@piceofpentogramm/alterclaude 0.1.0 → 0.1.2

package/README.md

@@ -2,59 +2,47 @@
 
 Use Claude Code with **any LLM** — not just Claude.
 
-AlterClaude is a fork of Claude Code that adds an OpenAI-compatible provider shim so you can plug in GPT-4o, DeepSeek, Gemini, Llama, Mistral, or any model that speaks the OpenAI chat completions API. It also supports the ChatGPT Codex backend for `codexplan` and `codexspark`, and local inference via [Atomic Chat](https://atomic.chat/) on Apple Silicon.
+AlterClaude — это форк [OpenClaude](https://github.com/Gitlawb/openclaude) (который, в свою очередь, форк Claude Code), с дополнительными улучшениями: фиолетовая тема, 3-шаговый мастер настройки провайдера, обновлённый интерфейс.
 
-All of Claude Code's tools work — bash, file read/write/edit, grep, glob, agents, tasks, MCP — just powered by whatever model you choose.
+Все инструменты Claude Code работают — bash, file read/write/edit, grep, glob, agents, tasks, MCP — просто вместо Claude ими управляет любая модель, которую вы выбрали.
 
 ---
 
-## Start Here
+## Быстрый старт (рекомендуемый)
 
-If you are new to terminals or just want the easiest path, start with the beginner guides:
-
-- [Non-Technical Setup](docs/non-technical-setup.md)
-- [Windows Quick Start](docs/quick-start-windows.md)
-- [macOS / Linux Quick Start](docs/quick-start-mac-linux.md)
-
-If you want source builds, Bun workflows, profile launchers, or full provider examples, use:
-
-- [Advanced Setup](docs/advanced-setup.md)
-
----
-
-## Beginner Install
-
-For most users, install the npm package:
+Установите пакет и запустите **встроенный мастер настройки** — `/provider`:
 
 ```bash
 npm install -g @piceofpentogramm/alterclaude
+alterclaude
 ```
 
-The package name is `@piceofpentogramm/alterclaude`, but the command you run is:
+Внутри AlterClaude введите:
 
-```bash
-alterclaude
+```
+/provider
 ```
 
-If you install via npm and later see `ripgrep not found`, install ripgrep system-wide and confirm `rg --version` works in the same terminal before starting AlterClaude.
+Мастер проведёт вас через настройку: выберите провайдера (OpenAI, OpenRouter, Gemini, Ollama, Codex), введите API-ключ, укажите endpoint и модель. Профиль сохранится автоматически.
 
 ---
 
-## Fastest Setup
+## Быстрый старт (вручную)
 
-### Windows PowerShell
+### OpenRouter
 
-```powershell
+```bash
 npm install -g @piceofpentogramm/alterclaude
 
-$env:CLAUDE_CODE_USE_OPENAI="1"
-$env:OPENAI_API_KEY="sk-your-key-here"
-$env:OPENAI_MODEL="gpt-4o"
+export CLAUDE_CODE_USE_OPENROUTER=1
+export OPENROUTER_API_KEY=sk-or-your-key-here
 
 alterclaude
 ```
 
-### macOS / Linux
+Модели по умолчанию: opus → `deepseek/deepseek-v4-pro`, sonnet → `deepseek/deepseek-v4-flash`, haiku → `tencent/hy3-preview`. Переопределить через `OPENROUTER_MODEL`.
+
+### OpenAI
 
 ```bash
 npm install -g @piceofpentogramm/alterclaude
@@ -66,81 +54,51 @@ export OPENAI_MODEL=gpt-4o
 alterclaude
 ```
 
-That is enough to start with OpenAI.
-
----
-
-### OpenRouter (Fastest)
+### Windows PowerShell
 
-```bash
+```powershell
 npm install -g @piceofpentogramm/alterclaude
 
-export CLAUDE_CODE_USE_OPENROUTER=1
-export OPENROUTER_API_KEY=sk-or-your-key-here
+$env:CLAUDE_CODE_USE_OPENAI="1"
+$env:OPENAI_API_KEY="sk-your-key-here"
+$env:OPENAI_MODEL="gpt-4o"
 
 alterclaude
 ```
 
-Default model: `deepseek/deepseek-v4-flash` (haiku → `tencent/hy3-preview`, sonnet → `deepseek/deepseek-v4-flash`, opus → `deepseek/deepseek-v4-pro`). Override with `OPENROUTER_MODEL`.
-
 ---
 
-## Choose Your Guide
-
-### Beginner
-
-- Want the easiest setup with copy-paste steps: [Non-Technical Setup](docs/non-technical-setup.md)
-- On Windows: [Windows Quick Start](docs/quick-start-windows.md)
-- On macOS or Linux: [macOS / Linux Quick Start](docs/quick-start-mac-linux.md)
-
-### Advanced
+## Выберите свой путь
 
-- Want source builds, Bun, local profiles, runtime checks, or more provider choices: [Advanced Setup](docs/advanced-setup.md)
+- **[Non-Technical Setup](docs/non-technical-setup.md)** — самый простой путь, копипаст
+- **[Windows Quick Start](docs/quick-start-windows.md)**
+- **[macOS / Linux Quick Start](docs/quick-start-mac-linux.md)**
+- **[Advanced Setup](docs/advanced-setup.md)** — сборка из исходников, Bun, профили, runtime checks
 
 ---
 
-## Common Beginner Choices
-
-### OpenRouter
-
-Best if you want to use any model through OpenRouter (DeepSeek, OpenAI, Anthropic, Gemini, and 200+ more). Set `CLAUDE_CODE_USE_OPENROUTER=1` and `OPENROUTER_API_KEY`.
-
-### OpenAI
-
-Best default if you already have an OpenAI API key.
-
-### Ollama
+## Что работает
 
-Best if you want to run models locally on your own machine.
+- **Все инструменты**: Bash, FileRead, FileWrite, FileEdit, Glob, Grep, WebFetch, WebSearch, Agent, MCP, LSP, NotebookEdit, Tasks
+- **Стриминг**: токены в реальном времени
+- **Tool calling**: многошаговые цепочки инструментов
+- **Изображения**: base64 и URL для vision-моделей
+- **Slash-команды**: `/commit`, `/review`, `/compact`, `/diff`, `/doctor`, `/provider` и другие
+- **Sub-агенты**: AgentTool порождает под-агентов с тем же провайдером
+- **Память**: персистентная система памяти
 
-### Codex
+## Что отличается от Claude Code
 
-Best if you already use the Codex CLI or ChatGPT Codex backend.
+- **Нет thinking mode** — Anthropic-специфичный extended thinking отключён
+- **Нет prompt caching** — Anthropic-заголовки кэширования пропущены
+- **Нет beta-фич** — Anthropic beta-заголовки игнорируются
+- **Token limits** — по умолчанию 32K max output, некоторые модели могут снижать
 
 ---
 
-## What Works
+## Как это работает
 
-- **All tools**: Bash, FileRead, FileWrite, FileEdit, Glob, Grep, WebFetch, WebSearch, Agent, MCP, LSP, NotebookEdit, Tasks
-- **Streaming**: Real-time token streaming
-- **Tool calling**: Multi-step tool chains (the model calls tools, gets results, continues)
-- **Images**: Base64 and URL images passed to vision models
-- **Slash commands**: /commit, /review, /compact, /diff, /doctor, etc.
-- **Sub-agents**: AgentTool spawns sub-agents using the same provider
-- **Memory**: Persistent memory system
-
-## What's Different
-
-- **No thinking mode**: Anthropic's extended thinking is disabled (OpenAI models use different reasoning)
-- **No prompt caching**: Anthropic-specific cache headers are skipped
-- **No beta features**: Anthropic-specific beta headers are ignored
-- **Token limits**: Defaults to 32K max output — some models may cap lower, which is handled gracefully
-
----
-
-## How It Works
-
-The shim (`src/services/api/openaiShim.ts`) sits between Claude Code and the LLM API:
+Прослойка (`src/services/api/openaiShim.ts`) находится между Claude Code и API LLM:
 
 ```
 Claude Code Tool System
@@ -149,67 +107,50 @@ Claude Code Tool System
   Anthropic SDK interface (duck-typed)
         |
         v
-  openaiShim.ts  <-- translates formats
+  openaiShim.ts  <-- переводит форматы
         |
         v
   OpenAI Chat Completions API
         |
         v
-  Any compatible model
+  Любая совместимая модель
 ```
 
-It translates:
+Конвертация:
 - Anthropic message blocks → OpenAI messages
 - Anthropic tool_use/tool_result → OpenAI function calls
 - OpenAI SSE streaming → Anthropic stream events
 - Anthropic system prompt arrays → OpenAI system messages
 
-The rest of Claude Code doesn't know it's talking to a different model.
-
----
-
-## Model Quality Notes
-
-Not all models are equal at agentic tool use. Here's a rough guide:
-
-| Model | Tool Calling | Code Quality | Speed |
-|-------|-------------|-------------|-------|
-| GPT-4o | Excellent | Excellent | Fast |
-| DeepSeek-V3 | Great | Great | Fast |
-| Gemini 2.0 Flash | Great | Good | Very Fast |
-| Llama 3.3 70B | Good | Good | Medium |
-| Mistral Large | Good | Good | Fast |
-| GPT-4o-mini | Good | Good | Very Fast |
-| Qwen 2.5 72B | Good | Good | Medium |
-| Smaller models (<7B) | Limited | Limited | Very Fast |
-
-For best results, use models with strong function/tool calling support.
+Остальной Claude Code не знает, что говорит с другой моделью.
 
 ---
 
-## Files Changed from Original
+## Модели и качество
 
-```
-src/services/api/openaiShim.ts   — NEW: OpenAI-compatible API shim (724 lines)
-src/services/api/client.ts       — Routes to shim when CLAUDE_CODE_USE_OPENAI=1
-src/utils/model/providers.ts     — Added 'openai' provider type
-src/utils/model/configs.ts       — Added openai model mappings
-src/utils/model/model.ts         — Respects OPENAI_MODEL for defaults
-src/utils/auth.ts                — Recognizes OpenAI as valid 3P provider
-```
+| Модель | Tool Calling | Качество кода | Скорость |
+|--------|-------------|---------------|----------|
+| GPT-4o | Отлично | Отлично | Быстро |
+| DeepSeek-V3 | Отлично | Отлично | Быстро |
+| Gemini 2.0 Flash | Отлично | Хорошо | Очень быстро |
+| Llama 3.3 70B | Хорошо | Хорошо | Средне |
+| Mistral Large | Хорошо | Хорошо | Быстро |
+| GPT-4o-mini | Хорошо | Хорошо | Очень быстро |
+| Qwen 2.5 72B | Хорошо | Хорошо | Средне |
+| Маленькие модели (<7B) | Ограниченно | Ограниченно | Очень быстро |
 
-6 files changed. 786 lines added. Zero dependencies added.
+Для лучших результатов используйте модели с сильной поддержкой function/tool calling.
 
 ---
 
 ## Origin
 
-This is a fork of Claude Code, which originally became publicly accessible through an npm source map exposure on March 31, 2026.
+AlterClaude — форк [OpenClaude](https://github.com/Gitlawb/openclaude), который, в свою очередь, форк Claude Code, ставшего публично доступным через экспозицию npm source map 31 марта 2026.
 
-The original Claude Code source is the property of Anthropic. This repository is not affiliated with or endorsed by Anthropic.
+Оригинальный Claude Code — собственность Anthropic. Этот репозиторий не аффилирован с Anthropic и не одобрен ими.
 
 ---
 
 ## License
 
-This repository is provided for educational and research purposes. The original source code is subject to Anthropic's terms. The OpenAI shim additions are public domain.
+MIT

package/dist/cli.mjs

@@ -120164,7 +120164,7 @@ function printStartupScreen() {
   const sLen = ` ● ${sL}    Ready — type /help to begin`.length;
   out.push(boxRow(sRow, W2, sLen));
   out.push(`${rgb(...BORDER)}╚${"═".repeat(W2 - 2)}╝${RESET}`);
-  out.push(`  ${DIM}${rgb(...DIMCOL)}alterclaude ${RESET}${rgb(...ACCENT)}v${"0.1.0"}${RESET}`);
+  out.push(`  ${DIM}${rgb(...DIMCOL)}alterclaude ${RESET}${rgb(...ACCENT)}v${"0.1.2"}${RESET}`);
   out.push("");
   process.stdout.write(out.join(`
 `) + `
@@ -358918,7 +358918,7 @@ function getAnthropicEnvMetadata() {
 function getBuildAgeMinutes() {
   if (false)
     ;
-  const buildTime = new Date("2026-05-29T15:02:15.447Z").getTime();
+  const buildTime = new Date("2026-05-29T15:25:34.035Z").getTime();
   if (isNaN(buildTime))
     return;
   return Math.floor((Date.now() - buildTime) / 60000);
@@ -441481,6 +441481,13 @@ function buildSavedProfileSummary(profile, env4) {
         modelLabel: getSafeDisplayValue(env4.OPENAI_MODEL, process.env, env4),
         endpointLabel: getSafeDisplayValue(env4.OPENAI_BASE_URL, process.env, env4)
       };
+    case "openrouter":
+      return {
+        providerLabel: "OpenRouter",
+        modelLabel: getSafeDisplayValue(env4.OPENROUTER_MODEL ?? DEFAULT_OPENROUTER_MODEL, process.env, env4),
+        endpointLabel: getSafeDisplayValue(env4.OPENROUTER_BASE_URL ?? OPENROUTER_BASE_URL, process.env, env4),
+        credentialLabel: maskSecretForDisplay(env4.OPENROUTER_API_KEY) !== undefined ? "configured" : undefined
+      };
     case "openai":
     default:
       return {
@@ -451503,7 +451510,7 @@ var init_bridge_kick = __esm(() => {
 var call58 = async () => {
   return {
     type: "text",
-    value: `${"99.0.0"} (built ${"2026-05-29T15:02:15.447Z"})`
+    value: `${"99.0.0"} (built ${"2026-05-29T15:25:34.035Z"})`
   };
 }, version2, version_default;
 var init_version = __esm(() => {
@@ -524644,7 +524651,7 @@ function WelcomeV2() {
             dimColor: true,
             children: [
               "v",
-              "0.1.0",
+              "0.1.2",
               " "
             ]
           }, undefined, true, undefined, this)
@@ -524844,7 +524851,7 @@ function WelcomeV2() {
           dimColor: true,
           children: [
             "v",
-            "0.1.0",
+            "0.1.2",
             " "
           ]
         }, undefined, true, undefined, this)
@@ -525070,7 +525077,7 @@ function AppleTerminalWelcomeV2(t0) {
         dimColor: true,
         children: [
           "v",
-          "0.1.0",
+          "0.1.2",
           " "
         ]
       }, undefined, true, undefined, this);
@@ -525324,7 +525331,7 @@ function AppleTerminalWelcomeV2(t0) {
       dimColor: true,
       children: [
         "v",
-        "0.1.0",
+        "0.1.2",
         " "
       ]
     }, undefined, true, undefined, this);
@@ -545872,7 +545879,7 @@ Usage: claude --remote "your task description"`, () => gracefulShutdown(1));
         pendingHookMessages
       }, renderAndRun);
     }
-  }).version("0.1.0 (Alter Claude)", "-v, --version", "Output the version number");
+  }).version("0.1.2 (Alter Claude)", "-v, --version", "Output the version number");
   program2.option("-w, --worktree [name]", "Create a new git worktree for this session (optionally specify a name)");
   program2.option("--tmux", "Create a tmux session for the worktree (requires --worktree). Uses iTerm2 native panes when available; use --tmux=classic for traditional tmux.");
   if (canUserConfigureAdvisor()) {
@@ -546452,7 +546459,7 @@ function validateProviderEnvOrExit() {
 async function main2() {
   const args = process.argv.slice(2);
   if (args.length === 1 && (args[0] === "--version" || args[0] === "-v" || args[0] === "-V")) {
-    console.log(`${"0.1.0"} (Alter Claude)`);
+    console.log(`${"0.1.2"} (Alter Claude)`);
     return;
   }
   {
@@ -546564,4 +546571,4 @@ async function main2() {
 }
 main2();
 
-//# debugId=A281A1585FC28D9664756E2164756E21
+//# debugId=80A0EDD9FC28F08A64756E2164756E21

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@piceofpentogramm/alterclaude",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models",
   "type": "module",
   "bin": {