@dgy970516

dsh-status-turbo

Name: dsh-status-turbo
Availability: InStock
Author: dgy970516

DSH(DeepSeek Harness)??:???????? -- ???????????? token ???????,??????????;?????????

Stars: 0
Language: JavaScript
Created: Oct 16, 2026
Updated: Oct 16, 2026

Auth

GitHub repo

Introduction

dsh-status-turbo

Turns "what is it stuck on right now?" into one line of ticking text above the composer.

dsh-status-turbo is a plugin for DeepSeek Harness. It keeps a single thin status bar above the message composer:

● Running tool(bash)   2:14   3.1K tok

For those moments three minutes into a long command — page frozen, no log output, is it dead or not — this line is the answer.

What it shows

It sits inside DSH's own composer footer stats row (the 6 turns · 283 steps / 27.9M tok · cache hit 96% / 10% line), on the right of the shipped entries — so it never adds an extra row or floats above the composer. It only fills in what that row does not already show:

Field	Meaning	Example
Phase	`assembling` / `requesting` / `streaming` / `tool(<name>)` / `approval` / `compacting`	`● Running tool bash · 2:14`
Phase elapsed	Refreshed every second. Needs no push — the client computes it from its own clock, so it keeps ticking while the log is silent	ditto
Step tokens	Input + output accumulated for the current step (since 0.19.2 only the number)	`3.1K tok`
Gear	Not on the status bar since 0.19.2 — the app's own effort selector already shows the same value, so it stays in the detail panel. The value is the reasoning effort this step actually sent (read from the logged `request/header`, not guessed locally)	—
No progress	No new output for more than `noProgressMs` (default 90s) → that cell turns amber and shows how long it has been stuck (since 0.19.2 four words only; the full sentence moves to `title`)	`2:49 no new output`

The host projects this as the turbo wire view, version v: 13 with 37 keys — v1's 19 keys, the 9 keys added in v2 (mountStatus, prefixEpoch, prefixCause, prefixAt, lastTurnMs, topTools, hookFaults, idleLine, lastSpill), then one key per later version: v3 activity, v4 waitTools / waitKind / subagents, v5 slowMs, v6 enhancement, v8 handoff, v9 rotation, v13 newSession (v7 added enhancement.mode inside an existing key, and v10 added the rotation.childId / seedOk / message fields inside rotation — neither raised the top-level key count). newSession carries the New session page's copy-ready opening text ({ text, oldId, cwd }). The client pins EXPECTED_V = 13: on a version mismatch it renders red text 投影版本错配（宿主 vN ≠ 客户端 vM） in place of the bar rather than disappearing.

Deliberately not repeated from the shipped row: session turns/steps, tok/s, total tokens, session-level cache hit rate, context usage. The per-step cache hit rate stays in the projection data (hitRate) but no longer occupies a cell — two different "cache hit" numbers on one line only confuse.

While idle the cell does not disappear — it keeps a one-line summary of the last turn: the phase name plus how long that turn took (● requesting · last turn 42.3s). The host sends that as idleLine / lastTurnMs, so the summary survives even with no new events.

Clicking the cell opens a detail panel below the composer (slot conversation.input.dock, id dsh-status-turbo.detail, order 0); clicking again collapses it. While collapsed — or before the first snapshot arrives — the panel renders nothing at all. The panel has 11 always-present sections, top to bottom: Now (what this step is doing — phase name · elapsed · tool name), Activity (the last few 'what the model thought / which tool it called / how it turned out', newest first), this turn / last turn / cache and usage / prefix / slowest tools (top 5 by maxMs) / waits / rotation / enhancement / handoff. Two more are conditional and simply do not appear when empty: the last oversized-result spill with its absolute path (lastSpill) and recent faults (hookFaults).

The activity stream is memory-only (a ring buffer — never written to disk, no new dependencies, no change to the requests sent): assistant/message records a reasoning excerpt (truncated to reasoningChars characters), tool/call records the tool name and its redacted arguments, tool/result records the first resultHeadLines lines of the result / error, and turn/end records the stop reason. Argument values whose key matches redactKeys (case-insensitive substring match) become '***' before they ever reach the UI, circular references degrade to [Circular], and a dirty argument never throws.

Install

Manual (profile assembly): drop the package into the profile's node_modules, then in the profile's cordis.patch.yml:

- insert:
    - id: dsh-status-turbo
      name: 'dsh-status-turbo'
      config:
        statusBar: true
        noProgressMs: 90000
        downgrade: true
        downgradeFloor: low
        minQuietSteps: 2
        spillThresholdBytes: 32768
        bulkInjectionBytes: 32768
        evidenceWhitelist:
          - '/exit code:?\s*0\b/mi'
          - '/(^|\n)\s*(#\s*(pass|tests|suites)\s+\d+|\d+\s+passing|Tests:\s+\d+\s+passed|Test Suites:\s+\d+\s+passed|ok\s+\d+\s+-)/m'
          - '/(^|\n)\s*(Successfully compiled|Compiled successfully|Found 0 errors|\d+\s+files?\s+checked,?\s*0\s+errors|Build succeeded|Done in \d)/mi'
        stuckAction: warn
        stuckRounds: 3
        stuckRepeats: 3
        mojibakeMinRuns: 2

Every key is optional; the block above is a short example (12 of the 46 default keys). The single source of truth for all 46 defaults is lib/state.js · DEFAULT_CONFIG, which the package's own cordis.patch.yml mirrors verbatim; every key with its default and meaning is tabulated under Configuration below.

⚠️ Do not list the same package in both dsh.profile.bundles and the profile's cordis.patch.yml — it would be loaded twice.

Saving compute: per-step reasoning gear (B1)

The plugin watches the tool trajectory and drops the reasoning effort for that step when the step plainly does not need deep thinking:

≥2 consecutive finished steps that ran only read-only tools (read/glob/grep/web_search …) with zero errors → drop one gear;
a write-capable tool (bash/edit/write/sql_exec …) or any error → back to the original gear immediately;
the original gear is whatever you selected for the session. The plugin only lowers, never raises, and never touches your default model or provider.

Every downgrade leaves two independent traces: a B1 降档: … line in the DSH log, and an extra gear row in the detail panel (0.19.2 moved it off the status bar).

Key	Default	Description
`downgrade`	`true`	Master switch. Only an explicit `false` disables it (then `llm` is not even injected)
`downgradeFloor`	`low`	Lowest gear allowed. Compared by index in the model's own ordered effort list; if the model does not publish it, drops one gear at a time
`minQuietSteps`	`2`	How many clean read-only steps are required. `1` is more aggressive, and easier to get wrong

No gear name is hard-coded — everything is asked from ctx.llm.resolveModelInfo(). Whenever it is unsure (no effort list, current gear not published, service missing, judgment threw), it runs the step at the original gear and never lets the plugin fail a request.

Saving context: oversized tool results (B3)

When a single tool result is huge, the host half shrinks it before it reaches the model:

it first asks the host's own toolResultPruner.pruneContent to trim the body;
if the result is still at or above spillThresholdBytes (default 32768), it is handed to the host's existing spill backend (spillStore.saveText), and the shrunken body carries a notice with the absolute path of the saved file — a path you can read with offset/limit or grep directly.

The notice is rendered verbatim by lib/spill.js: （已省略 {bytes} bytes；完整结果落盘于：{locator}。用 read 配 offset/limit，或 grep 这个路径继续。） If the backend hands back a locator that is not an absolute path, the plugin degrades instead of guessing (no fake path is ever printed). See the "Writes only its own data" note under Design constraints: for B3 the write is the host's, and the plugin itself never opens a file for writing in that path.

Seeing a dead cache prefix (B4)

Cache-prefix invalidation is visible as a 前缀已失效 pill on the status bar (only while the invalidation is fresh, i.e. within the last 5 minutes). The host counts three triggers:

Trigger	Condition
`compaction-start` / `compaction-end`	a `compaction/start` or `compaction/end` event
`bulk-injection`	one `tool/result` payload ≥ `bulkInjectionBytes` (default 32768)

The wire view exposes it as prefixEpoch / prefixCause / prefixAt. On a real recorded session this counter read 17 invalidations (bulk-injection ×9, compaction-start ×4, compaction-end ×4) — see tools/replay-log.mjs.

Notes appended inside the same tool return (C1 / C2 / C3)

Three cheap corrections are appended to the current tool result — they never add a round trip, and the session's step count does not change:

C1 — no verifiable evidence: a result that shows no evidence line at all (nothing matching evidenceWhitelist, exactly 3 regex sources, e.g. exit code: 0, N passing, Found 0 errors) gets 「上一条没有可核对的证据……别据此下结论。」
C2 — truncated read: a read that used offset/limit while the file has more lines gets 「你只看了 N / M 行（绝对路径）；后面还有内容没读，别基于这个片段下结论。」
C3 — mojibake / noise: broken text (≥ mojibakeMinRuns runs of U+FFFD) or output swamped by noise gets 「这段输出里的中文已经损坏……」 / 「这次输出被噪声淹没（x / y 行不是目标输出）……」

Stuck detection (D) — warn level only

stuckAction defaults to warn, which is zero side effect (it records a fault, nothing more). nudge and stop only happen if you configure them explicitly — and stop additionally requires the host's workspace/session-activity to report a live session, because it would otherwise kill long-running work such as an overnight build. Known gap: stuckRounds currently has no consumer — the host half only sees one half of the signal (stuckRepeats over consecutive identical aggregate keys), so D is not a complete implementation.

The New session page (0.18.0)

When a session has grown enough to be handed over (see the rotation* keys under Configuration below), the rotation creates a blank child session: since 0.21.1 nothing is written into it (before that the opening script was appended as its first user/message, so every new session opened with the same paragraph). The New session page shows that opening text so you can copy it with one click and paste it into the new session — no more making the new session guess what it was supposed to do.

The text is built from the template: {old} becomes the old session id and {cwd} the working directory. The default template is 继续旧会话 {old}（工作目录 {cwd}）。需要它的上下文时用 @{old} 查阅，不要假设我记得；先跟我确认要接着做的那件事。
What the page shows: a rotation section, the opening text inside a selectable <pre>, a Copy button (it reports '已复制' once the clipboard write succeeds, and '复制失败，请手动选中' when the clipboard is unavailable or refuses), one line with the working directory, and a hint to paste the text into the new session.
Where it lives: the bottom of this plugin's settings page (dsh-status-turbo.settings, right under the config form). 0.18.2 removes the 0.18.0 left-rail entry — one page instead of two, and no sidebar button to keep in sync.
Data comes through the shipped hook: the settings page is root-scoped with no session binding, so the card reads useSessions(state => state.current) and then state.byId[id]?.projectionValues?.turbo — the host already publishes every session's projection values inside the session list. No new subscription, HTTP route, or host RPC.
The child session is created through the agent lifecycle (0.19.0): the host half now calls ctx.agents.create({ sessionId, meta }) instead of ctx.sessions.create(...). A session published outside the agent lifecycle never gets a session-log writer, so it persists nothing — it lives in memory only and never appears in the session list. That call is asynchronous: its outcome (and the title pass) is appended to rotation-trace.jsonl once it settles. Without an agents service the host falls back to the old in-memory path.
…and attached to its workspace (0.19.1): persisting is not enough. The left-hand session list is built from each workspace's sessionIds, not from disk, so once the create promise settles the host half resolves the workspace by normalized path (workspaceRegistry.resolveByPath(cwd)) and calls attachSession(childId) — the same step the host's own new-session and fork paths take. The outcome (attached / no-registry / no-workspace / resolve-failed / attach-failed) lands in rotation-trace.jsonl; anything but attached also logs a warning.
…carrying a model and a preset, and switching by itself (0.19.3): the child agent is created with the parent's model (agentOptions, falling back to agentDefaultModel.currentSelection()) and the parent's agentPreset (mounted through setup), because the deployment persona section renders {{model}} and a child without one fails its first run.
…and switched through the client's real entry point (0.19.4): the client sessions service face (0.2.0-rc.2) is retain / using / retainInfo / refreshProjections / search / fork / scope / binding — there is no open, so every attempt fell through to failed / no-service. The page now prefers uiWorkspace.openSession(childId) and keeps sessions.open only as a legacy fallback, still retrying for ~20s so the switch survives the create → workspace-attach → session-list trip.
…named after the session it came from, and with a way out of "waiting" (0.20.0): a rotation child is a blank session (0.9.0 dropped fork), so it carries no title events — before 0.21.1 the fallback named it from its first user/message (the seed template, identical in every generation), and since 0.21.1 there is no first message at all. The host now reads the parent's persisted title (ctx.sessionTitle.get) and renames the child with the same convention sessions.fork({ increaseTitle: true }) uses (a trailing (N) / （N） is incremented keeping its brackets; anything else gets (1)); that write is a user-source session/title event, which pins the title against the fallback. Key: rotationIncreaseTitle (default true). On the client side the armed row is clickable again while auto is waiting — one click switches immediately — and a second row switches and archives the current session (performRotation(snapshot, { force: true, archiveOld: true })). As of 0.20.0 the host only reminds by default (rotationCreate: false): a threshold crossing is still recognised and still traced, but nothing is created — the panel suggests starting a new session and the opening script is copyable on the settings page; set rotationCreate: true to restore the automatic child session.
…plain-spoken and copyable (0.21.0): every config field and group label now has a Chinese description (raw keys such as rotationCreate no longer appear as labels) — a missing dictionary entry used to fall straight through to the key name because makeText's fallback is supplied at the call site, so the settings page consults DICT.zh first and only then the hard-coded fallback. The status bar gained a Copy button (left of the collapse toggle) that copies four lines — 会话名称：… / 会话 ID：… / 会话日志目录：… / 继续处理未完成的任务; a value that is unavailable drops its whole line instead of leaving a placeholder, and the button itself is always rendered — even against a host that sends no newSession at all it still copies the closing hand-off sentence. The name comes from the host's session-title, the directory is built as <DSH_HOME>/sessions/<project key>/<session id> (an empty string when there is no working directory — the path is never guessed); both are fields 0.21.0 added to the wire.
…and nothing is auto-filled into the child (0.21.1): the step that appended the opening script as the child's first user/message is gone (seedQuietly / seedMessage deleted), so a rotation child — even with rotationCreate: true — is created empty, and the script is taken by hand from the status bar's Copy button or the settings page. The rotation record no longer carries seedOk, and the client no longer renders the "seed written / failed" note.
Three states, stated apart: no current session ('pick one on the left'), projection not arrived yet ('waiting for this session's projection'), and no opening text reported by the host (a hint line only — no <pre>, no Copy button). It never reports 'none' for 'not yet'.
It never rotates anything: the host half still creates the blank session (since 0.21.1 with nothing written into it); this page only puts the same text in front of you.
On the wire it is the top-level newSession key ({ text, oldId, cwd }, v13 / 37 keys).

Not implemented this round: B2

Backgrounding long commands (returning a job id within 10s instead of blocking) is not implemented. The integration target does not exist on this machine (no dsh-plugin-background-tasks, and PreToolDecision has no result-replacing branch), and there is no supported hook for it. Evidence and the three follow-up leads are in docs/plan-B2.md. Please do not expect a B2 usage that is not there.

Configuration

Key	Default	Description
`statusBar`	`true`	Mount switch for the status bar. The host projects it into the wire field `mountStatus` (`'enabled'` / `'disabled'`); the client has three states: `enabled` → normal bar; `disabled` → renders nothing; field absent (an older host that does not send it) → a red cell `状态条开关缺失：配置未送达` instead of a silent no-op. Off means "no bar", not "silently dead switch"
`noProgressMs`	`90000`	No-progress threshold in milliseconds
`downgrade`	`true`	See the section above
`downgradeFloor`	`low`	See the section above
`minQuietSteps`	`2`	See the section above
`readOnlyTools`	10 tool names	0.9.2 (P1-4): the B1 read-only allowlist — only explicitly read-only tools count as "pure read / list / search"; anything not listed (`bash` / `edit` / `write` / `sql_exec` / `univer_execute`…) counts as "may write", and one such call breaks the consecutive run (deliberately conservative). Elements must be non-empty strings and invalid ones are filtered; an empty result falls back to this table (`[]` means "not configured", not "no read-only tools"). Defaults: `read` / `read_image` / `glob` / `grep` / `list_dir` / `search_context` / `web_search` / `web_fetch` / `cordis_inspect_list` / `cordis_inspect_query`
`spillThresholdBytes`	`32768`	B3: a result body this many UTF-8 bytes or larger may be spilled (AND-ed with the harness tool-result pruner)
`localTrimHeadChars`	`4096`	0.6.5: characters of the head kept by the local trimmer used when the host pruner is unavailable (`spillThresholdBytes` decides whether to spill; these three keys decide how much the model sees)
`localTrimTailChars`	`1024`	0.6.5: characters of the tail kept; the elided middle becomes one line saying how many characters were dropped
`localTrimMinChars`	`8192`	0.6.5: a longest-text block shorter than this is not trimmed (characters, unrelated to `spillThresholdBytes`); a trim no shorter than the original is skipped too
`bulkInjectionBytes`	`32768`	B4: one `tool/result` payload at or above this counts as a "bulk injection" that invalidates the cache prefix
`evidenceWhitelist`	3 regex sources	C1: 3 complete regex literals as strings (delimiters + flags included); matching any one counts as verifiable evidence
`stuckAction`	`warn`	D: `warn` (default, zero side effect) / `nudge` / `stop`
`stuckRounds`	`3`	D: consecutive `turn/end` without a new tool name. Currently has no consumer (known gap)
`stuckRepeats`	`3`	D: how many repeats of the same aggregate key count as stuck
`mojibakeMinRuns`	`2`	C3-a: longest run of consecutive U+FFFD before the encoding warning fires
`activityLimit`	`24`	0.6.0: how many activity entries the ring buffer keeps (drops from the head past this)
`activityBytes`	`8192`	0.6.0: total UTF-8 byte cap for the activity ring buffer (drops from the head past this)
`reasoningChars`	`400`	0.6.0: characters a single reasoning excerpt is truncated to
`resultHeadLines`	`6`	0.6.0: head lines kept from a tool result / error
`redactKeys`	11 keys	0.6.0: argument-redaction keys (case-insensitive substring match): `key` / `token` / `secret` / `password` / `passwd` / `pwd` / `authorization` / `cookie` / `dsn` / `apikey` / `credential`
`subagentWaitTools`	`['wait_agent']`	0.6.1: waiting tool names (waiting on a subagent); they skip "slowest tools" and are listed as their own wait kind
`humanWaitTools`	`['ask_user_question']`	0.6.1: waiting tool names (waiting on the user), classified `human`
`jobWaitTools`	`['job_output','job_wait']`	0.6.3: waiting tool names (waiting on a background job) — the fourth kind. Only a call whose arguments carry `wait: true` counts as `job`; a snapshot without `wait` counts as real execution
`slowMs`	`60000`	0.6.3: slow-call threshold in milliseconds; a tool whose `maxMs` reaches it carries `slow: true` on the wire, and the client adds ⚠ plus a pointer to the background-tasks plugin
`handoffExport`	`true`	Master switch for the 0.7.0 handoff export. On by default; an explicit `false` really does nothing (no probing, no process, no directory)
`handoffExportTokens`	`240000`	Export is considered once the step's input tokens reach this (lowered from 400000 in 0.8.1 — the measured hard stop on this machine was 341421)
`handoffExportMinDeltaTokens`	`60000`	Re-export only after the session grew by this much (lowered from 100000 in 0.8.1)
`handoffExportDir`	`'handoff'`	Export directory, relative to the session cwd
`handoffExportFull`	`false`	Whether to pass `--full` (attaches every block's raw messages; a much larger document)
`handoffExportBiliBin`	`''`	Path to the bili executable; the empty string selects the probing chain described below
`handoffExportTimeoutMs`	`120000`	0.9.2 (P1-4): hard timeout for one `bili export` (and for the lane-list read), in milliseconds. On timeout it kills first, destroys both pipes and only then escalates to `SIGKILL` (`lib/handoff.js · runBili`). One key shared by both call sites (`runExport` / `listLanes`); an invalid value falls back to 120000
`handoffExportWindowPercent`	`25`	Threshold as a percentage of the model window when the window is known. One knob shared by the token and byte criteria (lowered from 40 in 0.8.1: the old 40% × 1M equalled the old token knob, so it never bound)
`handoffExportMaxPerProcess`	`64`	Most exports started per process; exhausting it records `failed` plus one warning (raised from a hardcoded 8 in 0.7.5)
`handoffExportSubLanes`	`false`	Whether to export the session's sub-lanes (`\|<sub:…>`) as well. Off by default since 0.7.8 (one over-threshold lane used to cost one export per lane)
`handoffExportBytes`	`1800000`	Byte criterion: fires when the model-visible volume reaches it (OR-ed with the token criterion); lowered from 3000000 in 0.8.1 = 240000 × 7.5
`handoffExportMinDeltaBytes`	`450000`	Throttle for the byte criterion (lowered from 8000000 in 0.8.1 — the old value was above the threshold, making a second byte-triggered export a dead end)
`handoffExportFreshMs`	`300000`	Only fresh events trigger: an event folded from further back than this many milliseconds does nothing (blocks the cold-start replay burst)
`handoffExportRefreshBytes`	`0`	Whether one lane may be exported repeatedly. `0` = at most one document per lane (default since 0.7.8); setting a byte delta restores "refresh per watermark bucket"
`rotation`	`'auto'`	Rotation mode: `off` / `manual` (one clickable panel row) / `auto`. `auto` by default since 0.9.1
`rotationCooldownMs`	`600000`	Minimum interval between two rotations (process-wide, to break rotation chains)
`rotationOpenChild`	`true`	0.9.0: whether the client switches to the child session the host created (in `auto` mode it switches automatically)
`rotationFreshMs`	`300000`	0.8.1: rotation is judged only on fresh events (same purpose as `handoffExportFreshMs`)
`rotationRequireIdle`	`false`	0.9.2: whether rotation requires the session to have no open round. Default `false` — creating a blank session does not interrupt a running turn; `true` restores the 0.8.0 behaviour (measured: a session that is never idle never rotates)
`rotationArchiveOld`	`false`	Whether to archive the old session after switching (`false` since 0.8.1: archiving drops it from the same list projection the `@` picker reads, so the `@{old}` lead would break, and the UI has no un-archive entry)
`rotationIncreaseTitle`	`true`	0.20.0: whether a rotation child is renamed after the parent's persisted title with the official `(N)` convention (the parent's title is read through `ctx.sessionTitle.get`, the child written through `rename`; an absent service, a missing title or a failed rename only downgrade)
`rotationCreate`	`false`	0.20.0: whether a threshold crossing actually creates a new session. `false` (the default) only records `remind` — `shouldRotate` still recognises "at threshold", but nothing is created and the client shows a suggestion; set `true` to restore the 0.19.x automatic child session
`rotationSeedMessage`	`'继续旧会话 {old}（工作目录 {cwd}）。…'`	0.9.0: the opening-script template (`{old}` = old session id, `{cwd}` = working directory). Since 0.21.1 it is no longer written into the new session — it only renders the text you copy from the status bar button or the settings page; that copy is now the only route that puts the old session id into the context

Restart DSH after changing configuration.

Note: the per-key behaviour of the handoffExport* and rotation* families (0.7.0 handoff export, 0.8.0+ rotation) is described in Chinese in README.zh.md §「交接文档自动导出」/§「到量轮换」; the defaults above are the same values.

Manual acceptance

#	Steps	Expected
1	Have the model run `ping -n 120 127.0.0.1` (~2 min)	Within 1s the bar appears, phase = `Running tool(bash)`, elapsed ticks from 0
2	Do nothing for 2 minutes	Elapsed keeps advancing; a silent log never freezes it
3	Wait for the command to finish	Phase returns to `requesting`, then the cell flips to the idle summary `last turn …` — it does not vanish
4	Set `statusBar: false` and restart	No bar at all (the host still folds state, very cheap). If the field `mountStatus` is missing — i.e. an older host half — the cell instead shows the red `状态条开关缺失：配置未送达`; that red cell is a failure signal, not a working "off"
5	Produce more than `spillThresholdBytes` (32 KiB) of tool output in one result	The body is pruned and carries a notice with a readable absolute path (the spill locator)
6	Have the model claim "tests passed" without running them; or make it `read` a file with `offset`/`limit`	A correction note appears inside the same tool return — no extra round trip, session step count unchanged
7	Run a command that emits GBK mojibake, or one buried in noise	An "encoding broken" / "noise" note appears in the same tool return
8	Leave one step silent for 2 minutes	At 90s (`noProgressMs`) the no-progress cell turns amber and counts up
9	Inject memory / trigger compaction mid-session	A `前缀已失效` pill appears within 5 minutes, cause = `压缩开始` / `压缩结束` / `大块结果注入`
10	Remove the `conversation.composer.dock` declaration (or use a non-existent slot name) and restart	UI does not crash; console shows `[dsh-status-turbo] 状态条 3 秒内未能挂载到 conversation.composer.dock…`
11	Tamper with the projection version `v`	Red text "投影版本错配" appears in place of the bar instead of silently vanishing

The original §6 row 2 ("long commands stop blocking; a background job id within 10s") does not apply this round — B2 is not implemented, see docs/plan-B2.md. It is deliberately dropped and explained rather than left as a gap, so the rows above are renumbered into a continuous 1–11.

Development

node --test "test/*.test.mjs"      # pure fold + host/client contracts + UI contract + hooks

No build step: lib/ is source and artifact at once.
No zod: projection schemas use a passthrough stub (see docs/design.md §2.3).
Verify without opening the GUI — replay a real committed session log:
```
node tools/replay-log.mjs <session.v4.jsonl.zstd> [--peek] [--max N] [--stall-ms N]
```
It runs the exact same fold and labels over the log, printing which event changed the strip to what, and finally the longest tool-silence window — i.e. what the strip was showing during it. Measured on this session:
```
# jsonl lines 1182      # parseable events 1182 (bad lines skipped 0)
# longest tool window: pwsh silent 50.4s (at session +52m34s,
#   strip should read "执行工具(pwsh)  50.4s")
```
(Session logs live in D:\deepseek-harness\sessions\<workspace-slug>\session-<id>\session.v4.jsonl.zstd and are multi-frame zstd; the tool splits on the 28 B5 2F FD magic and inflates frame by frame.)
Layout: lib/state.js (pure fold: no services, no Date.now(), no third-party dependency; one Node builtin import — node:crypto for the A2 tool-argument fingerprint), lib/index.js (host half: the turbo wire projection plus B1 gear switching and the B3/C/D post-execute hooks), lib/config.js (the config schema built from DEFAULT_CONFIG, the live-config reader, and volatile-value unwrapping), lib/gears.js (B1 judgment, zero imports, tool-trajectory only), lib/spill.js (B3 — hands oversized results to the host's spill backend and renders the locator notice), lib/notes.js (C1/C2/C3 note texts and judgments, plus tool aggregation for the detail panel), lib/handoff.js (0.7.0 handoff export: threshold/throttle/freshness judgments, bili command probing, export argv), lib/rotation.js (pure rotation judgment shouldRotate, fed by the same handoffExport* thresholds), lib/rotation-host.js (0.9.0 plan B host action: creates the blank child session and writes the seed message — never throws), lib/client.js (client half: the summary cell at conversation.composer.dock, the detail panel at conversation.input.dock, and the New session card at the bottom of the plugin's settings page), tools/replay-log.mjs (offline replay), test/hooks.test.mjs + test/ui-contract.test.mjs (host-hook and UI-contract guards), test/panel.test.mjs (0.18.0 New session page guard: text card, copy button and its two messages, three-state fallback, icon and registration), test/mirror.test.mjs + test/client-audit.test.mjs (config-mirror / wire-version and client-audit guards), plus the per-pillar test files for the fold, gears, notes, spill, handoff, rotation and the two halves.

Design constraints (non-negotiable)

Reads only committed session-log events (via a projection). No host memory, no polling, no DOM injection, no React-fiber walking.
No network requests, no routes. Writes only its own data: dsh-status-turbo itself does import write APIs (existsSync from node:fs and mkdir / readFile / readdir / rename / writeFile from node:fs/promises, lib/index.js:58-59), and it touches writes in exactly two places, both of them its own data: ① the oversized result body for B3 is delegated to the host's existing spill backend (spillStore.saveText) and the plugin only prints back the absolute path it was handed — it opens no file for that path itself; ② since 0.7.0 the handoff export creates its directory and drops a .gitignore into it (lib/index.js:538, content in lib/handoff.js:246). Both of those calls goes through the plugin's own hostIo seam (lib/index.js:436) — it writes to disk no other way, and it never writes user settings.
Never touches agent-default-model, compaction config, or any user setting.
Never rewrites tool arguments or intercepts tools.
Every failure must surface (in the UI, or at minimum a console.error naming the cause). Silent return is not allowed.

License

MIT — see LICENSE. Third-party notes in THIRD_PARTY_NOTICES.md.