diff options
| author | Danilo M. <danix@danix.xyz> | 2026-10-30 17:37:48 +0100 |
|---|---|---|
| committer | Danilo M. <danix@danix.xyz> | 2026-10-30 17:37:48 +0100 |
| commit | 2c02a46c249a1ec6540e440e1d5a500437852b9e (patch) | |
| tree | 7852b48d2bd44cdb7be385beece8da27a4c701f8 | |
| parent | a329fe105c653ac24d60cbdb6f785efd9e382eee (diff) | |
| download | desktop-assistant-2c02a46c249a1ec6540e440e1d5a500437852b9e.tar.gz desktop-assistant-2c02a46c249a1ec6540e440e1d5a500437852b9e.zip | |
AGENTS: local-chat is archived
Point the prior-art reference at its archived path and state that the
canvas has replaced llamachat.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
| -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`, |