feat: merge curated dev updates with MoE routing, reliability fixes, and CI hardening#9
Merged
Conversation
Deploying knowbear with
|
| Latest commit: |
037a9c8
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://5455dd34.knowbear.pages.dev |
| Branch Preview URL: | https://development.knowbear.pages.dev |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request introduces significant improvements and refactoring across documentation, environment configuration, CI/CD automation, and backend authentication caching. The main focus is on removing the dependency on LiteLLM, migrating to native provider-based inference, and enhancing both operational and developer experience. The README and environment files have been thoroughly updated to reflect these architectural changes, and new CI/CD workflows and backend cache management improvements have been introduced.
Key changes:
Provider Migration & Documentation Refactor
The README (
README.md) has been rewritten to remove all references to LiteLLM, replacing them with detailed documentation of the new native provider-based routing system. This includes updated model routing logic, fallback chains, and a new section describing provider fallback matrices and frontend UX improvements. [1] [2] [3] [4] [5] [6] [7] [8] [9]The
.env.examplefile has been updated to remove LiteLLM-related variables and clarify configuration for new provider keys (Groq, Gemini, OpenRouter). Timeout settings and comments have been revised for clarity.CI/CD Automation
A new GitHub Actions workflow (
.github/workflows/vercel-deploy.yml) has been added for automated Vercel deployments. This workflow supports both production and preview deployments, validates required secrets, builds the project, deploys prebuilt artifacts, and blocks deployment if the/api/healthendpoint is not healthy. [1] [2]The CI workflow (
.github/workflows/ci.yml) now includes backend log hygiene guards to prevent accidentalprint()statements and unsafe logging of rawuser_idfields, enforcing privacy and code quality.Backend Improvements
api/auth.py) has been improved with a more robust, thread-safe cache for user "pro" state. It now uses anOrderedDictwith TTL and maximum entry pruning, and logs warnings via the structured logger instead of usingprint(). Supabase client getters are now cached and log missing credentials more cleanly. [1] [2]These changes collectively modernize the codebase, improve security and reliability, and provide clearer documentation for both users and developers.