Spaces:
Sleeping
Sleeping
Commit History
-
Add column legends/headers to workout, subscriptions and payments tables
Each logged-data table now explains what its columns mean: a header row + plain-language legend on the workout log, clearer headers with tooltips and a legend on the subscriptions table, and tooltips + a legend on monthly payments. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>d656880
-
Fix subscription audit crash on subs missing 'occurrences'
build_money_input hard-indexed s['occurrences'] and s['last_charged'], which KeyError'd when audited subscriptions came from the Memory tab (name/cost/last_used) instead of a CSV upload, taking down the whole money_review stream. Use .get() with fallbacks, matching the style already used for income/budget in the same function. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>2bc3243
-
Add config, model status, and VLM support
Introduce centralized configuration (.env.example + config.py) and wire it into app and engine. Add logging and a /status endpoint, new streaming API payment_impact, and reset_account. Refactor engine to track model state, surface friendly load errors, support a lazily-loaded vision-language model (VLM) for meal photos (describe_food_image), and improve generation streaming by hiding model reasoning (ANSWER_DELIM/_clean_response). Update meal-photo upload to prefer vision with OCR fallback and adjust warmup/launch to use config host/port. Update docs/contracts and remove mock websearch stubs; tests/static assets adjusted accordingly.0c4cd3b -
No-cache static files and tighten hidden CSS
Serve static assets with Cache-Control: no-cache by adding a NoCacheStaticFiles subclass and mounting it at /static; also return index FileResponse with a no-cache header to force revalidation. This prevents browsers from using stale CSS/JS after edits (fixes cases like a modal left open due to an outdated stylesheet). In CSS, add a global [hidden] { display: none !important; } rule and make .modal-overlay[hidden] use !important to ensure hidden elements are reliably hidden.0370dc3
-
Fix stuck schedule modal: hidden attr lost to .modal-overlay display:flex
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>fbfcc1c -
Add EasyOCR/CUDA support and UI improvements
Introduce GPU-capable OCR and CUDA bootstrap for Windows, plus several frontend UX features and docs updates. Key changes: - README: document EasyOCR (GPU/CPU) + Tesseract fallback and detailed CUDA/llama-cpp-python build instructions. - Add cuda_bootstrap.py and scripts/build_cuda.bat to preload NVIDIA/CUDA DLLs on Windows and assist building CUDA wheels. - engine.py / rag.py: attempt GPU offload using LIFEOS_GPU_LAYERS (default -1) with a safe fallback to CPU; ensure cuda_bootstrap runs before llama_cpp loads. - features/food.py: add ocr_image() that prefers EasyOCR (GPU when available) and falls back to Tesseract; remove direct tesseract coupling in app.py and use the new helper. - requirements.txt: add easyocr. - Static assets (JS/HTML/CSS): add workout log, calendar day modal view, "other" describe toggles, theme toggle with light-mode styles, small UI/text tweaks and polish. These changes enable optional GPU acceleration for model and OCR workloads, improve Windows CUDA runtime h…d1ce419 -
Configure Tesseract and fix stale embeddings
Add automatic Tesseract configuration and self-healing for embedding vectors. features/food.py: introduce configure_tesseract(pytesseract) which honors TESSERACT_CMD, probes common Windows install locations, and sets pytesseract.pytesseract.tesseract_cmd when needed. Call it from extract_deals to ensure OCR works when the tesseract binary isn't on PATH. app.py: call configure_tesseract before invoking pytesseract in upload_meal_photo. rag.py: detect notes whose stored vector length differs from the current embedder output, re-embed those notes, update in-memory entries and persist the corrected vectors under the store lock so recalls remain robust across different embedder dimensions.ab704ae
-
Sidebar UI, first/last name, chat refs, goals section, memory editor
- Sidebar nav (Kitchen/Health/Money/Goals/Chat/Profile/Memory) with Settings pinned bottom-left; collapses to icon rail under 900px - Chat: "Hello, {first_name}" greeting, @Kitchen/@Health/@Money domain reference chips that focus the model's memory slice, polished markdown rendering (tables, code, blockquotes, avatars) - Profile: first/last name split (name derived, legacy split on load), structured address (street, city, postal code, country) - Goals: dedicated section with progress cards, create/edit/delete, Socratic coach moved here from Money - Memory manager: edit/delete short-term rows per section (meals/workouts/calendar/subscriptions/payments) via whitelisted edit_memory; long-term RAG notes list/update/delete with re-embedding - Settings: voice/web defaults (localStorage), reset, about - Tests: extensions 13/13, integration 19 checks, food/health/money suites — all passing Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>1a4f133 -
Major feature expansion: profile, calendar, voice chat, goal coach
- Profile tab: name/city/address/income/diet/budget -> memory; optional city flyer-deal web search (off-grid preserved when unused) - Chat: mic input + spoken replies (browser Web Speech API), opt-in web-search toggle (default off, clearly labeled) - Kitchen: meal/receipt photo -> local OCR -> buying-pattern analysis - Health: preferred training days/time, 7-day calendar with events, deterministic free-slot planning around the calendar, browser reminders - Money: monthly payments editor + Socratic goal coach (one probing question per turn, then a concrete savings plan) - Frontend rewritten in clean UTF-8 with inline SVG icons (fixes mojibake), finite-only animations, resilience banners - New tests: tests/test_extensions.py (7) + integration suite now 15 checks, all passing; no regressions in food/health/money suites Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>86f6b4e -
README: fix venv command and document Space build fallback
Use py -3.13/python3.13 explicitly (bare 'python' can resolve to the Windows Store shim). Explain that the Space build falls back to compiling llama-cpp-python via build-essential+cmake from packages.txt. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>529def3 -
Fix HF Space build: install build-essential+cmake for llama-cpp-python
The Space build ignored requirements.txt's --extra-index-url and built the sdist, which failed without a compiler/CMake. packages.txt now installs build-essential and cmake so the sdist build succeeds on Spaces. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>c612a91 -
Single-file requirements + Python 3.13 real-inference setup guide
README now documents a venv + plain pip install backed by prebuilt llama.cpp CPU wheels (no compiler), and requirements.txt declares the abetlen extra index. Add *.log to .gitignore. Verified on a clean Python 3.13 venv: zero-compile install, real Nemotron-3-Nano-4B loaded, end-to-end generation at ~4 tok/s. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>9baf2dd -
Consolidate to one requirements.txt with prebuilt llama.cpp wheels
Drop requirements-mock.txt; a single requirements.txt now declares the abetlen CPU wheel index so pip installs a prebuilt, py3-none llama-cpp-python wheel (no compiler) on both a local venv and the HF Space Linux build. README updated for a real-inference Python 3.13 setup. Verified on a clean Python 3.13 venv: prebuilt wheel installed with zero compilation, real Nemotron-3-Nano-4B loaded, and end-to-end generation produced text at ~4 tok/s locally. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>aa3186b -
Add venv setup guide + split mock-mode requirements
README now walks through creating a venv, installing deps, and running (real inference on Python 3.13, mock mode on any Python). Add gradio to requirements.txt so a local venv is self-contained, and a separate requirements-mock.txt that omits llama-cpp-python for UI dev without a compiler/model. No API keys or .env needed — LifeOS is fully local; Modal stays dev-only (browser auth via `modal setup`). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>f9546fc -
Add LifeOS: local-first personal assistant on Nemotron-3-Nano-4B
Gradio 6 Server-mode app with hand-built frontend, three feature modules (kitchen/health/money), short-term JSON memory plus a local RAG long-term memory, llama.cpp inference for chat and embeddings, seed demo data, docs/architecture.md, and test suites. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>40cf485 -
initial commit
Verified signature5f1fd21