Report throughput in consistent units

Correct the latency claim: measure against llama.cpp, not our own worst case

Correct README to the verified claims

Filter empty thoughts from recording and chat display

Collapse empty chat-log black box; chat column hugs text bar

Full-vocab HVM cache (128K tokens) via chunked bf16 projection

Thought recording + contemplate mode + denoise parser for int8 digit collapse

fix: chat messages persist + agent generates 256 tokens per round (was 32)

Trim test target to Space-shipping files (C libs + py_compile only)

Drop __pycache__, clean slate

Port full dashboard engine: phoenix_dashboard + agent_core + hyper_vocab_memory + bqsm_assist

Add chat debug logging

Force rebuild

Increase chat timeout to 120s for Space CPU

Init ring buffers in start_mixer

Support both phoenix and mixer engines in chat

Update mixer.c with LM head projection + ring buffer chat I/O

Update mixer.c with actual ternary weight decoding from model

Add mixer.c source to Space repo

Add Start Mixer button + start_mixer function for fast mixing ring engine

Revert to ring buffer protocol; optimize log tail reading

Fix chat protocol: use named pipe (/tmp/phoenix_chat.pipe) per phoenix_brain.c chat mode

Download binary + model to /tmp to avoid Space auto-restart

Cache binary download (no force_download); fix indentation

Fix stop_phoenix: minimize lock holding, close fds outside lock

Add phoenix daemon monitor thread + tick log display

Force re-download binary; fix lock contention in get_boot_status

Fix lock contention: get_boot_status reads without lock, phox_chat checks minimal

Download pre-built phoenix binary from HF Hub instead of compiling on Space

Pre-built static phoenix binary; skip compilation on boot

Manual boot: tokenizer loads at startup, full boot on button click. Non-blocking stop_phoenix.

Remove blocking wait loop; tick() checks daemon log instead

Non-blocking boot wait: 0.5s sleep, only last 20 log lines

Fix boot wait loop: release lock between checks, extended timeout

Touch app.py to force Space rebuild

Fix tokenizer get_vocab API call

Fix Gradio 6.22 + remove torch dep: use tokenizers lib, gr.Timer API

Fix Gradio 6.0 compat: remove css/interactive params, fix tokenizer loading

Fix short_description length

Convert to Gradio: Phox wave-rider inference engine

initial commit