Conversation
Add psycopg2-binary and bcrypt to backend/requirements-local.txt to support Postgres and bcrypt hashing in the local environment. Fix a broken relative import in web/src/app/demo/argument-mapper/page.tsx by changing the path to ../../app/argument-mapper/argument-mapper-client to match the project layout and prevent module resolution errors.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Introduce a communication risk scanner and expand analytics/achievement logic across backend and frontend. Key changes: - Add /analyze/risk endpoint, RiskScanRequest/Response schemas, and AnalysisService.scan_communication_risk with demo and full-ML flows (including demo rewrite helper). - Improve analyze flow: unified final_result handling, fallback keyword detection, richer suggestions, sanitization and defaults. - Enhance user stats and achievements: compute wins, win_rate, current streak, skill metrics (coherence, evidence, extremity, reputation) and multiple achievement conditions; support X-User-ID header fallback for auth-sensitive endpoints. - Update LLM generator: stronger persona/stance prompts and new generate_rewrite method for polished rewrites. - Smart debate: ensure AI stance is opposite the user when selecting topic counters. - Frontend additions: new Risk Scanner page/client; argument mapper: fullscreen, export (PNG/SVG) support, pan/zoom improvements, node color/icon enhancements; wrap Analysis page client with Suspense for loading UI. - Configuration/docs: enriched backend .env.template (core settings, CORS, demo mode), README/docs update to use `python -m uvicorn ...`, and add .ruff_cache to .gitignore. - Database file updated (binary diff). These changes add a publish-safety feature for communication, improve analytics/UX, and provide better demo fallbacks when ML models are unavailable.
Implements the Learning subsystem: adds a FastAPI learning API (progress, complete-lesson, assessment, spaced-repetition, reset-assessment) and wires it into backend/main.py. Adds a full client-side course player and academy pages (course-player-client, academy client pages, learning-path client/pages), a courses config, and updates the frontend API client and layout to support locked/unlocked sidebar behavior and progress flow. Updates USP_PLAN.md to mark the courses and learning path as implemented and document features/flows. Also includes DB update and small UI/style adjustments (globals.css, profile client).
Introduce new demo pages and navigation for the Academy and Risk Scanner features. Adds pages: demo/academy (AcademyClient), demo/academy/[courseId] (CoursePlayerClient), demo/learning-path (LearningPathClient), and demo/risk-scanner (RiskScannerClient with Suspense fallback). Update demo layout to add an Academy section, include Risk Scanner in Tools, improve sidebar active-route logic to treat /demo/academy/* as active, and expand descriptive helper text for academy, learning-path, and risk-scanner. Also includes a binary update to backend/logicshield.db.
Introduce end-to-end support for audio transcription and richer argument node analysis. Changes include: - backend: add services/speech_transcriber.py (local Whisper pipeline with fallback) and new POST /debate/transcribe API in backend/api/main.py to accept uploaded audio and return transcribed text. - Argument analysis: extend ArgumentNode schema (text_full, suggestions, improved_text); enhance ArgumentVisualizer to detect more issues, refine strength scoring by node type, and generate suggestions + improved_text (optionally refined via LLM). - LLM: add refine_argument_node in llm_generator to request concise suggestions/improvements from HF and switch default model string. - Analysis sanitization: normalize issues structure and confidence values in backend/services/analysis.py. - Requirements: pin bcrypt to <5.0.0 for compatibility in requirements files. - Docs & config: update USP_PLAN.md (status/ordering and future enhancements), update .gitignore, add generated PDF summary. These changes enable voice debate workflows, improve robustness of analysis data, and provide automatic suggestions/rewrites for weak argument nodes.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add psycopg2-binary and bcrypt to backend/requirements-local.txt to support Postgres and bcrypt hashing in the local environment. Fix a broken relative import in web/src/app/demo/argument-mapper/page.tsx by changing the path to ../../app/argument-mapper/argument-mapper-client to match the project layout and prevent module resolution errors.