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).
sidechat.start passed `seed` without `meta.isSeeded: true` +
`inheritedEventCount`, so dsh-session treated the whole seed as the
child's OWN events and the child's Inbox constructor replayed the
parent's `agent/inbox/spliced` history — inheriting whatever input sat
UNCLAIMED in the parent at the click moment:
- next-turn: a queued follow-up behind a still-running turn;
- next-step (the reported long-context case, parent queue empty): a
tool-result context / steering spliced between step boundaries.
The first side prompt then claimed [phantom, boundary, question] — the
stale parent message was sent to the model BEFORE the boundary and
logged as a user/message. The fix passes the exact marker pair the
host's own session.fork uses (api-session-controller); ownEvents() now
stops at the end-seed boundary and the inherited inbox replays empty.
Regression tests run the REAL Session.create + Inbox in both
directions (old shape inherits the phantom, marked shape stays empty);
routes tests pin the two create options. Verified: pnpm typecheck /
test (5 pre-existing unrelated UI-spec failures on main unchanged) /
build.
- pins: CI mount-gate CLI, dsh.plugin.json engines floor, and the
@deepseek-ai/* peer floor / devDependencies baseline move to
0.1.2-alpha.5 (dsh-client-locale trails at 0.1.2-alpha.3 — no such
release upstream; ^0.1.2-alpha.3 already accepts the alpha.5 runtime)
- code: migrate the alpha.4 Session.events removal to snapshotEvents()
(sidechat transcript live reads, fork inheritance, jobs.output replay,
subagent activity) and drop the seedLength meta field the host removed
from CreateAgentOptions.meta
- gates: pnpm peers check clean, typecheck + 1137 unit tests green,
real-host mount smoke 14/14 on npm-published 0.1.2-alpha.5
DSH 0.1.2-alpha.2 is on npm under the `alpha` dist-tag, so the CI mount
pin and the @deepseek-ai/* devDependencies baseline move up from
0.1.1-rc.1/rc.2 (the dead dsh-client-runtime devDep goes away with
them). Verified end-to-end against a real 0.1.2-alpha.2 host: full
vitest suite (1106), typecheck, build/pack, consumer type surface, and
the headless mount smoke 14/14 — the token URL, slash RPC and
MarkdownText labels contracts are unchanged from alpha.1.
- dsh-settings dropped the runtime `settingsNamespace` export:
namespaces are validated at compile time (SettingsNamespaceInput), so
the host passes the 'dsh-better-sidebar' constant directly and the
fake settings service in smoke.spec casts to the branded type.
- dsh-subagent bumped SUBAGENT_DESCRIPTOR_VERSION 2 -> 3: the version is
stamped by the host package; the sidechat seed assertion now follows
the constant instead of pinning a literal.
- Restored SessionEvent.ignorable and the RemoteError wrapping were
verified to have no impact on this plugin.
- e2e scratch profiles (e2e-mount.sh / e2e-aggregate-mount.sh) add
'@deepseek-ai/*' to minimumReleaseAgeExclude (mirroring the repo
root): alpha releases are often <24h old when the lane runs, which
pnpm 11's default minimumReleaseAge would refuse to install.
- vitest excludes .worktrees/** — local task worktrees carried stale
code against the shared node_modules and broke on the devDeps bump.
- Version lockstep 0.17.2 (package.json, dsh.plugin.json,
SIDEBAR_SERVICE_VERSION, README/AGENTS/guide docs).
DSH 0.1.2-alpha.1 removed the client `ctx.connection.api` face (Remote
gateway migration), so every Side Chat transcript poll (`sessions.history`)
threw TypeError into the view's catch and was swallowed — the tab rendered
an empty transcript forever, silently (no console error, so the mount lane
never caught it). The successor APIs are not a drop-in either:
session/follow|page reject plain session addresses for origin:'subagent'
logs (agent-busy fence) and paging cannot read past the current cursor.
Move the transcript to the plugin's own wire — one transport for every
DSH generation:
- new `sidechat.events` route: live threads read the in-memory
`agent.session.events`; cold threads read `sessionPersistence.inspect`
(both seams exist since 0.1.0-rc.8; alpha.1's inspect returns the
expanded logical log, never the packed chunk-row encoding). The
inherited seed is cut host-side (`threadOwnLogEvents`), polls ride an
`afterSeq` delta, and the response is tail-capped at 8000 events (the
old client walk ceiling).
- SideChatView.fetchThread is single-path; collectOwnEvents (the client
walk) is gone, and so are the ctx.connection mirror and inject entry
(no consumer left).
- transcriptRows keeps re-cutting at session/end-seed as defense in
depth.
Verification:
- unit: sidechat.events route (seed cut, afterSeq delta + never
resurrecting the seed, cap, cold/live sources, 404/503/bad-request),
full suite 1104 passed; typecheck and build (purity gate) green.
- mount e2e vs a real dsh-v0.1.2-alpha.1 source build: 14/14, including
the Side Chat tab sweep polling sidechat.events (performance resource
assertion) and live + post-dispose (persisted) route reads.
- mount e2e vs PATH dsh 0.1.0-rc.8: 14/14 (no regression).
* 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