diguaandClaude Opus 4.8 d6896bf09a feat(semantic-index): move model to ai dir and preload on config save ...

Move local embedding model storage from getCacheDir() to getAiDataDir()
(~/.chatlab/ai/models/semantic-index) so the "clear cache" button in
settings no longer wipes downloaded models.

Also trigger model download immediately in the background when a local
model is configured, instead of waiting for the first index build.
Download status (idle/downloading/ready/error) is tracked in
SemanticIndexService, exposed via the SemanticIndexRuntime interface and
worker RPC, and surfaced in the settings UI as a pulsing indicator.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-24 14:41:33 +08:00

..

config

refactor: remove dead code and simplify over-engineered abstractions

2026-06-23 14:18:32 +08:00

core

refactor: remove dead code and simplify over-engineered abstractions

2026-06-23 14:18:32 +08:00

http-routes

feat(semantic-index): move model to ai dir and preload on config save

2026-06-24 14:41:33 +08:00

mcp-server

fix: enforce data directory compatibility gate at runtime boundaries

2026-06-08 10:14:42 +08:00

node-runtime

feat(semantic-index): move model to ai dir and preload on config save

2026-06-24 14:41:33 +08:00

parser

test(parser,config): cover representative fixtures and migrations

2026-06-08 10:14:42 +08:00

shared-types

fix(owner): correct per-session ownerId cache and share one PreferencesManager

2026-06-13 13:16:52 +08:00

sync

fix(sync): fold initial empty-page cursor before entering retry loop

2026-06-23 14:18:32 +08:00

tools

feat(semantic-index): run local embeddings in lazy worker

2026-06-23 14:18:32 +08:00