test(02-08): popover at three layers, incl. the Pixel 7 column

feat(02-08): word-lookup popover (reading, glosses, level, dictionary form) with published numbers

docs(02-07): complete the furigana rendering plan

test(02-07): rehearsal script; furigana at three layers, and a per-thread Sudachi tokenizer

feat(02-07): furigana controls, level picker, persistence; every transcript line rendered from tokens

feat(02-07): DOM-built ruby transcript renderer, stylesheet and standalone harness

docs(02-06): complete server functions, directive tokens and language bridge plan

test(02-06): language bridge parity under both transports

feat(02-06): analyze/translate/languageInfo on the shared turn loop; tokens on the turn event

feat(02-06): analyze/translate/language_info server functions, tokens on the directive, language warm-up

test(02-06): add failing server-function and directive tests

docs(02-05): complete canonical analyzer and fixed sample sentence set plan

feat(02-05): fixed sample sentence set with golden units (SC-1)

feat(02-05): analyze(text) - the canonical token record

test(02-05): add failing analyzer behaviour tests

docs(02-04): complete CPU translation model plan

feat(02-04): CTranslate2 + sentencepiece translator with warm-up

docs(02-03): complete ranked JMdict lookup and JLPT level derivation plan

test(02-04): add failing translation contract tests

fix(02-04): write the CT2 JSON files with LF so the README hashes match every checkout

docs(02-02): complete units and ruby plan

feat(02-03): JLPT word and kanji level derivation (N1+, name)

fix(02-03): rank headword precedence in the JMdict lookup

feat(02-04): OPUS-MT ja-en converted to CTranslate2 int8 (LFS) with conversion script

feat(02-02): committed reading-override table (人気 -> ひとけ before の)

test(02-02): add failing reading-override tests

feat(02-02): okurigana-aligned ruby spans

test(02-02): add failing ruby alignment table

feat(02-02): mode-C morphemes to whole-word units (rules A1-A7)

test(02-03): add failing JLPT level tests

feat(02-03): compact JMdict loader with ranked headword lookup

test(02-02): add failing unit-joining tests

test(02-03): add failing JMdict lookup tests

docs(02-01): complete wave 0 foundation plan

feat(02-01): compact JMdict projection (LFS) with build script and asset guards

feat(02-01): pinned JLPT vocabulary and kanji-level data with build script

chore(02-01): arm LFS for .spm and pin the language stack

docs(state): record phase 2 planning complete

docs(02): apply the second checker pass - import-shaped greps, scoped wave-2 guards, warm-up routing, utf-8 one-liner

docs(02): revise plans after checker review

docs(02): create phase 2 plans (10 plans, 8 waves) and fill the validation map

docs(phase-02): add validation strategy

docs(02): research phase domain

docs(state): record phase 2 context session

docs(02): capture phase context

docs(01-11): complete the audio-unlock gap-closure plan

test(01-11): prove the tap unlocks audio under a strict autoplay policy at three layers

fix(01-11): activation-aware resume grace; iframe stage context created at mount

fix(01-11): resume the AudioContext inside the gesture, refuse to speak on a stopped clock

docs(01): record the phone no-audio gap and plan its closure (01-11)