Commit Graph
7 Commits
Author SHA1 Message Date
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 b1fdaced9f Restrict the AI tab to HOST1 — the only node with the GPU, Ollama and the index 2026-08-04 17:25:40 -04:00
Gmer4Lfe 8d393a1e1c Add three chat profiles: Varaverk Assistant, General Chat, Code Sketcher
Explicit buttons rather than an automatic router. Misclassifying a Varaverk
question as chat produces a confident invention about the user's system, which
is exactly what retrieval exists to prevent — with buttons there is no hidden
heuristic to be wrong and the strict profile is the default you land on.

Only Varaverk Assistant retrieves; the other two would be carrying passages
that cannot help write a folder-copy script. Memory goes to all three, since
that is what lets chat know the setup without claiming authority over it.
History depth is per profile and set server-side: retrieval costs ~2500 of
16384, so the profiles that skip it can hold a real conversation. Code
Sketcher is told to flag flags it is unsure of, after it invented
rsync --no-overwrite.
2026-08-03 17:36:24 -04:00
Gmer4Lfe d0b3588f6c Give the assistant a standing memory file
A small operator-written file handed to the model at the start of every
conversation — who you are, how this install is set up, what has already been
decided. Injected ahead of the retrieved passages and marked operator-authored
so it outranks anything they contradict, and never cited as a source.

Deliberately not indexed and deliberately under DATA_DIR: it changes
constantly, vector similarity is the wrong way to retrieve things you were
told to remember, and gitignoring it keeps personal notes out of a pushed
repository. The character cap is a context budget — this text costs its share
of 16k on every single turn.
2026-08-03 17:11:27 -04:00
Gmer4Lfe 7f01b3040d Log entry into the AI endpoint before any dependency loads
A POST the browser demonstrably sent — correct token, correct body — left no
trace: no CSRF termination, no fatal, and no action log. Rejected-before-PHP
and died-inside-the-include are indistinguishable from outside, so the first
statement now records that execution arrived.
2026-08-02 18:16:58 -04:00
Gmer4Lfe 563ea0eb78 Log AI requests, and stop hiding a failed job-file write
There is no nginx access log on this host and the CSRF prepend exits with an
empty body, so a request that never arrived and one that arrived and failed
were indistinguishable — the page just sat at "starting…". The job-file write
was also suppressed with @, which would produce exactly that hang: a token
returned for a job that can never report.
2026-08-02 17:57:22 -04:00
Gmer4Lfe 264ba57cbb Add the AI tab — grounded chat over the documentation index
Token and poll rather than SSE, so the api layer keeps one response
convention and reuses the pattern manual_sync already proved. History is
capped at three turns because the model is only fully offloaded at 16384
context and unbounded history would cross that silently. The tab exists
only while AI_ENABLED is true, rejected server-side and not merely hidden.
2026-08-02 17:32:17 -04:00