slice + strategy.md §3 가 회의·퇴근 같은 강한 contextual cue 만 다루고
샤워·산책·자기 직전 같은 ambient 떠오름은 사각지대. 6개 심리 메커니즘
(habit stacking, ambient if-then, 환경 앵커, variable interval prompt,
Zeigarnik, 정체성 고리) 후보 + 슬라이스 내/후속 분류 + H1~H5 가설.
권장 순서: E (카피 priming) → 데이터 → C·F → A·D.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
dogfood 첫 알림 노출에서 '구출' 표현이 일상 한국어로 부자연스럽다는
피드백. 5개 UI 표면 + e2e 단언 + strategy.md §1·§3·§7 의 어휘 결정에
함께 묶임. drafting 시 결정 대기 #1(strategy 재검토 동반 여부)이
promoted 경로 좌우.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Reframe the file as a living register for in-flight dogfood feedback
rather than a single-feature stub. Each item carries a status label
(raw / drafting / ready-for-spec / promoted / rejected) and a fixed
six-slot template (관찰 / 제안 방향 / 결정 대기 / 가설·측정 / 범위 /
영향). Items graduate to their own spec file once mature; the entry
here then collapses to a one-line link.
- F1: Due-date 추출 (drafting) — content from the previous stub
normalized to the new template.
- F2: 태그 클릭 = 즉시 삭제 + undo 부재 (raw) — NoteCard.tsx:110
binds chip onClick to removeTag, no confirm or undo, and there is
no "filter by tag" affordance to match the user's mental model.
Direction: split click=filter, ✕-icon=remove with 5s undo toast.
README docs map updated to point at the new path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The due-date extraction work originated as feedback during dogfood, but
the dogfood strategy doc itself should stay feature-agnostic — it's the
generic operating manual for the 2-week dogfood, not a feedback log.
- Remove the "시간 표현 포함 노트 수" row from dogfood-strategy §3.1.
- Rephrase the due-date spec stub so H1 / §7 / §9 reference the spec's
own sample-collection plan instead of relying on the dogfood retro.
- Spec is now framed as "independent of slice exit"; entry timing is a
separate decision once an accumulated sample meets H1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Captures the design skeleton, hypotheses, and open questions for the
hybrid (rule-based first → AI fallback) Korean date-phrase extractor.
Schema impact, prompt change, UX copy, and library tradeoffs are
sketched but deferred — formalization waits for slice v0.4 dogfood
Pass and the H1 (time-phrase frequency ≥ 30%) check in week-1 retro.
Cross-link added to dogfood-strategy daily-metric table so the H1
data is collected during dogfood, and to README docs map.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
User reassessed model needs: 26b is overkill for slice-scope tasks
(short Korean title + 3-line summary + ≤3 kebab-case tags). e4b
(8.0B Q4_K_M, efficiency variant) sits closest to the original
"표준 9b" tier in spec §6.5 and gives faster responses with
adequate margin for the slice's simple structuring work.
Spec changes:
- Header bumped to v0.4 with new revision line.
- §1.1 retiers AI 파이프라인 from "고품질 26B" to "표준 e4b".
- §2.1 diagram, §3.1 ai_provider example, §4.1 provider name,
§4.2 request body, §4.6 health check, §5.4 copy catalog: model
string swapped 26b → e4b.
- §6.4 perf target restored to <30s provisional (e4b is similar
scale to original 9b reference, 60s margin no longer needed).
- §8 open issue rewritten: e4b is the standard-tier substitute,
with 26b/e2b documented as quality-up / speed-up fallback paths
if dogfood reveals issues with Korean output or tag formatting.
Plan changes:
- Header bumped to v0.4 with restated Goal.
- Architecture summary, Task 12 unit test mocks/expectations,
LocalOllamaProvider default model, copy banner, Task 33 dogfood
prerequisite: 26b → e4b throughout.
Tier ladder for dogfood escalation (from §8):
e2b (5.1B, speed) ← e4b (8.0B, default) → 26b (25.8B, quality)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Model swap: gemma4:9b has no official checkpoint; LAN server
(192.168.0.47:11434) ships gemma4:26b (25.8B Q4_K_M), which fits the
§6.5 26B cap and the "high-quality" tier. Updates §1.1, §2.1 diagram,
§3.1 ai_provider example, §4.1 provider name, §4.2 request body, §4.6
health check, §5.4 copy catalog, plan Task 12 (mock + default model),
Task 30 main entry, Task 33 dogfood intro.
Endpoint: LocalOllamaProvider now configurable via constructor opts.
Task 30 main entry and integration test read INKLING_OLLAMA_ENDPOINT
from env; unset falls back to localhost. LAN Ollama moves from
out-of-scope to in-scope via endpoint injection; only a separate
LanOllamaProvider class remains deferred.
Perf target §6.4: RTX 3060-referenced <30s target no longer valid
under 26B Q4_K_M + LAN. Set to <60s provisional; §8 adds a new open
issue to measure real p95 during first dogfood week and confirm.
§7.4 adds INKLING_OLLAMA_ENDPOINT env setup and recommends Volta over
nvm-windows for Windows Node 24.15.0 install.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pin Node 24 LTS (Krypton) as runtime. Document latest-stable-major
policy for dependencies with initial pin candidates as of 2026-04-24,
and .nvmrc-based version synchronization for dev/CI.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Initial design document covering the first end-to-end slice of Inkling:
Quick Capture, SQLite storage, Local Ollama AI pipeline (gemma4:9b),
and Inbox with inline editing. Scoped for dogfood on Windows/macOS.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
