dsh-lcx-codex 0.3.0 → 0.3.2

package/CHANGELOG.md

@@ -4,13 +4,22 @@
 
 ## Unreleased
 
+## 0.3.2 - 2026-08-21
+
 ### Fixed
 
-- Hosted Search 与 Alpha Search 现在和 Native V2 Compact 一样，复用 DSH 已添加的 `openai-responses` provider 路由、凭据引用、headers 与 retry policy；不再要求用户为插件重复配置 `LCX_API_KEY`。
-- README 将插件运行时凭据与运行在 DSH 外的 Alpha 探针/E2E 测试凭据明确分开。
-- README 改为简短的用户手册，以 npm 安装为主；Alpha 提示前置，并按 NewAPI 当前源码区分 4 种中转渠道类型与 Sub2API 直连，共 5 种部署路径。
+- Native V2 compact 与同路由 replay 现在和 DSH/Pi 普通 Responses 请求复用相同的 session `prompt_cache_key`、缓存 retention 与会话 header，避免压缩边界额外切换 NewAPI/Sub2API 的缓存和账号粘性域；`cacheRetention: none` 时同时省略这些缓存信号。
+- 移除未被插件直接导入或注入的 `@deepseek-ai/dsh-compaction-basic` peer 声明，避免 DSH/pnpm 安装时出现误导性的宿主依赖警告；Basic fallback 继续通过 DSH `llm/stream` 的 `next()` 链调用宿主实现。
+
+## 0.3.1 - 2026-08-21
 
-## 0.3.0 - 2026-08-20
+### Fixed
+
+- 删除未被 DSH 官方识别、且错误写死旧域名与 `LCX_API_KEY` 的 `dshhub` 权限块；README 改为声明网络目标和凭据由当前 `openai-responses` provider 动态决定。
+- 添加 npm 与 DSH 社区检索使用的标准关键词，其中包括 `dsh-plugin` GitHub topic 对应关键词。
+- 新增独立英文用户文档 `README_EN.md`，并与中文 README 互相链接。
+
+## 0.3.0 - 2026-08-21
 
 ### Changed
 
@@ -27,6 +36,9 @@
 
 ### Fixed
 
+- Hosted Search 与 Alpha Search 现在和 Native V2 Compact 一样，复用 DSH 已添加的 `openai-responses` provider 路由、凭据引用、headers 与 retry policy；不再要求用户为插件重复配置 `LCX_API_KEY`。
+- README 将插件运行时凭据与运行在 DSH 外的 Alpha 探针/E2E 测试凭据明确分开。
+- README 改为简短的用户手册，以 npm 安装为主；Alpha 提示前置，并按 NewAPI 当前源码区分 4 种中转渠道类型与 Sub2API 直连，共 5 种部署路径。
 - Native replay and portable migration no longer depend on the nonexistent `GenerateOptions.branchId`; fork safety uses public session ancestry and derived marker history while preserving existing v3 fingerprint compatibility.
 - README 的本地 link 安装示例不再包含开发机绝对路径。
 - Alpha 从 rc.8 公共 `session.requestContext()` 读取 active route，避免模型切换后的 capability 误判。

package/README.md

@@ -1,5 +1,10 @@
 # dsh-lcx-codex
 
+**简体中文** | [English](README_EN.md)
+
+[![npm version](https://img.shields.io/npm/v/dsh-lcx-codex.svg)](https://www.npmjs.com/package/dsh-lcx-codex)
+[![license](https://img.shields.io/npm/l/dsh-lcx-codex.svg)](LICENSE)
+
 社区维护的 DSH 插件，为兼容 OpenAI Responses/Codex 协议的 GPT 模型增加 Hosted Web Search、Alpha Search 和 Native V2 远程压缩。
 
 > [!IMPORTANT]
@@ -12,9 +17,42 @@
 - 直接使用 Sub2API 反代的 GPT 模型。
 - 使用 NewAPI 中转的 GPT 模型（也就是第三方中转）；NewAPI 的上游渠道连接 Sub2API。
 
-```text
-DSH -> Sub2API -> OpenAI Responses/Codex-compatible upstream
-DSH -> NewAPI -> Sub2API/compatible channel -> OpenAI Responses/Codex-compatible upstream
+```mermaid
+flowchart LR
+    accTitle: dsh-lcx-codex 技术路线
+    accDescr: 插件复用当前 DSH openai-responses 模型的路由和凭据，将 Hosted Search、capability-gated Alpha Search 与 Native V2 Compact 请求经受控传输发送到 Sub2API 直连或 NewAPI 中转部署。
+
+    dsh_session([DSH GPT 会话]) --> resolve_route[复用 provider、model、baseURL 和凭据]
+
+    subgraph plugin_capabilities ["dsh-lcx-codex"]
+        hosted_search[Hosted Search<br/>POST /responses + web_search]
+        alpha_gate{Alpha capability 匹配?}
+        alpha_search[Alpha Search<br/>POST /alpha/search]
+        alpha_disabled([Alpha 不注册])
+        native_compact[Native V2 Compact<br/>stream + compaction_trigger]
+    end
+
+    resolve_route --> hosted_search
+    resolve_route --> alpha_gate
+    resolve_route --> native_compact
+    alpha_gate -->|是| alpha_search
+    alpha_gate -->|否| alpha_disabled
+
+    hosted_search --> transport[受控鉴权、超时、重试和响应大小]
+    alpha_search --> transport
+    native_compact --> transport
+
+    transport --> deployment{部署路径}
+    deployment -->|直连| sub2api[Sub2API]
+    deployment -->|中转| newapi[NewAPI 兼容渠道]
+    sub2api --> upstream([OpenAI Responses/Codex-compatible upstream])
+    newapi --> upstream
+
+    upstream -.->|compaction output| checkpoint[(Checkpoint v3)]
+    checkpoint -->|同路由| opaque_replay[Opaque native replay]
+    checkpoint -->|路由或模型变化| portable_migration[Portable migration]
+    opaque_replay --> transport
+    portable_migration --> transport
 ```
 
 本项目不隶属于 OpenAI，也不是 OpenAI 官方发布的插件或 OAuth 客户端。
@@ -31,7 +69,7 @@ Alpha 只有在 capability 记录与当前 endpoint、provider、model 和 schem
 
 ## 安装
 
-发布到 npm 后，推荐直接安装包名：
+推荐从 npm 安装：
 
 ```powershell
 dsh plugin --profile web add dsh-lcx-codex
@@ -40,7 +78,7 @@ dsh plugin --profile web add dsh-lcx-codex
 也可以下载 GitHub Release 中的 `.tgz` 安装指定版本：
 
 ```powershell
-dsh plugin --profile web add .\dsh-lcx-codex-0.3.0.tgz
+dsh plugin --profile web add .\dsh-lcx-codex-0.3.2.tgz
 ```
 
 安装后启动 DSH：
@@ -86,6 +124,8 @@ node (Join-Path $dshHome 'profiles\web\node_modules\dsh-lcx-codex\scripts\probe-
 
 ## 数据与限制
 
+- 网络目标由当前活动 DSH `openai-responses` provider 的 `baseURL` 决定，不固定到 LCX 或其他域名；插件只在该地址下调用 `/responses` 和 `/alpha/search`
+- 凭据名称取自同一 provider 的 `apiKeyEnv`，并由 DSH credentials service 解析；插件不会自行保存 API key
 - Checkpoint：`$DSH_HOME/storages/lcx-codex/checkpoints-v3.json`
 - Alpha capability：`$DSH_HOME/storages/lcx-codex/web-alpha-capabilities.json`
 - Alpha refs：`$DSH_HOME/storages/lcx-codex/web-alpha-refs.json`

package/README_EN.md

@@ -0,0 +1,160 @@
+# dsh-lcx-codex
+
+[Chinese](README.md) | **English**
+
+[![npm version](https://img.shields.io/npm/v/dsh-lcx-codex.svg)](https://www.npmjs.com/package/dsh-lcx-codex)
+[![license](https://img.shields.io/npm/l/dsh-lcx-codex.svg)](LICENSE)
+
+A community-maintained DSH plugin that adds Hosted Web Search, Alpha Search, and Native V2 remote compaction to GPT models served through an OpenAI Responses/Codex-compatible API.
+
+> [!IMPORTANT]
+> Alpha Search currently has five supported deployment paths: a direct Sub2API connection, or one of four NewAPI channel types: `Sub2API`, `New API`, `ChatGPT Subscription (Codex)`, and `Advanced Custom`. A regular `OpenAI` channel does not support `/v1/alpha/search` and is rejected by NewAPI.
+
+This list comes from NewAPI's current [`AlphaSearchHelper`](https://github.com/QuantumNous/new-api/blob/f116414284162ad15d8925f7bca494c109b83e93/relay/alpha_search_handler.go). Other NewAPI versions may differ, so the capability probe remains authoritative for a specific deployment.
+
+`LCX` is only the plugin name. It is not a service provider or protocol. The plugin supports GPT models served through:
+
+- A direct Sub2API reverse proxy.
+- A NewAPI relay, meaning a third-party relay whose upstream channel connects to Sub2API.
+
+```mermaid
+flowchart LR
+    accTitle: dsh-lcx-codex architecture
+    accDescr: The plugin reuses the active DSH openai-responses model route and credential, then sends Hosted Search, capability-gated Alpha Search, and Native V2 Compact requests through a controlled transport to a direct Sub2API or NewAPI relay deployment.
+
+    dsh_session([DSH GPT session]) --> resolve_route[Reuse provider, model, baseURL, and credential]
+
+    subgraph plugin_capabilities ["dsh-lcx-codex"]
+        hosted_search[Hosted Search<br/>POST /responses + web_search]
+        alpha_gate{Alpha capability matches?}
+        alpha_search[Alpha Search<br/>POST /alpha/search]
+        alpha_disabled([Alpha is not registered])
+        native_compact[Native V2 Compact<br/>stream + compaction_trigger]
+    end
+
+    resolve_route --> hosted_search
+    resolve_route --> alpha_gate
+    resolve_route --> native_compact
+    alpha_gate -->|Yes| alpha_search
+    alpha_gate -->|No| alpha_disabled
+
+    hosted_search --> transport[Controlled authentication, timeout, retry, and response size]
+    alpha_search --> transport
+    native_compact --> transport
+
+    transport --> deployment{Deployment path}
+    deployment -->|Direct| sub2api[Sub2API]
+    deployment -->|Relay| newapi[Compatible NewAPI channel]
+    sub2api --> upstream([OpenAI Responses/Codex-compatible upstream])
+    newapi --> upstream
+
+    upstream -.->|Compaction output| checkpoint[(Checkpoint v3)]
+    checkpoint -->|Same route| opaque_replay[Opaque native replay]
+    checkpoint -->|Route or model changed| portable_migration[Portable migration]
+    opaque_replay --> transport
+    portable_migration --> transport
+```
+
+This project is not affiliated with OpenAI and is not an official OpenAI plugin or OAuth client.
+
+## Features
+
+| Feature | Tool or protocol | Behavior |
+|---|---|---|
+| Hosted Web Search | `websearch_gpt` | Uses `/responses` with `web_search` and returns text, direct sources, and citations |
+| Alpha Search | `websearch_alpha` | Uses `/alpha/search` for search, image, open/find/click, PDF screenshot, finance, weather, sports, and time actions |
+| Native V2 Compact | `/responses` with `compaction_trigger` | Stores checkpoint v3 and supports same-route replay, model migration, fork/tree sessions, restart recovery, and image attachments |
+
+Alpha is enabled only when a capability record matches the current endpoint, provider, model, and schema. Hosted and Alpha are separate protocols and never silently fall back to each other.
+
+## Installation
+
+Install from npm:
+
+```powershell
+dsh plugin --profile web add dsh-lcx-codex
+```
+
+You can also install a specific `.tgz` file from a GitHub Release:
+
+```powershell
+dsh plugin --profile web add .\dsh-lcx-codex-0.3.2.tgz
+```
+
+Start DSH after installation:
+
+```powershell
+dsh web
+```
+
+Open `Settings -> Plugins -> LCX / Codex capabilities` and enable Hosted, Alpha, or Native Compact as needed. The plugin is disabled by default.
+
+## Requirements
+
+- Node.js 20 or later
+- DSH `0.1.0-rc.8` or a compatible release
+- A GPT model already added to DSH and working in a normal conversation
+- The model must use the `openai-responses` provider from `llm-pi-ai`
+
+The plugin reuses the active DSH model's provider, model, Responses URL, credential reference, headers, and retry policy. Normal plugin operation does not require a second `LCX_API_KEY` configuration.
+
+The endpoint and model fields in the plugin UI are defaults for cases without an active session route and for compatibility with the older direct-route configuration. An existing DSH provider configuration takes precedence.
+
+## Alpha Probe
+
+Alpha capability is classified as `native`, `command-capable`, `emulated-search-only`, `unsupported`, or `unknown`. An HTTP 200 response alone does not prove that an action is native.
+
+The probe is a standalone Node.js script outside the DSH runtime, so it cannot use the DSH credentials service. It requires a local key file; normal plugin operation does not.
+
+```powershell
+$dshHome = if ($env:DSH_HOME) { $env:DSH_HOME } else { Join-Path $env:USERPROFILE '.dsh' }
+$env:LCX_API_KEY_FILE = 'C:\path\to\local-key.txt'
+$env:LCX_MODEL = 'the-exact-model-name'
+node (Join-Path $dshHome 'profiles\web\node_modules\dsh-lcx-codex\scripts\probe-alpha.mjs')
+```
+
+To also probe image, finance, weather, sports, and time actions:
+
+```powershell
+$env:LCX_ALPHA_PROBE_STRUCTURED = '1'
+node (Join-Path $dshHome 'profiles\web\node_modules\dsh-lcx-codex\scripts\probe-alpha.mjs')
+```
+
+The probe does not print the key or full response bodies. Restart DSH, or disable and re-enable Alpha, after the probe completes.
+
+## Data and Limits
+
+- The runtime network target is determined by the active DSH `openai-responses` provider's `baseURL`; it is not fixed to LCX or any other domain. The plugin only calls `/responses` and `/alpha/search` under that address.
+- The credential name comes from the same provider's `apiKeyEnv` and is resolved by the DSH credentials service. The plugin does not store API keys.
+- Checkpoints: `$DSH_HOME/storages/lcx-codex/checkpoints-v3.json`
+- Alpha capabilities: `$DSH_HOME/storages/lcx-codex/web-alpha-capabilities.json`
+- Alpha references: `$DSH_HOME/storages/lcx-codex/web-alpha-refs.json`
+- Only Native remote-compaction V2 is supported; `/responses/compact` is never called.
+- Checkpoints never store raw image bytes or data URLs.
+- Opaque checkpoints are not replayed across an incompatible provider, model, base URL, session, or lineage.
+- Image generation is not included.
+
+Never commit API keys, OAuth tokens, Authorization headers, account IDs, session cookies, or runtime sidecars to GitHub.
+
+## Update and Removal
+
+```powershell
+dsh plugin --profile web update dsh-lcx-codex
+dsh plugin --profile web remove dsh-lcx-codex
+```
+
+Removal does not delete `$DSH_HOME/storages/lcx-codex/`. Do not delete a checkpoint sidecar by itself while a session still references its marker.
+
+## Development
+
+```powershell
+npm install
+npm test
+npm run test:schema
+```
+
+Real E2E tests and the Alpha probe must read test credentials only from ignored local files or environment variables.
+
+## License
+
+[MIT](LICENSE)

package/lib/compact-v2.js

@@ -156,7 +156,7 @@ export function mergeFeatureHeader(headers) {
   return result
 }
 
-export function buildNativeCompactionBody({ model, input, instructions, promptCacheKey, tools }) {
+export function buildNativeCompactionBody({ model, input, instructions, promptCacheKey, promptCacheRetention, tools }) {
   if (!Array.isArray(input)) throw protocolError('Native compaction input must be an array', 'LCX_COMPACT_INVALID_INPUT')
   if (input.some((item) => isObject(item) && item.type === 'compaction_trigger')) {
     throw protocolError('Native compaction input already contains compaction_trigger', 'LCX_COMPACT_DUPLICATE_TRIGGER')
@@ -170,6 +170,7 @@ export function buildNativeCompactionBody({ model, input, instructions, promptCa
     ...(nativeTools !== undefined ? { tools: nativeTools } : {}),
     ...(instructions !== undefined ? { instructions: structuredClone(instructions) } : {}),
     ...(promptCacheKey !== undefined && promptCacheKey !== null ? { prompt_cache_key: String(promptCacheKey) } : {}),
+    ...(promptCacheRetention !== undefined && promptCacheRetention !== null ? { prompt_cache_retention: String(promptCacheRetention) } : {}),
   }
 }
 
@@ -273,6 +274,7 @@ export async function requestNativeCompaction({
   input,
   instructions,
   promptCacheKey,
+  promptCacheRetention,
   idempotencyKey,
   tools,
   headers,
@@ -281,7 +283,7 @@ export async function requestNativeCompaction({
   maxAttempts,
   maxResponseBytes,
 }) {
-  const body = buildNativeCompactionBody({ model, input, instructions, promptCacheKey, tools })
+  const body = buildNativeCompactionBody({ model, input, instructions, promptCacheKey, promptCacheRetention, tools })
   const requestHeaders = { ...(headers ?? {}) }
   if (idempotencyKey !== undefined && idempotencyKey !== null && !Object.keys(requestHeaders).some((name) => name.toLowerCase() === 'idempotency-key')) {
     requestHeaders['idempotency-key'] = String(idempotencyKey)

package/lib/index.js

@@ -1,6 +1,7 @@
 import z from '@deepseek-ai/schemastery'
 import { attributionHeaders, resolveRetryPolicy } from '@deepseek-ai/dsh-llm'
 import { settingsNamespace } from '@deepseek-ai/dsh-settings'
+import { clampOpenAIPromptCacheKey } from '@earendil-works/pi-ai/api/openai-prompt-cache'
 import { randomUUID } from 'node:crypto'
 import { homedir } from 'node:os'
 import { join } from 'node:path'
@@ -135,6 +136,7 @@ function normalizeCompactTransport(value) {
 }
 
 function normalizeConfig(input = {}) {
+  const cacheRetention = ['none', 'short', 'long'].includes(input.cacheRetention) ? input.cacheRetention : 'short'
   return {
     provider: input.provider || 'lcx',
     baseURL: String(input.baseURL || 'https://api.lcxbot.com/v1').replace(/\/+$/u, ''),
@@ -142,6 +144,8 @@ function normalizeConfig(input = {}) {
     model: input.model || 'gpt-5.6-sol',
     compactTransport: normalizeCompactTransport(input.compactTransport),
     headers: input.headers && typeof input.headers === 'object' ? { ...input.headers } : {},
+    cacheRetention,
+    supportsLongCacheRetention: input.supportsLongCacheRetention !== false,
     checkpointPath: input.checkpointPath || defaultCheckpointPath(),
     portableCheckpointPath: input.portableCheckpointPath || portableCheckpointPath(input.checkpointPath || defaultCheckpointPath()),
     alphaCapabilityPath: input.alphaCapabilityPath || defaultAlphaCapabilityPath(),
@@ -186,6 +190,8 @@ function resolveResponsesRouteConfig(ctx, options, fallbackConfig) {
     baseURL,
     apiKeyEnv,
     headers: profile.headers ?? fallbackConfig.headers,
+    cacheRetention: profile.cacheRetention ?? fallbackConfig.cacheRetention,
+    supportsLongCacheRetention: profile.compat?.supportsLongCacheRetention ?? fallbackConfig.supportsLongCacheRetention,
     model: options.model,
     compactTransport: profile.compactTransport ?? fallbackConfig.compactTransport,
     timeoutMs: profile.timeoutMs ?? fallbackConfig.timeoutMs,
@@ -301,7 +307,7 @@ async function authenticatedHeaders(ctx, config, sessionId, clientRequestId) {
     ...config.headers,
     ...attributionHeaders(),
     authorization: `Bearer ${await resolveApiKey(ctx, config)}`,
-    'x-client-request-id': clientRequestId ?? randomUUID(),
+    ...(clientRequestId === null ? {} : { 'x-client-request-id': clientRequestId ?? (sessionId ? String(sessionId) : randomUUID()) }),
     ...(sessionId ? { 'session-id': String(sessionId) } : {}),
   }
 }
@@ -361,19 +367,35 @@ function routeWithSessionAncestry(ctx, route) {
   return { ...route, ancestorSessionIds: sessionAncestry(ctx, route.sessionId) }
 }
 
-function promptCacheKey(route) {
-  return route?.sessionId ? routeFingerprint(route) : undefined
+function promptCacheSessionId(route, config) {
+  if (config?.cacheRetention === 'none') return undefined
+  return route?.sessionId ? String(route.sessionId) : undefined
+}
+
+function promptCacheKey(route, config) {
+  const sessionId = promptCacheSessionId(route, config)
+  return sessionId ? clampOpenAIPromptCacheKey(sessionId) : undefined
+}
+
+function promptCacheRetention(config) {
+  return config?.cacheRetention === 'long' && config.supportsLongCacheRetention !== false ? '24h' : undefined
+}
+
+function promptCacheHeaders(ctx, config, route) {
+  const sessionId = promptCacheSessionId(route, config)
+  return authenticatedHeaders(ctx, config, sessionId, sessionId === undefined ? null : undefined)
 }
 
 async function requestRemoteCompaction(options, input, config, signal, ctx, route, preflightHeaders) {
   try {
-    const headers = preflightHeaders ?? await authenticatedHeaders(ctx, config, options.sessionId)
+    const headers = preflightHeaders ?? await promptCacheHeaders(ctx, config, route)
     return await requestNativeCompaction({
       baseURL: config.baseURL,
       model: options.model,
       input,
       instructions: options.system,
-      promptCacheKey: promptCacheKey(route),
+      promptCacheKey: promptCacheKey(route, config),
+      promptCacheRetention: promptCacheRetention(config),
       idempotencyKey: randomUUID(),
       tools: options.tools,
       headers,
@@ -731,7 +753,7 @@ function checkpointReplayRecord(messages, store) {
   return { marker, record }
 }
 
-function nativeReplayBody(options, route, nativeOutput, tailInput) {
+function nativeReplayBody(options, route, config, nativeOutput, tailInput) {
   return {
     model: options.model,
     input: [...structuredClone(nativeOutput), ...structuredClone(tailInput)],
@@ -739,7 +761,8 @@ function nativeReplayBody(options, route, nativeOutput, tailInput) {
     store: false,
     ...(options.tools !== undefined ? { tools: responsesTools(options.tools) } : {}),
     ...(options.system !== undefined ? { instructions: options.system } : {}),
-    ...(promptCacheKey(route) ? { prompt_cache_key: promptCacheKey(route) } : {}),
+    ...(promptCacheKey(route, config) ? { prompt_cache_key: promptCacheKey(route, config) } : {}),
+    ...(promptCacheRetention(config) ? { prompt_cache_retention: promptCacheRetention(config) } : {}),
   }
 }
 
@@ -762,8 +785,8 @@ async function* nativeCheckpointReplayStream(options, config, portableStore, ctx
   try {
     const response = await fetchSse(
       `${config.baseURL}/responses`,
-      nativeReplayBody(options, route, nativeOutput, tailInput),
-      mergeFeatureHeader(await authenticatedHeaders(ctx, config, options.sessionId)),
+      nativeReplayBody(options, route, config, nativeOutput, tailInput),
+      mergeFeatureHeader(await promptCacheHeaders(ctx, config, route)),
       replaySignals.signal,
       config.timeoutMs + 1000,
       { maxResponseBytes: config.maxResponseBytes },
@@ -822,7 +845,7 @@ async function prepareRemoteCompaction(options, config, portableStore, ctx, sess
   const route = currentRoute(options, config)
   const lease = sessionTracker?.capture(route.sessionId)
   lease?.assert('request-start')
-  const headers = await authenticatedHeaders(ctx, config, options.sessionId)
+  const headers = await promptCacheHeaders(ctx, config, route)
   responsesTools(options.tools)
   const llm = ctx?.llm ?? ctx?.get?.('llm')
   const imageSupport = typeof llm?.resolveModelInfo === 'function'

package/package.json

@@ -1,7 +1,26 @@
 {
   "name": "dsh-lcx-codex",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "DSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models",
+  "keywords": [
+    "deepseek-harness",
+    "dsh",
+    "dsh-plugin",
+    "plugin",
+    "web-search",
+    "openai-responses",
+    "sub2api",
+    "newapi",
+    "compaction"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/kk3ya03-star/dsh-lcx-codex.git"
+  },
+  "homepage": "https://github.com/kk3ya03-star/dsh-lcx-codex#readme",
+  "bugs": {
+    "url": "https://github.com/kk3ya03-star/dsh-lcx-codex/issues"
+  },
   "type": "module",
   "main": "lib/index.js",
   "exports": {
@@ -20,6 +39,7 @@
     "cordis.patch.yml",
     "LICENSE",
     "README.md",
+    "README_EN.md",
     "CHANGELOG.md"
   ],
   "dsh": {
@@ -30,39 +50,6 @@
       "platform": "web"
     }
   },
-  "dshhub": {
-    "schemaVersion": 1,
-    "displayName": "dsh-lcx-codex",
-    "summary": "Sub2API/NewAPI GPT web search, capability-gated Alpha, and Responses native V2 compact",
-    "surfaces": [
-      "host",
-      "web"
-    ],
-    "capabilities": {
-      "provides": [
-        "hosted-web-search",
-        "capability-gated-alpha-search",
-        "native-responses-compaction"
-      ]
-    },
-    "compatibility": {
-      "dsh": ">=0.1.0-rc.8",
-      "node": ">=20"
-    },
-    "permissions": {
-      "network": [
-        "https://api.lcxbot.com"
-      ],
-      "credentials": [
-        "LCX_API_KEY"
-      ],
-      "storage": [
-        "$DSH_HOME/storages/lcx-codex/checkpoints-v3.json",
-        "$DSH_HOME/storages/lcx-codex/web-alpha-capabilities.json",
-        "$DSH_HOME/storages/lcx-codex/web-alpha-refs.json"
-      ]
-    }
-  },
   "dependencies": {
     "@earendil-works/pi-ai": "0.82.1"
   },
@@ -75,7 +62,6 @@
     "@deepseek-ai/dsh-client-runtime": "^0.1.0-rc.8",
     "@deepseek-ai/dsh-client-ui-settings": "^0.1.0-rc.8",
     "@deepseek-ai/dsh-client-ui-slots": "^0.1.0-rc.8",
-    "@deepseek-ai/dsh-compaction-basic": "^0.1.0-rc.8",
     "@deepseek-ai/dsh-credentials": "^0.1.0-rc.8",
     "@deepseek-ai/dsh-llm": "^0.1.0-rc.8",
     "@deepseek-ai/dsh-settings": "^0.1.0-rc.8",