=llm, custom_tools=self.custom_tools), 
-            ConsistencyCollectionExecuteStep(llm=llm, code_structure_db=code_structure_db, custom_tools=self.custom_tools),
-            ConsistencyCollectionObserveStep(llm=llm)
-        ]
-
-    def _compile(self, repo_path: str, gitignore_path: str):
-        def check_observe_step(state: ConsistencyCollectionWorkflowState):
-            if "final_answer" in state and state["final_answer"] is not None:
-                return END
-            return "plan_step"
-        def check_plan_step(state: ConsistencyCollectionWorkflowState):
-            if "plan_actions" in state and state["plan_actions"] is not None and len(state["plan_actions"]) > 0:
-                return "execute_step"
-            return END
-        
-        graph = StateGraph(ConsistencyCollectionWorkflowState)
-        graph.add_node("plan_step", self.steps[0].execute)
-        graph.add_node("execute_step", self.steps[1].execute)
-        graph.add_node("observe_step", self.steps[2].execute)
-        graph.add_edge(START, "plan_step")
-        graph.add_conditional_edges("plan_step", check_plan_step, {"execute_step", END})
-        graph.add_edge("execute_step", "observe_step")
-        graph.add_conditional_edges("observe_step", check_observe_step, {"plan_step", END})
-
-        self.graph = graph.compile()
-
-    def collect(self, user_guide_api_documentation: str) -> tuple[bool, str | None]:
-        s = self._go_graph({
-            "user_guide_api_documentation": user_guide_api_documentation,
-            "step_count": 0,
-        })
-        # analyze the final assembly result
-        if "final_assembly_result" in s and s["final_assembly_result"] is not None:
-            self._print_step(step_name="Final Assembly Result")
-            self._print_step(step_output=s["final_assembly_result"])
-            return True, s["final_assembly_result"]
-        else:
-            return False, s["thoughts"] if "thoughts" in s else None
-