prosolis
3cc23b8ea4
Reported as "the Portuguese option isn't translating the advice in English — it's just reprinting Portuguese." Nothing was wrong with targetFor. It was reading a direction the account could not leave. learnerPairs held only zh, so SetPair refused learning_pair for pt-PT and every Portuguese account was learning_en by force. targetFor then did exactly what it says: explanations follow the half of the pair she is not learning, which for a forced learning_en account is Portuguese. A Portuguese document, corrected in Portuguese, explained in Portuguese, with no way to ask for English — correct behaviour derived from a fact about the roster that was no longer true. The note in learnerPairs was written one phase too early to see it. It said turning a pair around needs a word list and a dictionary reading into English, and that fr, es and pt-PT had neither. Portuguese has both. Word boundaries are spaces — the megabyte jieba needs is a property of a writing system that doesn't use them, not a debt every pair owes. And the dictionary arrived with dict.db, which reads pt→en as readily as en→pt; dreamProvider.reverse has been answering that question since the pair shipped. What was actually blocking the pair a native English speaker learning Portuguese needs was this list. So pt-PT joins it, and the pt-PT pack gets the learner copy the control renders from — each label in the language of whoever would pick it, since someone on the wrong side of that switch cannot read the side they are reaching for. fr and es clear the same two bars through the same dict.db and stay out: their packs carry no learner block yet, which is a translation question rather than a data one, and the server should keep saying no until one is written. Two things that assumed learning_pair meant Chinese, now that it doesn't. The segmenter gate reads the pair as well as the direction, or a Portuguese learner would load a megabyte of Chinese word list and hover Portuguese words at /api/hanzi. And that endpoint's own comment justified skipping providerFor with a guarantee it no longer has; the real guarantee was always the caller's — it is only ever asked about tokens the Chinese segmenter found — and a stray lookup was already safe, answering a miss with an empty 200. Tests in both packages. The auth test that pinned pt-PT's refusal now pins its acceptance, with fr and es still refused; the suggestions test pins the consequence where it actually lands, which is the language she reads her advice in. Claude-Session: https://claude.ai/code/session_01GJHNvirh7Hzhc9RL3HAvz7
🌸 Petal
A self-hosted, privacy-first writing editor with warm bubbly design, auto-save, and
local-LLM grammar/ESL suggestions. See petal-spec.md for the full
design spec and BUILD_PLAN.md for build progress.
Stack
Go + chi backend · SQLite (modernc, pure Go) · React + Vite + Tiptap + Tailwind v4 frontend ·
local vLLM/Ollama for AI suggestions. Single-binary deployment (frontend embedded via go:embed).
Local development
Two processes during development:
# 1. Backend (serves /api on :8080)
go run ./cmd/server
# 2. Frontend dev server (HMR on :5173, proxies /api → :8080)
cd web && npm install && npm run dev
Open http://localhost:5173 while developing.
Production build (single binary)
cd web && npm run build # emits web/dist (embedded by the Go binary)
cd .. && go build -o petal ./cmd/server
./petal # serves UI + API on :8080
Configuration is via environment variables — copy .env.example to .env.
Deployment
docker compose up -d --build # petal + the two Piper read-aloud sidecars
Behind Traefik on the parodia.dev VPS; vLLM stays on millenia over headscale.
Full runbook — first deploy, the LLM link, backups and restore — in
deploy/README.md.
Status
Early build, multi-session. Auth (Authentik OIDC) is next; Copyleaks plagiarism is
still parked — see BUILD_PLAN.md.