restored header

added dev and co-dev in readme

updated authors and project contributors

perf: increase llama_cpp initialization and prefill timeouts to 120s for worst-case CPU performance

regex adjustments

perf: increase llama_cpp timeout thresholds to 60s for slow CPU architectures

fix: improve mock backend conversation memory and history-aware responses

fix: Update mock ledger parser regex to prevent matching rupees as dates and support dynamic items (e.g. cotton)

feat: Add interactive multi-calendar management, sowing date recalculation, and aggregated multi-calendar proactive nudges

docs: Add pull request description markdown

docs: Update README with enhancements; implement GGUF latency fallback, KV cache thread-safety lock, mock structured parser, start-from-scratch reset, mobile CSS responsiveness, and nudge parser fixes

Fix backend Server import by migrating to FastAPI and mounting Gradio fallback UI

feat: use dynamic profile details in LLM prompt

feat: migrate to custom SPA frontend on gr.Server with offline contacts, distress bypass, and onboarding tests

fix: resolve prefix repetition loop by yielding deltas only in stream

updated code so it runs on hf and pixel 10

docs: Document Hugging Face CPU single-thread constraint in README.md

docs: Add detailed Android/Termux troubleshooting guide to README.md

update README with Android Termux guides for both llama.cpp and Ollama

update README with exhaustive setup guide for llama.cpp and Ollama

limit n_threads to 1 on HF Spaces to prevent repack scheduler crashes

bind Gradio server to 0.0.0.0:7860 for Docker container routing on HF

optimize Dockerfile by using precompiled wheels index and removing compiler tools

fix colorTo in README metadata

mock to realtime local model execution with llama.cpp

mock run working

Initial commit