Record remote embedding guidance

This commit is contained in:
Meta Vens 2026-05-19 16:38:04 +01:00
commit 82e97b450d

View file

@ -43,6 +43,9 @@ constraints:
pronunciations, phrase grouping, stress, and broad IPA stringing.
- Long-term speech handoff should use learned line-expression vectors from
Weksa and learned synth-control decoding in AquaSynth.
- Large offline text-embedding jobs should use the neighboring Ollama
inference box documented in `E:\Projects\gamecult-ops` rather than running
on the local Weksa workspace by default.
invariants:
- Ontology owns meaning.
@ -183,8 +186,8 @@ open_questions:
morphology, and diachrony definitions?
- What compiled runtime bundle format keeps game-time rendering fast and
inspectable?
- Which model provider and embedding strategy should be used for offline
semantic decomposition and critique?
- Which Ollama embedding model on `192.168.1.84` should be the default for
offline semantic decomposition and critique?
- How much deterministic validation belongs in v0?
- What is the minimal Rust to Dust language-project slice that proves the
engine without hard-coding the setting into it?