diff options
| -rw-r--r-- | AGENTS.md | 8 |
1 files changed, 4 insertions, 4 deletions
@@ -119,14 +119,14 @@ mode** on `http://localhost:8181` with an OpenAI-compatible API. `model =` and optional `mmproj =`), GGUF files under `/data/LLM-models/`. - `--models-max 1`: the router keeps **one** model loaded. If the assistant asks for a different model than the one in use, the router swaps it out, - under whoever else is using it (e.g. llamachat). Prefer reusing whatever + under whoever else is using it. Prefer reusing whatever model is loaded, or accept the reload latency knowingly. - `/v1/models` lists models and each one's `architecture.input_modalities`. A model reporting `"audio"` accepts `input_audio` content parts directly, which is a possible shortcut that skips whisper entirely. Not evaluated. -Prior art: `../local-chat` (llamachat, PySide6) is a client for the same -router. It already records 16 kHz mono WAV and sends it as `input_audio` +Prior art: `../ARCHIVED/local-chat` (llamachat, PySide6, archived) was a +client for the same router. It records 16 kHz mono WAV and sends it as `input_audio` to audio-capable models, and parses `presets.ini`. Reuse its findings, do not import from it. @@ -890,7 +890,7 @@ kokoro-onnx GitHub release `model-files-v1.0`. - **Local memory:** `docs/superpowers/plans/2026-09-30-local-memory.md` still applies; its tasks 1-4 target this daemon, the voice-specific bits of task 4 aside. -- **llamachat ports**, if the canvas replaces llamachat for good: +- **llamachat ports**, now that the canvas has replaced it (archived): attachments, skills, a model picker (model-written titles done). - **Phase 2 tools:** tools that write or modify (events, messages, desktop), with a review step, own spec. Desktop modes done (`mode`, |