9 Commits

Include renames

Author	SHA1	Message	Date
Gmer4Lfe	500f9d92c8	Redact credentials on the way into a stored chat ... A stored transcript is replayed into a later prompt when reopened, so a key typed while changing a setting would be handed back to the model on every subsequent turn.	2026-08-09 19:07:34 -04:00
Gmer4Lfe	d9225d06d9	Route a General Chat question to the profile that fits it	2026-08-09 00:36:13 -04:00
Gmer4Lfe	37784bce6c	Offer Troubleshoot as a profile, and say plainly when it has no log	2026-08-09 00:25:52 -04:00
Gmer4Lfe	3a45c18555	Document today's restructures, and give data/ a README that ships with it	2026-08-09 00:01:05 -04:00
Gmer4Lfe	83508cfb1b	Pull partner token ledgers into a RAM cache so fleet totals are fleet-wide	2026-08-04 18:14:38 -04:00
Gmer4Lfe	969a85f303	Record token usage per turn and show daily, weekly and all-time totals by host	2026-08-04 18:04:46 -04:00
Gmer4Lfe	0cf208b80a	Remove the Open-WebUI retrieval bridge — Varaverk is the only Ollama client now	2026-08-04 17:11:46 -04:00
Gmer4Lfe	eb36641523	Expose --kind on ai_query so definitional questions can reach the prose ... The index already stored chunk origin and search.js already filtered on it; only the wrapper refused the flag. Intent routing boosts PURPOSE for "what is X", which buried README.md and made the system answer that it had no definition of itself.	2026-08-02 13:09:17 -04:00
Gmer4Lfe	6a959fb5e4	Add AI entry points, conf schema, and folder docs ... ai_index.sh and ai_query.sh follow the usual conventions — fail-closed gate, root check, lock, dry-run, status — with Node doing only the vector maths and SQLite blobs, the same split api_cache_writer.sh uses for PHP. AI_* and HOST*_OLLAMA_* land in both confs and both templates in this pass. Everything ships off: AI_ENABLED false, every AI_ASSIST_* false, conf writes disabled with an empty whitelist. Nothing in the ecosystem consults it.	2026-08-02 01:21:24 -04:00