Revision as of 15:45, 2 January 2026

Future Development Plans

This page tracks proposed improvements for the "Righting Sentences" application. Items are not listed by priority.

Migrate framework to FastAPI
Import Deep Chat frontend
Create an editorial logic file in Python to replace banned.py
Add triad logic to editorial_logic.py
Add detection for negative-positive sentence construction to editorial_logic.py
Expand the banned words list
Create Google Cloud bucket
Add middleware to `main.py` that logs prompt violations to the bucket
Google native authentication (IAM)
User SSO
Add Firestore for chat memory state instead of stateless text windows
Enable document parsing
Session management for Firestone (session_id)

@@ Line 1: / Line 1: @@
 = Future Development Plans =
-This page tracks proposed features, architectural changes, and improvements for the "Righting Sentences" application. Items are listed in no particular order of priority.
+This page tracks proposed improvements for the "Righting Sentences" application. Items are not listed by priority.
-* **Migrate Framework to FastAPI:** Refactor the current Flask backend to FastAPI to improve performance and leverage modern async capabilities, preparing for a "headless" architecture.
+* Migrate framework to FastAPI
-* **Implement "Deep Chat" Frontend:** Replace the current HTML/CSS frontend with the open-source "Deep Chat" React component to support rich chat features, file uploads, and markdown rendering.
+* Import Deep Chat frontend
-* **Create "Editorial Logic" Python Module:** Consolidate all style rules into a single `editorial_logic.py` file, replacing `banned_words.txt` and Vale.
+* Create an editorial logic file in Python to replace banned.py
-* **Add "Triad" Detection Logic:** Update editorial logic to detect and flag sentences using the "X, Y, and Z" (three adjectives/verbs) structure.
+* Add triad logic to editorial_logic.py
-* **Add "Negative-Positive" Structure Detection:** Update editorial logic to flag "It's not X, it's Y" sentence structures.
+* Add detection for negative-positive sentence construction to editorial_logic.py
-* **Expand Banned Words List:** Add new editorial constraints (e.g., "delve", "tapestry", "landscape") to the Python logic.
+* Expand the banned words list
-* **Establish Google Cloud Storage Data Pipeline:** Create a mechanism to log "Bad Prompt" + "Good Correction" pairs as JSONL files in a Google Cloud Storage bucket (`saxton-training-data`).
+* Create Google Cloud bucket
-* **Implement "The Tap" (Silent Logging):** Add middleware to `main.py` that silently runs editorial logic on every model response and logs violations to the bucket without user intervention.
+* Add middleware to `main.py` that logs prompt violations to the bucket
-* **Switch to Google Native Authentication (IAM):** Remove API keys for Gemini; transition to using Google Cloud Service Account permissions (Vertex AI User role).
+* Google native authentication (IAM)
-* **Implement Cloud Run Native SSO:** Configure Cloud Run to "Require Authentication" and manage access via IAM "Cloud Run Invoker" roles (initially manual list, later IAP).
+* User SSO
-* **Transition to Vertex AI Models:** Set Gemini 1.5 Flash (or Pro) as the default model, accessed via the `vertexai` library instead of `google-generativeai`.
+* Add Firestore for chat memory state instead of stateless text windows
-* **Add Firestore for Chat Memory:** Implement a Google Cloud Firestore database to store conversation history, allowing the model to remember context (stateful chat).
+* Enable document parsing
-* **Enable Document Parsing:** Add `python-docx` to the backend to parse uploaded Word documents and inject their content into the model's context window.
+* Session management for Firestone (session_id)
-* **Implement Session Management:** Update the backend to handle `session_id` to persist conversations across browser refreshes using Firestore.
-* **Adopt "Strangler Fig" Deployment Pattern:** Deploy major updates (e.g., v3.0) to fresh Cloud Run instances while keeping legacy versions active but deprecated to ensure seamless migration.
-* **Security Hardening:** Remove all direct, public links to the active application from public-facing documentation/wikis to prevent bot traffic.
-* **Long-Form Content Agent:** Develop a "Chain of Prompting" workflow (Outline -> Section-by-Section generation) to overcome model laziness in 2,000+ word requests.
-* **Fine-Tuning Strategy:** Plan to use data collected from GPT-4o (Teacher) via "The Tap" to fine-tune a Gemini Flash model (Student) on Vertex AI.
-* **Hybrid Development Workflow:** Maintain the ability to run the application locally (MacBook) using `gcloud auth application-default login` for cost-free development and data collection.