Move the plugin onto the DSH 0.1.5-alpha.1 baseline (peer floor
^0.1.5-alpha.1, CI pinned to the alpha dist-tag) and fix the two host
contract changes that alpha line introduced.
Baseline:
- all @deepseek-ai/dsh-* peer/dev deps -> 0.1.5-alpha.1; optional peer
@deepseek-ai/dsh-client-ui-sidebar-right (declared, unused until the
native-surface phase); devDep @deepseek-ai/dsh-agent-loop (inbox fold)
- dsh.plugin.json engines >=0.1.5-alpha.1; version 0.19.0-alpha.0;
SIDEBAR_SERVICE_VERSION follows
Live assistant stream (assistant/chunk is gone):
- 0.1.5 publishes in-flight model deltas as process-local
agent/assistant-stream frames instead of durable assistant/chunk events
and embeds the settled stream in assistant/message / assistant/attempt.
src/assistant-live.ts folds the frames into a bounded per-session buffer;
sidechat.events serves the current attempt as `live` rows (replaced every
poll, never a delta) and the transcript renders them; the inherited
in-progress snapshot reads message content / attempt stream / live frames.
Cold session reads (persistence.inspect is gone):
- 0.1.5 reads a stored session through an explicit read handle
(open(id,'read') -> handle.read() -> close()). src/session-store.ts owns
that protocol; every cold read (sidechat transcript, cold-resume preset,
session.cwd, changes replay) goes through it.
Dead code and docs:
- drop the remote.session.openWorkspacePath interception: 0.1.5's chat opens
files through ctx.sidebarRight.openResource instead, so the wrapper had no
caller and would hijack the host's "open in app" gesture; the
interceptOpenPath pref, its settings row and its locale keys go with it
- AGENTS.md §3 + external-plugin-guide.md describe the new baseline
- vitest setup bridges Node's localStorage accessor to jsdom's store (the
pre-existing 26 failures on Node >= 22)
- desktop-layout e2e seeds through host RPC and types into the Lexical
composer (0.1.5 replaced the textarea) instead of driving the directory
picker
Verified: pnpm typecheck / lint / build / test (124 files, 1327 tests) /
check:consumer-types, plus pnpm test:mount against a real
@deepseek-ai/dsh@0.1.5-alpha.1 host (18/18).
* fix(sidechat): split context injection from the first user message
The first composer message rode the same user/message event as the side
boundary prompt (+ parked snapshot), and the transcript dropped that whole
row by its boundary prefix — swallowing the user's first question.
Deliver first contact as TWO messages: the boundary+snapshot rides
agent.inject (queued next-step context, claimed first at the opening step,
no wake) stamped with source kind 'plugin', and the question is the
follow-up that wakes the driver. The log records injection and question as
separate events; the transcript maps injections (plugin-sourced, or the
legacy boundary-prefix blob of pre-split threads) onto a collapsible
injection row and renders genuine user messages — the first one included —
as user rows. boundaryDelivered still recognizes the injection by its
unchanged boundary-prefix opening.
* feat(sidechat): codex-style collapsible rows and creating shimmer
Tool calls, thinking and context injections now share one quiet
single-line chrome (chevron + label + a one-line argument summary) that
expands into an indented body on a hairline thread — no cards or fills.
Streaming labels and the creating hero shimmer (shimmer = generating);
failed tools go danger; reduced-motion stills every loop.
* fix(sidebar): debounce subagent auto-open past the title frame
The host delivers a new child's origin and title in separate frames, so a
Side Chat thread's first visible frame lacks its 'Side: ' label and
tripped the 0→N auto-open — every thread creation popped the task page.
The trigger now rearms for 500ms and re-evaluates the original baseline
against the live snapshot, by which time the title filter recognizes the
thread. Genuine subagents still auto-open, half a second later.
* fix(sidechat): render legacy threads' first message as its own bubble
Threads created before the host split still log the boundary (+snapshot)
and the question as ONE 'user' message; the transcript mapped that row
wholly onto the injection row, so the user's first question only appeared
inside the expansion. The boundary prompt is a known constant, so the
legacy row now splits THERE: the injection row keeps the prompt, the
remainder renders as the user's real message (a pre-split snapshot, when
present, rides along — the common case is a pure question). Row React keys
become kind:seq so the split's two rows never collide.
Menghuan1918