DeepSeek Harness 会话费用统计插件:本会话成本、当日费用、历史记录与官方价格同步,支持多厂商多模型价格计费(内置 170+ 模型 ID 价格目录与自动匹配)、主流 Coding Plan 订阅额度查询与显示(16 家,含 WorkBuddy 官方积分、OpenDesign 工作区查询、含小米 MiMo Token Plan 控制台 Cookie 查询、SCNet Token Plan 本地 Credits 计量与火山方舟 Volcano Ark Coding Plan AK/SK 签名查询)、自定义 Provider 余额查询(可配任意 HTTP 端点)与余额进度条、峰谷计价时
The plugin will be installed here. Keep web if you are unsure.
npx -y @deepseek-ai/dsh plugin --profile web add github:Han-1413141/dsh-cost-meter#bec37954e82de712563ad7265bbe2e75fd96cf93
Description
DeepSeek Harness 会话费用统计插件:本会话成本、当日费用、历史记录与官方价格同步,支持多厂商多模型价格计费(内置 170+ 模型 ID 价格目录与自动匹配)、主流 Coding Plan 订阅额度查询与显示(16 家,含 WorkBuddy 官方积分、OpenDesign 工作区查询、含小米 MiMo Token Plan 控制台 Cookie 查询、SCNet Token Plan 本地 Credits 计量与火山方舟 Volcano Ark Coding Plan AK/SK 签名查询)、自定义 Provider 余额查询(可配任意 HTTP 端点)与余额进度条、峰谷计价时段显示与切换前弹窗/系统通知提醒(位置/提前量/类型可配),界面中英双语。Session cost tracking plugin for DeepSeek Harness: per-conversation cost, daily totals, history and official price sync, with multi-vendor model pricing (built-in 170+ model-ID catalog with auto-matching), Coding Plan quota queries & display for 16 vendors (incl. WorkBuddy official credits, OpenDesign workspace queries, Xiaomi MiMo Token Plan via console cookie, local credits metering for the SCNet Token Plan and Volcano Ark Coding Plan via AK/SK signature), plan/API dual-track billing with per-1% & full-window Token Plan usage estimates, custom provider balance lookup (configurable HTTP endpoint) and balance progress bar, plus peak/off-peak pricing display with pre-switch popup & system-notification alerts (position / lead time / type configurable), in a bilingual (Chinese/English) UI.
Compatibility and provenance
Cost Meter is published as dsh-cost-meter and currently resolves to version 1.9.56. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.
Session cost tracking plugin for the DeepSeek Harness web GUI (bilingual UI)
v1.9.56 keeps fee reads inside the two-second ledger save window, combining frequent updates into fewer background transactions while showing current usage.
Host floor: DSH 0.2.0 · Adaptation target: 0.2.2-alpha.3. Expand the compatibility notes below for exact declarations, host records and troubleshooting.
Release notes: v1.9.56. Fully restart DSH after updating.
Per-conversation cost · daily totals · OpenCode Go subscription quota display · budget with usage percentage · official account balance · custom provider balance · balance progress bar · history · peak/off-peak pricing hours display (peak hours UTC 01:00–04:00, 06:00–10:00; weekends and Chinese public holidays are off-peak all day, with separate labels) · pre-switch popup & system-notification alerts for peak/off-peak changes (position / lead time / alert type configurable) · one-click price sync from the official docs · Codex-style token usage heat grid · multi-vendor model pricing (built-in 170+ model-ID catalog with auto-matching) · mainstream Coding Plan quota queries & display (Anthropic / Z.ai / MiniMax / Kimi / OpenRouter / SiliconFlow / CommandCode / Cline Pass / SCNet / Volcano Ark / Qwen / Xiaomi MiMo / Factory Droid) plan/API dual-track billing (subscription quota vs pay-as-you-go money separated, per-1% & full-window token/equivalent-cost estimates with daily/weekly/monthly curves) · subscription plugin compatibility (Codex / ChatGPT subscription plans) · mobile layout (dsh-pocket) · quota strip above the input box (budget / Go / coding-plan usage in one row, toggleable)
Compatibility, configuration and troubleshooting
Minimum supported host: DSH 0.2.0. The plugin declares the floor in engines.dsh, the host's admission gate for plugins, and no longer supports any DSH 0.1.x release; the adaptation target is 0.2.2-alpha.3. Exact ranges and how the host reads them: compatibility declaration.
Host records inside the declared range, and the earlier 0.1.x history, are in the compatibility record; the per-release list lives in package.json (dsh.compatibility.dshReleases).
If startup reports Ledger is busy and the cost widgets are missing, see ledger lock recovery.
Community and feedback: Join the WeChat group →. The WeChat group is open. You're welcome to join.
Feature overview
Feature
Location
Description
OpenRouter model prices
Model picker / Settings → Cost → Prices
Hover a model for token rates and update time, or search the full catalog in Settings; automatic foreground refresh, price-change markers in the table and official model links. No API key or inference charges. Guide
Cost statistics
Below the conversation input / title bar / Settings → Cost → Cost statistics
Day, week, month, all retained and custom periods; API/Plan split, trends, model/conversation rankings and per-call costs. Guide; statistics requires DSH’s asynchronous module loader
Per-model cost card
Sidebar / composer dock (optional)
Disabled by default; inline Top-N, Other totals, shares and optional tokens, Today / Last 90 days, remembered expansion and a Top-1 chip. See the guide
Per-conversation cost
Composer footer / session title bar
Live accumulated cost + input/cache/output tokens; the composer footer shows cache hit rate before Input (cache reads / all input, including cache writes); Display settings can show only amounts below the composer, with the full line retained on hover; saved composer/header/off positions remain available, and the title bar keeps its compact “Cost details” button
Official balance
Sidebar top / Settings page (configurable)
Total / granted / topped-up balance, auto-refresh + manual refresh; optional three-segment progress bar (blue/orange/gray), whose today segment only counts official-channel spend (coding plans / custom providers excluded)
Custom provider balance
Sidebar / Settings page (configurable)
Configurable HTTP balance lookup (e.g. LiteLLM); bilingual labels, currency, extract rules (dot path / number / add / subtract / divide — use divide for NewApi-style quota endpoints, see example); collapsible panel alongside Coding Plan quotas
OpenCode Go quota
Sidebar / Settings / bottom-right dock (configurable)
Rolling-5h / weekly / monthly usage percent and reset times, each window toggleable independently, budget used % can show alongside; key auto-discovered (dedicated ref / official Go route apiKeyEnv / env / opencode login) or entered manually
Custom provider balance example (NewApi template)
POST with a JSON body: in Settings → Cost → Quota, expand a custom balance entry, select POST, then fill in Request body (JSON). For example, if the endpoint expects an account and returns {"data":{"balance":12.5}}:
Set Extract rules (JSON) to {"remaining":"data.balance"}. Valid JSON is saved per entry and sent exactly as entered, including nested values and large integer IDs. Invalid JSON shows an error and keeps the last valid configuration; clearing the editor removes the body. GET/HEAD send no body while retaining it for a later switch back to POST. Content-Type: application/json is added automatically unless you supply a Content-Type header (any capitalization).
Existing request.body objects and raw strings remain supported. The body is ordinary saved configuration; {{VAR}} credential substitution applies only to request headers. For header authentication, use a reference such as {"Authorization":"Bearer {{MY_API_KEY}}"} and the credential input below it.
Display currency conversion: open Settings → Cost → Quota, expand a custom balance entry, and enable Convert USD balance to display currency. It defaults to off for each entry. Keep Source currency set to the endpoint's actual currency. With a USD balance of 54.3792, a CNY display rate of 7.2 and two decimal places, the balance displays as ¥391.53. Spend and API/manual limits convert together in the sidebar, settings and tooltips; progress percentages and stored balances do not change. Enter a manual limit in the source currency. The setting persists as convertToDisplayCurrency: true inside that customBalances[] entry (legacy customBalance is also supported).
The global exchange rate converts USD to the display currency. CNY/EUR source balances and Credits keep their original units; the switch is disabled for them. Alibaba Cloud balances use the currency returned by its API. No exchange-rate lookup or extra balance request is made when toggling this setting. Turning it off restores the original currency immediately.
DeepSeek CNY billing: USD prices × the display exchange rate and the official CNY table can give different amounts. Settings → Cost → Prices now explains this and provides a CNY selection button. See currency selection, sync and settlement timing.
For Qianwen / Alibaba Cloud fund accounts, use Add Qianwen / Alibaba Cloud balance to query available funds with a RAM AccessKey signature. The card uses the currency returned by the API. See the setup, permissions and balance definition.
Qwen Token Plan can use the official CLI subscription quota. Install the CLI on the DSH host and run qianwen auth login as the same OS user. Local estimates remain the default; CLI mode shows current account credits without changing the local ledger.
Local Qwen Token Plan credits include Plan calls assigned to Qwen. Existing subscription aliases such as qwen and qwen-tokenplan remain supported; custom providers can select Qwen under Model statistics → Billing class, or use an explicit vendor name and plan marker for auto detection. Explicit API calls are excluded. The pay-as-you-go qianwen provider is not assigned merely because its model ID is identical. Models outside the credits table need all three rates configured.
Baidu Qianfan Token Plan Personal now supports quota queries via console Cookie, including credits and Token modes. Store the Cookie in the Baidu quota card or set BAIDU_QIANFAN_COOKIE on the DSH host.
Xiaomi MiMo Token Plan quotas are queried with the MiMo console cookie, not an API key: log in at platform.xiaomimimo.com, press F12 → Network → find the balanceAlertConfig request and paste the full cookie request header into the MiMo card in Settings → Cost → Quotas (it must include serviceToken and userId; the DSH credential store keeps it as MIMO_COOKIE). The card shows the plan/compensation credit windows with the period-end reset (Beijing time) plus a balance row. Copy a fresh console cookie when the card reports an expired login. Token Plan inference keys (tp-* / ttp-*) are not accepted by this console adapter. Local plan statistics use the calendar month; compensation and balance are displayed without estimates because local calls cannot be attributed to those pools.
Each CLIProxyAPI source has a Gemini quota only option for its Antigravity groups. It defaults to off. Intentional filtering to no visible quota shows an empty list; malformed quota data still reports an error.
The extract rules accept four forms: a numeric constant, a dot path string, add/subtract over multiple paths, and divide scaling by a by divisor. divide fits NewApi and other endpoints that meter balance in integer quota (1 USD = 500000 quota — the same conversion cc-switch uses).
unit: "CREDITS": displays non-monetary credits using the configured decimal precision and a Credits suffix. Dollar spend is not converted to credits or shown as today's credit usage. Credit bars use the endpoint's credit cap; the global monetary budget does not apply.
Plain HTTP is allowed for loopback endpoints: http:// is accepted when the host is 127.0.0.1 / localhost / [::1] (the traffic never leaves the machine), which covers local read-only routes that listen on loopback only and serve no TLS (e.g. dsh-workbuddy-connect's /plugins/dsh-workbuddy-connect/status). Every non-loopback host still requires https; plaintext is refused.
WorkBuddy credits example (local plugin route)
The dedicated WorkBuddy credits quota card now supports dsh-xdpool. Select Credit source → dsh-xdpool when using multiple connectors; current, all and selected accounts work across CN/global pools. See the integration notes.
With dsh-workbuddy-connect installed, its web status route already returns the aggregated credit total — no credential needs to be copied:
Adjust the port and response fields to the local service. This example requires the other plugin to expose that route. Cost-meter refuses redirects and continues to enforce configured credential host allowlists.
For NewApi GET /api/usage/token (response { "code": 200, "data": { "total_granted": ..., "total_used": ..., "total_available": ..., "unlimited_quota": false } }):
{{NEWAPI_API_KEY}} resolves from the DSH credential vault or an environment variable (placeholders work in headers only — the URL must be a literal address);
Unlimited-quota tokens (unlimited_quota: true) have no total_available, so remaining cannot be extracted and the query reports “remaining is missing or not numeric” — use a limited-quota token or a middle-layer endpoint that converts the units;
Entry point: Settings → Cost (Quota tab) → “Custom provider balance” → expand config; or write config.customBalance in storages/cost-meter/ledger.json.
Credentials & security
Variable naming: {{VAR_NAME}} follows the <ROUTE>_API_KEY convention — <ROUTE> is the Provider ID from the DSH Models page (Settings → Models), uppercased with non-alphanumeric characters replaced by underscores, e.g. openai→{{OPENAI_API_KEY}}, anthropic→{{ANTHROPIC_API_KEY}}, abc23-d→{{ABC23_D_API_KEY}}. Sharing a name with the Models page means the balance query and model calls share the same key (both resolve from the DSH credential store). This note is also shown above the “Headers (JSON)” input in Settings.
Credential input fields: after expanding an entry, the “Credential input” section renders one write-only field per {{VAR}} placeholder found in the headers — the key goes straight into the DSH credential store (never written to disk, never echoed back, never stored in ledger.json); no need to hand-edit environment variables or credential files.
Automatic plaintext migration: older versions let a literal Bearer sk-… in the headers leak into ledger.json in plaintext. The plugin imports such keys into the DSH credential store at startup and replaces the header value with a {{CUSTOM_BALANCE_KEY_…}} placeholder (derived from the entry's host + header name, stable across restarts) — nothing breaks. From now on ledger.json and the config shipped to the browser never contain plaintext keys: suspected secret headers (Authorization / X-Api-Key / Bearer / sk- prefixes / long opaque strings) are blanked, while placeholders and ordinary headers pass through.
Credential allowlist allowedHosts: when headers carry credentials (placeholders or plaintext), the outbound host must be on this list or the request is refused — protection against leaked keys when importing someone else's config. Without a list, requests proceed with a one-time logged warning. The entry panel provides an “Allowed hosts” input (comma-separated).
Mixed credential templates: a header containing both a static secret and dynamic placeholders cannot be migrated as one nested credential. It is reported as pending and excluded from persisted/client config. Store the static part separately and use credential references throughout. Pure forms such as Bearer {{VAR}} and {{USER}}:{{PASS}} remain supported.
CLIProxyAPI Gateway Quotas and WorkBuddy Credits (Issue #87)
Connects to a local or LAN-deployed CLIProxyAPI proxy gateway to observe quotas across upstream providers and WorkBuddy plugin credits in one place:
Native Multi-Provider Discovery & Quotas: Auto-discovers active credentials via the CPA Management API and queries official native endpoints for Antigravity, Claude, Codex, Kimi, and xAI (Grok). Normalized into standard 5h / 7d / weekly / monthly usage percentage windows with ISO reset timestamps.
WorkBuddy Plugin Credits: Queries WorkBuddy's read-only management route (/v0/management/plugins/workbuddy/credits) to display total, used, and remaining credit balances alongside package lifecycle end-dates, preserving separate account cards.
Zero Metering Side-Effects Guarantee: Completely read-only — strictly avoids mutating actions such as Codex reset-credit consume, xAI token-consuming chat completion probes, and any WorkBuddy POST routes.
Strict Credential Isolation & Transport Security:
Management Keys are stored strictly write-only in the DSH credential store (CLIPROXYAPI_MANAGEMENT_KEY_<SOURCE_ID>_<HASH>), never exposed in config, state, or browser views.
Management calls are strictly restricted to 3 fixed paths (/v0/management/auth-files, /v0/management/api-call, /v0/management/plugins/workbuddy/credits). Arbitrary upstream URLs are forbidden.
Outbound host whitelist (allowedHosts): Non-loopback origins require exact host matches, and plain HTTP requires an explicit allowInsecureHttp opt-in.
HTTP redirects are strictly forbidden (redirect: 'manual'; any 3xx response is rejected) to guard against credential leakage or request hijacking.
Privacy and metadata sanitization: Strips raw tokens, cookies, and identity claims from auth-files discovery; emails are masked in public state (s***@domain).
Bilingual UI
The plugin UI (session badge, sidebar balance row & budget box, and the entire Settings page) supports Simplified Chinese and English:
Language options: Simplified Chinese / English / Follow DSH (auto);
Default is “Follow DSH”: auto uses DSH’s active language and updates live, including the statistics screen and Settings sidebar label. Older hosts without the locale face use the saved DSH preference when available, then the browser language (zh* → Chinese, otherwise English). Auto stays auto in the saved config;
Switch it under Settings → Cost → Display settings → Language — the whole plugin UI updates instantly and auto-saves; the section label in the Settings sidebar switches too (费用 / Cost);
An explicit Chinese/English plugin choice overrides DSH for both UI and server-generated notices. In auto mode, the Host reads DSH’s saved language preference; without an observable preference it retains the Chinese compatibility fallback. Browser/native-only provisional choices and different clients’ languages cannot be inferred by the Host, so notices may differ in those cases.
Screenshots & walkthrough
All screenshots were captured on a live DeepSeek Harness instance. They show the Chinese UI by default; the plugin UI itself is bilingual (Simplified Chinese / English) — switch to English under Settings → Cost → Display settings → Language.
Main page
Sidebar bottom (top to bottom: official balance → quota/budget box → settings button):
The balance row shows the official open-platform total balance; hovering reveals the granted/topped-up split; with “Balance progress bar” enabled, both official and custom balances use the same three-segment box (blue = remaining, orange = today, gray = spent);
With no budget enabled, that spot shows the “Today ¥x” badge.
Quota / budget box — three states (OpenCode Go quota and the budget each toggle independently in the same rounded style; with both on they merge into one card — Go on top, budget below, thin divider, each keeps its own warning colors; the “box details” toggle collapses secondary rows to just label + used % + progress bar):
The budget box shows “budget · used % · progress bar · today's cost & share of budget · used/limit”; ≥80% warning, ≥100% over-budget; rail mode narrows to a percentage tile;
The peak/off-peak hours display shows UTC peak hours 01:00–04:00 and 06:00–10:00 with the current tier; the budget box and today's cost area show a compact one-line period strip — a thin orange/blue track with a marker line on the current period, and text on the right showing the current period plus the countdown to the next switch (refreshed every 30 seconds); no prices are shown; it can be disabled independently in Settings, and the “Peak period strip style” option switches between the Compact and Classic looks; collapsed rail mode shows the same design vertically with a short horizontal label (“Peak / Off-peak”) below — the countdown and full text appear on hover;
Peak/off-peak period strip & collapsed vertical progress bar:
Compact: only the short horizontal label (“Peak / Off-peak”) below the vertical bar;
Classic: the full caption stacked vertically below the bar, including the countdown to the next switch; in both styles the full text is also available on hover.
The display follows the peakNotice / peakEnabled / peakEffectiveAt / peakWindows gates and uses the configured UTC peak windows;
Settings → Cost → Peak/off-peak pricing includes an independent “Prominent notice during peak hours” toggle; turning it off hides both the expanded strip and the collapsed vertical bar;
The first image above is the Settings peak panel (notice toggle, style switch and live preview); see the grouped captures for the strip and collapsed vertical bar; the dock toggles and box-details switches are shown in the second image.
The Go box shows the main window's used % and progress bar (default rolling 5h; switchable to weekly/monthly in Display settings), with the other two windows and reset times in a row below:
Per-conversation cost (one merged row in the composer footer; the session title bar keeps only its compact “Cost details” button):
The row leads with the current currency symbol, then the session amount and hit-rate/input/cache/output details; the whole row opens the details dialog, and “Amount only” condenses it to the amount segment.
OpenCode Go quota panel (very top of the Settings page: three progress bars, main window highlighted, manual refresh; a neutral hint when there is no subscription, one-click disable):
Requirements: Node.js ≥ 20 + DeepSeek Harness (a version with the dsh plugin command; npm install -g @deepseek-ai/dsh) + pnpm on the DSH process's PATH, including npm-name installs and Plugin Hub installs. Node.js ≥ 22.13 is recommended for the pinned pnpm 11 below; Node.js 20 users can use pnpm 10.
One-click install (recommended)
First-time setup on macOS / Linux: install pnpm in the terminal you use to start DSH (the same commands also work on Windows):
npm package name (published to the npm registry, always tracks the latest version; no git needed):
dsh plugin --profile web add dsh-cost-meter
PowerShell one-click script (copy the whole line, paste, press Enter; pnpm is provisioned automatically, git is auto-detected — no clone needed; the install chain is pinned to the release tag v1.9.56 — review the script before running):
Or a plain command line (the machine must already have pnpm and git; also pinned to the tag):
dsh plugin --profile web add github:Han-1413141/dsh-cost-meter#v1.9.56
Without git, use the GitHub tag archive:
dsh plugin --profile web add https://github.com/Han-1413141/dsh-cost-meter/archive/refs/tags/v1.9.56.tar.gz
After installing, restartdsh web (plugin rows, the Typert manifest and the client bundle are all scanned at startup):
dsh web
Install troubleshooting: pnpm was not found (macOS / Linux)
dsh: pnpm was not found; install pnpm and make it available on PATH. means DSH cannot start its package manager; the plugin has not loaded yet. Installing by npm package name still requires pnpm.
After the setup above, check the commands from the same terminal and OS user that start DSH:
command -v node
command -v pnpm
command -v dsh
If npm installed pnpm but the shell cannot find it, add npm's global executable directory for the current shell, then retry:
export PATH="$(npm prefix -g)/bin:$PATH"
pnpm --version
dsh plugin --profile web add dsh-cost-meter@latest
dsh web
Stop the existing DSH process before restarting it. Plugin Hub runs inside DSH and inherits that process's PATH; reopening the browser alone will not refresh it. With nvm/fnm, select the Node.js version used by DSH before installing pnpm. If npm reports EACCES, use a user-owned Node.js installation/global prefix as described in the pnpm guide, then repeat the PATH check. For a persistent shell setup, add the executable directory to your shell profile. A successful install on your machine is confirmed by the plugin appearing after DSH restarts.
Symptom: dsh plugin --profile web add fails with [ERR_PNPM_MINIMUM_RELEASE_AGE_VIOLATION] N lockfile entries failed verification.
Cause: your environment (pnpm config or a policy bundled into the invoking installer) enforces the "minimum release age" supply-chain protection — any lockfile entry published more recently than the threshold is rejected. Plugin releases from before runtime dependencies were exact-pinned declared floating ranges, so a fresh install resolved them to whatever was newest at that moment (a floating @deepseek-ai/dsh-credentials range was observed to land on a build published barely a week earlier), which such a policy refuses.
Fix:
Upgrade the plugin and use the host's plugin installer: zod remains exact-pinned. @deepseek-ai/dsh-credentials and @deepseek-ai/dsh-home-paths are now peer dependencies supplied by DSH, avoiding duplicate old host packages that can fail dependency preflight (issue #106). Pinning prevents version drift but cannot satisfy every age threshold;
If an age restriction remains, wait until the version reaches the threshold, or review the exact package and version in the error before choosing to add an individual exclusion to the profile's pnpm-workspace.yaml (default $DSH_HOME/profiles/web/pnpm-workspace.yaml):
minimumReleaseAgeExclude:
- '<name@version from the error>'
DSH 0.2.0-rc.1 passes packed installation, Web startup, shared-module checks, synthetic billing, RPC and the full regression suite, and the current declaration accepts >=0.2.0-rc.1 <0.3.0-0 while rejecting 0.1.x and 0.3.0. Earlier 0.1.x checks (0.1.2-rc.1, 0.1.3-alpha.2, 0.1.5-alpha.1) are kept in the compatibility record for reference only; 0.1.3-alpha.1 remains unknown because its official npm version was unavailable during the earlier check. See the compatibility record for the environment and limits.
If Plugin Hub reports only diagnostics: .../.plugin-manager/logs/operation-.../pnpm.log, that line does not identify the failed package or command. Open the named pnpm.log and include the first actual error when reporting the failure; remove credentials and private paths before sharing it. Git URL and npm-name installation on DSH 0.2.0-rc.1 are covered by isolated Windows checks, but an individual machine's failure still requires its diagnostic log.
Account-mode balance: in DSH Desktop a signed-in official account is read without any API key; if you still get HTTP 401, save a dedicated Open Platform key under Settings → Cost → Account balance. See credential sources and priority.
Install troubleshooting: uninstall fails with ERR_PNPM_RESOLUTION_POLICY_VIOLATIONS_UNHANDLED (DSH 0.2.1-rc.x)
On DSH 0.2.1-rc.1 / 0.2.1-rc.2 the host bundles pnpm 11.28.5, which enables a built-in 24-hour minimumReleaseAge. Uninstalling or reinstalling a plugin can then fail with ERR_PNPM_RESOLUTION_POLICY_VIOLATIONS_UNHANDLED; the plugin page shows something like Uninstall failed plus ✓ Lockfile passes supply-chain policies (verified 28m ago) and Progress: resolved 1, reused 0, .... A package younger than 24 hours (the plugin version just installed, or a host 0.2.1-rc.x package) is enough to trigger it. The unhandled-callback error comes from the host's bundled pnpm, so the plugin cannot patch it.
Workarounds:
Wait until the package is 24 hours old, then retry. The plugin keeps working in the meantime.
Add an exact exclusion to the profile's pnpm-workspace.yaml (keep existing entries), then fully restart DSH and retry:
minimumReleaseAgeExclude:
- dsh-cost-meter@1.9.56
For a one-off CLI operation, forward the pnpm flag: dsh plugin --profile desktop remove dsh-cost-meter --config.minimum-release-age=0 (or add --trust-lockfile when only lockfile verification fails). Both flags were verified against pnpm 11.28.5 in a temporary profile.
Read the first ERR_PNPM_* line in <profile>/.plugin-manager/logs/operation-*/pnpm.log before reporting and remove credentials. Do not delete the profile or the ledger. Details: pnpm supply-chain policy.
Update / Uninstall
# update: re-run the new release's install.ps1 (the pinned tag inside it moves with the release)
dsh plugin --profile web remove dsh-cost-meter # uninstall
Installation errors and plugins still disabled after reinstall: see troubleshooting.
Local development
git clone https://github.com/Han-1413141/dsh-cost-meter.git
cd <parent directory of the clone>
dsh plugin --profile web add link:./dsh-cost-meter # symlink; edit lib/client.js, refresh the page, done
Price units match the official docs: USD / 1M tokens;
cost = cache-missed input × cache-miss + output × output + (cache read + cache write) × cache-hit (cache writes follow the legacy official rule and are billed at the hit price);
Pure two-tier peak/off-peak pricing (the official scheme since 2026-08): peak hours (01:00–04:00, 06:00–10:00 UTC) bill at the peak price and all other hours at the off-peak price (off-peak = half of peak). The base tier equals the off-peak tier, and billing falls back to off-peak when peak/off-peak is disabled; the Settings page shows the live tier (peak / off-peak); the budget/today's cost area shows a peak/off-peak period strip (current/next period with countdown), and the collapsed rail shows a vertical peak/off-peak progress bar;
Weekends and Chinese public holidays: weekends are off-peak all day from 2026-08-23 00:00 Beijing time, including work-shift weekends. Chinese public holidays are also off-peak all day. peakHolidays contains Beijing dates in YYYY-MM-DD format and defaults to the published 2026 Mid-Autumn and National Day dates after the peak-pricing change; edit the list in Settings → Cost → Peak pricing for future holidays. The period strip labels holidays separately and counts down to the next actual price change. Historical DeepSeek costs are recalculated once from complete session logs; rows without complete logs keep their recorded amounts;
Historical billing correctness: calls before 2026-08-16 16:00 UTC (the peak-era boundary) are billed at the base prices of that time, and later calls at the two-tier scheme;
The ledger always stores amounts in USD; currency and FX rate only affect display (default 1 USD = 7.2 CNY, configurable);
The session badge is billed exactly at the moment each call is made (host-exported per-call cost), just like daily/monthly/cumulative totals and the budget;
Billing uses usage blocks reported through the host's llm/stream, including sub-agents, compression, title generation and other auxiliary calls in isolated LLM services. Child sessions retain their own sessionId and do not contribute to the parent badge; background calls without a sessionId contribute only to daily/monthly/lifetime totals. Memory or other plugins that call external APIs directly without reporting usage to the host cannot be tracked;
Peak/off-peak tiers follow the request-initiation moment: a streaming call can span the tier boundary hour; attributing by completion time would put a request started minutes earlier into the wrong tier;
Peak effective-time anchoring: the official pricing page no longer lists an effective time, and price sync no longer resets the peak effective moment to "now" — historical recomputes (session projection refolds / per-model backfill) always tier events against the 2026-08-16 16:00 UTC boundary, so peak-hour history is no longer re-costed at half price; ledgers polluted earlier are clamped back automatically on upgrade (idempotent migration);
Data storage
Ledger: $DSH_HOME/storages/cost-meter/ledger.json (atomic write + 2-second debounce; retained per historyDays, up to 200 per-session entries per day);
API keys never touch disk: all credentials (OpenCode Go key, coding-plan keys, Volcano AK/SK) live only in the DSH credential store — neither the ledger file nor anything sent back to the settings page contains plaintext; the settings inputs are write-only and never echo a saved key back;
Every settings change is saved instantly and automatically (600 ms debounce) — no manual save needed;
Delete the ledger file to reset everything, or use “Clear all history” in Settings;
Privacy boundary: balance/quota endpoints (official balance and each coding plan) only get contacted after you explicitly enable the corresponding provider — no network traffic for disabled ones.
dsh-cost-meter
├── cordis.patch.yml # bundle patch: inserts the cost-meter row into the web profile
├── install.ps1 # one-click install/update script (irm … | iex)
├── .github/workflows/ # CI: install-smoke for the one-click install path
├── package.json # dsh.bundle patch declaration + dsh.client browser declaration
└── lib/
├── index.js # host plugin: llm/stream billing wrapper, costUsage session
│ # projection, costMeter service (hand-written typertRemote
│ # binding), balance lookup
├── pricing.js # official price table, official page HTML parsing, peak/off-peak math
├── store.js # ledger persistence & config management ($DSH_HOME/storages/cost-meter)
├── typert.host.js # ./typert export: Typert manifest (auto-registered by typert-loader)
└── client.js # ./client export: browser single-file bundle (badges/box/settings)
Data channels:
Per-conversation cost: the host registers the costUsage session projection (pure token buckets, split per model); the browser reads it via useProjection('costUsage') and prices it with the current price table;
Global ledger / budget / balance / config: costMeter/getState | updateConfig | fetchPrices | refreshBalance | resetHistory over the Typert gateway RPC (remote.costMeter.*);
Balance: calls the official GET {baseURL}/user/balance, reusing the same API key as model requests (credential service / env var), with an in-process cache expiring per refreshMinutes.
The plugin never imports cordis/dsh Service/Context runtime classes (only Node builtins, zod, and pure functions from dsh-home-paths and dsh-credentials), so it shares one runtime instance with the host with no duplicated dependency risk.
How official price sync works
fetchPrices fetches the official pricing page (Docusaurus server-side pre-rendered; the English page lists USD prices and the Chinese page CNY prices, selected by the "official price currency" setting — currency is auto-detected from the money symbols, and peak windows on the Chinese page are converted from Beijing time to UTC by −8h) and parses:
the base price table (transposed layout: first row MODEL + model ids, price labels followed by the prices);
the peak/off-peak price table (two rows per model: OFF-PEAK / PEAK);
the effective time (“take effect at …”) and the peak-hour windows (“Peak hours are …”).
The parsed result is written into the price table and persisted; if the page structure changes, sync reports an error and keeps the previous prices, with manual editing as a fallback.
AI price sync
docs/AI-PRICE-SYNC-PROMPT.en.md (English) and docs/AI-PRICE-SYNC-PROMPT.md (中文) provide prompts you can copy straight into any AI:
the AI reads the official pricing on its own → outputs per-model, time-of-day (base/off-peak/peak + effective time) price JSON → you review and apply it (Settings page / RPC / file — pick one). Handy when the official prices change.
Development & verification
corepack pnpm install # dependencies
node --check lib/index.js && node --check lib/pricing.js \
&& node --check lib/store.js && node --check lib/typert.host.js \
&& node --check lib/client.js # syntax checks
node test/verify.mjs # pure-module verification (parsing/billing/ledger/config)
node test/mock-balance.mjs # (optional) local balance API mock: 3101
dsh --profile web --dump-config # composition-tree check
dsh --profile web --port 3099 # real startup (watch logs and the UI)
Known limitations
For loading placeholders followed by “No matching sessions” after opening Cost,
see non-destructive sidebar search recovery.
Check and clear the host search before changing stored data.
Official-page parsing depends on the current page structure; after a redesign, “Sync prices from official docs” fails — edit the price table manually as a fallback;
The session badge's fallback estimate (used when ledger data is unavailable) prices all of a session's calls at the tier of the current moment, including plan-type sessions: a session spanning peak and off-peak hours gets its off-peak portion overestimated during peak hours; exact figures come from the ledger (which bills each call at its own initiation moment);
Price sync overwrites the same-named models listed on the official page; custom model entries are unaffected;
Balance lookup needs network access to api.deepseek.com and a valid API key; the API key is only ever sent to the official domain (if baseURL points at a non-official host, balance queries refuse to run — model requests are unaffected);
The OpenCode Go quota endpoint is the official opencode.ai endpoint (community-documented); if its response shape changes, the Settings page shows an error and the display can be turned off in Display settings;
The per-1% quota / full-window figures in Token Plan stats are estimates: vendors only report percentages with ones-digit quantization (a displayed 1% may really be 0.5%–1.5%), so the plugin derives them from end-to-end deltas over continuous sample segments to suppress quantization noise (segments spanning <5 percentage points are tagged "low reading precision"; samples older than 7 days fall back to live ratio; window edges align to whole hours). Server percentages cover ALL usage of the account — consumption of the same key on other machines/CLIs is not in the local ledger, so low estimates are expected; treat them as cross-plan comparisons only;
Plan/API classification is inferred from channel and config; mixed subscription/PAYG usage of one vendor (e.g. Kimi) can be overridden per provider:model in settings.
A restart of dsh web is required after installing/updating the plugin.
Community
Join the WeChat group to discuss the plugin, share feedback, and suggest features.
Version policy: releases increment only the patch number (for example 1.9.0 → 1.9.1), including feature releases, new plugin compatibility and UI updates. The minor/major positions stay fixed unless a breaking change requires them and is explicitly approved; 1.9.0 was the last minor bump.
A per-version overview and the community-issue resolution log live in docs/UPDATE-HISTORY.md (中文); the itemized changelog is CHANGELOG.md.
Multi-vendor coding-plan quota queries (Anthropic Claude Pro/Max, Z.ai / Zhipu GLM Coding Plan, MiniMax Token Plan, Kimi Code weekly + 5-hour quotas with PAYG balance fallback when no subscription key, OpenRouter credits, SiliconFlow balance, CommandCode 5h/weekly windows + monthly credits balance, Cline Pass 5-hour/weekly/monthly windows, Xiaomi MiMo Token Plan plan/compensation credit windows + period-end reset + balance via console cookie); per-vendor enable switch, key, display position and refresh interval (sidebar card in the same box style as the Go quota; the collapsed rail shows percentages), official endpoints by default, with a configurable trusted MiniMax origin; neutral hints when no credentials/subscription; SCNet Token Plan supports external console snapshots; without a valid snapshot, monthly usage is estimated from the local ledger via the official credits deduction table (no credentials needed)
Subscription plugin compatibility
Settings → Cost → Codex / sidebar & quota cards
Detects installed Codex / ChatGPT subscription plugins and classifies their subscription calls as Plan quota instead of pay-as-you-go API spend; new usage is classified at record time, and a one-time dismissible prompt decides whether historical Codex billing is reclassified (idempotent). Explicit plan/API choices are never overridden. Details
Reads actual quota windows from dsh-codex-subscription, the native DSH pi-ai login, dsh-chatgpt-sub, @eddyskywalker/dsh-chatgpt-subscription, or dsh-codex-connect. Select auto (tries these sources in order), subscription, pi-ai, chatgpt-sub, chatgpt, or connect. Enable quota display and select dsh-chatgpt-sub for its bound account's remaining bars and reset times. Weekly-only accounts show no 5h bar. An explicit source uses only that source's current account; billing classification remains separate.
SQLite session storage (better-session)
Host integration
Auto-detects the host session backend; with @morlay/better-session / @morlay/session-rdb (SQLite) storage, historical backfill, legacy import, history repricing, hour-bucket repair, fork cleanup and per-session cost/trajectory/call details keep working. The JSONL path is unchanged; old JSONL and RDB histories are not merged automatically. Guide
OpenDesign quota
Sidebar / Settings (OpenDesign vendor)
Workspace coding-plan windows from the console API; with a Control Key, a 401/403 from the primary endpoint triggers one conservative /billing/preflight Bearer fallback, and window/wallet reads degrade independently. Troubleshooting
Mobile / dsh-pocket layout
All cost UIs
On screens ≤1023px and dsh-pocket mobile layouts: single-column cards, horizontally scrolling tabs, 36px touch targets, dialogs capped at 90vh with safe-area padding and scrolling wide tables; desktop layout unchanged
Quota strip
Above the input box (toggle in Display settings)
One compact chip row for budget used % / the Go main window / each enabled coding-plan usage window (short label + mini progress bar, ≥80% warn, ≥100% over, hover for reset times); click any chip to refresh its data source (budget → state, Go → Go quota, vendor → all its windows); multiple windows of one vendor merge into a single segmented chip; a first-run guide card lets you decide whether to enable it; hides itself when there is no quota data
Click to refresh
Sidebar balance/quota boxes
Click the official balance / custom balance / coding-plan box (collapsed rail included) to fetch the latest data immediately; the box pulses while refreshing, failures keep the previous value and surface the reason in the hover tooltip; keyboard Enter/Space also triggers; a one-time guide card appears after the update
Simple sidebar display
Settings → Cost → Display
Optional, with a one-time choice after updating. Condenses cards and caps panel height at 38% of the viewport and 320 px, while preserving amounts, quotas, refresh actions and hover details. Turn off to restore your layout. Guide
Today's cost
Sidebar bottom (above the settings button)
“Today ¥x”, hover for call count and token details
Budget box
Sidebar bottom (between the balance row and the settings button)
Rounded-square frame: budget, used %, progress bar, today's cost & share of budget, used/limit; ≥80% warning, ≥100% over-budget
Summary cards
Settings page
Today / this month / cumulative cost and call counts
External usage
Settings → Cost
Read-only snapshots from other processes on the same account; per-source tokens/calls/cost and recent days, plus DSH + external daily/monthly/all-time totals. Fresh external cost for today joins official balance reconciliation.
Token usage stats
Settings page (Cost section)
All-time token totals (input/cache/output/calls) + a Codex-style 26-week daily usage heat grid that fills the settings width; hover a cell for that day's detail
Token Plan usage stats
Settings page (Usage)
Per enabled coding plan (incl. Go): per-1% quota and full-window token / equivalent-cost estimates for the current windows (sample delta / live ratio), plus daily/weekly/monthly usage curves; plan-channel amounts are equivalent-only and never touch real money (issue #64)
Today's sessions
Settings page
Per-session call count, input/cache/output tokens and cost
History
Settings page
Per-day totals; retention days configurable (default 180)
Pre-install history import
Automatic on first launch
After install/upgrade, the first launch automatically replays all host session logs to import conversations from before the plugin was installed (missing dates are rebuilt whole; existing dates only gain previously unknown sessions; idempotent and never double-counts live metering; costs priced at per-event historical rates); a manual re-run entry remains in Settings
Budget settings
Settings page, top
Limit, period (today / month / cumulative / custom date range), used %
Shows UTC peak hours 01:00–04:00 and 06:00–10:00 with the current tier; weekends and configured Chinese public holidays (Beijing dates) are off-peak all day, with separate labels; expanded view shows a period strip and countdown, collapsed view shows a vertical bar; independently toggleable
Peak/off-peak switch popup alert
Global overlay
A full-width bracketed popup appears when the next tier switch is within the configured lead time (default 2 minutes, 1–30), with an alert-colored badge distinguishing entering peak vs off-peak; position selectable (bottom-right / screen center), alert type selectable (entering peak / entering off-peak / both), one alert per switch point; optionally sends a browser (system) notification (so you still get alerted when the page is backgrounded; requires granting notification permission); configured in the peak pricing panel in Settings, with a one-click popup preview (rendered by the real component — copy, position and notifications exactly as they will fire)
Official price sync
Settings page
Fetches and parses the official pricing page, applies with one click; the official price currency is selectable (USD · English page / CNY · Chinese page) — CNY prices are booked at the display exchange rate and match the official CNY bill when displayed in CNY
UI language
Settings → Display settings
Simplified Chinese / English / Follow DSH (auto); switches instantly and auto-saves
Hide official balance / hide today's cost
Settings → Display settings
Two independent toggles: when on, the matching UI blocks (sidebar balance row & panels / today's cost row, budget details, overview today card) are not rendered at all; token and call-count stats stay visible — safe for screen sharing and screenshots
Meaning of the four columns in the per-1% & full-window panel, the end-to-end delta estimation method and precision tags, the scope boundary (dsh-made calls only) and usage curves (中文)
OpenAI, Anthropic, Google Gemini, Mistral and other providers with input/output, cache and reasoning-token pricing isolated by provider + model
Model-name auto-matching
Settings / ledger
Unknown model ids are matched against the price table: case/spaces/hyphens/dots and bracket annotations (e.g. (go)) are ignored — a normalized-equal or containing name hits (e.g. gpt5.6 luna(go)); router providers (opencode/zen etc.) search across all vendors; can be restricted to exact match, and unmatched models can be pinned to a specific entry in Settings
Extended price catalog
Settings → Extended price catalog
Built-in reference catalog grouped by vendor and model family (expandable; vendors collapsed by default); mount entries into billing with one click — mounted third-party models live inside the catalog and stay editable; a per-model “Show directly in Cost settings” toggle chooses which models (DeepSeek included) appear directly in the price table
Historical pricing: changing pricing currency, rates or mappings affects subsequent calls. Saved price versions preserve older details; explicit recalculation requires confirmation and retains original amounts, price versions and a full ledger backup. See the update notes.
Aligning with official bills: ① minute-level lag vs live official numbers is expected — the ledger flushes on a 2s debounce, and streams still in flight at shutdown are billed server-side while their usage block is never received (the gap concentrates in cache-hit columns); ② reasoning tokens are reported separately by the API and are not billed — the token columns sum five buckets and will never line up with the official three columns, so reconcile by amount; ③ with pricing currency set to CNY, entries are recorded directly on the official CNY price list (recommended for CNY-billed accounts); with USD, displayed amounts go through a fixed FX rate and carry a small structural difference (the two lists' per-column ratios are not uniform); ④ granted-balance expiry or reclaim is not consumption: when the day's balance drop is confined to the granted bucket (top-up balance unchanged) and local official-channel usage explains at most a quarter of it, the reconciliation baseline is reset with an informational expiry/reclaim notice instead of a consumption-drift warning;
Budget and over-budget warnings only warn — they never block calls.
Plan/API dual-track billing (issue #64): calls on subscription-style channels (MiniMax, Codex / ChatGPT subscription plugins, etc.) are recorded as catalog-price equivalents only; budget/today-cost/overview cards count the pay-as-you-go (API) channel exclusively.
Full-repo security audit fixes: resolved 3 high-risk findings — ledger writes lost on exit (close/flush ordering), command injection in the release script, panel null-pointer crash on null Go monthly window — plus 30+ medium/low issues including missing hour-bucket entries for routed calls, dead balance-reconciliation warnings, failed custom-balance extraction silently showing $0, and leaked upstream streams on consumer abort; ledger corruption auto-backup, write-failure retry, config-patch atomicity and prototype-chain hardening included. Itemized list: CHANGELOG.md.
"Include plan totals" toggle under the overview cards switches every amount between real-money (API channels only, default) and total equivalent cost (plan subscriptions included); routed calls with a missing provider whose models match third-party catalogs are auto-classified into the matching plan, and legacy per-day residuals without model details count toward the API scope; The Token Plan stats panel in Settings → Usage provides per-1% and full-window token/equivalent-cost estimates plus daily/weekly/monthly usage curves; classification is configurable per vendor and per provider:model.
