fix(ai): restore missing event_attrs to fix NameError in deployed backend

fix(github): improve upload stability with retries and branch detection

fix(ai): prevent duplicate comments by stripping existing annotations

faster-AI-1CPU

ai-test

feat(ai): update code commenter, title generator, and add class explainer utils

b

perf(ai): implement high-speed snippet strategy for tags, attributes, CSS and JS

feat(ai): strengthen comment density prompt and fix UI refresh on AI update

fix(backend): align preview_comments with frontend expectations and ignore extra fields

fix(backend): fix 500 errors by adding Optional typing and robust error logging in /preview_comments

fix(backend): update endpoints to handle extra frontend fields, fix health check, and improve AI HTML extraction

fix: set nemotron-nano-12b-v2-vl as primary model

debug: add full trace logging to diagnose model failures

refactor: replace cloudflare with nemotron-nano as primary, pure openrouter chain

fix: validate cloudflare output has comments/valid title before accepting

fix(cloudflare): merge system prompt into user prompt to force instruction following

fix(cloudflare): enforce explicit max_tokens to prevent truncation bugs

feat: replace primary model with Cloudflare Workers AI

fix: remove failing mistral model from fallback chain

fix: replace huggingface fallback with openrouter mistral

fix: switch to flash-lite and phi-3-mini-4k to resolve API limits

feat: complete 5-tier Gemini-first fallback architecture

chore: sync backend updates for benchmarking

Swap model order and enforce inline comment format

Update fallback AI models for stable benchmarking

fix: simplify hf config

m

fix: configuration error - aligned entry point to app.py and enforced LF/BOM-less encoding

fix: configuration error - matched all template keys in README

nn

debug: nuclear smoke test to isolate infrastructure errors

fix: configuration error - corrected YAML metadata formatting (no BOM)

fix: configuration error and dependency optimization

fix: configuration error - added correctly formatted Hugging Face metadata header

changes

chore: stable deployment with HF metadata, gunicorn, and system deps

chore: full sync with all dependencies and system unrar

chore: configure git lfs for images

merge: keep local version over HF Space (our version is authoritative)

feat: benchmark/production mode split, 3-retry backoff, /health_check endpoint

Update title_generator.py

Update code_commenter.py

feat: add llama-3.3-8b to openrouter fallback chain

fix typo in inference client parameter

chore: fix huggingface failover timeouts and model

Update code_commenter.py

Update code_commenter.py

Update title_generator.py

Update code_commenter.py