dsh-ai-quota
DeepSeek Harness 插件：查询 AI 订阅配额和余额（Codex、Kimi、GLM Coding Plan、DeepSeek、302.AI、OpenCode Go），作为模型工具和设置页面
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Carrick-K7/dsh-ai-quota#03dee0e4ac02c8a84b087fc179a4b5552cabfab0
Ai Quota 以 dsh-ai-quota 发布，当前版本为 0.11.2。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
A DeepSeek Harness plugin that shows your AI subscription quotas & balances — Codex, Kimi, GLM Coding Plan, DeepSeek, 302.AI, OpenCode Go — in one place.
English · 中文
Settings page: per-window usage bars (Codex / Kimi / GLM Coding Plan / OpenCode Go) and plain balances (DeepSeek, 302.AI), with manual refresh and a freshness line in relative time; the gear button opens the embedded visibility settings, one switch per provider.
query_ai_quota — ask any agent session to check your quota; returns a human-readable summary.localStorage), so flipping one is instant — no host round-trip, no plugin reload. The query_ai_quota tool always returns every provider.refreshIntervalMs (default 2 min; 0 disables) and serves a warm cache, so every surface reads instantly. An open conversation additionally re-reads its provider's quota every 60 s (silently, without a loading flicker), so a session left running for a while never keeps the balance it loaded with; a hidden tab is skipped and caught up when it becomes visible again.subscription windows or balance entries; one provider failing never affects the others.dsh plugin --profile web add github:Carrick-K7/dsh-ai-quota
The bundled cordis.patch.yml declaration makes dsh plugin append the plugin row to dsh.profile.bundles automatically. Restart dsh web afterwards (pnpm must be on PATH).
All keys optional, defaults shown.
| Key | Default | Meaning |
|---|---|---|
timeoutMs | 15000 | Per-provider query timeout (ms) |
refreshIntervalMs | 120000 | Auto-refresh interval (ms); 0 = off |
codexCli | codex | codex CLI command or absolute path |
deepseekApiKeyEnv | DEEPSEEK_API_KEY | DSH credential ref (fallback: same-named env var) |
opencodeGoApiKeyEnv | OPENCODE_GO_API_KEY | DSH credential ref (fallback: same-named env var) |
ai302ApiKeyEnv | AI_302_API_KEY | DSH credential ref (fallback: same-named env var) |
glmApiKeyEnv | ZAI_CODING_CN_API_KEY | DSH credential ref for the GLM Coding Plan key (falls back to ZAI_CODING_API_KEY, then GLM_CODING_API_KEY) |
deepseekBaseUrl | https://api.deepseek.com | DeepSeek API base URL |
opencodeBaseUrl | https://opencode.ai/zen/go/v1/usage | OpenCode Go usage endpoint |
ai302BaseUrl | https://api.302.ai | 302.AI API base URL |
glmBaseUrl | https://open.bigmodel.cn | GLM Coding Plan API host; only the origin is used, so a coding base like …/api/coding/paas/v4 works. International accounts: https://api.z.ai |
kimiBaseUrl | https://api.kimi.com/coding/v1 | Kimi usage endpoint base (appends /usages) |
kimiOauthHost | https://auth.kimi.com | Kimi OAuth refresh endpoint (appends /api/oauth/token) |
kimiClientId | Kimi Code CLI's public client id | OAuth client_id (usually unchanged) |
The chip reads the provider route of the current model selection (e.g. opencode-go-carrick, kimi-coding, deepseek-official, openai-codex) and never the model id — kimi-k3 on an OpenCode Go route is an OpenCode Go quota, not a Kimi one. A route is recognized when its id (or, for an opaque alias, its provider display name) contains one of 302, opencode, codex, kimi/moonshot, deepseek, zai/zhipu/bigmodel/glm. Any other route shows no chip rather than another account's balance.
The chip then re-reads that provider every 60 s while it is mounted, reading the host's warm cache (so no extra upstream calls). If the host snapshot itself is older than 10 min — i.e. the host auto-refresh is off or stalled — the poll escalates to a real query, throttled to once per 10 min per provider.
apiKeyEnv is a credential ref (defaults DEEPSEEK_API_KEY / AI_302_API_KEY / OPENCODE_GO_API_KEY), so a key stored in DSH (e.g. $DSH_HOME/.credentials.yaml) wins; a same-named process env var is the fallback for standalone deployments. OpenCode Go also falls back to the opencode-go entry in ~/.local/share/opencode/auth.json.ZAI_CODING_CN_API_KEY, with ZAI_CODING_API_KEY and GLM_CODING_API_KEY tried next, so either region's key name works. Point glmBaseUrl at https://api.z.ai for an international coding plan.kimi login again if it is gone).| Provider | Source |
|---|---|
| Codex | Local codex app-server --stdio JSON-RPC (account/rateLimits/read) — 5h / 7d windows |
| Kimi | GET {kimiBaseUrl}/usages (Kimi Code CLI's OAuth login state) |
| GLM Coding Plan | GET {glmBaseUrl}/api/monitor/usage/quota/limit (bearer key) — 5h credit cycle / weekly quota / monthly MCP budget |
| DeepSeek | GET {deepseekBaseUrl}/user/balance (bearer key) |
| 302.AI | GET {ai302BaseUrl}/dashboard/balance (bearer key) |
| OpenCode Go | GET {opencodeBaseUrl} (bearer key) |
