mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-15 03:41:10 +02:00
Real end-to-end testing against the now-working local mana-llm
surfaced two model behaviours the prompt couldn't talk down:
1. gemma3:4b stamps today's date on every task that doesn't have a
real time anchor. "Mülltonnen rausstellen" came back with
dueDate=2026-04-08 and priority=low even though the prompt
explicitly said "MUST be null when no date is mentioned". After
typing "Buy milk" the user would silently get a today-due task,
which is worse than no parsing at all.
2. The model occasionally returns dueDate as a full ISO timestamp
("2026-04-09T14:00:00") when the transcript mentions a time. The
coerce regex previously matched the prefix and let the timestamp
through unchanged, which then breaks the YYYY-MM-DD-shaped Dexie
field downstream.
Fix: deterministic post-processing in coerce. The prompt is also
tightened with explicit "ONLY when…" rules but the guards are the
load-bearing change since gemma3:4b ignores prompt restrictions.
- Strict YYYY-MM-DD extraction: a leading-anchor regex match keeps
only the date prefix even if the model adds a time component.
- DATE_TRIGGER_PATTERNS: substring scan over the original transcript
for German + English date words. If the LLM returned a dueDate but
the transcript has zero matches, drop the date — it was a
hallucination. False positives are preferable to false negatives:
letting through a fake date is more annoying than suppressing a
real one the user can re-type.
- PRIORITY_TRIGGER_PATTERNS: same idea for priority. The model thinks
taxes are inherently urgent; we don't want to inherit that opinion.
The labels field is left noisy on purpose — "müll", "unbedingt",
"erledigen" all come back from a single transcript and only the ones
that fuzzy-match an existing workspace tag end up on the task, so
filtering filler words at this layer would be wasted work.
Verified against five transcripts spanning bare/explicit/relative
date in DE + EN. Real LLM round-trip via http://localhost:5173 →
https://llm.mana.how → ollama gemma3:4b. Local mana-llm now reaches
its Ollama backend after the gpu-proxy routing fix in
|
||
|---|---|---|
| .. | ||
| api | ||
| calc/packages/shared | ||
| calendar | ||
| cards | ||
| chat | ||
| citycorners | ||
| contacts | ||
| context | ||
| docs | ||
| guides | ||
| inventar | ||
| mana | ||
| manavoxel | ||
| memoro | ||
| moodlit | ||
| mukke | ||
| news | ||
| nutriphi | ||
| photos | ||
| picture | ||
| planta | ||
| presi | ||
| questions | ||
| skilltree | ||
| storage | ||
| times | ||
| todo | ||
| traces | ||
| uload | ||
| zitare/packages/content | ||