Team Workflow aggiornato #37

2025-10-19T19:04:55+02:00

Berack96 commented

2025-10-19 19:04:55 +02:00

(Migrated from github.com)

This pull request refactors the agent pipeline input and output structure by consolidating and simplifying class definitions.

Simo93-rgb (Migrated from github.com) approved these changes 2025-10-20 18:04:14 +02:00

copilot-pull-request-reviewer[bot] (Migrated from github.com) reviewed 2025-10-20 18:05:29 +02:00

copilot-pull-request-reviewer[bot] (Migrated from github.com) left a comment

Pull Request Overview

This PR refactors the agent pipeline to introduce a multi-step workflow with query validation, team-based information recovery, and report generation. The changes replace the previous "predictor" approach with a more structured "query analyzer" and "report generator" pattern.

Key Changes:

Introduced query validation and report generation steps into the pipeline workflow
Refactored agent prompts to provide clearer instructions with fallback strategies and error handling
Consolidated pipeline input/output structures by moving core classes to a dedicated module

Reviewed Changes

Copilot reviewed 18 out of 18 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
tests/agents/test_team.py	Added test suite for team agent workflow execution
tests/agents/test_report.py	Added test suite for report generation agent
tests/agents/test_query_check.py	Added test suite for query validation logic
src/app/configs.py	Replaced `predictor_model` with `query_analyzer_model` and `report_generation_model`
src/app/api/wrapper_handler.py	Changed logging level from info to debug for wrapper operations
src/app/agents/prompts/team_social.txt	Updated social agent instructions with fallback tool strategy and error handling
src/app/agents/prompts/team_news.txt	Updated news agent instructions with fallback tool strategy and error handling
src/app/agents/prompts/team_market.txt	Updated market agent instructions with fallback tool strategy and error handling
src/app/agents/prompts/team_leader.txt	Completely restructured team leader instructions with workflow rules and report structure
src/app/agents/prompts/report_generation.txt	Added new report generation instructions for markdown formatting
src/app/agents/prompts/query_check.txt	Added new query validation instructions
src/app/agents/prompts/predictor.txt	Removed predictor agent instructions (replaced by new workflow)
src/app/agents/prompts/init.py	Updated exports to reflect new agent structure
src/app/agents/predictor.py	Removed predictor module (replaced by query analyzer and report generator)
src/app/agents/pipeline.py	Refactored pipeline to use multi-step workflow with query check and report generation
src/app/agents/core.py	Created new module consolidating pipeline inputs/outputs and agent factory methods
src/app/agents/init.py	Updated exports to reflect new structure
configs.yaml	Updated agent configuration with new model assignments

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

## Pull Request Overview This PR refactors the agent pipeline to introduce a multi-step workflow with query validation, team-based information recovery, and report generation. The changes replace the previous "predictor" approach with a more structured "query analyzer" and "report generator" pattern. **Key Changes:** - Introduced query validation and report generation steps into the pipeline workflow - Refactored agent prompts to provide clearer instructions with fallback strategies and error handling - Consolidated pipeline input/output structures by moving core classes to a dedicated module ### Reviewed Changes Copilot reviewed 18 out of 18 changed files in this pull request and generated 6 comments. <details> <summary>Show a summary per file</summary> | File | Description | | ---- | ----------- | | tests/agents/test_team.py | Added test suite for team agent workflow execution | | tests/agents/test_report.py | Added test suite for report generation agent | | tests/agents/test_query_check.py | Added test suite for query validation logic | | src/app/configs.py | Replaced `predictor_model` with `query_analyzer_model` and `report_generation_model` | | src/app/api/wrapper_handler.py | Changed logging level from info to debug for wrapper operations | | src/app/agents/prompts/team_social.txt | Updated social agent instructions with fallback tool strategy and error handling | | src/app/agents/prompts/team_news.txt | Updated news agent instructions with fallback tool strategy and error handling | | src/app/agents/prompts/team_market.txt | Updated market agent instructions with fallback tool strategy and error handling | | src/app/agents/prompts/team_leader.txt | Completely restructured team leader instructions with workflow rules and report structure | | src/app/agents/prompts/report_generation.txt | Added new report generation instructions for markdown formatting | | src/app/agents/prompts/query_check.txt | Added new query validation instructions | | src/app/agents/prompts/predictor.txt | Removed predictor agent instructions (replaced by new workflow) | | src/app/agents/prompts/__init__.py | Updated exports to reflect new agent structure | | src/app/agents/predictor.py | Removed predictor module (replaced by query analyzer and report generator) | | src/app/agents/pipeline.py | Refactored pipeline to use multi-step workflow with query check and report generation | | src/app/agents/core.py | Created new module consolidating pipeline inputs/outputs and agent factory methods | | src/app/agents/__init__.py | Updated exports to reflect new structure | | configs.yaml | Updated agent configuration with new model assignments | </details> --- <sub>**Tip:** Customize your code reviews with copilot-instructions.md. <a href="/Berack96/upo-appAI/new/main/.github?filename=copilot-instructions.md" class="Link--inTextBlock" target="_blank" rel="noopener noreferrer">Create the file</a> or <a href="https://docs.github.com/en/copilot/customizing-copilot/adding-repository-custom-instructions-for-github-copilot" class="Link--inTextBlock" target="_blank" rel="noopener noreferrer">learn how to get started</a>.</sub>

configs.yaml

						
				@@ -41,5 +41,6 @@ api:

				agents:

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 18:05:29 +02:00

The predictor_model configuration field appears to be unused after the refactoring that replaced it with query_analyzer_model and report_generation_model. This configuration should be removed to avoid confusion.

The `predictor_model` configuration field appears to be unused after the refactoring that replaced it with `query_analyzer_model` and `report_generation_model`. This configuration should be removed to avoid confusion. ```suggestion ```

src/app/agents/__init__.py

						
				@@ -1,4 +1,4 @@

				from app.agents.predictor import PredictorInput, PredictorOutput

				from app.agents.pipeline import Pipeline, PipelineInputs, PipelineEvent

				from app.agents.pipeline import Pipeline, PipelineEvent

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 18:05:29 +02:00

PipelineInputs is imported twice from different modules, which will cause the second import to shadow the first. Remove the duplicate import from line 1.

from app.agents.pipeline import Pipeline, PipelineEvent

`PipelineInputs` is imported twice from different modules, which will cause the second import to shadow the first. Remove the duplicate import from line 1. ```suggestion from app.agents.pipeline import Pipeline, PipelineEvent ```

src/app/agents/core.py

						
				@@ -0,0 +46,4 @@

				        Sceglie il modello LLM da usare per il Team Leader.

				        """

				        assert index >= 0 and index < len(self.configs.models.all_models), "Index out of range for models list."

				        self.team_leader_model = self.configs.models.all_models[index]

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 18:05:28 +02:00

Variable assignment uses team_leader_model instead of leader_model as mentioned in the method's docstring. The docstring should be updated or the variable name should be consistent.

Variable assignment uses `team_leader_model` instead of `leader_model` as mentioned in the method's docstring. The docstring should be updated or the variable name should be consistent.

src/app/agents/prompts/team_news.txt

						
				@@ -5,3 +1,1 @@

				2.  `get_top_headlines(limit: int)`: Get the 'limit' top global news headlines.

				3.  `get_latest_news_aggregated(query: str, limit: int)`: Get aggregated latest news articles for a specific 'query'.

				4.  `get_top_headlines_aggregated(limit: int)`: Get aggregated top global news headlines.

				**TASK:** You are a specialized **Crypto News Analyst**. Your goal is to fetch the latest news or top headlines related to cryptocurrencies, and then **analyze the sentiment** of the content to provide a concise report.

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 18:05:28 +02:00

Corrected spelling of 'Etherium' to 'Ethereum'.

- **Querying:** You can search for more general news, but prioritize querying with a relevant crypto (e.g., 'Bitcoin', 'Ethereum').

Corrected spelling of 'Etherium' to 'Ethereum'. ```suggestion - **Querying:** You can search for more general news, but prioritize querying with a relevant crypto (e.g., 'Bitcoin', 'Ethereum'). ```

tests/agents/test_query_check.py

						
				@@ -0,0 +1,48 @@

				import pytest

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 18:05:28 +02:00

Corrected spelling of 'Etherium' to 'Ethereum'.

        response = self.agent.run("Ha senso investire in Ethereum?")  #type: ignore

Corrected spelling of 'Etherium' to 'Ethereum'. ```suggestion response = self.agent.run("Ha senso investire in Ethereum?") #type: ignore ```

tests/agents/test_team.py

						
				@@ -0,0 +1,37 @@

				import asyncio

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 18:05:27 +02:00

Unconditional assertion failure will cause this test to always fail. This appears to be a debugging leftover that should be removed.

Unconditional assertion failure will cause this test to always fail. This appears to be a debugging leftover that should be removed. ```suggestion ```

copilot-pull-request-reviewer[bot] (Migrated from github.com) reviewed 2025-10-20 21:52:01 +02:00

copilot-pull-request-reviewer[bot] (Migrated from github.com) left a comment

Pull Request Overview

Copilot reviewed 19 out of 19 changed files in this pull request and generated 10 comments.

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

## Pull Request Overview Copilot reviewed 19 out of 19 changed files in this pull request and generated 10 comments. --- <sub>**Tip:** Customize your code reviews with copilot-instructions.md. <a href="/Berack96/upo-appAI/new/main/.github?filename=copilot-instructions.md" class="Link--inTextBlock" target="_blank" rel="noopener noreferrer">Create the file</a> or <a href="https://docs.github.com/en/copilot/customizing-copilot/adding-repository-custom-instructions-for-github-copilot" class="Link--inTextBlock" target="_blank" rel="noopener noreferrer">learn how to get started</a>.</sub>

src/app/agents/core.py

						
				@@ -0,0 +46,4 @@

				        Sceglie il modello LLM da usare per il Team Leader.

				        """

				        assert index >= 0 and index < len(self.configs.models.all_models), "Index out of range for models list."

				        self.team_leader_model = self.configs.models.all_models[index]

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:51:58 +02:00

The choose_team_leader method assigns to self.team_leader_model but the initialization in __init__ uses a different assignment pattern via get_model_by_name(). This inconsistency means the model assignment won't have the same validation and could break if index is out of bounds. Use self.team_leader_model = self.configs.models.all_models[index] with proper validation or use the same pattern as __init__.

        model_list = self.configs.models.all_models
        if 0 <= index < len(model_list):
            model_name = model_list[index].name
            self.team_leader_model = self.configs.get_model_by_name(model_name)
        else:
            raise IndexError(f"Model index {index} out of range for team leader selection.")

The `choose_team_leader` method assigns to `self.team_leader_model` but the initialization in `__init__` uses a different assignment pattern via `get_model_by_name()`. This inconsistency means the model assignment won't have the same validation and could break if `index` is out of bounds. Use `self.team_leader_model = self.configs.models.all_models[index]` with proper validation or use the same pattern as `__init__`. ```suggestion model_list = self.configs.models.all_models if 0 <= index < len(model_list): model_name = model_list[index].name self.team_leader_model = self.configs.get_model_by_name(model_name) else: raise IndexError(f"Model index {index} out of range for team leader selection.") ```

src/app/agents/core.py

						
				@@ -0,0 +53,4 @@

				        Sceglie il modello LLM da usare per il Team.

				        """

				        assert index >= 0 and index < len(self.configs.models.all_models), "Index out of range for models list."

				        self.team_model = self.configs.models.all_models[index]

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:51:59 +02:00

The choose_team method has the same issue as choose_team_leader: it directly indexes into all_models without validation, which could raise an IndexError if the index is invalid. Consider adding bounds checking or using a safer retrieval method.

        all_models = self.configs.models.all_models
        if not (0 <= index < len(all_models)):
            raise ValueError(f"Invalid index {index} for team models. Must be between 0 and {len(all_models)-1}.")
        self.team_model = all_models[index]

The `choose_team` method has the same issue as `choose_team_leader`: it directly indexes into `all_models` without validation, which could raise an `IndexError` if the index is invalid. Consider adding bounds checking or using a safer retrieval method. ```suggestion all_models = self.configs.models.all_models if not (0 <= index < len(all_models)): raise ValueError(f"Invalid index {index} for team models. Must be between 0 and {len(all_models)-1}.") self.team_model = all_models[index] ```

src/app/agents/pipeline.py

						
				@@ -93,12 +46,14 @@ class Pipeline:

				    """

				    def __init__(self, inputs: PipelineInputs):

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:51:58 +02:00

The Pipeline class is missing a docstring. Add a class-level docstring explaining its purpose, key responsibilities, and basic usage pattern.

The `Pipeline` class is missing a docstring. Add a class-level docstring explaining its purpose, key responsibilities, and basic usage pattern.

src/app/agents/plan_memory_tool.py

						
				@@ -0,0 +1,55 @@

				from agno.tools.toolkit import Toolkit

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:51:59 +02:00

The # type: ignore comment suggests a type-checking issue. If Toolkit.__init__ requires specific typing that conflicts with how it's being called, consider using a more specific type ignore directive like # type: ignore[call-arg] or address the underlying type mismatch.

The `# type: ignore` comment suggests a type-checking issue. If `Toolkit.__init__` requires specific typing that conflicts with how it's being called, consider using a more specific type ignore directive like `# type: ignore[call-arg]` or address the underlying type mismatch.

src/app/agents/prompts/query_check.txt

						
				@@ -0,0 +1,18 @@

				GOAL: check if the query is crypto-related

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:52:00 +02:00

Corrected spelling of 'releated' to 'related'.

    - if is not crypto related, then output why is not related in a brief message

Corrected spelling of 'releated' to 'related'. ```suggestion - if is not crypto related, then output why is not related in a brief message ```

tests/agents/test_query_check.py

						
				@@ -0,0 +1,48 @@

				import pytest

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:51:59 +02:00

The #type: ignore comment is missing a space after #. Use # type: ignore for consistency with Python style conventions.

The `#type: ignore` comment is missing a space after `#`. Use `# type: ignore` for consistency with Python style conventions.

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:52:00 +02:00

The #type: ignore comment is missing a space after #. Use # type: ignore for consistency with Python style conventions.

        response = self.agent.run("What is the capital of France?")  # type: ignore

The `#type: ignore` comment is missing a space after `#`. Use `# type: ignore` for consistency with Python style conventions. ```suggestion response = self.agent.run("What is the capital of France?") # type: ignore ```

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:52:00 +02:00

The #type: ignore comment is missing a space after #. Use # type: ignore for consistency with Python style conventions.

The `#type: ignore` comment is missing a space after `#`. Use `# type: ignore` for consistency with Python style conventions.

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:52:00 +02:00

The #type: ignore comment is missing a space after #. Use # type: ignore for consistency with Python style conventions.

        response = self.agent.run("Ha senso investire in Ethereum?")  # type: ignore

The `#type: ignore` comment is missing a space after `#`. Use `# type: ignore` for consistency with Python style conventions. ```suggestion response = self.agent.run("Ha senso investire in Ethereum?") # type: ignore ```

tests/agents/test_report.py

						
				@@ -0,0 +1,31 @@

				import pytest

copilot-pull-request-reviewer[bot] (Migrated from github.com) commented

2025-10-20 21:51:59 +02:00

The #type: ignore comment is missing a space after #. Use # type: ignore for consistency with Python style conventions.

        response = self.agent.run(sample_data)  # type: ignore

The `#type: ignore` comment is missing a space after `#`. Use `# type: ignore` for consistency with Python style conventions. ```suggestion response = self.agent.run(sample_data) # type: ignore ```

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: Berack/upo-app-agents#37

				`@@ -0,0 +1,18 @@`
				`GOAL: check if the query is crypto-related`