dsh-plugin-subscription-oauth 0.10.2 → 0.12.0

package/README.md

@@ -2,180 +2,35 @@
 
 # dsh-plugin-subscription-oauth
 
-[![Listed on dsh-plugin.org](https://dsh-plugin.org/badges/listed.svg)](https://dsh-plugin.org/plugins/EricFL1998/dsh-subscription-oauth)
-[![npm](https://img.shields.io/npm/v/dsh-plugin-subscription-oauth.svg)](https://www.npmjs.com/package/dsh-plugin-subscription-oauth)
-[![Licence: MIT](https://img.shields.io/badge/licence-MIT-blue.svg)](LICENSE)
-
-**Use the AI subscriptions you already pay for as LLM providers in DeepSeek
-Harness — no API key.** Sign in once per provider from **Settings →
-Subscriptions** (订阅) and that account's models join the session model picker,
-with its plan quota shown next to the connection.
-
-```sh
-dsh plugin --profile web add dsh-plugin-subscription-oauth
-```
-
-The same package installs straight from the repository, which needs no registry:
-
-```sh
-dsh plugin --profile web add github:EricFL1998/dsh-subscription-oauth
-```
-
-| | |
-| --- | --- |
-| **Capability** | 模型与推理 / Model & inference — it registers LLM provider routes |
-| **Licence** | [MIT](LICENSE) |
-| **Built for** | DeepSeek Harness `0.2.0-rc.2` (`@deepseek-ai/dsh-llm`), Node ≥ 20 |
-| **Platforms** | Windows, macOS and Linux; nothing platform-specific beyond Node itself |
-| **Accounts** | your own subscriptions only — credentials stay on your machine |
-| **Network** | the providers' own hosts and the OAuth endpoints listed below; no telemetry, no third-party relay |
-
-| Route | Provider | Login | Wire |
-| --- | --- | --- | --- |
-| `kimi` | Kimi Code | OAuth **device flow** (RFC 8628) | OpenAI **Responses** — `https://api.kimi.com/coding/v1/responses` |
-| `grok` | Grok (X Premium) | OIDC **authorization code + PKCE** on a loopback callback | OpenAI **Responses** — `https://api.x.ai/v1/responses` |
-| `antigravity` | Google Antigravity | Google **authorization code + PKCE** (`/oauth-callback`) plus Cloud AI Companion project discovery | Cloud Code Assist `v1internal` — `streamGenerateContent?alt=sse` |
-| `glm` | GLM (BigModel) | ZCode's **browser sign-in with a polled flow** (China region) | OpenAI **Responses** — `https://open.bigmodel.cn/api/coding/paas/v4/responses` |
-| `ark` | Volcengine Ark | Volcengine **SSO** (authorization code + PKCE on a loopback callback) | OpenAI **Responses** — `https://ark.cn-beijing.volces.com/api/coding/v3/responses` |
-| `auto` | Auto | none — it holds no account of its own | delegates to whichever route owns the model it picks |
-
-The Kimi device flow is the one `opencodex` uses; the Grok flow is the one its
-CLI uses (`auth.x.ai` discovery, client `b1a00492-…`, port `56121`, scope
-`grok-cli:access`); the Antigravity flow is Google's desktop OAuth client
-(`accounts.google.com`, port `51121`, scopes including `cclog` and
-`experimentsandconfigs`), with the account's project discovered through
-`loadCodeAssist`.
-
-**GLM signs in the way ZCode does**, not with an API key: the plugin asks
-`zcode.z.ai` for a login flow, opens `bigmodel.cn/login` in the browser, and polls
-the flow until the subscription's tokens come back. Nothing has to receive a
-`zcode://oauth/callback` redirect and no app secret is involved, because the
-callback is completed server-side and the flow is authenticated by a secret the
-plugin generates itself. Allowances are read from BigModel's own
-`/api/monitor/usage/quota/limit`, which meters a rolling five-hour window and a
-weekly one.
-
-**Ark signs in with Volcengine SSO** (authorization code + PKCE on a loopback
-callback, the flow its own CLI uses) and then has to satisfy two planes that want
-different credentials. The **data plane** takes only an ordinary API key as a plain
-bearer — it refuses STS credentials outright — while the **control plane**, a
-different host, is signed with the temporary STS credentials that the SSO token
-response carries. So a sign-in mints one API key through the control plane (reusing
-a key this plugin already created, if there is one) and keeps the STS set for the
-quota, which is read per subscription period and per model's free allowance.
-
-## What it registers
-
-| Surface | What appears |
-| --- | --- |
-| `ctx.llm` | the `kimi`, `grok`, `antigravity`, `glm` and `auto` provider routes (models, reasoning efforts, streaming) |
-| Settings | a **Subscriptions** section: one card per provider — sign in, sign out, default account, token refresh, plan quota, model catalog, manage dialog |
-| Model picker | each provider's own models, plus **`auto` as its own route** spanning them — Kimi ships `kimi-for-coding`, `k3`, `k3[1m]`, `k3-256k`; Grok seeds `grok-4.6`, `grok-4.5` and adds whatever its live catalog reports; Antigravity lists the agent-callable subset of what its endpoint reports (`fetchAvailableModels`), filtering out tabs, commit-message and transcription surfaces; GLM ships the `glm-5.3` family (`glm-5.3`, `glm-5.3-flash`, `glm-5.2`, `glm-5.1`, `glm-5`) and adds whatever its coding host lists |
-
-Credentials live at `~/.dsh/plugins/kimi-oauth/auth.json` (mode `0600`,
-written atomically, one section per provider). The directory keeps the name this
-plugin had when it served Kimi Code alone: it holds **live logins**, so it is left
-in place rather than renamed, and every profile that mounted the earlier version
-finds its accounts exactly where it left them. This machine's Kimi device id
-lives beside it in `kimi-device-id`; it is stable across restarts, because the
-service correlates usage to it.
+**Use the AI subscriptions you already pay for as LLM providers in DeepSeek Harness — no API key.**
 
-### Token lifetimes, and why the card may say "expired"
+Sign in once per provider from **Settings → Subscriptions** and that provider's models join the session model picker, with its plan quota shown live next to the connection. Tokens stay on your machine; every request streams through the provider's own API.
 
-Kimi Code access tokens live **15 minutes**; the refresh token lives **30 days**.
-Grok access tokens are similar. Every request refreshes automatically when the
-access token is within five minutes of lapsing, and the Settings card refreshes
-eagerly while you are looking at it — so what it shows is the live expiry, and
-"token expired" appears only when a refresh genuinely failed and the account
-needs a new sign-in. Access-token expiry is normal and does not mean the login
-is gone.
+[![npm](https://img.shields.io/npm/v/dsh-plugin-subscription-oauth.svg)](https://www.npmjs.com/package/dsh-plugin-subscription-oauth)
+[![Licence: MIT](https://img.shields.io/badge/licence-MIT-blue.svg)](LICENSE)
 
-## Settings page
+## Supported providers
 
-| Every route folded | A subscription card open | A card with its catalog |
+| Provider | What you get | Sign-in |
 | --- | --- | --- |
-| ![Folded provider list](docs/images/providers-folded.png) | ![GLM card with plan quota](docs/images/glm-card-open.png) | ![Kimi card with its catalog](docs/images/kimi-card-open.png) |
-
-The page leads with **`auto`**, the way to reach every other route at once; the
-routes it stands in for follow in the order they were configured. Each route is one
-**folded row** — status dot, name, route key, a one-line summary of the connection,
-and an **Edit** button — so the section reads as a list of providers and opens one
-on demand. **Every visit starts folded** — an open card is a gesture within one
-visit, not a stored setting — so re-opening Settings always shows the same compact
-list. Inside an open card are the
-account rows (★ sets the default account, `退出登录`/`Sign out` removes one), the
-model catalog, and the plan quota. Controls follow the host's own settings-form
-vocabulary — a 6 px radius (`--dsw-radius-sm`), a transparent fill, a hairline
-border, and the theme's hover/active/focus tokens — declared in one scoped
-stylesheet, so the page keeps that look instead of falling back to the browser's
-default button chrome.
-
-The **Models** heading is its own disclosure, **folded on every visit** too: click it to open the
-catalog. **Each model has its own switch** (a toggle,
-not a checkbox), which decides whether the session model picker offers it. The
-choice is stored on the host (`~/.dsh/plugins/kimi-oauth/preferences.json`) as a
-hidden list, so it survives restarts and every session sees it; a model added by a
-later catalog refresh appears automatically rather than arriving hidden. A hidden
-model is listed dimmed and stays **resolvable** — an existing session that already
-selected it keeps working — so hiding is a picker-visibility choice, not a
-revocation. `· 已隐藏 N 个` in the header counts the hidden ones.
-
-**Add model** publishes an id this build has never heard of, so a model released
-after the plugin was built is usable at once. The id is checked for shape, not
-against a list — the endpoint is the only authority on what it serves — and it is
-stored per route, published with conservative metadata, and listed with a `×` so a
-typo can be removed again. **Drag a row** by its ⠿ grip (or press ↑ / ↓ while the
-grip is focused) to re-order the list; that order is what the picker follows for
-that route.
-
-**`auto` is a provider of its own** (route `auto`), not a model inside each one: it
-stands in for the enabled models of *every* provider the harness serves in one list,
-each row badged with the provider that owns it. That includes the routes this plugin
-registers **and** the ones it does not — the built-in DeepSeek providers and any
-provider you added yourself — because it enumerates the harness roster
-(`ctx.llm.listProviders()` / `listModels()`) and dispatches through it rather than
-looking only at its own routes. It leads both the Settings section and the model
-picker, because it is the one entry that reaches every route. It has no account, so
-its card offers no connect or manage — only the list. A switch takes a model out of
-Auto **without** hiding it from the picker, drag re-orders what Auto tries first, and
-the arrangement is stored separately (`auto.order` / `auto.off`). Switch every model
-off and Auto is simply not offered in the picker.
-
-A provider with no signed-in account contributes no rows: `listModels` answers with
-nothing until a route has a session, so signing out removes that route's models from
-the picker and from Auto at the same time, and its card hides the catalog instead of
-offering models that cannot be called.
-
-Auto falls through to the next model when the provider refuses the preferred one
-(renamed or gone, rate-limited, out of allowance, or a transport failure). A
-concrete model id never falls back — it dispatches to exactly that model. Once a
-stream has produced any output the turn belongs to that model, so a later failure
-is reported instead of being papered over by a second model's text. Every fallback
-is logged (`model X unavailable … falling back to Y`).
+| **Kimi Code** | `kimi-for-coding`, `k3`, `k3[1m]`, `k3-256k` + live catalog | OAuth device flow (show code, confirm in browser) |
+| **Grok (X Premium)** | `grok-4.7`, `grok-4.6`, … + live catalog, **⚡ lightspeed** fast variant | Browser OAuth (auto-redirect) |
+| **Google Antigravity** | Claude Sonnet/Opus, Gemini Flash, GPT-OSS, with reasoning tiers | Google account OAuth |
+| **GLM (BigModel)** | `glm-5.3`, `glm-5.3-flash`, `glm-5.2`, `glm-5.1`, `glm-5` | ZCode browser sign-in (polled) |
+| **Volcengine Ark** | Ark coding models + live catalog | Volcengine SSO |
+| **Xiaomi MiMo** | MiMo Pro, MiMo Flash | Xiaomi account (QR / password) |
+| **WorkBuddy (国内版)** | Hy, GLM, Kimi, DeepSeek, MiniMax models | Browser OAuth (Tencent) |
 
-**Plan and usage** shows the subscription tier and every allowance the provider
-states, with a meter and a reset time: Kimi's rolling 5-hour window, weekly window
-and included credit (`GET /coding/v1/usages`); Grok's weekly included credit
-(`cli-chat-proxy.grok.com/v1/billing?format=credits`, plus the plan tier from the
-token's own `tier` claim); and Antigravity's **four** buckets — Gemini and Claude,
-each rolling and weekly — read from `v1internal:retrieveUserQuotaSummary`, falling
-back to the per-model `quotaInfo` of `fetchAvailableModels` (worst-spent model per
-family, classified by id, display name and tier, so an `Opus` row counts as
-Claude). A provider that states nothing says so instead of inventing a figure.
+Every provider also feeds the **`auto`** route, which spans them all: pick `auto` and the harness walks your enabled models in order until one answers.
 
-A reset is stated by how far off it is, on every route: **minutes** within the hour
-(`40 分钟后重置`), **hours** within the day (`4 小时后重置`), and the date beyond that
-(`重置时间 2026/10/17 13:54`) — the count is what a reader acts on when deciding whether
-there is room left, and a date is what they need when it is a week away. Because the
-page re-reads the figures on a slow interval, the count follows along while it is
-open.
+## Features
 
-**Manage** opens a dialog with per-account token refresh, the credential-file
-path, and the resolved endpoints.
-
-While a device authorization is pending the card shows the code, its expiry, and
-the buttons to open or copy it, and the status dot turns amber. A loopback
-provider (Grok) instead shows a sign-in link and waits for the browser redirect.
+- **One sign-in per provider** — no API keys to find, paste, or rotate. The plugin runs the provider's own OAuth/device flow and keeps the token on disk (`~/.dsh/plugins/kimi-oauth/auth.json`, mode `0600`).
+- **Live plan usage** — the Settings card and the composer chip show each account's remaining quota (Kimi's 5-hour / weekly windows + credit, Grok's weekly credit, Antigravity's Gemini + Claude buckets, GLM/Ark/MiMo/WorkBuddy credits), with a meter and reset time.
+- **Model picker integration** — each provider's models appear in the session picker with context windows and reasoning tiers; hide or re-order them per provider.
+- **⚡ Fast / lightspeed variants** — for models that have one (e.g. Grok 4.7 → `grok-4.7-build-fast`), a bolt button beside the model selector switches to the fast variant; it reads as a reasoning rung so the base model always stays selectable.
+- **Cross-account pool** — sign in to several accounts on one provider; the plugin draws on the next account when one's allowance runs out.
+- **Auto fallback** — `auto` moves to the next enabled model when a provider refuses the preferred one (renamed, rate-limited, out of quota), and stops falling back once a stream has started.
 
 ## Install
 
@@ -183,252 +38,56 @@ provider (Grok) instead shows a sign-in link and waits for the browser redirect.
 dsh plugin --profile web add dsh-plugin-subscription-oauth
 ```
 
-`web` is the profile that serves the Settings page; use `desktop` (or any other
-profile name) if that is the one you run.
+Then restart DeepSeek Harness and open **Settings → Subscriptions** (订阅).
 
-The CLI forwards its arguments to pnpm, so a pinned version, a git URL and a local
-path are all spelled the same way:
+To install a specific version, or straight from the repository:
 
 ```sh
-dsh plugin --profile web add dsh-plugin-subscription-oauth@0.2.2
+dsh plugin --profile web add dsh-plugin-subscription-oauth@0.10.2
 dsh plugin --profile web add github:EricFL1998/dsh-subscription-oauth
-dsh plugin --profile web add /path/to/dsh-plugin-subscription-oauth
 ```
 
-Restart `dsh web` (or the desktop app) afterwards so the new bundle loads. A local
-directory is installed as a `link:`, so afterwards `npm run build` in the checkout
-is enough to publish a change; restart again to pick it up.
-
-The host packages (`@deepseek-ai/dsh-llm` and the rest) are **optional** peers: the
-harness provides them at runtime, so installing this plugin does not fetch a second
-copy of the host it is running inside.
-
-### Releasing (maintainers)
+## How to use
 
-`prepublishOnly` rebuilds `lib/` — the TypeScript output plus the browser bundle — so
-a published tarball can never carry a stale client:
-
-```sh
-npm version patch   # or minor/major
-npm publish
-```
+1. **Open Settings → Subscriptions.** You see one card per provider; signed-in providers sort to the front, `auto` leads.
+2. **Connect** a provider. A browser window (or a device code) starts the provider's own sign-in. Finish it there — the card updates by itself.
+3. **Pick a model.** The provider's models now appear in the composer model picker, and the chip shows live usage.
+4. **Expand a card** to manage accounts (set default, sign out, refresh token), toggle which models appear, re-order them, add a model id this build doesn't know yet, and see the credential file / endpoints.
 
-For a headless composition that only needs the model route (no Settings page):
+> **Tip:** to use a different account on a provider, sign out first, then connect again — the browser sign-in follows whichever account the provider's page is signed in with.
 
-```sh
-dsh --profile headless --patch /path/to/dsh-plugin-subscription-oauth/overlay.yml "your task"
-```
+## What it registers
 
-where `overlay.yml` is a one-entry patch naming
-`/path/to/dsh-plugin-subscription-oauth/lib/index.js`. Log in once from a web profile
-first — the token file is shared.
+| Surface | What appears |
+| --- | --- |
+| `ctx.llm` | the `kimi`, `grok`, `antigravity`, `glm`, `ark`, `mimo`, `workbuddy` and `auto` provider routes (models, reasoning, streaming) |
+| Settings | a **Subscriptions** section: one card per provider |
+| Model picker | each provider's own models, plus **`auto`** spanning them all |
+| Composer chip | live plan usage for the provider in force |
 
-## Hiding a built-in provider from the picker
+## Hiding a provider
 
-A plugin cannot unregister another bundle's route (`ctx.llm` has no unregister
-API), so hiding a built-in provider is a profile-patch change. To hide the
-**DeepSeek API-key** route and its models while keeping the **DeepSeek account**
-(sign-in) route:
+To keep a provider's models out of the picker without uninstalling, drop it from the route list in your profile's `cordis.patch.yml`:
 
-```yaml
+```yml
 # $DSH_HOME/profiles/<profile>/cordis.patch.yml
-- id: llm-deepseek
-  name: "@deepseek-ai/dsh-llm-deepseek-api-key"
-  config:
-    models: []
+plugins:
+  dsh-plugin-subscription-oauth:
+    providers: [kimi, grok, antigravity, glm, ark, mimo, workbuddy]
 ```
 
-`models` replaces the adapter's default catalog, so `deepseek-official` reports
-no models and the picker hides the empty group (`Empty groups are hidden`); the
-route stays registered, so a session that already saved one of its model ids
-keeps working. Leave `llm-deepseek-account` alone to keep the account route.
-Restart the profile (or let HMR reload) for the change to apply.
-
-## Use
-
-1. Open **Settings → Subscriptions** (订阅) and press **Connect** on the card you want.
-2. Finish the sign-in the card shows: Kimi Code and (when answered) a device code
-   you approve in the browser; Grok and Antigravity open a sign-in page and wait for
-   the redirect. The section updates by itself while an attempt is pending.
-3. Open the model picker in any session and choose a model under that provider —
-   or leave it on **Auto** to let the enabled models be tried in order.
-
-Not signed in? The provider stays out of the picker, and a request fails with
-`INVALID_CREDENTIAL` pointing at the Settings page. Nothing else breaks.
-
-Multiple accounts are supported: connect again to add another. The ★ default
-account serves requests; use **Use by default** to switch.
-
-## Config
-
-```yaml
-- id: llm-subscription-oauth
-  name: dsh-plugin-subscription-oauth
-  config:
-    providers: [kimi, grok, antigravity]  # routes to register; all are default
-    enabled: true
-    discovery: true                  # consult each endpoint's live model list
-    streamIdleTimeoutMs: 300000      # abandon a silent stream after this
-    defaultModel: kimi-for-coding    # model the picker preselects on the Kimi route
-    extraModels: []                  # Kimi ids to publish without shipped metadata
-    # oauthHost: https://auth.kimi.com
-    # apiBase: https://api.kimi.com/coding/v1
-```
-
-Only the Kimi route takes `oauthHost`/`apiBase`/`defaultModel`/`extraModels`: the
-Grok and Antigravity endpoints are fixed by their own clients, and their model
-lists come from the live catalog. Omitting a route from `providers` simply leaves
-it unregistered.
-
-`oauthHost` and `apiBase` can also come from the environment
-(`KIMI_CODE_OAUTH_HOST` / `KIMI_OAUTH_HOST`, `KIMI_CODE_API_BASE` /
-`KIMI_API_BASE`); an explicit config value wins. `apiBase` accepts either the
-bare base or the full `.../responses` URL.
-
-## How it works
-
-The package is a standard DeepSeek Harness plugin: `lib/index.js` exports
-`apply(ctx)`, which registers one `ctx.llm` adapter per route and mounts the
-Settings section through `ctx.slots`. `lib/client.js` is the browser half — the
-section itself, loaded by the harness bundle loader. Nothing runs outside the
-harness process, and uninstalling the bundle removes every route it added.
-
-**Login** is the RFC 8628 device authorization grant against
-`auth.kimi.com`. The plugin requests a device code, shows it, and polls the
-token endpoint with `authorization_pending` / `slow_down` / `access_denied` /
-`expired_token` handling until the browser approves. Tokens are stored per
-account, keyed by the `user_id` (or `sub`) claim inside Kimi's JWTs.
-
-**Grok** signs in with the flow its own CLI uses: OIDC discovery at
-`auth.x.ai`, an authorization-code exchange with PKCE on a loopback callback
-(`127.0.0.1:56121/callback`), and a refresh grant that keeps the client identity.
-**Antigravity** is Google's desktop OAuth client on `127.0.0.1:51121`, whose
-scopes include `cloud-platform`; login is only complete once `loadCodeAssist`
-reports the account's Cloud AI Companion project, because every later
-`v1internal` call is scoped to it.
-
-**Requests** carry three identity layers:
-
-* the bearer access token, refreshed ahead of expiry (5-minute preempt) with one
-  in-flight refresh shared per account;
-* Kimi's `X-Msh-*` client identity (`KimiCLI/<version>`, platform, device id) —
-  the service admits the request by this family;
-* the harness attribution product. Because Kimi admits a request by the CLI
-  product token while the harness requires its own attribution on every provider
-  request, the two are joined into one RFC 9110 `User-Agent` value rather than
-  sent as two competing fields.
-
-**The wire** is OpenAI Responses: `instructions` + `input` items,
-`function_call` / `function_call_output` kept adjacent (the endpoint requires
-it), `stream: true`, `store: false`, `prompt_cache_key` from the session id for
-cache affinity, and `reasoning.effort` mapped from the harness's effort id.
-Stored reasoning is never replayed as text — the endpoint keeps a subscription
-account's thinking encrypted server-side, so each turn stands on its own visible
-content.
-
-Kimi locks temperature and sampling penalties on subscription coding models, so a
-caller-supplied `temperature` is dropped rather than rejected upstream.
-
-## Troubleshooting
-
-| Symptom | Cause |
-| --- | --- |
-| `<provider> login expired; sign in again…` | the refresh token was rejected; connect again |
-| No models in the picker | not signed in, or the route was not re-announced — check **Settings → Subscriptions** |
-| No models at all for Antigravity | the account's `fetchAvailableModels` returned nothing; the route ships no curated list, so press **Refresh** after signing in |
-| `model not found` | the id is not served by your plan; use **Refresh** |
-| The code card never clears | the attempt is still pending or expired; press **Cancel** and connect again |
-| `model discovery failed … using the built-in catalog` | the live list was unreachable; the shipped catalog still works (Kimi and Grok ship one, Antigravity does not) |
-| Rows cannot be dragged | the layout is switched off in Settings, or the drag started on the checkbox — grab the ⠿ grip |
+Omit the ones you don't want. The list defaults to every implemented route.
 
-## Security notes
+## Security
 
-### What it stores, and where
-
-| Path | Contents | Mode |
-| --- | --- | --- |
-| `~/.dsh/plugins/kimi-oauth/auth.json` | one section per provider: access token, refresh token, expiry, account id, plan | `0600`, written atomically |
-| `~/.dsh/plugins/kimi-oauth/preferences.json` | model visibility, your ordering, and Auto's chain — no secrets | `0600` |
-| `~/.dsh/plugins/kimi-oauth/kimi-device-id` | the stable device id Kimi's API expects | `0600` |
-
-The directory keeps the name this plugin had when it served Kimi Code alone: it
-holds **live logins**, so renaming it would sign everyone out. Nothing is stored
-outside `~/.dsh`, and nothing is uploaded anywhere except to the providers
-themselves.
-
-### What it talks to
-
-| Route | Hosts contacted | Why |
-| --- | --- | --- |
-| `kimi` | `auth.kimi.com`, `api.kimi.com` | device-flow sign-in, then the coding API |
-| `grok` | `auth.x.ai`, `api.x.ai`, `cli-chat-proxy.grok.com` | OIDC sign-in, the Responses API, the plan's credit figure |
-| `antigravity` | `accounts.google.com`, `oauth2.googleapis.com`, `cloudcode-pa.googleapis.com` | Google sign-in, the account's project, then Cloud Code Assist (including its quota accounting) |
-| `glm` | `bigmodel.cn`, `zcode.z.ai`, `open.bigmodel.cn` | browser sign-in brokered by ZCode, then the coding-plan API and its allowance |
-| `ark` | `signin.volcengine.com`, `ark.cn-beijing.volces.com`, `ark.cn-beijing.volcengineapi.com` | Volcengine SSO, then the coding-plan API (data plane) and the signed control plane that mints the API key and reports the allowance |
-
-There is no analytics, no update ping and no relay through anyone else's server:
-every request goes to the host that owns the account. No request body, prompt or
-token is ever logged.
-
-### Boundaries worth knowing
-
-* The token file is written with mode `0600`; only the account id, email, host,
-  and device id are ever shown in the UI — never a token.
-* The Kimi and GLM flows need no listener on this machine at all: Kimi polls, and
-  GLM's browser callback is completed server-side by the provider. Grok and
-  Antigravity hold one loopback listener **only** while a login attempt is pending,
-  on `127.0.0.1:56121` and `127.0.0.1:51121`, and it is closed as soon as the
-  attempt settles or lapses. A loopback destination is never proxied.
-* Outbound requests honour `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY` and
-  `NO_PROXY`.
-* Signing in authorizes this machine for that account — the provider's own consent
-  screen is the consent step, and it is never completed on your behalf.
-* A plugin cannot unregister another bundle's provider (`ctx.llm` has no unregister
-  API), so this plugin never hides anything you had before; see
-  [Hiding a built-in provider from the picker](#hiding-a-built-in-provider-from-the-picker)
-  if that is what you want.
-* **Known limits**: OpenAI-compatible API keys are not supported by design (this is
-  a subscription plugin); GLM's flow has no refresh grant, so a lapsed sign-in asks
-  you to sign in again rather than renewing silently; Antigravity ships no curated
-  model list and depends on its endpoint answering.
+- Credentials are stored locally at `~/.dsh/plugins/kimi-oauth/auth.json` (mode `0600`, written atomically), one section per provider.
+- The plugin talks only to the providers' own hosts and OAuth endpoints — no telemetry, no third-party relay.
+- Your subscriptions only; nothing is shared across machines.
 
 ## Develop
 
-```sh
-npm install        # development baseline: published DSH 0.2.0-rc.2 packages
-npm run build      # tsc (lib/) + tsdown (lib/client.js browser bundle)
-npm test           # node --test over the compiled unit specs
-npm run typecheck  # tsc --noEmit
-```
-
-`tools/probe-kimi-oauth.mjs` performs a live check that Kimi accepts the shipped
-client id and identity headers; it starts a device authorization and immediately
-abandons it, so no account is touched (`npm run build` first).
-
-### Reviewing the settings UI without a host
-
-`tools/preview-entry.tsx` mounts the real section with a stubbed RPC caller, so
-a design change can be screenshotted on its own. Query flags drive the states:
-`?dark=1`, `?grok=1`, `?ag=1`, `?busy=1`, `?hide=1`, `?collapse=1`, `?manage=1`.
-
-```sh
-npm run preview                                 # bundles probe/preview.js
-# then open probe/preview.html in a browser, or screenshot it headlessly:
-msedge --headless=new --user-data-dir=%TEMP%\shot --window-size=620,1900 \
-  --screenshot=shot.png "file:///<checkout>/probe/preview.html?dark=1&grok=1&ag=1"
-```
-
-The harness deliberately styles no `button` of its own: the shell gives its
-controls chrome through a CSS class plugin markup does not carry, so a preview
-that decorated bare buttons would hide exactly the regression this page had.
-
-Query flags: `dark=1` (dark theme), `compact=1` (model list collapsed),
-`busy=1` (pending device authorization), `manage=1` (manage dialog open).
-`probe/` holds only generated preview output and is gitignored; the committed
-screenshots live in `docs/images/`.
-
-After `npm run build`, restart `dsh web` to pick up the change.
+See the [developer README](README.dev.md) for the full wire protocol, token lifetimes, troubleshooting, and how to run the test suite.
 
 ## License
 
-MIT
+[MIT](LICENSE)