Merge pull request #1 from bkrabach/papayne/assistant-drive

dedupes functionality from attachment agent into assistant drive

.devcontainer/devcontainer.json

@@ -57,7 +57,6 @@
         "epivision.vscode-file-header",
         "esbenp.prettier-vscode",
         "github.vscode-github-actions",
-        "matt-rudge.auto-open-preview-panel",
         "ms-azuretools.vscode-docker",
         "ms-python.debugpy",
         "ms-python.python",

.vscode/settings.json

@@ -23,13 +23,15 @@
     "**/.data/**",
     "**/__pycache__/**"
   ],
-  "python.analysis.fixAll": ["source.unusedImports"],
+  "python.analysis.fixAll": [
+    "source.unusedImports"
+  ],
   "python.analysis.inlayHints.functionReturnTypes": true,
   "python.analysis.typeCheckingMode": "basic",
   "python.defaultInterpreterPath": "${workspaceFolder}/workbench-service/.venv",
   "python.languageServer": "Pylance",
   "python.testing.pytestEnabled": true,
-  "python.testing.cwd": "${workspaceFolder:v1}/workbench-service",
+  "python.testing.cwd": "${workspaceFolder}/workbench-service",
   "python.testing.pytestArgs": [],
   "[python]": {
     "editor.defaultFormatter": "charliermarsh.ruff",
@@ -56,7 +58,9 @@
       "source.fixAll": "explicit"
     }
   },
-  "css.lint.validProperties": ["composes"],
+  "css.lint.validProperties": [
+    "composes"
+  ],
   "editor.defaultFormatter": "esbenp.prettier-vscode",
   "eslint.lintTask.enable": true,
   "editor.formatOnPaste": true,

CONTRIBUTING.md

@@ -99,6 +99,8 @@ We use and recommend the following workflow:
 8. Wait for feedback or approval of your changes from the code maintainers.
 9. When area owners have signed off, and all checks are green, your PR will be merged.
 
+For a detailed walkthrough of this workflow, including how to set up forks and manage your Git workflow, refer to the [Detailed Workflow Walkthrough](#detailed-workflow-walkthrough) section.
+
 ### Adding Assistants
 
 We appreciate your interest in extending Semantic Workbench's functionality through
@@ -120,3 +122,99 @@ and test runs must be clean.
 
 If the CI build fails for any reason, the PR issue will be updated with a link
 that can be used to determine the cause of the failure.
+
+### Detailed Workflow Walkthrough
+
+This detailed guide walks you through the process of contributing to our repository via forking, cloning, and managing your Git workflow.
+
+Start by forking the repository on GitHub. This creates a copy of the repository under your GitHub account.
+
+Clone your forked repository to your local machine:
+
+```bash
+git clone https://github.com/YOUR_USERNAME/semanticworkbench.git
+cd semanticworkbench
+```
+
+Add the original repository as an upstream remote:
+
+```bash
+git remote add upstream https://github.com/microsoft/semanticworkbench.git
+```
+
+Check your remotes to ensure you have both `origin` and `upstream`:
+
+```bash
+git remote -v
+```
+
+You should see something like this:
+
+```
+origin    https://github.com/YOUR_USERNAME/semanticworkbench.git (fetch)
+origin    https://github.com/YOUR_USERNAME/semanticworkbench.git (push)
+upstream  https://github.com/microsoft/semanticworkbench.git (fetch)
+upstream  https://github.com/microsoft/semanticworkbench.git (push)
+```
+
+To keep your fork updated with the latest changes from upstream, configure your local `main` branch to track the upstream `main` branch:
+
+```bash
+git branch -u upstream/main main
+```
+
+Alternatively, you can edit your `.git/config` file:
+
+```ini
+[branch "main"]
+    remote = upstream
+    merge = refs/heads/main
+```
+
+Before starting a new feature or bug fix, ensure that your fork is up-to-date with the latest changes from upstream:
+
+```bash
+git checkout main
+git pull upstream main
+```
+
+Create a new branch for your feature or bug fix:
+
+```bash
+git checkout -b feature-name
+```
+
+Make your changes in the codebase. Once you are satisfied, add and commit your changes:
+
+```bash
+git add .
+git commit -m "Description of your changes"
+```
+
+Push your changes to your fork:
+
+```bash
+git push origin feature-name
+```
+
+Go to your fork on GitHub, and you should see a `Compare & pull request` button. Click it and submit your pull request (PR) against the original repository’s `main` branch.
+
+If there are changes in the main repository after you created your branch, sync them to your branch:
+
+```bash
+git checkout main
+git pull upstream main
+git checkout feature-name
+git rebase main
+```
+
+Once your PR is merged, you can delete your branch both locally and from GitHub.
+
+**Locally:**
+
+```bash
+git branch -d feature-name
+```
+
+**On GitHub:**
+Go to your fork and delete the branch from the `Branches` section.

README.md

@@ -103,6 +103,8 @@ When you submit a pull request, a CLA bot will automatically determine whether y
 a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
 provided by the bot. You will only need to do this once across all repos using our CLA.
 
+Please see the detailed [contributing guide](CONTRIBUTING.md) for more information on how you can get involved.
+
 This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
 For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
 contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.

assistants/guided-conversation-assistant/assistant/agents/guided_conversation/config.py

@@ -90,7 +90,7 @@ class GuidedConversationAgentConfigModel(BaseModel):
             description="A loose natural language description of the steps of the conversation",
         ),
         UISchema(widget="textarea", placeholder="[optional]"),
-    ] = config_defaults.conversation_flow
+    ] = config_defaults.conversation_flow.strip()
 
     context: Annotated[
         str,
@@ -99,7 +99,7 @@ class GuidedConversationAgentConfigModel(BaseModel):
             description="General background context for the conversation.",
         ),
         UISchema(widget="textarea", placeholder="[optional]"),
-    ] = config_defaults.context
+    ] = config_defaults.context.strip()
 
     class ResourceConstraint(ResourceConstraint):
         mode: Annotated[

assistants/guided-conversation-assistant/assistant/agents/guided_conversation/config_defaults.py

@@ -15,8 +15,10 @@ class ArtifactModel(BaseModel):
     initial_feedback: str = Field(description="Feedback on the student's final revised poem.")
     final_feedback: str = Field(description="Feedback on how the student was able to improve their poem.")
     inappropriate_behavior: list[str] = Field(
-        description="""List any inappropriate behavior the student attempted while chatting with you. \
-It is ok to leave this field Unanswered if there was none."""
+        description="""
+List any inappropriate behavior the student attempted while chatting with you.
+It is ok to leave this field Unanswered if there was none.
+"""
     )
 
 
@@ -27,7 +29,8 @@ class ArtifactModel(BaseModel):
 ]
 
 # Conversation Flow (optional) - This defines in natural language the steps of the conversation.
-conversation_flow = """1. Start by explaining interactively what an acrostic poem is.
+conversation_flow = """
+1. Start by explaining interactively what an acrostic poem is.
 2. Then give the following instructions for how to go ahead and write one:
     1. Choose a word or phrase that will be the subject of your acrostic poem.
     2. Write the letters of your chosen word or phrase vertically down the page.
@@ -39,14 +42,17 @@ class ArtifactModel(BaseModel):
     Pizza parties on the weekend,
     Puppies we bend down to tend,
     Yelling yay when we win the game
-4. Finally have the student write their own acrostic poem using the word or phrase of their choice. Encourage them to be creative and have fun with it.
-After they write it, you should review it and give them feedback on what they did well and what they could improve on.
-Have them revise their poem based on your feedback and then review it again.
+4. Finally have the student write their own acrostic poem using the word or phrase of their choice. Encourage them
+to be creative and have fun with it. After they write it, you should review it and give them feedback on what they
+did well and what they could improve on. Have them revise their poem based on your feedback and then review it again.
 """
 
 # Context (optional) - This is any additional information or the circumstances the agent is in that it should be aware of.
 # It can also include the high level goal of the conversation if needed.
-context = """You are working 1 on 1 a 4th grade student who is chatting with you in the computer lab at school while being supervised by their teacher."""
+context = """
+You are working 1 on 1 a 4th grade student who is chatting with you in the computer lab at school while being
+supervised by their teacher.
+"""
 
 
 # Resource Constraints (optional) - This defines the constraints on the conversation such as time or turns.

assistants/prospector-assistant/.vscode/settings.json

@@ -59,6 +59,7 @@
     "pydantic",
     "pyproject",
     "tiktoken",
+    "updown",
     "virtualenvs"
   ]
 }

assistants/prospector-assistant/assistant/agents/artifact_agent.py

@@ -1,4 +1,3 @@
-import pathlib
 from pathlib import Path
 from typing import TYPE_CHECKING, Annotated, Literal, Union
 
@@ -12,40 +11,21 @@
 from semantic_workbench_assistant.config import UISchema
 from semantic_workbench_assistant.storage import read_model, write_model
 
+from .. import helpers
+
 if TYPE_CHECKING:
     from ..config import AssistantConfigModel
 
-
-#
-# region Helpers
-#
-
-
-# helper for loading an include from a text file
-def load_text_include(filename) -> str:
-    # get directory relative to this module
-    directory = pathlib.Path(__file__).parent.parent
-
-    # get the file path for the prompt file
-    file_path = directory / "text_includes" / filename
-
-    # read the prompt from the file
-    return file_path.read_text()
-
-
-# endregion
-
-
 #
 # region Models
 #
 
 
 class ArtifactAgentConfigModel(BaseModel):
-    enable_artifacts: Annotated[
+    enabled: Annotated[
         bool,
         Field(
-            description=load_text_include("artifact_agent_enable_artifacts.md"),
+            description=helpers.load_text_include("artifact_agent_enabled.md"),
         ),
         UISchema(enable_markdown_in_description=True),
     ] = False
@@ -283,7 +263,7 @@ async def get(self, context: ConversationContext) -> AssistantConversationInspec
 
         # get the configuration for the artifact agent
         config = await self.config_provider.get(context.assistant)
-        if not config.agents_config.artifact_agent.enable_artifacts:
+        if not config.agents_config.artifact_agent.enabled:
             return AssistantConversationInspectorStateDataModel(
                 data={"content": "Artifacts are disabled in assistant configuration."}
             )

assistants/prospector-assistant/assistant/agents/attachment_agent.py

@@ -1,11 +1,12 @@
 import base64
 import io
 import logging
-from pathlib import Path
 from typing import Annotated, Any
 
 import docx2txt
 import pdfplumber
+from assistant_drive import Drive, DriveConfig
+from context import Context
 from openai.types import chat
 from pydantic import BaseModel, Field
 from semantic_workbench_api_model.workbench_model import File
@@ -14,11 +15,6 @@
     FileStorageContext,
 )
 from semantic_workbench_assistant.config import UISchema
-from semantic_workbench_assistant.storage import (
-    read_model,
-    read_models_in_dir,
-    write_model,
-)
 
 logger = logging.getLogger(__name__)
 
@@ -84,15 +80,16 @@ async def create_or_update_attachment_from_file(
         content = await _file_to_str(context, file)
 
         # see if there is already an attachment with this filename
-        attachment = read_model(_get_attachment_storage_path(context, filename), Attachment)
-        if attachment:
+        try:
+            attachment = _get_attachment_drive(context).read_model(Attachment, filename)
             # if there is, update the content
             attachment.content = content
-        else:
+        except FileNotFoundError:
             # if there isn't, create a new attachment
             attachment = Attachment(filename=filename, content=content, metadata=metadata)
 
-        write_model(_get_attachment_storage_path(context, filename), attachment)
+        # write the attachment to the storage
+        _get_attachment_drive(context).write_model(attachment, filename)
 
     @staticmethod
     def delete_attachment_for_file(context: ConversationContext, file: File) -> None:
@@ -101,7 +98,7 @@ def delete_attachment_for_file(context: ConversationContext, file: File) -> None
         """
 
         filename = file.filename
-        _get_attachment_storage_path(context, filename).unlink(missing_ok=True)
+        _get_attachment_drive(context).delete(filename)
 
     @staticmethod
     def generate_attachment_messages(
@@ -120,7 +117,7 @@ def generate_attachment_messages(
         """
 
         # get all attachments and exit early if there are none
-        attachments = read_models_in_dir(_get_attachment_storage_path(context), Attachment)
+        attachments = _get_attachment_drive(context).read_models(Attachment)
         if not attachments:
             return []
 
@@ -233,14 +230,13 @@ def reduce_attachment_payload_from_content(value: Any) -> Any:
 #
 
 
-def _get_attachment_storage_path(context: ConversationContext, filename: str | None = None) -> Path:
+def _get_attachment_drive(context: ConversationContext) -> Drive:
     """
-    Get the path where attachments are stored.
+    Get the Drive instance for the attachments.
     """
-    path = FileStorageContext.get(context).directory / "attachments"
-    if filename:
-        path /= filename
-    return path
+    drive_context = Context(session_id=context.id)
+    drive_root = str(FileStorageContext.get(context).directory / "attachments")
+    return Drive(DriveConfig(context=drive_context, root=drive_root))
 
 
 async def _raw_content_from_file(context: ConversationContext, file: File) -> bytes: