- GET /auth/mfa/totp/secret — retrieve decrypted TOTP secret for auth app
- POST /auth/mfa/push/create, GET /pending, POST /:id/respond, GET /:id/status
- POST /auth/qr/create, POST /auth/qr/confirm, GET /auth/qr/:id/status
- Kotlin SDK: getTotpSecret, getPendingApprovals, respondToApproval, confirmQrLogin
- Swift SDK: getTotpSecret, getPendingApprovals, respondToApproval, confirmQrLogin
- All 53 auth tests passing
- BUG-4: Add optimistic concurrency control with retry to updateSessionStats
- BUG-5: Document transaction limitations in batch operations
- BUG-7: Fix test isolation with unique productIds per test run
- BUG-8: Add session ownership validation to ingest endpoints
- refresh.sh: idempotent script, auto-discovers repos, updates symlinks + copies docs/workflows
- launchd plist: scheduled daily at 11 PM + on login
- /refresh-chat-history workflow for on-demand Cascade runs
- README updated with auto-refresh docs and full data inventory
- Repo docs and workflows refreshed from all 4 repos
Add a helper script to quickly verify Ollama reachability across localhost, WSL gateway, and nameserver paths to speed up Windows+WSL troubleshooting.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stabilize Windows+WSL setup by fixing script line-ending pitfalls, WSL Ollama host detection, and dashboard startup behavior so models are detected reliably in Mission Control.
Co-authored-by: Cursor <cursoragent@cursor.com>
Covers: what it is, architecture diagram, prerequisites (Python 3.12,
Bun, Rust), step-by-step install for macOS and WSL2, running backend
+ web frontend, first use (model download, voice profiles, story editor),
Make commands reference, platform performance table, troubleshooting
(proxy workaround, MPS/CUDA, transformers conflict), file structure,
and relevance to LysnrAI
- HP Z240 spec: expanded from 7-line raw info to full spec document
with hardware details, capabilities assessment, OpenClaw server
use case, home lab services table, GPU upgrade path, machine
comparison, and setup recommendations
- README: added Machines table (Razer/HP Z240/Dell P16s), expanded
files table, added Related: OpenClaw section with links to OPEN_CLAW/
- Move openclaw-personal-ai-assistant.md from windows_specific/ to OPEN_CLAW/
- Add validate-security.sh: cross-platform security scanner with visual output
- 7 check categories: installation, gateway config, file permissions,
network security, API keys, system security, openclaw doctor
- Green ticks (pass), red crosses (fail), yellow warnings
- Numbered recommendations list with fix commands
- Works on macOS, Linux, and WSL2
Covers: what it is, installation on Windows/WSL2 and macOS, channels,
models, configuration, security, HP Z240 as always-on gateway host,
Tailscale remote access, troubleshooting, CLI reference, and skills.
New capabilities/ subfolder with detailed guides:
- 01: GPU inference speed (benchmarks, Ollama tuning, API usage)
- 02: Whisper batch transcription (scripts, Python integration, use cases)
- 03: TTS generation at scale (Orpheus + Qwen3, batch scripts, voice cloning)
- 04: Fine-tuning / training (LoRA, QLoRA, data prep, Ollama export)
- 05: CUDA / TensorRT / ML research (toolchain setup, Triton kernels, profiling)
- 06: Stable Diffusion / image gen (ComfyUI, SDXL, FLUX, batch generation)
- 07: Multi-GPU workloads (scaling path, eGPU, cloud, cost planning)
- README: index with learning order and prerequisites
Each guide covers: what it is, how to use it, benefits, skills to learn
E1: Per-message action bar (copy, regenerate dropdown, rating) on hover
E2: Per-code-block copy button in MarkdownResponse with 'Copied!' feedback
E3: 'Try with other model' — regenerate dropdown shows loaded models
E4: Live streaming metrics (token count + tok/s during stream)
E5: Rating (thumbs up/down) persisted per message in IndexedDB
- add lib/router.ts with task classifier, model hint mapping, resolve fallback chain, and auto-detect defaults
- integrate auto-routing mode in conversation model selector with __auto__ option
- persist/read model defaults from localStorage (llm-model-defaults)
- route prompts to selected/routed model before streaming
- add multi-modal input controls (attach file, image, voice)
- support attachment chips, removal, drag-and-drop file attach
- add audio transcription flow via /api/whisper/transcribe and append result to input
- support sending attachments payload alongside text from InputBar
