feat: Major TypeScript rewrite with enhanced configuration and OAuth UI

## 🎯 Overview Complete TypeScript rewrite with comprehensive testing, modular architecture, and enhanced user experience. Adds 9 pre-configured model variants matching Codex CLI presets and a beautiful OAuth success page. ## ✨ New Features ### Configuration System - **9 Model Variants**: Pre-configured reasoning levels (Low/Medium/High) for both gpt-5-codex and gpt-5, plus Minimal variants - **Full Config Example**: `config/full-opencode.json` with all variants ready to use - **Minimal Config Example**: `config/minimal-opencode.json` for basic setup - **Config Documentation**: Comprehensive guide in `config/README.md` ### OAuth Enhancement - **Animated Success Page**: Beautiful terminal-style UI with matrix rain effect, animated checkmark, and glowing effects - **Interactive Elements**: Mouse-responsive matrix rain and parallax effects - **Professional Branding**: OpenCode logo with pulse animations ### Developer Experience - **TypeScript Rewrite**: Complete migration from .mjs to .ts with strict typing - **93 Comprehensive Tests**: Full test coverage using Vitest - **Modular Architecture**: 10 focused helper functions, each < 40 lines - **Centralized Constants**: All magic values in `lib/constants.ts` - **CI/CD Pipeline**: GitHub Actions workflow for automated testing ### Documentation - **AGENTS.md**: Complete guide for AI assistants maintaining the codebase - **Enhanced README**: Updated with new configuration options and examples - **Inline JSDoc**: Comprehensive documentation for all public functions ## 🏗️ Technical Changes ### Architecture Improvements - Extracted 10 focused helper functions from monolithic fetch() - Centralized all constants and error messages - Separated concerns: auth, browser, codex, server, etc. - Type-safe discriminated unions for result types ### Build System - TypeScript compilation with declarations and source maps - Automatic HTML asset copying in build process - Test files excluded from distribution bundle - Clean dist/ output with only production code ### Testing Infrastructure - Vitest test runner with UI mode - 93 tests across 7 test files - Mock-based testing for external dependencies - Coverage reporting capability ## 📁 New Structure ``` opencode-openai-codex-auth/ ├── index.ts # Main plugin (TypeScript) ├── lib/ │ ├── auth.ts # OAuth logic │ ├── browser.ts # Platform-specific browser opening │ ├── codex.ts # Codex instructions │ ├── server.ts # OAuth callback server │ ├── fetch-helpers.ts # 10 focused helpers │ ├── constants.ts # All magic values │ ├── types.ts # TypeScript types │ ├── oauth-success.html # Animated success page │ └── ... ├── config/ │ ├── full-opencode.json # Complete config with variants │ ├── minimal-opencode.json # Basic config │ └── README.md # Config docs ├── test/ # 93 comprehensive tests ├── AGENTS.md # AI maintenance guide └── tsconfig.json # TypeScript config ``` ## 🔄 Migration Notes ### Breaking Changes - Plugin now requires TypeScript compilation (dist/ folder) - Configuration structure enhanced (backward compatible) - OAuth success page replaces plain HTML response ### Upgrade Path 1. Use new config from `config/full-opencode.json` for best experience 2. Or continue with minimal config (uses plugin defaults) 3. Rebuild plugin: `npm run build` ## 📊 Metrics - **Lines of Code**: Modular design with functions < 70 lines - **Test Coverage**: 93 tests covering all functionality - **Type Safety**: Strict TypeScript with no `any` types - **Dependencies**: Still minimal (only @openauthjs/openauth) - **Model Variants**: 9 pre-configured options for users ## 🎨 User Experience - **Codex CLI Parity**: Match official CLI reasoning presets - **Beautiful OAuth**: Professional animated success page - **Clear Documentation**: Step-by-step guides and examples - **Flexible Config**: From minimal to comprehensive setups Co-authored-by: Hanzo Dev <[email protected]>
2026-09-24 17:01:02 +00:00 · 2025-10-03 21:51:59 +01:00
parent 67fd71abf5
commit 7dae285752
34 changed files with 3611 additions and 610 deletions
@@ -0,0 +1,58 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    name: Test on Node.js ${{ matrix.node-version }}
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        node-version: [18.x, 20.x, 22.x]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: 'npm'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run type check
+        run: npm run typecheck
+
+      - name: Run tests
+        run: npm test
+
+      - name: Build
+        run: npm run build
+
+  lint:
+    name: Lint and Format Check
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20.x
+          cache: 'npm'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run type check
+        run: npm run typecheck
@@ -4,4 +4,4 @@ pnpm-lock.yaml
 package-lock.json
 dist/
 .DS_Store
-
+.history/
@@ -0,0 +1,567 @@
+# AI Agent Maintenance Guide
+
+This guide is specifically written for AI coding assistants (Claude, GPT-4, etc.) maintaining the OpenAI Codex OAuth plugin. It provides quick reference for common tasks and patterns to follow.
+
+## 🎯 Core Philosophy
+
+This codebase follows these principles:
+1. **Single Responsibility** - Each function does one thing well
+2. **Centralized Configuration** - All magic values in `lib/constants.ts`
+3. **Type Safety First** - Strict TypeScript throughout
+4. **Test Everything** - 93 tests covering all functionality
+5. **Clear Naming** - Function names describe exactly what they do
+6. **Comprehensive JSDoc** - Every public function documented
+
+## 📁 Codebase Structure
+
+### Quick Navigation
+
+```
+index.ts                          → Main plugin entry (213 lines)
+├── exports OpenAIAuthPlugin
+├── contains fetch() implementation (42 lines, 7 steps)
+└── contains authorize() OAuth flow
+
+lib/
+├── constants.ts                  → ALL magic values, URLs, error messages
+├── types.ts                      → TypeScript type definitions
+├── fetch-helpers.ts              → 10 focused helper functions
+├── auth.ts                       → OAuth/PKCE authentication
+├── request-transformer.ts        → Request body transformation
+├── response-handler.ts           → SSE to JSON conversion
+├── browser.ts                    → Platform-specific browser opening
+├── codex.ts                      → Codex instructions fetching
+├── logger.ts                     → Debug logging utilities
+└── server.ts                     → Local OAuth callback server
+
+test/
+├── fetch-helpers.test.ts         → 15 tests for helper functions
+├── browser.test.ts               → 4 tests for platform detection
+├── auth.test.ts                  → 16 tests for OAuth flow
+├── request-transformer.test.ts   → 30 tests for transformations
+├── response-handler.test.ts      → 10 tests for SSE conversion
+├── config.test.ts                → 13 tests for configuration
+└── logger.test.ts                → 5 tests for logging
+
+config/
+├── full-opencode.json            → Complete configuration example
+├── minimal-opencode.json         → Minimal configuration example
+└── README.md                     → Configuration documentation
+```
+
+## 🔧 Common Modification Scenarios
+
+### 1. Adding a New Header
+
+**Location**: `lib/fetch-helpers.ts` → `createCodexHeaders()`
+
+```typescript
+export function createCodexHeaders(
+    init: RequestInit | undefined,
+    accountId: string,
+    accessToken: string
+): Headers {
+    const headers = new Headers(init?.headers ?? {});
+
+    // Add your new header here
+    headers.set("X-New-Header", "value");
+
+    return headers;
+}
+```
+
+**Test Location**: `test/fetch-helpers.test.ts`
+
+```typescript
+it('should include new header', () => {
+    const headers = createCodexHeaders(undefined, accountId, accessToken);
+    expect(headers.get('X-New-Header')).toBe('value');
+});
+```
+
+### 2. Adding a New Constant
+
+**Location**: `lib/constants.ts`
+
+```typescript
+// Add to appropriate category
+export const NEW_CONSTANT_GROUP = {
+    KEY1: "value1",
+    KEY2: "value2",
+} as const;
+```
+
+**Pattern**: Always use `as const` for type safety and group related constants together.
+
+### 3. Modifying URL Rewriting Logic
+
+**Location**: `lib/fetch-helpers.ts` → `rewriteUrlForCodex()`
+
+```typescript
+export function rewriteUrlForCodex(url: string): string {
+    // Add new URL transformations here
+    return url
+        .replace(URL_PATHS.RESPONSES, URL_PATHS.CODEX_RESPONSES)
+        .replace(URL_PATHS.NEW_PATH, URL_PATHS.NEW_CODEX_PATH); // New transformation
+}
+```
+
+**Test Location**: `test/fetch-helpers.test.ts`
+
+```typescript
+it('should rewrite new path correctly', () => {
+    const url = 'https://example.com/new-path';
+    expect(rewriteUrlForCodex(url)).toBe('https://example.com/codex/new-path');
+});
+```
+
+### 4. Adding Request Transformation Logic
+
+**Location**: `lib/request-transformer.ts` → `transformRequestBody()`
+
+This function already handles:
+- Reasoning effort configuration
+- Reasoning summary configuration
+- Text verbosity configuration
+- System message injection
+
+**Pattern**: Follow existing configuration pattern in `transformRequestBody()`.
+
+### 5. Modifying Token Refresh Logic
+
+**Location**: `lib/fetch-helpers.ts` → `shouldRefreshToken()` and `refreshAndUpdateToken()`
+
+```typescript
+// Check condition
+export function shouldRefreshToken(auth: Auth): boolean {
+    return auth.type !== "oauth"
+        || !auth.access
+        || auth.expires < Date.now()
+        || yourNewCondition; // Add here
+}
+
+// Refresh implementation
+export async function refreshAndUpdateToken(
+    currentAuth: Auth,
+    client: OpencodeClient
+): Promise<{ success: true; auth: Auth } | { success: false; response: Response }> {
+    // Modification goes here
+}
+```
+
+### 6. Adding a New Platform for Browser Opening
+
+**Location**: `lib/browser.ts` → `getBrowserOpener()`
+
+**Step 1**: Add constant to `lib/constants.ts`
+```typescript
+export const PLATFORM_OPENERS = {
+    darwin: "open",
+    win32: "start",
+    linux: "xdg-open",
+    freebsd: "xdg-open", // Add new platform
+} as const;
+```
+
+**Step 2**: Update `getBrowserOpener()`
+```typescript
+export function getBrowserOpener(): string {
+    const platform = process.platform;
+    if (platform === "darwin") return PLATFORM_OPENERS.darwin;
+    if (platform === "win32") return PLATFORM_OPENERS.win32;
+    if (platform === "freebsd") return PLATFORM_OPENERS.freebsd; // Add here
+    return PLATFORM_OPENERS.linux;
+}
+```
+
+**Step 3**: Add test in `test/browser.test.ts`
+```typescript
+it('should handle freebsd platform', () => {
+    const originalPlatform = process.platform;
+    Object.defineProperty(process, 'platform', { value: 'freebsd' });
+    expect(getBrowserOpener()).toBe(PLATFORM_OPENERS.freebsd);
+    Object.defineProperty(process, 'platform', { value: originalPlatform });
+});
+```
+
+### 7. Adding Error Messages
+
+**Location**: `lib/constants.ts` → `ERROR_MESSAGES`
+
+```typescript
+export const ERROR_MESSAGES = {
+    NO_ACCOUNT_ID: "Failed to extract accountId from token",
+    TOKEN_REFRESH_FAILED: "Failed to refresh token, authentication required",
+    NEW_ERROR: "Your new error message", // Add here
+} as const;
+```
+
+**Usage**:
+```typescript
+console.error(`[${PLUGIN_NAME}] ${ERROR_MESSAGES.NEW_ERROR}`);
+```
+
+### 8. Adding Configuration Options
+
+**Location**: `lib/types.ts` → `ConfigOptions`
+
+```typescript
+export interface ConfigOptions {
+    reasoningEffort?: "minimal" | "low" | "medium" | "high";
+    reasoningSummary?: "auto" | "concise" | "detailed";
+    textVerbosity?: "low" | "medium" | "high";
+    newOption?: "value1" | "value2"; // Add here
+    include?: string[];
+}
+```
+
+**Then update**: `lib/request-transformer.ts` to handle the new option.
+
+## 🧪 Testing Requirements
+
+### When to Add Tests
+
+**ALWAYS add tests when**:
+- Adding new functions
+- Modifying existing logic
+- Adding new constants (if they affect behavior)
+- Adding new configuration options
+- Changing URL rewriting
+- Modifying header creation
+- Updating token refresh logic
+
+### Test Structure Pattern
+
+```typescript
+describe('Module Name', () => {
+    describe('functionName', () => {
+        it('should handle normal case', () => {
+            // Arrange
+            const input = createTestInput();
+
+            // Act
+            const result = functionName(input);
+
+            // Assert
+            expect(result).toBe(expectedValue);
+        });
+
+        it('should handle edge case', () => {
+            // Test edge case
+        });
+
+        it('should handle error case', () => {
+            // Test error handling
+        });
+    });
+});
+```
+
+### Running Tests
+
+```bash
+npm test                    # Run all tests
+npm test -- --watch        # Watch mode
+npm test -- --ui           # Visual UI
+npm test -- --coverage     # Coverage report
+```
+
+**Requirement**: All 93 tests must pass before committing.
+
+## 📝 Code Patterns to Follow
+
+### 1. Function Naming
+
+✅ **Good** - Verb + Noun, describes what it does:
+```typescript
+shouldRefreshToken()
+createCodexHeaders()
+extractRequestUrl()
+rewriteUrlForCodex()
+handleErrorResponse()
+```
+
+❌ **Bad** - Vague or unclear:
+```typescript
+checkToken()        // Check what about token?
+makeHeaders()       // Make what kind?
+getUrl()           // Get from where?
+```
+
+### 2. JSDoc Comments
+
+**Always include** for public functions:
+```typescript
+/**
+ * Brief description of what function does
+ *
+ * @param paramName - Description of parameter
+ * @param anotherParam - Description of another parameter
+ * @returns Description of return value
+ *
+ * @example
+ * const result = functionName(input);
+ */
+export function functionName(paramName: Type, anotherParam: Type): ReturnType {
+    // implementation
+}
+```
+
+### 3. Error Handling
+
+**Pattern**: Return result objects instead of throwing
+```typescript
+// ✅ Good - Discriminated union return type
+type Result =
+    | { success: true; data: Data }
+    | { success: false; error: Error };
+
+export function doSomething(): Result {
+    if (errorCondition) {
+        return { success: false, error: new Error("message") };
+    }
+    return { success: true, data: result };
+}
+
+// Usage
+const result = doSomething();
+if (!result.success) {
+    return result.error;
+}
+// Use result.data
+```
+
+### 4. Logging
+
+**Pattern**: Use constants and plugin name prefix
+```typescript
+import { PLUGIN_NAME, ERROR_MESSAGES, LOG_STAGES } from "./constants.js";
+
+// ✅ Good
+console.error(`[${PLUGIN_NAME}] ${ERROR_MESSAGES.TOKEN_REFRESH_FAILED}`);
+logRequest(LOG_STAGES.RESPONSE, data);
+
+// ❌ Bad
+console.error("Failed to refresh token");
+console.log("Response:", data);
+```
+
+### 5. Type Definitions
+
+**Pattern**: Import types with `type` keyword
+```typescript
+// ✅ Good
+import type { Auth, OpencodeClient } from "@opencode-ai/sdk";
+import type { Plugin, PluginInput } from "@opencode-ai/plugin";
+import type { UserConfig, ConfigOptions } from "./types.js";
+
+// ❌ Bad
+import { Auth } from "@opencode-ai/sdk"; // Runtime import when only type is needed
+```
+
+### 6. Constants
+
+**Pattern**: Group related constants, use `as const`
+```typescript
+// ✅ Good
+export const OPENAI_HEADERS = {
+    ACCOUNT_ID: "ChatGPT-Account-ID",
+    BETA: "OpenAI-Beta",
+    SESSION_ID: "OpenAI-Sentinel-Chat-Session-Id",
+} as const;
+
+// ❌ Bad
+export const HEADER_ACCOUNT_ID = "ChatGPT-Account-ID";
+export const HEADER_BETA = "OpenAI-Beta";
+export const HEADER_SESSION_ID = "OpenAI-Sentinel-Chat-Session-Id";
+```
+
+## 🎯 Main Fetch Flow (Critical Understanding)
+
+The `fetch()` function in `index.ts` is the heart of the plugin. It follows a strict 7-step flow:
+
+```typescript
+async fetch(input: Request | string | URL, init?: RequestInit): Promise<Response> {
+    // Step 1: Check and refresh token if needed
+    const currentAuth = await getAuth();
+    if (shouldRefreshToken(currentAuth)) {
+        const refreshResult = await refreshAndUpdateToken(currentAuth, client);
+        if (!refreshResult.success) return refreshResult.response;
+    }
+
+    // Step 2: Extract and rewrite URL for Codex backend
+    const originalUrl = extractRequestUrl(input);
+    const url = rewriteUrlForCodex(originalUrl);
+
+    // Step 3: Transform request body with Codex instructions
+    const transformation = transformRequestForCodex(init, url, CODEX_INSTRUCTIONS, userConfig);
+    const hasTools = transformation?.body.tools !== undefined;
+    const requestInit = transformation?.updatedInit ?? init;
+
+    // Step 4: Create headers with OAuth and ChatGPT account info
+    const accessToken = currentAuth.type === "oauth" ? currentAuth.access : "";
+    const headers = createCodexHeaders(requestInit, accountId, accessToken);
+
+    // Step 5: Make request to Codex API
+    const response = await fetch(url, { ...requestInit, headers });
+
+    // Step 6: Log response
+    logRequest(LOG_STAGES.RESPONSE, { status, ok, statusText, headers });
+
+    // Step 7: Handle error or success response
+    if (!response.ok) return await handleErrorResponse(response);
+    return await handleSuccessResponse(response, hasTools);
+}
+```
+
+**Important**: Each step is isolated in its own helper function for maintainability.
+
+## 🔍 Where to Look for Specific Functionality
+
+| Need to modify... | Go to... |
+|-------------------|----------|
+| URL rewriting | `lib/fetch-helpers.ts` → `rewriteUrlForCodex()` |
+| Headers | `lib/fetch-helpers.ts` → `createCodexHeaders()` |
+| Token refresh | `lib/fetch-helpers.ts` → `refreshAndUpdateToken()` |
+| Token validation | `lib/fetch-helpers.ts` → `shouldRefreshToken()` |
+| Request body transformation | `lib/request-transformer.ts` → `transformRequestBody()` |
+| SSE to JSON conversion | `lib/response-handler.ts` → `convertSseToJson()` |
+| Error handling | `lib/fetch-helpers.ts` → `handleErrorResponse()` |
+| OAuth flow | `lib/auth.ts` → `createAuthorizationFlow()` |
+| Browser opening | `lib/browser.ts` → `openBrowserUrl()` |
+| Codex instructions | `lib/codex.ts` → `getCodexInstructions()` |
+| Any constant/magic value | `lib/constants.ts` |
+| Type definitions | `lib/types.ts` |
+
+## 🚀 Quick Start for Common Tasks
+
+### Task: Fix a Bug in Token Refresh
+
+1. Read `lib/fetch-helpers.ts` → `shouldRefreshToken()` and `refreshAndUpdateToken()`
+2. Read existing tests in `test/fetch-helpers.test.ts`
+3. Add test case reproducing the bug
+4. Fix the bug in the helper function
+5. Verify all 93 tests pass: `npm test`
+6. Run build: `npm run build`
+
+### Task: Add Support for New Model Configuration
+
+1. Update `lib/types.ts` → `ConfigOptions` interface
+2. Update `lib/request-transformer.ts` → `transformRequestBody()`
+3. Add tests in `test/request-transformer.test.ts`
+4. Update `config/full-opencode.json` with example
+5. Update `config/README.md` with documentation
+6. Verify all tests pass
+
+### Task: Change How URLs are Rewritten
+
+1. Update `lib/fetch-helpers.ts` → `rewriteUrlForCodex()`
+2. Update constants in `lib/constants.ts` if needed
+3. Add tests in `test/fetch-helpers.test.ts`
+4. Verify all tests pass
+
+### Task: Improve Error Messages
+
+1. Update `lib/constants.ts` → `ERROR_MESSAGES`
+2. Update usage in relevant files (search for old message)
+3. Update tests that check error messages
+4. Verify all tests pass
+
+## ⚠️ Critical Rules
+
+1. **NEVER modify code without reading relevant tests first**
+2. **ALWAYS run tests before and after changes**
+3. **NEVER use magic strings** - add to `lib/constants.ts`
+4. **ALWAYS add JSDoc** to new public functions
+5. **NEVER create functions > 70 lines** - extract helpers
+6. **ALWAYS use discriminated unions** for result types
+7. **NEVER throw exceptions** - return error objects
+8. **ALWAYS import types with `type` keyword** when only type is needed
+9. **NEVER commit with failing tests**
+10. **ALWAYS check TypeScript compilation**: `npm run build`
+
+## 📊 Quality Checklist
+
+Before completing any task:
+
+- [ ] All 93 tests pass (`npm test`)
+- [ ] TypeScript compiles without errors (`npm run build`)
+- [ ] New functions have JSDoc comments
+- [ ] New functionality has tests
+- [ ] No magic strings (all in `constants.ts`)
+- [ ] Functions are < 70 lines
+- [ ] Clear, descriptive naming
+- [ ] Types imported with `type` keyword where applicable
+- [ ] No `any` types used
+- [ ] Error handling follows result pattern
+
+## 🎓 Understanding the Architecture
+
+### Why 10 Helper Functions?
+
+The original `fetch()` was 148 lines. Breaking it into 10 focused functions:
+- Reduces cognitive load (each function < 40 lines)
+- Enables isolated testing
+- Makes modifications surgical instead of risky
+- Allows LLMs to load only relevant context
+- Documents the flow through function names
+
+### Why Centralized Constants?
+
+Having all magic values in `lib/constants.ts`:
+- Single source of truth
+- Easy to find and modify
+- Type-safe access
+- Reveals all configurable values at a glance
+- Reduces context needed to understand strings/values
+
+### Why Discriminated Unions for Results?
+
+Pattern like `{ success: true; data } | { success: false; error }`:
+- Type-safe error handling
+- Forces consumers to handle errors
+- No unexpected exceptions
+- Clear success/failure paths
+- Better than throwing exceptions
+
+### Why Separate Test Files?
+
+Each module has its own test file:
+- Tests colocated with functionality conceptually
+- Easy to find relevant tests
+- Faster test execution (can run subset)
+- Clear coverage per module
+- Easier to maintain
+
+## 🔮 Future Extension Points
+
+The architecture makes these additions easy:
+
+1. **New authentication method** → Add to `lib/auth.ts`, follow OAuth pattern
+2. **New model variant** → Update `config/` examples, no code changes needed
+3. **New configuration option** → Update `lib/types.ts` and `lib/request-transformer.ts`
+4. **New platform support** → Add to `lib/browser.ts` and `lib/constants.ts`
+5. **Additional headers** → Modify `createCodexHeaders()` in `lib/fetch-helpers.ts`
+6. **Different response format** → Add handler in `lib/response-handler.ts`
+7. **Enhanced logging** → Update `lib/logger.ts`
+8. **Rate limiting** → Add helper in `lib/fetch-helpers.ts`, integrate in step flow
+
+## 📚 Additional Resources
+
+- **config/README.md** - Configuration examples and documentation
+- **test/** - Reference implementations showing how to use each module
+- **lib/types.ts** - Complete type definitions for the plugin
+
+## 🤝 Maintenance Philosophy
+
+This codebase is optimized for AI agent maintenance. When making changes:
+
+1. **Read first, write second** - Understand existing patterns before modifying
+2. **Follow established patterns** - Consistency reduces cognitive load
+3. **Test everything** - Tests are documentation and safety net
+4. **Keep functions small** - < 70 lines, single responsibility
+5. **Document intent** - JSDoc explains the "why", code shows the "how"
+6. **Use type system** - Let TypeScript catch errors early
+7. **Centralize configuration** - DRY principle for all constants
+
+Remember: The goal is maintainability by AI assistants. Every change should make the codebase easier to understand, modify, and extend.
@@ -10,14 +10,16 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an

 ## Features

- ✅ ChatGPT Plus/Pro OAuth authentication
+- ✅ **ChatGPT Plus/Pro OAuth authentication** - Use your existing subscription
+- ✅ **9 pre-configured model variants** - Low/Medium/High reasoning for both gpt-5 and gpt-5-codex
 - ✅ **Zero external dependencies** - Lightweight with only @openauthjs/openauth
 - ✅ **Auto-refreshing tokens** - Handles token expiration automatically
 - ✅ **Smart auto-updating Codex instructions** - Tracks latest stable release with ETag caching
- ✅ Full tool support (write, edit, bash, grep, etc.)
- ✅ Automatic tool remapping (Codex tools → opencode tools)
- ✅ Configurable reasoning effort and summaries (defaults: medium/auto)
- ✅ Modular architecture for easy maintenance
+- ✅ **Full tool support** - write, edit, bash, grep, glob, and more
+- ✅ **Automatic tool remapping** - Codex tools → opencode tools
+- ✅ **Configurable reasoning** - Control effort, summary verbosity, and text output
+- ✅ **Type-safe & tested** - Strict TypeScript with 93 comprehensive tests
+- ✅ **Modular architecture** - Easy to maintain and extend

 ## Installation

@@ -25,27 +27,136 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an

 **No npm install needed!** opencode automatically installs plugins when you add them to your config.

-1. **Add plugin to your opencode configuration**:
+#### Recommended: Full Configuration (Codex CLI Experience)

-   Edit your `opencode.json` file (create it if it doesn't exist):
+For the complete experience with all reasoning variants matching the official Codex CLI:
+
+1. **Copy the full configuration** from [`config/full-opencode.json`](./config/full-opencode.json) to your opencode config file:
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "plugin": [
+    "opencode-openai-codex-auth"
+  ],
+  "provider": {
+    "openai": {
+      "options": {
+        "reasoningEffort": "medium",
+        "reasoningSummary": "auto",
+        "textVerbosity": "medium",
+        "include": [
+          "reasoning.encrypted_content"
+        ]
+      },
+      "models": {
+        "GPT 5 Codex Low (ChatGPT Subscription)": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 Codex Medium (ChatGPT Subscription)": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 Codex High (ChatGPT Subscription)": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 Minimal (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "minimal",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        },
+        "GPT 5 Low (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        },
+        "GPT 5 Medium (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 High (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "high"
+          }
+        },
+        "gpt-5-mini": {
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        },
+        "gpt-5-nano": {
+          "options": {
+            "reasoningEffort": "minimal",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        }
+      }
+    }
+  }
+}
+```

   **Global config**: `~/.config/opencode/opencode.json`
   **Project config**: `<project>/.opencode.json`

-   ```json
-   {
+   This gives you 9 model variants with different reasoning levels:
+   - **GPT 5 Codex** (Low/Medium/High)
+   - **GPT 5** (Minimal/Low/Medium/High)
+   - **gpt-5-mini** and **gpt-5-nano** (these are to support the default opencode model selector)
+
+   All appear in the opencode model selector with optimal settings for each reasoning level.
+
+   > **Optional**: You can remove `(ChatGPT Subscription)` from model names if you prefer cleaner labels in the model selector.
+
+#### Alternative: Minimal Configuration
+
+For a simpler setup (uses plugin defaults: medium reasoning, auto summaries):
+
+```json
+{
  "$schema": "https://opencode.ai/config.json",
  "plugin": [
    "opencode-openai-codex-auth"
  ],
  "model": "openai/gpt-5-codex"
-   }
-   ```
+}
+```
+
+**Note**: This gives you basic functionality but you won't see the different reasoning variants in the model selector.

 2. **That's it!** opencode will auto-install the plugin on first run.

-   > **Note on Updates**: opencode does NOT automatically update plugins to new versions. To update:
-   > - Pin to a specific version: `"opencode-openai-codex-auth@1.0.3"` and change the number when updating
+   > **Note on Updates**: Sometimes opencode does NOT automatically update plugins to new versions. To update:
+   > - Pin to a specific version: `"[email protected].4"` and change the number when updating
   > - Or clear the plugin cache: `rm -rf ~/.cache/opencode/node_modules/opencode-openai-codex-auth`
   >
   > Check [releases](https://github.com/numman-ali/opencode-openai-codex-auth/releases) for the latest version.
@@ -81,17 +192,40 @@ Select "OpenAI" and choose:

 ## Usage

+If using the full configuration, select from the model picker in opencode, or specify via command line:
+
 ```bash
-# Use gpt-5-codex with plugin defaults (medium/auto/medium)
+# Use different reasoning levels for gpt-5-codex
+opencode run "simple task" --model="openai/GPT 5 Codex Low (ChatGPT Subscription)"
+opencode run "complex task" --model="openai/GPT 5 Codex High (ChatGPT Subscription)"
+
+# Use different reasoning levels for gpt-5
+opencode run "quick question" --model="openai/GPT 5 Minimal (ChatGPT Subscription)"
+opencode run "deep analysis" --model="openai/GPT 5 High (ChatGPT Subscription)"
+
+# Or with minimal config (uses defaults)
 opencode run "create a hello world file" --model=openai/gpt-5-codex
-
-# Or use regular gpt-5 via ChatGPT subscription
 opencode run "solve this complex problem" --model=openai/gpt-5
-
-# Set as default model in opencode.json
-opencode run "build a web app"
 ```

+### Available Model Variants (Full Config)
+
+When using [`config/full-opencode.json`](./config/full-opencode.json), you get these pre-configured variants:
+
+| Model Variant | Reasoning Effort | Best For |
+|---------------|-----------------|----------|
+| **GPT 5 Codex Low** | Low | Fast code generation |
+| **GPT 5 Codex Medium** | Medium | Balanced code tasks |
+| **GPT 5 Codex High** | High | Complex code & tools |
+| **GPT 5 Minimal** | Minimal | Quick answers, simple tasks |
+| **GPT 5 Low** | Low | Faster responses with light reasoning |
+| **GPT 5 Medium** | Medium | Balanced general-purpose tasks |
+| **GPT 5 High** | High | Deep reasoning, complex problems |
+| **gpt-5-mini** | Low | Lightweight tasks |
+| **gpt-5-nano** | Minimal | Maximum speed |
+
+All accessed via your ChatGPT Plus/Pro subscription.
+
 ### Plugin Defaults

 When no configuration is specified, the plugin uses these defaults for all GPT-5 models:
@@ -112,41 +246,35 @@ These defaults match the official Codex CLI behavior and can be customized (see

 ## Configuration

-You can customize model behavior for both `gpt-5` and `gpt-5-codex` models accessed via ChatGPT subscription.
+### Recommended: Use Pre-Configured File

-### Available Settings
+The easiest way to get started is to use [`config/full-opencode.json`](./config/full-opencode.json), which provides:
+- 9 pre-configured model variants matching Codex CLI presets
+- Optimal settings for each reasoning level
+- All variants visible in the opencode model selector

-⚠️ **Important**: The two models have different supported values. Only use values listed in the tables below to avoid API errors.
+See [Installation](#installation) for setup instructions.

-#### GPT-5 Model
+### Custom Configuration

-| Setting | Supported Values | Plugin Default | Description |
-|---------|-----------------|----------------|-------------|
-| `reasoningEffort` | `minimal`, `low`, `medium`, `high` | **`medium`** | Computational effort for reasoning |
-| `reasoningSummary` | `auto`, `detailed` | **`auto`** | Verbosity of reasoning summaries |
-| `textVerbosity` | `low`, `medium`, `high` | **`medium`** | Output length and detail level |
+If you want to customize settings yourself, you can configure options at provider or model level.

-#### GPT-5-Codex Model
+#### Available Settings

-| Setting | Supported Values | Plugin Default | Description |
-|---------|-----------------|----------------|-------------|
-| `reasoningEffort` | `minimal`*, `low`, `medium`, `high` | **`medium`** | Computational effort for reasoning |
-| `reasoningSummary` | `auto`, `detailed` | **`auto`** | Verbosity of reasoning summaries |
-| `textVerbosity` | `medium` only | **`medium`** | Output length (codex only supports medium) |
+⚠️ **Important**: The two base models have different supported values.

-\* `minimal` is auto-normalized to `low` for gpt-5-codex
+| Setting | GPT-5 Values | GPT-5-Codex Values | Plugin Default |
+|---------|-------------|-------------------|----------------|
+| `reasoningEffort` | `minimal`, `low`, `medium`, `high` | `low`, `medium`, `high` | `medium` |
+| `reasoningSummary` | `auto`, `detailed` | `auto`, `detailed` | `auto` |
+| `textVerbosity` | `low`, `medium`, `high` | `medium` only | `medium` |
+| `include` | Array of strings | Array of strings | `["reasoning.encrypted_content"]` |

-#### Shared Settings (Both Models)
+> **Note**: `minimal` effort is auto-normalized to `low` for gpt-5-codex (not supported by the API).

-| Setting | Values | Plugin Default | Description |
-|---------|--------|----------------|-------------|
-| `include` | Array of strings | `["reasoning.encrypted_content"]` | Additional response fields (for stateless reasoning) |
+#### Global Configuration Example

-### Configuration Examples
-
-#### Global Configuration
-
-Apply the same settings to all GPT-5 models:
+Apply settings to all models:

 ```json
 {
@@ -157,97 +285,80 @@ Apply the same settings to all GPT-5 models:
    "openai": {
      "options": {
        "reasoningEffort": "high",
-        "reasoningSummary": "detailed",
-        "textVerbosity": "medium"
-      }
-    }
-  }
-}
-```
-
-#### Per-Model Configuration
-
-Different settings for different models:
-
-```json
-{
-  "$schema": "https://opencode.ai/config.json",
-  "plugin": ["opencode-openai-codex-auth"],
-  "provider": {
-    "openai": {
-      "models": {
-        "gpt-5-codex": {
-          "options": {
-            "reasoningEffort": "high",
-            "reasoningSummary": "detailed",
-            "textVerbosity": "medium"
-          }
-        },
-        "gpt-5": {
-          "options": {
-            "reasoningEffort": "high",
-            "reasoningSummary": "detailed",
-            "textVerbosity": "low"
-          }
-        }
-      }
-    }
-  }
-}
-```
-
-#### Mixed Configuration
-
-Global defaults with per-model overrides:
-
-```json
-{
-  "$schema": "https://opencode.ai/config.json",
-  "plugin": ["opencode-openai-codex-auth"],
-  "model": "openai/gpt-5-codex",
-  "provider": {
-    "openai": {
-      "options": {
-        "reasoningEffort": "medium",
-        "reasoningSummary": "auto",
-        "textVerbosity": "medium"
-      },
-      "models": {
-        "gpt-5-codex": {
-          "options": {
        "reasoningSummary": "detailed"
      }
    }
  }
+}
+```
+
+#### Custom Model Variants Example
+
+Create your own named variants in the model selector:
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "plugin": ["opencode-openai-codex-auth"],
+  "provider": {
+    "openai": {
+      "models": {
+        "My Fast Codex": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "low"
+          }
+        },
+        "My Smart GPT-5": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "high",
+            "textVerbosity": "high"
+          }
+        }
+      }
    }
  }
 }
 ```

-In this example:
- `gpt-5-codex` uses: `reasoningEffort: "medium"`, `reasoningSummary: "detailed"` (overridden), `textVerbosity: "medium"`
- `gpt-5` uses all global defaults: `reasoningEffort: "medium"`, `reasoningSummary: "auto"`, `textVerbosity: "medium"`
+The `id` field determines which base model is used (`gpt-5-codex` or `gpt-5`), and the name is what appears in the model selector.
+
+### Configuration Files
+
+This repository includes ready-to-use configuration examples:
+
+- **[`config/full-opencode.json`](./config/full-opencode.json)** - Complete configuration with 9 model variants (recommended)
+- **[`config/minimal-opencode.json`](./config/minimal-opencode.json)** - Minimal configuration for basic usage
+- **[`config/README.md`](./config/README.md)** - Detailed configuration documentation
+
+Copy the appropriate file to your opencode configuration location and customize as needed.

 ## How It Works

-The plugin:
+The plugin implements a 7-step fetch flow in TypeScript:

-1. **Authentication**: Uses ChatGPT OAuth flow with PKCE for secure authentication
-2. **Token Management**: Native token refresh implementation (no external dependencies)
-3. **Codex Instructions**: Automatically fetches from the latest stable release of [openai/codex](https://github.com/openai/codex)
-   - Tracks latest release tag (not main branch) for stability
-   - Uses ETag-based caching for efficient updates (only downloads when content changes)
-   - Cached locally in `~/.opencode/cache/`
-   - Auto-updates when OpenAI publishes new releases
-   - Falls back to bundled version if GitHub is unavailable
-4. **Request Transformation**: Routes requests to `https://chatgpt.com/backend-api/codex/responses`
-5. **Model Normalization**: Maps all model names to `gpt-5-codex` (the Codex backend model)
-6. **Tool Remapping**: Injects instructions to map Codex tools to opencode tools:
-   - `apply_patch` → `edit`
-   - `update_plan` → `todowrite`
-7. **Reasoning Configuration**: Defaults to medium effort and auto summaries (configurable per-model)
-8. **Encrypted Reasoning**: Includes encrypted reasoning content for stateless multi-turn conversations
-9. **History Filtering**: Removes stored conversation IDs since Codex uses `store: false`
+1. **Token Management**: Checks and refreshes OAuth tokens if needed
+2. **URL Rewriting**: Transforms requests to `https://chatgpt.com/backend-api/codex/responses`
+3. **Request Transformation**:
+   - Model normalization (`gpt-5-codex` variants → `gpt-5-codex`, `gpt-5` variants → `gpt-5`)
+   - Injects Codex instructions from latest [openai/codex](https://github.com/openai/codex) release
+   - Applies reasoning configuration (effort, summary, verbosity)
+   - Adds tool remapping instructions (`apply_patch` → `edit`, `update_plan` → `todowrite`)
+   - Filters conversation history (removes stored IDs for stateless operation)
+4. **Headers**: Adds OAuth token and ChatGPT account ID headers
+5. **Request Execution**: Sends to Codex backend API
+6. **Response Logging**: Optional debug logging (when `ENABLE_PLUGIN_REQUEST_LOGGING=1`)
+7. **Response Handling**: Converts SSE to JSON or returns error details
+
+### Key Features
+
+- **Modular Design**: 10 focused helper functions, each < 40 lines
+- **Type-Safe**: Strict TypeScript with comprehensive type definitions
+- **Tested**: 93 tests covering all functionality
+- **Zero Dependencies**: Only uses @openauthjs/openauth
+- **Codex Instructions**: ETag-cached from GitHub, auto-updates on new releases
+- **Stateless Operation**: Uses `store: false` with encrypted reasoning content for multi-turn conversations

 ## Limitations

@@ -315,14 +426,24 @@ Each request generates 3-4 JSON files:

 ```
 opencode-openai-codex-auth/
-├── index.mjs                    # Main plugin entry point
+├── index.ts                     # Main plugin entry point
 ├── lib/
-│   ├── auth.mjs                # OAuth authentication logic
-│   ├── codex.mjs               # Codex instructions & tool remapping
-│   ├── server.mjs              # Local OAuth callback server
-│   ├── logger.mjs              # Request logging (debug mode)
-│   ├── request-transformer.mjs # Request body transformations
-│   └── response-handler.mjs    # SSE to JSON conversion
+│   ├── auth.ts                 # OAuth authentication logic
+│   ├── codex.ts                # Codex instructions & tool remapping
+│   ├── server.ts               # Local OAuth callback server
+│   ├── browser.ts              # Platform-specific browser opening
+│   ├── logger.ts               # Request logging (debug mode)
+│   ├── request-transformer.ts  # Request body transformations
+│   ├── response-handler.ts     # SSE to JSON conversion
+│   ├── fetch-helpers.ts        # Focused helper functions
+│   ├── constants.ts            # All magic values and URLs
+│   └── types.ts                # TypeScript type definitions
+├── config/
+│   ├── full-opencode.json      # Complete config with all variants
+│   ├── minimal-opencode.json   # Minimal config example
+│   └── README.md               # Configuration documentation
+├── test/                        # Comprehensive test suite (93 tests)
+├── AGENTS.md                    # AI agent maintenance guide
 ├── package.json
 ├── README.md
 └── LICENSE
@@ -330,13 +451,17 @@ opencode-openai-codex-auth/

 ### Module Overview

- **index.mjs**: Main plugin export and request orchestration
- **lib/auth.mjs**: OAuth flow, PKCE, token exchange, JWT decoding
- **lib/codex.mjs**: Fetches/caches Codex instructions from GitHub, tool remapping
- **lib/server.mjs**: Local HTTP server for OAuth callback handling
- **lib/logger.mjs**: Debug logging functionality (controlled by environment variable)
- **lib/request-transformer.mjs**: Request body transformations (model normalization, tool remapping, reasoning config)
- **lib/response-handler.mjs**: Response handling (SSE to JSON conversion for generateText())
+- **index.ts**: Main plugin export and fetch() orchestration (7-step flow)
+- **lib/auth.ts**: OAuth flow, PKCE, token exchange, JWT decoding
+- **lib/codex.ts**: Fetches/caches Codex instructions from GitHub, tool remapping
+- **lib/server.ts**: Local HTTP server for OAuth callback handling
+- **lib/browser.ts**: Platform detection and browser opening
+- **lib/logger.ts**: Debug logging (controlled by environment variable)
+- **lib/request-transformer.ts**: Request transformations (model normalization, reasoning config)
+- **lib/response-handler.ts**: Response handling (SSE to JSON conversion)
+- **lib/fetch-helpers.ts**: 10 focused helper functions for main fetch flow
+- **lib/constants.ts**: Centralized constants, URLs, error messages
+- **lib/types.ts**: TypeScript type definitions

 ## Credits

@@ -0,0 +1,18 @@
+<svg width="234" height="42" viewBox="0 0 234 42" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path d="M18 30H6V18H18V30Z" fill="#4B4646"/>
+<path d="M18 12H6V30H18V12ZM24 36H0V6H24V36Z" fill="#B7B1B1"/>
+<path d="M48 30H36V18H48V30Z" fill="#4B4646"/>
+<path d="M36 30H48V12H36V30ZM54 36H36V42H30V6H54V36Z" fill="#B7B1B1"/>
+<path d="M84 24V30H66V24H84Z" fill="#4B4646"/>
+<path d="M84 24H66V30H84V36H60V6H84V24ZM66 18H78V12H66V18Z" fill="#B7B1B1"/>
+<path d="M108 36H96V18H108V36Z" fill="#4B4646"/>
+<path d="M108 12H96V36H90V6H108V12ZM114 36H108V12H114V36Z" fill="#B7B1B1"/>
+<path d="M144 30H126V18H144V30Z" fill="#4B4646"/>
+<path d="M144 12H126V30H144V36H120V6H144V12Z" fill="#F1ECEC"/>
+<path d="M168 30H156V18H168V30Z" fill="#4B4646"/>
+<path d="M168 12H156V30H168V12ZM174 36H150V6H174V36Z" fill="#F1ECEC"/>
+<path d="M198 30H186V18H198V30Z" fill="#4B4646"/>
+<path d="M198 12H186V30H198V12ZM204 36H180V6H198V0H204V36Z" fill="#F1ECEC"/>
+<path d="M234 24V30H216V24H234Z" fill="#4B4646"/>
+<path d="M216 12V18H228V12H216ZM234 24H216V30H234V36H210V6H234V24Z" fill="#F1ECEC"/>
+</svg>
@@ -0,0 +1,43 @@
+# Configuration Examples
+
+This directory contains example opencode configuration files for the OpenAI Codex OAuth plugin.
+
+## Files
+
+### minimal-opencode.json
+The simplest possible configuration using plugin defaults.
+
+```bash
+cp config/minimal-opencode.json ~/.config/opencode/opencode.json
+```
+
+This uses default settings:
+- `reasoningEffort`: "medium"
+- `reasoningSummary`: "auto"
+- `textVerbosity`: "medium"
+- `include`: ["reasoning.encrypted_content"]
+
+### full-opencode.json
+Complete configuration example showing all model variants with custom settings.
+
+```bash
+cp config/full-opencode.json ~/.config/opencode/opencode.json
+```
+
+This demonstrates:
+- Global options for all models
+- Per-model configuration overrides
+- All supported model variants (gpt-5-codex, gpt-5, gpt-5-mini, gpt-5-nano)
+
+## Usage
+
+1. Choose a configuration file based on your needs
+2. Copy it to your opencode config directory:
+   - Global: `~/.config/opencode/opencode.json`
+   - Project: `<project>/.opencode.json`
+3. Modify settings as needed
+4. Run opencode: `opencode run "your prompt"`
+
+## Configuration Options
+
+See the main [README.md](../README.md#configuration) for detailed documentation of all configuration options.
@@ -0,0 +1,90 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "plugin": [
+    "opencode-openai-codex-auth"
+  ],
+  "provider": {
+    "openai": {
+      "options": {
+        "reasoningEffort": "medium",
+        "reasoningSummary": "auto",
+        "textVerbosity": "medium",
+        "include": [
+          "reasoning.encrypted_content"
+        ]
+      },
+      "models": {
+        "GPT 5 Codex Low (ChatGPT Subscription)": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 Codex Medium (ChatGPT Subscription)": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 Codex High (ChatGPT Subscription)": {
+          "id": "gpt-5-codex",
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 Minimal (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "minimal",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        },
+        "GPT 5 Low (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        },
+        "GPT 5 Medium (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium"
+          }
+        },
+        "GPT 5 High (ChatGPT Subscription)": {
+          "id": "gpt-5",
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "high"
+          }
+        },
+        "gpt-5-mini": {
+          "options": {
+            "reasoningEffort": "low",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        },
+        "gpt-5-nano": {
+          "options": {
+            "reasoningEffort": "minimal",
+            "reasoningSummary": "auto",
+            "textVerbosity": "low"
+          }
+        }
+      }
+    }
+  }
+}
@@ -0,0 +1,5 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "plugin": ["opencode-openai-codex-auth"],
+  "model": "openai/gpt-5-codex"
+}
@@ -1,264 +0,0 @@
-import { spawn } from "node:child_process";
-import {
-	createAuthorizationFlow,
-	exchangeAuthorizationCode,
-	decodeJWT,
-	refreshAccessToken,
-	REDIRECT_URI,
-} from "./lib/auth.mjs";
-import { getCodexInstructions } from "./lib/codex.mjs";
-import { startLocalOAuthServer } from "./lib/server.mjs";
-import { logRequest } from "./lib/logger.mjs";
-import { transformRequestBody } from "./lib/request-transformer.mjs";
-import { convertSseToJson, ensureContentType } from "./lib/response-handler.mjs";
-
-/**
- * @type {import('@opencode-ai/plugin').Plugin}
- */
-export async function OpenAIAuthPlugin({ client }) {
-	return {
-		auth: {
-			provider: "openai",
-			/**
-			 * @param {() => Promise<any>} getAuth
-			 * @param {any} provider - Provider configuration from opencode.json
-			 */
-			async loader(getAuth, provider) {
-				const auth = await getAuth();
-
-				// Only handle OAuth auth type, skip API key auth
-				if (auth.type !== "oauth") {
-					return {};
-				}
-
-				// Extract accountId from access token JWT
-				const decoded = decodeJWT(auth.access);
-				const accountId =
-					decoded?.["https://api.openai.com/auth"]?.chatgpt_account_id;
-
-				if (!accountId) {
-					console.error(
-						"[openai-codex-plugin] Failed to extract accountId from token",
-					);
-					return {};
-				}
-
-				// Extract user configuration from provider structure
-				// Supports both global options and per-model options following Anthropic pattern
-				const userConfig = {
-					global: provider?.options || {},
-					models: provider?.models || {},
-				};
-
-				// Fetch Codex instructions (cached with ETag)
-				const CODEX_INSTRUCTIONS = await getCodexInstructions();
-
-				// Return options that will be passed to the OpenAI SDK
-				return {
-					apiKey: "chatgpt-oauth", // Dummy key - actual auth handled by fetch
-					baseURL: "https://chatgpt.com/backend-api",
-					/**
-					 * @param {any} input
-					 * @param {any} init
-					 */
-					async fetch(input, init) {
-						// Get current auth and refresh if needed
-						const currentAuth = await getAuth();
-						if (
-							currentAuth.type !== "oauth" ||
-							!currentAuth.access ||
-							currentAuth.expires < Date.now()
-						) {
-							// Token expired or missing, refresh it
-							const refreshResult = await refreshAccessToken(
-								currentAuth.refresh,
-							);
-							if (refreshResult.type === "failed") {
-								console.error(
-									"[openai-codex-plugin] Failed to refresh token, authentication required",
-								);
-								return new Response(
-									JSON.stringify({ error: "Token refresh failed" }),
-									{ status: 401 },
-								);
-							}
-
-							// Update stored credentials
-							await client.auth.set({
-								path: { id: "openai" },
-								body: {
-									type: "oauth",
-									access: refreshResult.access,
-									refresh: refreshResult.refresh,
-									expires: refreshResult.expires,
-								},
-							});
-
-							// Update current auth reference
-							currentAuth.access = refreshResult.access;
-							currentAuth.refresh = refreshResult.refresh;
-							currentAuth.expires = refreshResult.expires;
-						}
-
-						let url = typeof input === "string" ? input : input.url;
-
-						// Rewrite /responses to /codex/responses for Codex backend
-						url = url.replace("/responses", "/codex/responses");
-
-						// Track body for later use
-						let body;
-
-						// Parse and modify request body
-						if (init?.body) {
-							try {
-								body = JSON.parse(init.body);
-								const originalModel = body.model;
-
-								// Log original request
-								logRequest("before-transform", {
-									url,
-									originalModel,
-									model: body.model,
-									hasTools: !!body.tools,
-									hasInput: !!body.input,
-									inputLength: body.input?.length,
-									body,
-								});
-
-								// Transform request body for Codex API with user configuration
-								body = transformRequestBody(body, CODEX_INSTRUCTIONS, userConfig);
-
-								// Log transformed request
-								logRequest("after-transform", {
-									url,
-									originalModel,
-									normalizedModel: body.model,
-									hasTools: !!body.tools,
-									hasInput: !!body.input,
-									inputLength: body.input?.length,
-									reasoning: body.reasoning,
-									textVerbosity: body.text?.verbosity,
-									include: body.include,
-									body,
-								});
-
-								init.body = JSON.stringify(body);
-							} catch (e) {
-								console.error(
-									"[openai-codex-plugin] Error parsing request:",
-									e,
-								);
-							}
-						}
-
-						// Add ChatGPT OAuth headers
-						const headers = new Headers(init?.headers ?? {});
-						headers.delete("x-api-key");
-						headers.set("Authorization", `Bearer ${currentAuth.access}`);
-						headers.set("chatgpt-account-id", accountId);
-						headers.set("OpenAI-Beta", "responses=experimental");
-						headers.set("originator", "codex_cli_rs");
-						headers.set("session_id", crypto.randomUUID());
-
-						const response = await fetch(url, {
-							...init,
-							headers,
-						});
-
-						// Log response status
-						logRequest("response", {
-							status: response.status,
-							ok: response.ok,
-							statusText: response.statusText,
-							headers: Object.fromEntries(response.headers.entries()),
-						});
-
-						// Log errors
-						if (!response.ok) {
-							const text = await response.text();
-							console.error(
-								`[openai-codex-plugin] ${response.status} error:`,
-								text,
-							);
-							logRequest("error-response", {
-								status: response.status,
-								error: text,
-							});
-							// Return a new response with the error text so the SDK can parse it
-							return new Response(text, {
-								status: response.status,
-								statusText: response.statusText,
-								headers: response.headers,
-							});
-						}
-
-						// Ensure response has content-type header
-						const responseHeaders = ensureContentType(response.headers);
-
-						// For non-tool requests (compact/summarize), convert streaming SSE to JSON
-						// generateText() expects a non-streaming JSON response, not SSE
-						if (body?.tools === undefined) {
-							return await convertSseToJson(response, responseHeaders);
-						}
-
-						// For tool requests, return stream as-is (streamText handles SSE)
-						return new Response(response.body, {
-							status: response.status,
-							statusText: response.statusText,
-							headers: responseHeaders,
-						});
-					},
-				};
-			},
-			methods: [
-				{
-					label: "ChatGPT Plus/Pro (Codex Subscription)",
-					type: "oauth",
-					authorize: async () => {
-						const { pkce, state, url } = await createAuthorizationFlow();
-						const serverInfo = await startLocalOAuthServer({ state });
-						const redirectUri = REDIRECT_URI;
-
-						try {
-							const opener =
-								process.platform === "darwin"
-									? "open"
-									: process.platform === "win32"
-										? "start"
-										: "xdg-open";
-							spawn(opener, [url], {
-								stdio: "ignore",
-								shell: process.platform === "win32",
-							});
-						} catch {}
-
-						return {
-							url: url,
-							method: "auto",
-							instructions:
-								"A browser window should open. Complete login to finish.",
-							callback: async () => {
-								const result = await serverInfo.waitForCode(state);
-								serverInfo.close();
-								if (!result) return { type: "failed" };
-								const tokens = await exchangeAuthorizationCode(
-									result.code,
-									pkce.verifier,
-									redirectUri,
-								);
-								return tokens?.type === "success" ? tokens : { type: "failed" };
-							},
-						};
-					},
-				},
-				{
-					provider: "openai",
-					label: "Manually enter API Key",
-					type: "api",
-				},
-			],
-		},
-	};
-}
-
-export default OpenAIAuthPlugin;
@@ -0,0 +1,212 @@
+import type { Plugin, PluginInput } from "@opencode-ai/plugin";
+import type { Auth } from "@opencode-ai/sdk";
+import { createAuthorizationFlow, exchangeAuthorizationCode, decodeJWT, REDIRECT_URI } from "./lib/auth.js";
+import { getCodexInstructions } from "./lib/codex.js";
+import { startLocalOAuthServer } from "./lib/server.js";
+import { logRequest } from "./lib/logger.js";
+import { openBrowserUrl } from "./lib/browser.js";
+import {
+	shouldRefreshToken,
+	refreshAndUpdateToken,
+	extractRequestUrl,
+	rewriteUrlForCodex,
+	transformRequestForCodex,
+	createCodexHeaders,
+	handleErrorResponse,
+	handleSuccessResponse,
+} from "./lib/fetch-helpers.js";
+import type { UserConfig } from "./lib/types.js";
+import {
+	DUMMY_API_KEY,
+	CODEX_BASE_URL,
+	PROVIDER_ID,
+	JWT_CLAIM_PATH,
+	PLUGIN_NAME,
+	ERROR_MESSAGES,
+	LOG_STAGES,
+	AUTH_LABELS,
+} from "./lib/constants.js";
+
+/**
+ * OpenAI Codex OAuth authentication plugin for opencode
+ *
+ * This plugin enables opencode to use OpenAI's Codex backend via ChatGPT Plus/Pro
+ * OAuth authentication, allowing users to leverage their ChatGPT subscription
+ * instead of OpenAI Platform API credits.
+ *
+ * @example
+ * ```json
+ * {
+ *   "plugin": ["opencode-openai-codex-auth"],
+ *   "model": "openai/gpt-5-codex"
+ * }
+ * ```
+ */
+export const OpenAIAuthPlugin: Plugin = async ({ client }: PluginInput) => {
+	return {
+		auth: {
+			provider: PROVIDER_ID,
+			/**
+			 * Loader function that configures OAuth authentication and request handling
+			 *
+			 * This function:
+			 * 1. Validates OAuth authentication
+			 * 2. Extracts ChatGPT account ID from access token
+			 * 3. Loads user configuration from opencode.json
+			 * 4. Fetches Codex system instructions from GitHub (cached)
+			 * 5. Returns SDK configuration with custom fetch implementation
+			 *
+			 * @param getAuth - Function to retrieve current auth state
+			 * @param provider - Provider configuration from opencode.json
+			 * @returns SDK configuration object or empty object for non-OAuth auth
+			 */
+			async loader(getAuth: () => Promise<Auth>, provider: unknown) {
+				const auth = await getAuth();
+
+				// Only handle OAuth auth type, skip API key auth
+				if (auth.type !== "oauth") {
+					return {};
+				}
+
+				// Extract ChatGPT account ID from JWT access token
+				const decoded = decodeJWT(auth.access);
+				const accountId = decoded?.[JWT_CLAIM_PATH]?.chatgpt_account_id;
+
+				if (!accountId) {
+					console.error(`[${PLUGIN_NAME}] ${ERROR_MESSAGES.NO_ACCOUNT_ID}`);
+					return {};
+				}
+
+				// Extract user configuration (global + per-model options)
+				const providerConfig = provider as { options?: Record<string, unknown>; models?: UserConfig["models"] } | undefined;
+				const userConfig: UserConfig = {
+					global: providerConfig?.options || {},
+					models: providerConfig?.models || {},
+				};
+
+				// Fetch Codex system instructions (cached with ETag for efficiency)
+				const CODEX_INSTRUCTIONS = await getCodexInstructions();
+
+				// Return SDK configuration
+				return {
+					apiKey: DUMMY_API_KEY,
+					baseURL: CODEX_BASE_URL,
+					/**
+					 * Custom fetch implementation for Codex API
+					 *
+					 * Handles:
+					 * - Token refresh when expired
+					 * - URL rewriting for Codex backend
+					 * - Request body transformation
+					 * - OAuth header injection
+					 * - SSE to JSON conversion for non-tool requests
+					 * - Error handling and logging
+					 *
+					 * @param input - Request URL or Request object
+					 * @param init - Request options
+					 * @returns Response from Codex API
+					 */
+					async fetch(input: Request | string | URL, init?: RequestInit): Promise<Response> {
+						// Step 1: Check and refresh token if needed
+						const currentAuth = await getAuth();
+						if (shouldRefreshToken(currentAuth)) {
+							const refreshResult = await refreshAndUpdateToken(currentAuth, client);
+							if (!refreshResult.success) {
+								return refreshResult.response;
+							}
+						}
+
+						// Step 2: Extract and rewrite URL for Codex backend
+						const originalUrl = extractRequestUrl(input);
+						const url = rewriteUrlForCodex(originalUrl);
+
+						// Step 3: Transform request body with Codex instructions
+						const transformation = transformRequestForCodex(init, url, CODEX_INSTRUCTIONS, userConfig);
+						const hasTools = transformation?.body.tools !== undefined;
+						const requestInit = transformation?.updatedInit ?? init;
+
+						// Step 4: Create headers with OAuth and ChatGPT account info
+						const accessToken = currentAuth.type === "oauth" ? currentAuth.access : "";
+						const headers = createCodexHeaders(requestInit, accountId, accessToken);
+
+						// Step 5: Make request to Codex API
+						const response = await fetch(url, {
+							...requestInit,
+							headers,
+						});
+
+						// Step 6: Log response
+						logRequest(LOG_STAGES.RESPONSE, {
+							status: response.status,
+							ok: response.ok,
+							statusText: response.statusText,
+							headers: Object.fromEntries(response.headers.entries()),
+						});
+
+						// Step 7: Handle error or success response
+						if (!response.ok) {
+							return await handleErrorResponse(response);
+						}
+
+						return await handleSuccessResponse(response, hasTools);
+					},
+				};
+			},
+			methods: [
+				{
+					label: AUTH_LABELS.OAUTH,
+					type: "oauth" as const,
+					/**
+					 * OAuth authorization flow
+					 *
+					 * Steps:
+					 * 1. Generate PKCE challenge and state for security
+					 * 2. Start local OAuth callback server on port 1455
+					 * 3. Open browser to OpenAI authorization page
+					 * 4. Wait for user to complete login
+					 * 5. Exchange authorization code for tokens
+					 *
+					 * @returns Authorization flow configuration
+					 */
+					authorize: async () => {
+						const { pkce, state, url } = await createAuthorizationFlow();
+						const serverInfo = await startLocalOAuthServer({ state });
+
+						// Attempt to open browser automatically
+						openBrowserUrl(url);
+
+						return {
+							url,
+							method: "auto" as const,
+							instructions: AUTH_LABELS.INSTRUCTIONS,
+							callback: async () => {
+								const result = await serverInfo.waitForCode(state);
+								serverInfo.close();
+
+								if (!result) {
+									return { type: "failed" as const };
+								}
+
+								const tokens = await exchangeAuthorizationCode(
+									result.code,
+									pkce.verifier,
+									REDIRECT_URI,
+								);
+
+								return tokens?.type === "success"
+									? tokens
+									: { type: "failed" as const };
+							},
+						};
+					},
+				},
+				{
+					label: AUTH_LABELS.API_KEY,
+					type: "api" as const,
+				},
+			],
+		},
+	};
+};
+
+export default OpenAIAuthPlugin;
@@ -1,5 +1,6 @@
 import { generatePKCE } from "@openauthjs/openauth/pkce";
 import { randomBytes } from "node:crypto";
+import type { PKCEPair, AuthorizationFlow, TokenResult, ParsedAuthInput, JWTPayload } from "./types.js";

 // OAuth constants (from openai/codex)
 export const CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann";
@@ -10,18 +11,18 @@ export const SCOPE = "openid profile email offline_access";

 /**
 * Generate a random state value for OAuth flow
- * @returns {string} Random hex string
+ * @returns Random hex string
 */
-export function createState() {
+export function createState(): string {
 	return randomBytes(16).toString("hex");
 }

 /**
 * Parse authorization code and state from user input
- * @param {string} input - User input (URL, code#state, or just code)
- * @returns {{code?: string, state?: string}} Parsed authorization data
+ * @param input - User input (URL, code#state, or just code)
+ * @returns Parsed authorization data
 */
-export function parseAuthorizationInput(input) {
+export function parseAuthorizationInput(input: string): ParsedAuthInput {
 	const value = (input || "").trim();
 	if (!value) return {};

@@ -49,16 +50,16 @@ export function parseAuthorizationInput(input) {

 /**
 * Exchange authorization code for access and refresh tokens
- * @param {string} code - Authorization code from OAuth flow
- * @param {string} verifier - PKCE verifier
- * @param {string} [redirectUri] - OAuth redirect URI
- * @returns {Promise<{type: "success", access: string, refresh: string, expires: number} | {type: "failed"}>}
+ * @param code - Authorization code from OAuth flow
+ * @param verifier - PKCE verifier
+ * @param redirectUri - OAuth redirect URI
+ * @returns Token result
 */
 export async function exchangeAuthorizationCode(
-	code,
-	verifier,
-	redirectUri = REDIRECT_URI,
-) {
+	code: string,
+	verifier: string,
+	redirectUri: string = REDIRECT_URI,
+): Promise<TokenResult> {
 	const res = await fetch(TOKEN_URL, {
 		method: "POST",
 		headers: { "Content-Type": "application/x-www-form-urlencoded" },
@@ -75,7 +76,11 @@ export async function exchangeAuthorizationCode(
 		console.error("[openai-codex-plugin] code->token failed:", res.status, text);
 		return { type: "failed" };
 	}
-	const json = await res.json();
+	const json = (await res.json()) as {
+		access_token?: string;
+		refresh_token?: string;
+		expires_in?: number;
+	};
 	if (
 		!json?.access_token ||
 		!json?.refresh_token ||
@@ -94,16 +99,16 @@ export async function exchangeAuthorizationCode(

 /**
 * Decode a JWT token to extract payload
- * @param {string} token - JWT token to decode
- * @returns {any} Decoded payload or null if invalid
+ * @param token - JWT token to decode
+ * @returns Decoded payload or null if invalid
 */
-export function decodeJWT(token) {
+export function decodeJWT(token: string): JWTPayload | null {
 	try {
 		const parts = token.split(".");
 		if (parts.length !== 3) return null;
 		const payload = parts[1];
 		const decoded = Buffer.from(payload, "base64").toString("utf-8");
-		return JSON.parse(decoded);
+		return JSON.parse(decoded) as JWTPayload;
 	} catch {
 		return null;
 	}
@@ -111,10 +116,10 @@ export function decodeJWT(token) {

 /**
 * Refresh access token using refresh token
- * @param {string} refreshToken - Refresh token
- * @returns {Promise<{type: "success", access: string, refresh: string, expires: number} | {type: "failed"}>}
+ * @param refreshToken - Refresh token
+ * @returns Token result
 */
-export async function refreshAccessToken(refreshToken) {
+export async function refreshAccessToken(refreshToken: string): Promise<TokenResult> {
 	try {
 		const response = await fetch(TOKEN_URL, {
 			method: "POST",
@@ -136,7 +141,11 @@ export async function refreshAccessToken(refreshToken) {
 			return { type: "failed" };
 		}

-		const json = await response.json();
+		const json = (await response.json()) as {
+			access_token?: string;
+			refresh_token?: string;
+			expires_in?: number;
+		};
 		if (
 			!json?.access_token ||
 			!json?.refresh_token ||
@@ -156,17 +165,18 @@ export async function refreshAccessToken(refreshToken) {
 			expires: Date.now() + json.expires_in * 1000,
 		};
 	} catch (error) {
-		console.error("[openai-codex-plugin] Token refresh error:", error);
+		const err = error as Error;
+		console.error("[openai-codex-plugin] Token refresh error:", err);
 		return { type: "failed" };
 	}
 }

 /**
 * Create OAuth authorization flow
- * @returns {Promise<{pkce: any, state: string, url: string}>}
+ * @returns Authorization flow details
 */
-export async function createAuthorizationFlow() {
-	const pkce = await generatePKCE();
+export async function createAuthorizationFlow(): Promise<AuthorizationFlow> {
+	const pkce = (await generatePKCE()) as PKCEPair;
 	const state = createState();

 	const url = new URL(AUTHORIZE_URL);
@@ -0,0 +1,35 @@
+/**
+ * Browser utilities for OAuth flow
+ * Handles platform-specific browser opening
+ */
+
+import { spawn } from "node:child_process";
+import { PLATFORM_OPENERS } from "./constants.js";
+
+/**
+ * Gets the platform-specific command to open a URL in the default browser
+ * @returns Browser opener command for the current platform
+ */
+export function getBrowserOpener(): string {
+	const platform = process.platform;
+	if (platform === "darwin") return PLATFORM_OPENERS.darwin;
+	if (platform === "win32") return PLATFORM_OPENERS.win32;
+	return PLATFORM_OPENERS.linux;
+}
+
+/**
+ * Opens a URL in the default browser
+ * Silently fails if browser cannot be opened (user can copy URL manually)
+ * @param url - URL to open
+ */
+export function openBrowserUrl(url: string): void {
+	try {
+		const opener = getBrowserOpener();
+		spawn(opener, [url], {
+			stdio: "ignore",
+			shell: process.platform === "win32",
+		});
+	} catch (error) {
+		// Silently fail - user can manually open the URL from instructions
+	}
+}
@@ -2,6 +2,7 @@ import { readFileSync, writeFileSync, existsSync, mkdirSync } from "node:fs";
 import { join, dirname } from "node:path";
 import { fileURLToPath } from "node:url";
 import { homedir } from "node:os";
+import type { GitHubRelease, CacheMetadata } from "./types.js";

 // Codex instructions constants
 const GITHUB_API_RELEASES = "https://api.github.com/repos/openai/codex/releases/latest";
@@ -14,12 +15,12 @@ const __dirname = dirname(__filename);

 /**
 * Get the latest release tag from GitHub
- * @returns {Promise<string>} Release tag name (e.g., "rust-v0.43.0")
+ * @returns Release tag name (e.g., "rust-v0.43.0")
 */
-async function getLatestReleaseTag() {
+async function getLatestReleaseTag(): Promise<string> {
 	const response = await fetch(GITHUB_API_RELEASES);
 	if (!response.ok) throw new Error(`Failed to fetch latest release: ${response.status}`);
-	const data = await response.json();
+	const data = (await response.json()) as GitHubRelease;
 	return data.tag_name;
 }

@@ -27,19 +28,19 @@ async function getLatestReleaseTag() {
 * Fetch Codex instructions from GitHub with ETag-based caching
 * Uses HTTP conditional requests to efficiently check for updates
 * Always fetches from the latest release tag, not main branch
- * @returns {Promise<string>} Codex instructions
+ * @returns Codex instructions
 */
-export async function getCodexInstructions() {
+export async function getCodexInstructions(): Promise<string> {
 	try {
 		// Get the latest release tag
 		const latestTag = await getLatestReleaseTag();
 		const CODEX_INSTRUCTIONS_URL = `https://raw.githubusercontent.com/openai/codex/${latestTag}/codex-rs/core/gpt_5_codex_prompt.md`;

 		// Load cached metadata (includes ETag and tag)
-		let cachedETag = null;
-		let cachedTag = null;
+		let cachedETag: string | null = null;
+		let cachedTag: string | null = null;
 		if (existsSync(CACHE_METADATA_FILE)) {
-			const metadata = JSON.parse(readFileSync(CACHE_METADATA_FILE, "utf8"));
+			const metadata = JSON.parse(readFileSync(CACHE_METADATA_FILE, "utf8")) as CacheMetadata;
 			cachedETag = metadata.etag;
 			cachedTag = metadata.tag;
 		}
@@ -50,7 +51,7 @@ export async function getCodexInstructions() {
 		}

 		// Make conditional request with If-None-Match header
-		const headers = {};
+		const headers: Record<string, string> = {};
 		if (cachedETag) {
 			headers["If-None-Match"] = cachedETag;
 		}
@@ -84,7 +85,7 @@ export async function getCodexInstructions() {
 					tag: latestTag,
 					lastChecked: Date.now(),
 					url: CODEX_INSTRUCTIONS_URL,
-				}),
+				} satisfies CacheMetadata),
 				"utf8",
 			);

@@ -93,9 +94,10 @@ export async function getCodexInstructions() {

 		throw new Error(`HTTP ${response.status}`);
 	} catch (error) {
+		const err = error as Error;
 		console.error(
 			"[openai-codex-plugin] Failed to fetch instructions from GitHub:",
-			error.message,
+			err.message,
 		);

 		// Try to use cached version even if stale
@@ -0,0 +1,74 @@
+/**
+ * Constants used throughout the plugin
+ * Centralized for easy maintenance and configuration
+ */
+
+/** Plugin identifier for logging and error messages */
+export const PLUGIN_NAME = "openai-codex-plugin";
+
+/** Base URL for ChatGPT backend API */
+export const CODEX_BASE_URL = "https://chatgpt.com/backend-api";
+
+/** Dummy API key used for OpenAI SDK (actual auth via OAuth) */
+export const DUMMY_API_KEY = "chatgpt-oauth";
+
+/** Provider ID for opencode configuration */
+export const PROVIDER_ID = "openai";
+
+/** HTTP Status Codes */
+export const HTTP_STATUS = {
+	OK: 200,
+	UNAUTHORIZED: 401,
+} as const;
+
+/** OpenAI-specific headers */
+export const OPENAI_HEADERS = {
+	BETA: "OpenAI-Beta",
+	ACCOUNT_ID: "chatgpt-account-id",
+	ORIGINATOR: "originator",
+	SESSION_ID: "session_id",
+} as const;
+
+/** OpenAI-specific header values */
+export const OPENAI_HEADER_VALUES = {
+	BETA_RESPONSES: "responses=experimental",
+	ORIGINATOR_CODEX: "codex_cli_rs",
+} as const;
+
+/** URL path segments */
+export const URL_PATHS = {
+	RESPONSES: "/responses",
+	CODEX_RESPONSES: "/codex/responses",
+} as const;
+
+/** JWT claim path for ChatGPT account ID */
+export const JWT_CLAIM_PATH = "https://api.openai.com/auth" as const;
+
+/** Error messages */
+export const ERROR_MESSAGES = {
+	NO_ACCOUNT_ID: "Failed to extract accountId from token",
+	TOKEN_REFRESH_FAILED: "Failed to refresh token, authentication required",
+	REQUEST_PARSE_ERROR: "Error parsing request",
+} as const;
+
+/** Log stages for request logging */
+export const LOG_STAGES = {
+	BEFORE_TRANSFORM: "before-transform",
+	AFTER_TRANSFORM: "after-transform",
+	RESPONSE: "response",
+	ERROR_RESPONSE: "error-response",
+} as const;
+
+/** Platform-specific browser opener commands */
+export const PLATFORM_OPENERS = {
+	darwin: "open",
+	win32: "start",
+	linux: "xdg-open",
+} as const;
+
+/** OAuth authorization labels */
+export const AUTH_LABELS = {
+	OAUTH: "ChatGPT Plus/Pro (Codex Subscription)",
+	API_KEY: "Manually enter API Key",
+	INSTRUCTIONS: "A browser window should open. Complete login to finish.",
+} as const;
@@ -0,0 +1,227 @@
+/**
+ * Helper functions for the custom fetch implementation
+ * These functions break down the complex fetch logic into manageable, testable units
+ */
+
+import type { Auth } from "@opencode-ai/sdk";
+import type { OpencodeClient } from "@opencode-ai/sdk";
+import { refreshAccessToken } from "./auth.js";
+import { logRequest } from "./logger.js";
+import { transformRequestBody } from "./request-transformer.js";
+import { convertSseToJson, ensureContentType } from "./response-handler.js";
+import type { UserConfig, RequestBody } from "./types.js";
+import {
+	PLUGIN_NAME,
+	HTTP_STATUS,
+	OPENAI_HEADERS,
+	OPENAI_HEADER_VALUES,
+	URL_PATHS,
+	ERROR_MESSAGES,
+	LOG_STAGES,
+} from "./constants.js";
+
+/**
+ * Determines if the current auth token needs to be refreshed
+ * @param auth - Current authentication state
+ * @returns True if token is expired or invalid
+ */
+export function shouldRefreshToken(auth: Auth): boolean {
+	return (
+		auth.type !== "oauth" ||
+		!auth.access ||
+		auth.expires < Date.now()
+	);
+}
+
+/**
+ * Refreshes the OAuth token and updates stored credentials
+ * @param currentAuth - Current auth state
+ * @param client - Opencode client for updating stored credentials
+ * @returns Updated auth or error response
+ */
+export async function refreshAndUpdateToken(
+	currentAuth: Auth,
+	client: OpencodeClient
+): Promise<{ success: true; auth: Auth } | { success: false; response: Response }> {
+	const refreshToken = currentAuth.type === "oauth" ? currentAuth.refresh : "";
+	const refreshResult = await refreshAccessToken(refreshToken);
+
+	if (refreshResult.type === "failed") {
+		console.error(`[${PLUGIN_NAME}] ${ERROR_MESSAGES.TOKEN_REFRESH_FAILED}`);
+		return {
+			success: false,
+			response: new Response(
+				JSON.stringify({ error: "Token refresh failed" }),
+				{ status: HTTP_STATUS.UNAUTHORIZED }
+			),
+		};
+	}
+
+	// Update stored credentials
+	await client.auth.set({
+		path: { id: "openai" },
+		body: {
+			type: "oauth",
+			access: refreshResult.access,
+			refresh: refreshResult.refresh,
+			expires: refreshResult.expires,
+		},
+	});
+
+	// Update current auth reference if it's OAuth type
+	if (currentAuth.type === "oauth") {
+		currentAuth.access = refreshResult.access;
+		currentAuth.refresh = refreshResult.refresh;
+		currentAuth.expires = refreshResult.expires;
+	}
+
+	return { success: true, auth: currentAuth };
+}
+
+/**
+ * Extracts URL string from various request input types
+ * @param input - Request input (string, URL, or Request object)
+ * @returns URL string
+ */
+export function extractRequestUrl(input: Request | string | URL): string {
+	if (typeof input === "string") return input;
+	if (input instanceof URL) return input.toString();
+	return input.url;
+}
+
+/**
+ * Rewrites OpenAI API URLs to Codex backend URLs
+ * @param url - Original URL
+ * @returns Rewritten URL for Codex backend
+ */
+export function rewriteUrlForCodex(url: string): string {
+	return url.replace(URL_PATHS.RESPONSES, URL_PATHS.CODEX_RESPONSES);
+}
+
+/**
+ * Transforms request body and logs the transformation
+ * @param init - Request init options
+ * @param url - Request URL
+ * @param codexInstructions - Codex system instructions
+ * @param userConfig - User configuration
+ * @returns Transformed body and updated init, or undefined if no body
+ */
+export function transformRequestForCodex(
+	init: RequestInit | undefined,
+	url: string,
+	codexInstructions: string,
+	userConfig: UserConfig
+): { body: RequestBody; updatedInit: RequestInit } | undefined {
+	if (!init?.body) return undefined;
+
+	try {
+		const body = JSON.parse(init.body as string) as RequestBody;
+		const originalModel = body.model;
+
+		// Log original request
+		logRequest(LOG_STAGES.BEFORE_TRANSFORM, {
+			url,
+			originalModel,
+			model: body.model,
+			hasTools: !!body.tools,
+			hasInput: !!body.input,
+			inputLength: body.input?.length,
+			body: body as unknown as Record<string, unknown>,
+		});
+
+		// Transform request body
+		const transformedBody = transformRequestBody(body, codexInstructions, userConfig);
+
+		// Log transformed request
+		logRequest(LOG_STAGES.AFTER_TRANSFORM, {
+			url,
+			originalModel,
+			normalizedModel: transformedBody.model,
+			hasTools: !!transformedBody.tools,
+			hasInput: !!transformedBody.input,
+			inputLength: transformedBody.input?.length,
+			reasoning: transformedBody.reasoning as unknown,
+			textVerbosity: transformedBody.text?.verbosity,
+			include: transformedBody.include,
+			body: transformedBody as unknown as Record<string, unknown>,
+		});
+
+		return {
+			body: transformedBody,
+			updatedInit: { ...init, body: JSON.stringify(transformedBody) },
+		};
+	} catch (e) {
+		console.error(`[${PLUGIN_NAME}] ${ERROR_MESSAGES.REQUEST_PARSE_ERROR}:`, e);
+		return undefined;
+	}
+}
+
+/**
+ * Creates headers for Codex API requests
+ * @param init - Request init options
+ * @param accountId - ChatGPT account ID
+ * @param accessToken - OAuth access token
+ * @returns Headers object with all required Codex headers
+ */
+export function createCodexHeaders(
+	init: RequestInit | undefined,
+	accountId: string,
+	accessToken: string
+): Headers {
+	const headers = new Headers(init?.headers ?? {});
+	headers.delete("x-api-key"); // Remove any existing API key
+	headers.set("Authorization", `Bearer ${accessToken}`);
+	headers.set(OPENAI_HEADERS.ACCOUNT_ID, accountId);
+	headers.set(OPENAI_HEADERS.BETA, OPENAI_HEADER_VALUES.BETA_RESPONSES);
+	headers.set(OPENAI_HEADERS.ORIGINATOR, OPENAI_HEADER_VALUES.ORIGINATOR_CODEX);
+	headers.set(OPENAI_HEADERS.SESSION_ID, crypto.randomUUID());
+	return headers;
+}
+
+/**
+ * Handles error responses from the Codex API
+ * @param response - Error response from API
+ * @returns Response with error details
+ */
+export async function handleErrorResponse(response: Response): Promise<Response> {
+	const text = await response.text();
+	console.error(`[${PLUGIN_NAME}] ${response.status} error:`, text);
+
+	logRequest(LOG_STAGES.ERROR_RESPONSE, {
+		status: response.status,
+		error: text,
+	});
+
+	return new Response(text, {
+		status: response.status,
+		statusText: response.statusText,
+		headers: response.headers,
+	});
+}
+
+/**
+ * Handles successful responses from the Codex API
+ * Converts SSE to JSON for non-tool requests
+ * @param response - Success response from API
+ * @param hasTools - Whether the request included tools
+ * @returns Processed response (SSE→JSON for non-tool, stream for tool requests)
+ */
+export async function handleSuccessResponse(
+	response: Response,
+	hasTools: boolean
+): Promise<Response> {
+	const responseHeaders = ensureContentType(response.headers);
+
+	// For non-tool requests (compact/summarize), convert streaming SSE to JSON
+	// generateText() expects a non-streaming JSON response, not SSE
+	if (!hasTools) {
+		return await convertSseToJson(response, responseHeaders);
+	}
+
+	// For tool requests, return stream as-is (streamText handles SSE)
+	return new Response(response.body, {
+		status: response.status,
+		statusText: response.statusText,
+		headers: responseHeaders,
+	});
+}
@@ -3,7 +3,7 @@ import { join } from "node:path";
 import { homedir } from "node:os";

 // Logging configuration
-const LOGGING_ENABLED = process.env.ENABLE_PLUGIN_REQUEST_LOGGING === "1";
+export const LOGGING_ENABLED = process.env.ENABLE_PLUGIN_REQUEST_LOGGING === "1";
 const LOG_DIR = join(homedir(), ".opencode", "logs", "codex-plugin");

 // Log startup message about logging state
@@ -15,10 +15,10 @@ let requestCounter = 0;

 /**
 * Log request data to file (only when LOGGING_ENABLED is true)
- * @param {string} stage - The stage of the request (e.g., "before-transform", "after-transform")
- * @param {object} data - The data to log
+ * @param stage - The stage of the request (e.g., "before-transform", "after-transform")
+ * @param data - The data to log
 */
-export function logRequest(stage, data) {
+export function logRequest(stage: string, data: Record<string, unknown>): void {
 	// Only log if explicitly enabled via environment variable
 	if (!LOGGING_ENABLED) return;

@@ -48,8 +48,7 @@ export function logRequest(stage, data) {
 		);
 		console.log(`[openai-codex-plugin] Logged ${stage} to ${filename}`);
 	} catch (e) {
-		console.error("[openai-codex-plugin] Failed to write log:", e.message);
+		const error = e as Error;
+		console.error("[openai-codex-plugin] Failed to write log:", error.message);
 	}
 }
-
-export { LOGGING_ENABLED };
@@ -0,0 +1,712 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>OpenCode - Authentication Successful</title>
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:ital,wght@0,100;0,200;0,300;0,400;0,500;0,600;0,700;1,100;1,200;1,300;1,400;1,500;1,600;1,700&display=swap" rel="stylesheet">
+    <style>
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+        }
+
+        body {
+            font-family: "IBM Plex Mono", monospace;
+            font-weight: 400;
+            background: #0a0a0a;
+            color: #B7B1B1;
+            overflow: hidden;
+            height: 100vh;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            position: relative;
+        }
+
+        /* Matrix rain background */
+        .matrix {
+            position: fixed;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            z-index: 1;
+            opacity: 0.35;
+        }
+
+        /* Scan lines effect */
+        .scanline {
+            position: fixed;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            background: linear-gradient(
+                transparent 50%,
+                rgba(0, 0, 0, 0.1) 50%
+            );
+            background-size: 100% 4px;
+            z-index: 2;
+            pointer-events: none;
+            animation: scan 8s linear infinite;
+        }
+
+        @keyframes scan {
+            0% { transform: translateY(0); }
+            100% { transform: translateY(4px); }
+        }
+
+        /* Vignette effect */
+        .vignette {
+            position: fixed;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            box-shadow: inset 0 0 200px rgba(0, 0, 0, 0.8);
+            z-index: 2;
+            pointer-events: none;
+        }
+
+        .container {
+            width: 90%;
+            max-width: 650px;
+            text-align: center;
+            z-index: 10;
+            position: relative;
+            animation: fadeIn 0.8s ease-out;
+        }
+
+        @keyframes fadeIn {
+            from {
+                opacity: 0;
+                transform: scale(0.95);
+            }
+            to {
+                opacity: 1;
+                transform: scale(1);
+            }
+        }
+
+        .logo {
+            margin-bottom: 60px;
+            opacity: 0;
+            animation: logoEntrance 1.2s cubic-bezier(0.34, 1.56, 0.64, 1) 0.3s forwards;
+            position: relative;
+        }
+
+        @keyframes logoEntrance {
+            0% {
+                opacity: 0;
+                transform: translateY(-50px) rotateX(90deg);
+            }
+            100% {
+                opacity: 1;
+                transform: translateY(0) rotateX(0);
+            }
+        }
+
+        .logo svg {
+            width: 300px;
+            height: auto;
+            filter: drop-shadow(0 0 30px rgba(241, 236, 236, 0.3));
+            animation: pulse 3s ease-in-out infinite;
+        }
+
+        @keyframes pulse {
+            0%, 100% {
+                filter: drop-shadow(0 0 30px rgba(241, 236, 236, 0.3));
+            }
+            50% {
+                filter: drop-shadow(0 0 50px rgba(241, 236, 236, 0.5));
+            }
+        }
+
+        /* Glowing orb behind logo */
+        .logo::before {
+            content: '';
+            position: absolute;
+            top: 50%;
+            left: 50%;
+            transform: translate(-50%, -50%);
+            width: 200px;
+            height: 200px;
+            background: radial-gradient(circle, rgba(241, 236, 236, 0.1) 0%, transparent 70%);
+            border-radius: 50%;
+            animation: orbPulse 4s ease-in-out infinite;
+            z-index: -1;
+        }
+
+        @keyframes orbPulse {
+            0%, 100% {
+                transform: translate(-50%, -50%) scale(1);
+                opacity: 0.3;
+            }
+            50% {
+                transform: translate(-50%, -50%) scale(1.2);
+                opacity: 0.6;
+            }
+        }
+
+        .terminal-window {
+            background: rgba(26, 26, 26, 0.95);
+            backdrop-filter: blur(10px);
+            -webkit-backdrop-filter: blur(10px);
+            border: 1px solid rgba(75, 70, 70, 0.3);
+            border-radius: 12px;
+            margin: 30px 0;
+            opacity: 0;
+            animation: boxEntrance 0.8s cubic-bezier(0.34, 1.56, 0.64, 1) 0.6s forwards;
+            position: relative;
+            overflow: hidden;
+            box-shadow:
+                0 0 60px rgba(0, 0, 0, 0.5),
+                inset 0 1px 0 rgba(255, 255, 255, 0.05);
+        }
+
+        .terminal-header {
+            background: rgba(15, 15, 15, 0.9);
+            padding: 14px 18px;
+            display: flex;
+            align-items: center;
+            gap: 8px;
+            border-bottom: 1px solid rgba(75, 70, 70, 0.3);
+            position: relative;
+        }
+
+        .terminal-button {
+            width: 12px;
+            height: 12px;
+            border-radius: 50%;
+            transition: transform 0.2s;
+        }
+
+        .terminal-button:hover {
+            transform: scale(1.2);
+        }
+
+        .terminal-button.red {
+            background: #ff5f56;
+            box-shadow: 0 0 10px rgba(255, 95, 86, 0.3);
+            animation: pulse 2s infinite;
+        }
+
+        .terminal-button.yellow {
+            background: #ffbd2e;
+            box-shadow: 0 0 10px rgba(255, 189, 46, 0.3);
+            animation: pulse 2s infinite 0.3s;
+        }
+
+        .terminal-button.green {
+            background: #27c93f;
+            box-shadow: 0 0 10px rgba(39, 201, 63, 0.3);
+            animation: pulse 2s infinite 0.6s;
+        }
+
+        @keyframes pulse {
+            0%, 100% { opacity: 1; }
+            50% { opacity: 0.6; }
+        }
+
+        .terminal-title {
+            flex: 1;
+            text-align: center;
+            font-size: 12px;
+            color: #6a6565;
+            opacity: 0.8;
+            letter-spacing: 0.5px;
+        }
+
+        .status-box {
+            padding: 50px 40px;
+            position: relative;
+        }
+
+        @keyframes boxEntrance {
+            from {
+                opacity: 0;
+                transform: translateY(30px);
+            }
+            to {
+                opacity: 1;
+                transform: translateY(0);
+            }
+        }
+
+        /* Animated border gradient */
+        .terminal-window::before {
+            content: '';
+            position: absolute;
+            top: -2px;
+            left: -2px;
+            right: -2px;
+            bottom: -2px;
+            background: linear-gradient(
+                45deg,
+                transparent,
+                rgba(241, 236, 236, 0.1),
+                transparent,
+                rgba(241, 236, 236, 0.1)
+            );
+            background-size: 400% 400%;
+            border-radius: 12px;
+            z-index: -1;
+            animation: gradientShift 8s ease infinite;
+        }
+
+        @keyframes gradientShift {
+            0%, 100% { background-position: 0% 50%; }
+            50% { background-position: 100% 50%; }
+        }
+
+        .checkmark-container {
+            width: 100px;
+            height: 100px;
+            margin: 0 auto 40px;
+            position: relative;
+        }
+
+        .checkmark-circle {
+            width: 100px;
+            height: 100px;
+            border-radius: 50%;
+            border: 4px solid transparent;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            position: relative;
+            animation: circleAppear 0.6s ease-out 1s both;
+        }
+
+        @keyframes circleAppear {
+            from {
+                transform: scale(0) rotate(-180deg);
+                border-color: transparent;
+            }
+            to {
+                transform: scale(1) rotate(0);
+                border-color: #4B4646;
+            }
+        }
+
+        /* Spinning rings around checkmark */
+        .checkmark-circle::before,
+        .checkmark-circle::after {
+            content: '';
+            position: absolute;
+            width: 120%;
+            height: 120%;
+            border: 2px solid transparent;
+            border-top-color: rgba(241, 236, 236, 0.2);
+            border-radius: 50%;
+            animation: rotate 3s linear infinite;
+        }
+
+        .checkmark-circle::after {
+            width: 140%;
+            height: 140%;
+            border-top-color: rgba(183, 177, 177, 0.1);
+            animation: rotate 4s linear infinite reverse;
+        }
+
+        @keyframes rotate {
+            to { transform: rotate(360deg); }
+        }
+
+        .checkmark {
+            width: 35px;
+            height: 18px;
+            border-left: 5px solid #F1ECEC;
+            border-bottom: 5px solid #F1ECEC;
+            transform: rotate(-45deg) scale(0);
+            animation: checkmarkDraw 0.5s cubic-bezier(0.65, 0, 0.45, 1) 1.3s forwards;
+            filter: drop-shadow(0 0 10px rgba(241, 236, 236, 0.5));
+        }
+
+        @keyframes checkmarkDraw {
+            0% {
+                transform: rotate(-45deg) scale(0);
+            }
+            50% {
+                transform: rotate(-45deg) scale(1.1);
+            }
+            100% {
+                transform: rotate(-45deg) scale(1);
+            }
+        }
+
+        .title {
+            font-size: 32px;
+            color: #00ff41;
+            margin-bottom: 20px;
+            font-weight: 500;
+            letter-spacing: 1px;
+            text-shadow: 0 0 20px rgba(0, 255, 65, 0.5);
+            opacity: 0;
+            animation: fadeInUp 0.6s ease-out 1.8s forwards;
+        }
+
+        @keyframes fadeInUp {
+            from {
+                opacity: 0;
+                transform: translateY(20px);
+            }
+            to {
+                opacity: 1;
+                transform: translateY(0);
+            }
+        }
+
+        .message {
+            font-size: 16px;
+            color: #9a9595;
+            line-height: 1.8;
+            margin-bottom: 30px;
+            opacity: 0;
+            animation: fadeInUp 0.6s ease-out 2s forwards;
+        }
+
+        .terminal-output {
+            background: rgba(10, 10, 10, 0.6);
+            border: 1px solid rgba(75, 70, 70, 0.2);
+            border-radius: 8px;
+            padding: 25px;
+            text-align: left;
+            font-size: 14px;
+            line-height: 2;
+            margin-top: 25px;
+            position: relative;
+            overflow: hidden;
+        }
+
+        /* Terminal typing effect */
+        .terminal-output::before {
+            content: '';
+            position: absolute;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 2px;
+            background: linear-gradient(90deg, transparent, #4B4646, transparent);
+            animation: scanProgress 2s ease-out 2.2s forwards;
+        }
+
+        @keyframes scanProgress {
+            from {
+                transform: translateX(-100%);
+            }
+            to {
+                transform: translateX(100%);
+            }
+        }
+
+        .terminal-line {
+            opacity: 0;
+            transform: translateX(-20px);
+            animation: terminalType 0.4s ease-out forwards;
+            display: flex;
+            align-items: center;
+            gap: 12px;
+        }
+
+        .terminal-line:nth-child(1) { animation-delay: 2.2s; }
+        .terminal-line:nth-child(2) { animation-delay: 2.4s; }
+        .terminal-line:nth-child(3) { animation-delay: 2.6s; }
+        .terminal-line:nth-child(4) { animation-delay: 2.8s; }
+
+        @keyframes terminalType {
+            to {
+                opacity: 1;
+                transform: translateX(0);
+            }
+        }
+
+        .prompt {
+            color: #6a6565;
+            font-weight: 500;
+        }
+
+        .success {
+            color: #B7B1B1;
+        }
+
+        .terminal-line::after {
+            content: '';
+            flex: 1;
+            height: 1px;
+            background: linear-gradient(90deg, rgba(75, 70, 70, 0.3), transparent);
+        }
+
+        .footer {
+            margin-top: 40px;
+            font-size: 14px;
+            color: #6a6565;
+            opacity: 0;
+            animation: fadeInUp 0.6s ease-out 3.2s forwards;
+            text-shadow: 0 0 10px rgba(106, 101, 101, 0.5);
+        }
+
+        .cursor {
+            display: inline-block;
+            width: 2px;
+            height: 16px;
+            background: #8a8585;
+            margin-left: 6px;
+            animation: blink 1s infinite;
+            box-shadow: 0 0 8px #8a8585;
+        }
+
+        @keyframes blink {
+            0%, 49% { opacity: 1; }
+            50%, 100% { opacity: 0; }
+        }
+
+        /* Floating particles */
+        .particle {
+            position: fixed;
+            width: 2px;
+            height: 2px;
+            background: rgba(183, 177, 177, 0.3);
+            border-radius: 50%;
+            pointer-events: none;
+            z-index: 5;
+            animation: float 8s linear infinite;
+        }
+
+        @keyframes float {
+            0% {
+                transform: translateY(100vh) translateX(0) scale(0);
+                opacity: 0;
+            }
+            10% {
+                opacity: 1;
+                transform: translateY(90vh) translateX(10px) scale(1);
+            }
+            90% {
+                opacity: 1;
+            }
+            100% {
+                transform: translateY(-10vh) translateX(-10px) scale(0);
+                opacity: 0;
+            }
+        }
+
+        /* Success glow effect */
+        @keyframes successGlow {
+            0%, 100% {
+                box-shadow:
+                    0 0 60px rgba(0, 0, 0, 0.5),
+                    inset 0 1px 0 rgba(255, 255, 255, 0.05);
+            }
+            50% {
+                box-shadow:
+                    0 0 80px rgba(241, 236, 236, 0.1),
+                    inset 0 1px 0 rgba(255, 255, 255, 0.05);
+            }
+        }
+
+        .terminal-window {
+            animation:
+                boxEntrance 0.8s cubic-bezier(0.34, 1.56, 0.64, 1) 0.6s forwards,
+                successGlow 4s ease-in-out 2s infinite;
+        }
+    </style>
+</head>
+<body>
+    <canvas class="matrix" id="matrix"></canvas>
+    <div class="scanline"></div>
+    <div class="vignette"></div>
+
+    <div class="container">
+        <div class="logo">
+            <svg width="300" height="54" viewBox="0 0 234 42" fill="none" xmlns="http://www.w3.org/2000/svg">
+                <path d="M18 30H6V18H18V30Z" fill="#4B4646"/>
+                <path d="M18 12H6V30H18V12ZM24 36H0V6H24V36Z" fill="#B7B1B1"/>
+                <path d="M48 30H36V18H48V30Z" fill="#4B4646"/>
+                <path d="M36 30H48V12H36V30ZM54 36H36V42H30V6H54V36Z" fill="#B7B1B1"/>
+                <path d="M84 24V30H66V24H84Z" fill="#4B4646"/>
+                <path d="M84 24H66V30H84V36H60V6H84V24ZM66 18H78V12H66V18Z" fill="#B7B1B1"/>
+                <path d="M108 36H96V18H108V36Z" fill="#4B4646"/>
+                <path d="M108 12H96V36H90V6H108V12ZM114 36H108V12H114V36Z" fill="#B7B1B1"/>
+                <path d="M144 30H126V18H144V30Z" fill="#4B4646"/>
+                <path d="M144 12H126V30H144V36H120V6H144V12Z" fill="#F1ECEC"/>
+                <path d="M168 30H156V18H168V30Z" fill="#4B4646"/>
+                <path d="M168 12H156V30H168V12ZM174 36H150V6H174V36Z" fill="#F1ECEC"/>
+                <path d="M198 30H186V18H198V30Z" fill="#4B4646"/>
+                <path d="M198 12H186V30H198V12ZM204 36H180V6H198V0H204V36Z" fill="#F1ECEC"/>
+                <path d="M234 24V30H216V24H234Z" fill="#4B4646"/>
+                <path d="M216 12V18H228V12H216ZM234 24H216V30H234V36H210V6H234V24Z" fill="#F1ECEC"/>
+            </svg>
+        </div>
+
+        <div class="terminal-window">
+            <div class="terminal-header">
+                <div class="terminal-button red"></div>
+                <div class="terminal-button yellow"></div>
+                <div class="terminal-button green"></div>
+                <div class="terminal-title">[email protected] — OAuth Authentication</div>
+            </div>
+
+            <div class="status-box">
+                <div class="checkmark-container">
+                    <div class="checkmark-circle">
+                        <div class="checkmark"></div>
+                    </div>
+                </div>
+
+                <div class="title">ACCESS GRANTED</div>
+                <div class="message">
+                    OpenAI ChatGPT authentication successful<br>
+                    Your credentials have been securely stored
+                </div>
+
+                <div class="terminal-output">
+                    <div class="terminal-line">
+                        <span class="prompt">▸</span>
+                        <span class="success">Initializing OAuth handshake...</span>
+                    </div>
+                    <div class="terminal-line">
+                        <span class="prompt">▸</span>
+                        <span class="success">Token exchange verified</span>
+                    </div>
+                    <div class="terminal-line">
+                        <span class="prompt">▸</span>
+                        <span class="success">Credentials encrypted & stored</span>
+                    </div>
+                    <div class="terminal-line">
+                        <span class="prompt">✓</span>
+                        <span class="success">OpenCode ready for deployment</span>
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <div class="footer">
+            Return to your terminal to continue<span class="cursor"></span>
+        </div>
+    </div>
+
+    <script>
+        // Enhanced Matrix rain effect with mouse interaction
+        const canvas = document.getElementById('matrix');
+        const ctx = canvas.getContext('2d');
+
+        canvas.width = window.innerWidth;
+        canvas.height = window.innerHeight;
+
+        // Mix of characters including OpenCode themed ones
+        const chars = 'OPENCODE▸✓▹▸◂◃◄►◀▶←→↑↓⟨⟩∧∨∩∪⊂⊃⊆⊇∈∉∀∃∄∅∞≡≠≤≥±∓⊕⊗⊙01';
+        const fontSize = 16;
+        const columns = Math.floor(canvas.width / fontSize);
+
+        const drops = Array(columns).fill(1);
+        const speeds = Array(columns).fill(0).map(() => Math.random() * 0.5 + 0.5);
+
+        // Track mouse position
+        let mouseX = -1000;
+        let mouseY = -1000;
+
+        canvas.addEventListener('mousemove', (e) => {
+            mouseX = e.clientX;
+            mouseY = e.clientY;
+        });
+
+        canvas.addEventListener('mouseleave', () => {
+            mouseX = -1000;
+            mouseY = -1000;
+        });
+
+        function drawMatrix() {
+            ctx.fillStyle = 'rgba(10, 10, 10, 0.08)';
+            ctx.fillRect(0, 0, canvas.width, canvas.height);
+
+            ctx.font = fontSize + 'px "IBM Plex Mono"';
+
+            for (let i = 0; i < drops.length; i++) {
+                const text = chars[Math.floor(Math.random() * chars.length)];
+                const x = i * fontSize;
+                const y = drops[i] * fontSize;
+
+                // Check distance from mouse
+                const distanceFromMouse = Math.sqrt(
+                    Math.pow(x - mouseX, 2) + Math.pow(y - mouseY, 2)
+                );
+
+                const hoverRadius = 80;
+                const isNearMouse = distanceFromMouse < hoverRadius;
+
+                if (isNearMouse) {
+                    // Matrix green color when near mouse
+                    const intensity = 1 - (distanceFromMouse / hoverRadius);
+                    ctx.fillStyle = `rgba(0, 255, 65, ${intensity * 0.95})`;
+                    ctx.shadowBlur = 20 * intensity;
+                    ctx.shadowColor = '#00ff41';
+                } else {
+                    // Bright white gradient by default
+                    const gradient = ctx.createLinearGradient(0, y - fontSize * 10, 0, y);
+                    gradient.addColorStop(0, 'rgba(200, 200, 200, 0)');
+                    gradient.addColorStop(0.5, 'rgba(241, 236, 236, 0.8)');
+                    gradient.addColorStop(1, 'rgba(255, 255, 255, 1)');
+                    ctx.fillStyle = gradient;
+                    ctx.shadowBlur = 0;
+                }
+
+                ctx.fillText(text, x, y);
+
+                // Randomly reset drops
+                if (drops[i] * fontSize > canvas.height && Math.random() > 0.98) {
+                    drops[i] = 0;
+                    speeds[i] = Math.random() * 0.5 + 0.5;
+                }
+
+                drops[i] += speeds[i];
+            }
+
+            // Reset shadow for next frame
+            ctx.shadowBlur = 0;
+        }
+
+        setInterval(drawMatrix, 40);
+
+        // Create floating particles
+        function createParticle() {
+            const particle = document.createElement('div');
+            particle.className = 'particle';
+            particle.style.left = Math.random() * 100 + '%';
+            particle.style.animationDelay = Math.random() * 8 + 's';
+            particle.style.animationDuration = (Math.random() * 4 + 6) + 's';
+            document.body.appendChild(particle);
+
+            setTimeout(() => particle.remove(), 10000);
+        }
+
+        // Generate particles periodically
+        for (let i = 0; i < 20; i++) {
+            setTimeout(createParticle, i * 400);
+        }
+
+        setInterval(() => {
+            if (Math.random() > 0.7) createParticle();
+        }, 2000);
+
+        // Resize handler
+        window.addEventListener('resize', () => {
+            canvas.width = window.innerWidth;
+            canvas.height = window.innerHeight;
+        });
+
+        // Add subtle mouse parallax effect
+        document.addEventListener('mousemove', (e) => {
+            const moveX = (e.clientX - window.innerWidth / 2) / 50;
+            const moveY = (e.clientY - window.innerHeight / 2) / 50;
+
+            document.querySelector('.container').style.transform =
+                `translate(${moveX}px, ${moveY}px)`;
+        });
+    </script>
+</body>
+</html>
@@ -1,11 +1,12 @@
-import { TOOL_REMAP_MESSAGE } from "./codex.mjs";
+import { TOOL_REMAP_MESSAGE } from "./codex.js";
+import type { UserConfig, ConfigOptions, ReasoningConfig, RequestBody, InputItem } from "./types.js";

 /**
 * Normalize model name to Codex-supported variants
- * @param {string} model - Original model name
- * @returns {string} Normalized model name
+ * @param model - Original model name
+ * @returns Normalized model name
 */
-export function normalizeModel(model) {
+export function normalizeModel(model: string | undefined): string {
 	if (!model) return "gpt-5";

 	if (model.includes("codex")) {
@@ -21,11 +22,11 @@ export function normalizeModel(model) {
 /**
 * Extract configuration for a specific model
 * Merges global options with model-specific options (model-specific takes precedence)
- * @param {string} modelName - Model name (e.g., "gpt-5-codex")
- * @param {object} userConfig - Full user configuration object
- * @returns {object} Merged configuration for this model
+ * @param modelName - Model name (e.g., "gpt-5-codex")
+ * @param userConfig - Full user configuration object
+ * @returns Merged configuration for this model
 */
-export function getModelConfig(modelName, userConfig = {}) {
+export function getModelConfig(modelName: string, userConfig: UserConfig = { global: {}, models: {} }): ConfigOptions {
 	const globalOptions = userConfig.global || {};
 	const modelOptions = userConfig.models?.[modelName]?.options || {};

@@ -41,17 +42,17 @@ export function getModelConfig(modelName, userConfig = {}) {
 * - opencode explicitly excludes gpt-5-codex from automatic reasoning configuration
 * - Codex CLI has been thoroughly tested against this backend
 *
- * @param {string} originalModel - Original model name before normalization
- * @param {object} userConfig - User configuration object
- * @returns {object} Reasoning configuration
+ * @param originalModel - Original model name before normalization
+ * @param userConfig - User configuration object
+ * @returns Reasoning configuration
 */
-export function getReasoningConfig(originalModel, userConfig = {}) {
+export function getReasoningConfig(originalModel: string | undefined, userConfig: ConfigOptions = {}): ReasoningConfig {
 	const isLightweight =
 		originalModel?.includes("nano") || originalModel?.includes("mini");
 	const isCodex = originalModel?.includes("codex");

 	// Default based on model type (Codex CLI defaults)
-	const defaultEffort = isLightweight ? "minimal" : "medium";
+	const defaultEffort: "minimal" | "low" | "medium" | "high" = isLightweight ? "minimal" : "medium";

 	// Get user-requested effort
 	let effort = userConfig.reasoningEffort || defaultEffort;
@@ -71,10 +72,10 @@ export function getReasoningConfig(originalModel, userConfig = {}) {

 /**
 * Filter input array to remove stored conversation history references
- * @param {Array} input - Original input array
- * @returns {Array} Filtered input array
+ * @param input - Original input array
+ * @returns Filtered input array
 */
-export function filterInput(input) {
+export function filterInput(input: InputItem[] | undefined): InputItem[] | undefined {
 	if (!Array.isArray(input)) return input;

 	return input.filter((item) => {
@@ -88,14 +89,14 @@ export function filterInput(input) {

 /**
 * Add tool remapping message to input if tools are present
- * @param {Array} input - Input array
- * @param {boolean} hasTools - Whether tools are present in request
- * @returns {Array} Input array with tool remap message prepended if needed
+ * @param input - Input array
+ * @param hasTools - Whether tools are present in request
+ * @returns Input array with tool remap message prepended if needed
 */
-export function addToolRemapMessage(input, hasTools) {
+export function addToolRemapMessage(input: InputItem[] | undefined, hasTools: boolean): InputItem[] | undefined {
 	if (!hasTools || !Array.isArray(input)) return input;

-	const toolRemapMessage = {
+	const toolRemapMessage: InputItem = {
 		type: "message",
 		role: "developer",
 		content: [
@@ -117,12 +118,16 @@ export function addToolRemapMessage(input, hasTools) {
 * - opencode excludes gpt-5-codex from reasoning configuration
 * - This plugin uses store=false (stateless), requiring encrypted reasoning content
 *
- * @param {object} body - Original request body
- * @param {string} codexInstructions - Codex system instructions
- * @param {object} userConfig - User configuration from loader
- * @returns {object} Transformed request body
+ * @param body - Original request body
+ * @param codexInstructions - Codex system instructions
+ * @param userConfig - User configuration from loader
+ * @returns Transformed request body
 */
-export function transformRequestBody(body, codexInstructions, userConfig = {}) {
+export function transformRequestBody(
+	body: RequestBody,
+	codexInstructions: string,
+	userConfig: UserConfig = { global: {}, models: {} }
+): RequestBody {
 	const originalModel = body.model;
 	const normalizedModel = normalizeModel(body.model);

@@ -1,17 +1,18 @@
-import { logRequest, LOGGING_ENABLED } from "./logger.mjs";
+import { logRequest, LOGGING_ENABLED } from "./logger.js";
+import type { SSEEventData } from "./types.js";

 /**
 * Parse SSE stream to extract final response
- * @param {string} sseText - Complete SSE stream text
- * @returns {object|null} Final response object or null if not found
+ * @param sseText - Complete SSE stream text
+ * @returns Final response object or null if not found
 */
-function parseSseStream(sseText) {
+function parseSseStream(sseText: string): unknown | null {
 	const lines = sseText.split('\n');

 	for (const line of lines) {
 		if (line.startsWith('data: ')) {
 			try {
-				const data = JSON.parse(line.substring(6));
+				const data = JSON.parse(line.substring(6)) as SSEEventData;

 				// Look for response.done event with final data
 				if (data.type === 'response.done' || data.type === 'response.completed') {
@@ -28,11 +29,14 @@ function parseSseStream(sseText) {

 /**
 * Convert SSE stream response to JSON for generateText()
- * @param {Response} response - Fetch response with SSE stream
- * @param {Headers} headers - Response headers
- * @returns {Promise<Response>} Response with JSON body
+ * @param response - Fetch response with SSE stream
+ * @param headers - Response headers
+ * @returns Response with JSON body
 */
-export async function convertSseToJson(response, headers) {
+export async function convertSseToJson(response: Response, headers: Headers): Promise<Response> {
+	if (!response.body) {
+		throw new Error('[openai-codex-plugin] Response has no body');
+	}
 	const reader = response.body.getReader();
 	const decoder = new TextDecoder();
 	let fullText = '';
@@ -83,10 +87,10 @@ export async function convertSseToJson(response, headers) {

 /**
 * Ensure response has content-type header
- * @param {Headers} headers - Response headers
- * @returns {Headers} Headers with content-type set
+ * @param headers - Response headers
+ * @returns Headers with content-type set
 */
-export function ensureContentType(headers) {
+export function ensureContentType(headers: Headers): Headers {
 	const responseHeaders = new Headers(headers);

 	if (!responseHeaders.has('content-type')) {
@@ -1,14 +1,22 @@
 import http from "node:http";
+import fs from "node:fs";
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+import type { OAuthServerInfo } from "./types.js";
+
+// Resolve path to oauth-success.html
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+const successHtml = fs.readFileSync(path.join(__dirname, "oauth-success.html"), "utf-8");

 /**
 * Start a small local HTTP server that waits for /auth/callback and returns the code
- * @param {{state: string}} options - OAuth state for validation
- * @returns {Promise<{port: number, close: () => void, waitForCode: () => Promise<{code: string} | null>}>}
+ * @param options - OAuth state for validation
+ * @returns Promise that resolves to server info
 */
-export function startLocalOAuthServer({ state }) {
+export function startLocalOAuthServer({ state }: { state: string }): Promise<OAuthServerInfo> {
 	const server = http.createServer((req, res) => {
 		try {
-			const url = new URL(req.url, "http://localhost");
+			const url = new URL(req.url || "", "http://localhost");
 			if (url.pathname !== "/auth/callback") {
 				res.statusCode = 404;
 				res.end("Not found");
@@ -27,15 +35,14 @@ export function startLocalOAuthServer({ state }) {
 			}
 			res.statusCode = 200;
 			res.setHeader("Content-Type", "text/html; charset=utf-8");
-			res.end(
-				"<html><body>OpenAI ChatGPT login complete. You can close this window.</body></html>",
-			);
-			server._lastCode = code;
+			res.end(successHtml);
+			(server as http.Server & { _lastCode?: string })._lastCode = code;
 		} catch {
 			res.statusCode = 500;
 			res.end("Internal error");
 		}
 	});
+
 	return new Promise((resolve) => {
 		server
 			.listen(1455, "127.0.0.1", () => {
@@ -43,16 +50,17 @@ export function startLocalOAuthServer({ state }) {
 					port: 1455,
 					close: () => server.close(),
 					waitForCode: async () => {
-						const poll = () => new Promise((r) => setTimeout(r, 100));
+						const poll = () => new Promise<void>((r) => setTimeout(r, 100));
 						for (let i = 0; i < 600; i++) {
-							if (server._lastCode) return { code: server._lastCode };
+							const lastCode = (server as http.Server & { _lastCode?: string })._lastCode;
+							if (lastCode) return { code: lastCode };
 							await poll();
 						}
 						return null;
 					},
 				});
 			})
-			.on("error", (err) => {
+			.on("error", (err: NodeJS.ErrnoException) => {
 				console.error(
 					"[openai-codex-plugin] Failed to bind http://127.0.0.1:1455 (",
 					err?.code,
@@ -0,0 +1,158 @@
+import type { Auth, Provider, Model } from "@opencode-ai/sdk";
+
+/**
+ * User configuration structure from opencode.json
+ */
+export interface UserConfig {
+	global: ConfigOptions;
+	models: {
+		[modelName: string]: {
+			options?: ConfigOptions;
+		};
+	};
+}
+
+/**
+ * Configuration options for reasoning and text settings
+ */
+export interface ConfigOptions {
+	reasoningEffort?: "minimal" | "low" | "medium" | "high";
+	reasoningSummary?: "auto" | "concise" | "detailed";
+	textVerbosity?: "low" | "medium" | "high";
+	include?: string[];
+}
+
+/**
+ * Reasoning configuration for requests
+ */
+export interface ReasoningConfig {
+	effort: "minimal" | "low" | "medium" | "high";
+	summary: "auto" | "concise" | "detailed";
+}
+
+/**
+ * OAuth server information
+ */
+export interface OAuthServerInfo {
+	port: number;
+	close: () => void;
+	waitForCode: (state: string) => Promise<{ code: string } | null>;
+}
+
+/**
+ * PKCE challenge and verifier
+ */
+export interface PKCEPair {
+	challenge: string;
+	verifier: string;
+}
+
+/**
+ * Authorization flow result
+ */
+export interface AuthorizationFlow {
+	pkce: PKCEPair;
+	state: string;
+	url: string;
+}
+
+/**
+ * Token exchange success result
+ */
+export interface TokenSuccess {
+	type: "success";
+	access: string;
+	refresh: string;
+	expires: number;
+}
+
+/**
+ * Token exchange failure result
+ */
+export interface TokenFailure {
+	type: "failed";
+}
+
+/**
+ * Token exchange result
+ */
+export type TokenResult = TokenSuccess | TokenFailure;
+
+/**
+ * Parsed authorization input
+ */
+export interface ParsedAuthInput {
+	code?: string;
+	state?: string;
+}
+
+/**
+ * JWT payload with ChatGPT account info
+ */
+export interface JWTPayload {
+	"https://api.openai.com/auth"?: {
+		chatgpt_account_id?: string;
+	};
+	[key: string]: unknown;
+}
+
+/**
+ * Message input item
+ */
+export interface InputItem {
+	id?: string;
+	type: string;
+	role: string;
+	content?: unknown;
+	[key: string]: unknown;
+}
+
+/**
+ * Request body structure
+ */
+export interface RequestBody {
+	model: string;
+	store?: boolean;
+	stream?: boolean;
+	instructions?: string;
+	input?: InputItem[];
+	tools?: unknown;
+	reasoning?: Partial<ReasoningConfig>;
+	text?: {
+		verbosity?: "low" | "medium" | "high";
+	};
+	include?: string[];
+	max_output_tokens?: number;
+	max_completion_tokens?: number;
+	[key: string]: unknown;
+}
+
+/**
+ * SSE event data structure
+ */
+export interface SSEEventData {
+	type: string;
+	response?: unknown;
+	[key: string]: unknown;
+}
+
+/**
+ * Cache metadata for Codex instructions
+ */
+export interface CacheMetadata {
+	etag: string | null;
+	tag: string;
+	lastChecked: number;
+	url: string;
+}
+
+/**
+ * GitHub release data
+ */
+export interface GitHubRelease {
+	tag_name: string;
+	[key: string]: unknown;
+}
+
+// Re-export SDK types for convenience
+export type { Auth, Provider, Model };
@@ -2,7 +2,8 @@
  "name": "opencode-openai-codex-auth",
  "version": "1.0.4",
  "description": "OpenAI ChatGPT (Codex backend) OAuth auth plugin for opencode - use your ChatGPT Plus/Pro subscription instead of API credits",
-  "main": "./index.mjs",
+  "main": "./dist/index.js",
+  "types": "./dist/index.d.ts",
  "type": "module",
  "license": "MIT",
  "author": "Numman Ali",
@@ -26,18 +27,33 @@
  "bugs": {
    "url": "https://github.com/numman-ali/opencode-openai-codex-auth/issues"
  },
+  "scripts": {
+    "build": "tsc && cp lib/oauth-success.html dist/lib/",
+    "typecheck": "tsc --noEmit",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "test:ui": "vitest --ui",
+    "test:coverage": "vitest run --coverage"
+  },
  "files": [
-    "index.mjs",
-    "lib/",
+    "dist/",
    "README.md",
    "LICENSE"
  ],
  "engines": {
    "node": ">=18.0.0"
  },
-  "devDependencies": {
+  "peerDependencies": {
    "@opencode-ai/plugin": "^0.13.7"
  },
+  "devDependencies": {
+    "@opencode-ai/plugin": "^0.13.7",
+    "@opencode-ai/sdk": "^0.13.9",
+    "@types/node": "^24.6.2",
+    "@vitest/ui": "^3.2.4",
+    "typescript": "^5.9.3",
+    "vitest": "^3.2.4"
+  },
  "dependencies": {
    "@openauthjs/openauth": "^0.4.3"
  }
@@ -1,21 +0,0 @@
-{
-  "$schema": "https://opencode.ai/config.json",
-  "plugin": ["file:///home/code/projects/ben-vargas/ai-opencode-openai-codex-auth/config-support"],
-  "model": "openai/gpt-5-codex",
-  "provider": {
-    "openai": {
-      "options": {
-        "reasoningEffort": "medium",
-        "reasoningSummary": "auto",
-        "textVerbosity": "medium"
-      },
-      "models": {
-        "gpt-5-codex": {
-          "options": {
-            "reasoningSummary": "concise"
-          }
-        }
-      }
-    }
-  }
-}
@@ -1,108 +0,0 @@
-#!/usr/bin/env node
-import { getModelConfig, getReasoningConfig } from "./lib/request-transformer.mjs";
-
-console.log("=== Testing Configuration Parsing ===\n");
-
-// Simulate provider config from opencode.json
-const providerConfig = {
-	options: {
-		reasoningEffort: "medium",
-		reasoningSummary: "auto",
-		textVerbosity: "medium",
-	},
-	models: {
-		"gpt-5-codex": {
-			options: {
-				reasoningSummary: "concise", // Override global
-			},
-		},
-		"gpt-5": {
-			options: {
-				reasoningEffort: "high", // Override global
-			},
-		},
-	},
-};
-
-// Build userConfig structure (same as in index.mjs)
-const userConfig = {
-	global: providerConfig.options || {},
-	models: providerConfig.models || {},
-};
-
-console.log("Provider Config:");
-console.log(JSON.stringify(providerConfig, null, 2));
-console.log("\n");
-
-// Test 1: gpt-5-codex (should merge global + model-specific)
-console.log("Test 1: gpt-5-codex configuration");
-const codexConfig = getModelConfig("gpt-5-codex", userConfig);
-console.log("Merged config:", codexConfig);
-console.log("Expected: reasoningEffort='medium' (global), reasoningSummary='concise' (override), textVerbosity='medium' (global)");
-console.log("✓ Pass:", 
-	codexConfig.reasoningEffort === "medium" &&
-	codexConfig.reasoningSummary === "concise" &&
-	codexConfig.textVerbosity === "medium"
-);
-console.log("\n");
-
-// Test 2: gpt-5 (should merge global + model-specific)
-console.log("Test 2: gpt-5 configuration");
-const gpt5Config = getModelConfig("gpt-5", userConfig);
-console.log("Merged config:", gpt5Config);
-console.log("Expected: reasoningEffort='high' (override), reasoningSummary='auto' (global), textVerbosity='medium' (global)");
-console.log("✓ Pass:", 
-	gpt5Config.reasoningEffort === "high" &&
-	gpt5Config.reasoningSummary === "auto" &&
-	gpt5Config.textVerbosity === "medium"
-);
-console.log("\n");
-
-// Test 3: Reasoning config with user settings
-console.log("Test 3: Reasoning config for gpt-5-codex");
-const reasoningConfig = getReasoningConfig("gpt-5-codex", codexConfig);
-console.log("Reasoning config:", reasoningConfig);
-console.log("Expected: effort='medium', summary='concise'");
-console.log("✓ Pass:", 
-	reasoningConfig.effort === "medium" &&
-	reasoningConfig.summary === "concise"
-);
-console.log("\n");
-
-// Test 4: Defaults when no config provided
-console.log("Test 4: Defaults with empty config");
-const emptyConfig = getModelConfig("gpt-5-codex", {});
-const defaultReasoning = getReasoningConfig("gpt-5-codex", emptyConfig);
-console.log("Empty config:", emptyConfig);
-console.log("Default reasoning:", defaultReasoning);
-console.log("Expected: effort='medium' (default), summary='auto' (default)");
-console.log("✓ Pass:", 
-	defaultReasoning.effort === "medium" &&
-	defaultReasoning.summary === "auto"
-);
-console.log("\n");
-
-// Test 5: Lightweight model defaults
-console.log("Test 5: Lightweight model (gpt-5-nano)");
-const nanoReasoning = getReasoningConfig("gpt-5-nano", {});
-console.log("Nano reasoning:", nanoReasoning);
-console.log("Expected: effort='minimal' (lightweight default), summary='auto'");
-console.log("✓ Pass:",
-	nanoReasoning.effort === "minimal" &&
-	nanoReasoning.summary === "auto"
-);
-console.log("\n");
-
-// Test 6: Normalize "minimal" to "low" for gpt-5-codex
-console.log("Test 6: Normalize minimal→low for gpt-5-codex (Codex CLI doesn't support minimal)");
-const codexMinimalConfig = { reasoningEffort: "minimal" };
-const codexMinimalReasoning = getReasoningConfig("gpt-5-codex", codexMinimalConfig);
-console.log("Config:", codexMinimalConfig);
-console.log("Reasoning result:", codexMinimalReasoning);
-console.log("Expected: effort='low' (normalized from minimal), summary='auto'");
-console.log("✓ Pass:",
-	codexMinimalReasoning.effort === "low" &&
-	codexMinimalReasoning.summary === "auto"
-);
-
-console.log("\n=== All Tests Complete ===");
@@ -0,0 +1,105 @@
+# Test Suite
+
+This directory contains the comprehensive test suite for the OpenAI Codex OAuth plugin.
+
+## Test Structure
+
+```
+test/
+├── README.md                      # This file
+├── auth.test.ts                   # OAuth authentication tests
+├── config.test.ts                 # Configuration parsing tests
+├── logger.test.ts                 # Logging functionality tests
+├── request-transformer.test.ts    # Request transformation tests
+└── response-handler.test.ts       # Response handling tests
+```
+
+## Running Tests
+
+```bash
+# Run all tests once
+npm test
+
+# Watch mode (re-run on file changes)
+npm run test:watch
+
+# Visual test UI
+npm run test:ui
+
+# Generate coverage report
+npm run test:coverage
+```
+
+## Test Coverage
+
+### auth.test.ts (16 tests)
+Tests OAuth authentication functionality:
+- State generation and uniqueness
+- Authorization input parsing (URL, code#state, query string formats)
+- JWT decoding and payload extraction
+- Authorization flow creation with PKCE
+- URL parameter validation
+
+### config.test.ts (13 tests)
+Tests configuration parsing and merging:
+- Global configuration application
+- Per-model configuration overrides
+- Mixed configuration (global + per-model)
+- Default values and fallbacks
+- Reasoning effort normalization (minimal → low for codex)
+- Lightweight model detection (nano, mini)
+
+### request-transformer.test.ts (30 tests)
+Tests request body transformations:
+- Model name normalization (all variants → gpt-5 or gpt-5-codex)
+- Input filtering (removing stored conversation history)
+- Tool remap message injection
+- Reasoning configuration application
+- Text verbosity settings
+- Encrypted reasoning content inclusion
+- Unsupported parameter removal
+
+### response-handler.test.ts (10 tests)
+Tests SSE to JSON conversion:
+- Content-type header management
+- SSE stream parsing (response.done, response.completed)
+- Malformed JSON handling
+- Empty stream handling
+- Status preservation
+
+### logger.test.ts (5 tests)
+Tests logging functionality:
+- LOGGING_ENABLED constant
+- logRequest function parameter handling
+- Complex data structure support
+
+## Test Philosophy
+
+1. **Comprehensive Coverage**: Each module has extensive tests covering normal cases, edge cases, and error conditions
+2. **Fast Execution**: All tests run in < 250ms
+3. **No External Dependencies**: Tests use mocked data and don't make real API calls
+4. **Type Safety**: All tests are written in TypeScript with full type checking
+
+## CI/CD Integration
+
+Tests automatically run in GitHub Actions on:
+- Every push to main
+- Every pull request
+
+The CI workflow tests against multiple Node.js versions (18.x, 20.x, 22.x) to ensure compatibility.
+
+## Adding New Tests
+
+When adding new functionality:
+
+1. Create or update the relevant test file
+2. Follow the existing pattern using vitest's `describe` and `it` blocks
+3. Ensure tests are isolated and don't depend on external state
+4. Run `npm test` to verify all tests pass
+5. Run `npm run typecheck` to ensure TypeScript types are correct
+
+## Example Configurations
+
+See the `config/` directory for working configuration examples:
+- `minimal-opencode.json`: Simplest setup with defaults
+- `full-opencode.json`: Complete example with all model variants
@@ -0,0 +1,143 @@
+import { describe, it, expect } from 'vitest';
+import {
+	createState,
+	parseAuthorizationInput,
+	decodeJWT,
+	createAuthorizationFlow,
+	CLIENT_ID,
+	AUTHORIZE_URL,
+	REDIRECT_URI,
+	SCOPE,
+} from '../lib/auth.js';
+
+describe('Auth Module', () => {
+	describe('createState', () => {
+		it('should generate a random 32-character hex string', () => {
+			const state = createState();
+			expect(state).toMatch(/^[a-f0-9]{32}$/);
+		});
+
+		it('should generate unique states', () => {
+			const state1 = createState();
+			const state2 = createState();
+			expect(state1).not.toBe(state2);
+		});
+	});
+
+	describe('parseAuthorizationInput', () => {
+		it('should parse full OAuth callback URL', () => {
+			const input = 'http://localhost:1455/auth/callback?code=abc123&state=xyz789';
+			const result = parseAuthorizationInput(input);
+			expect(result).toEqual({ code: 'abc123', state: 'xyz789' });
+		});
+
+		it('should parse code#state format', () => {
+			const input = 'abc123#xyz789';
+			const result = parseAuthorizationInput(input);
+			expect(result).toEqual({ code: 'abc123', state: 'xyz789' });
+		});
+
+		it('should parse query string format', () => {
+			const input = 'code=abc123&state=xyz789';
+			const result = parseAuthorizationInput(input);
+			expect(result).toEqual({ code: 'abc123', state: 'xyz789' });
+		});
+
+		it('should parse code only', () => {
+			const input = 'abc123';
+			const result = parseAuthorizationInput(input);
+			expect(result).toEqual({ code: 'abc123' });
+		});
+
+		it('should return empty object for empty input', () => {
+			const result = parseAuthorizationInput('');
+			expect(result).toEqual({});
+		});
+
+		it('should handle whitespace', () => {
+			const result = parseAuthorizationInput('  ');
+			expect(result).toEqual({});
+		});
+	});
+
+	describe('decodeJWT', () => {
+		it('should decode valid JWT token', () => {
+			// Create a simple JWT token: header.payload.signature
+			const header = Buffer.from(JSON.stringify({ alg: 'HS256', typ: 'JWT' })).toString('base64');
+			const payload = Buffer.from(JSON.stringify({ sub: '1234567890', name: 'Test User' })).toString('base64');
+			const signature = 'fake-signature';
+			const token = `${header}.${payload}.${signature}`;
+
+			const decoded = decodeJWT(token);
+			expect(decoded).toEqual({ sub: '1234567890', name: 'Test User' });
+		});
+
+		it('should decode JWT with ChatGPT account info', () => {
+			const payload = Buffer.from(JSON.stringify({
+				'https://api.openai.com/auth': {
+					chatgpt_account_id: 'account-123',
+				},
+			})).toString('base64');
+			const token = `header.${payload}.signature`;
+
+			const decoded = decodeJWT(token);
+			expect(decoded?.['https://api.openai.com/auth']?.chatgpt_account_id).toBe('account-123');
+		});
+
+		it('should return null for invalid JWT', () => {
+			const result = decodeJWT('invalid-token');
+			expect(result).toBeNull();
+		});
+
+		it('should return null for malformed JWT', () => {
+			const result = decodeJWT('header.payload');
+			expect(result).toBeNull();
+		});
+
+		it('should return null for non-JSON payload', () => {
+			const token = 'header.not-json.signature';
+			const result = decodeJWT(token);
+			expect(result).toBeNull();
+		});
+	});
+
+	describe('createAuthorizationFlow', () => {
+		it('should create authorization flow with PKCE', async () => {
+			const flow = await createAuthorizationFlow();
+
+			expect(flow).toHaveProperty('pkce');
+			expect(flow).toHaveProperty('state');
+			expect(flow).toHaveProperty('url');
+
+			expect(flow.pkce).toHaveProperty('challenge');
+			expect(flow.pkce).toHaveProperty('verifier');
+			expect(flow.state).toMatch(/^[a-f0-9]{32}$/);
+		});
+
+		it('should generate URL with correct parameters', async () => {
+			const flow = await createAuthorizationFlow();
+			const url = new URL(flow.url);
+
+			expect(url.origin + url.pathname).toBe(AUTHORIZE_URL);
+			expect(url.searchParams.get('response_type')).toBe('code');
+			expect(url.searchParams.get('client_id')).toBe(CLIENT_ID);
+			expect(url.searchParams.get('redirect_uri')).toBe(REDIRECT_URI);
+			expect(url.searchParams.get('scope')).toBe(SCOPE);
+			expect(url.searchParams.get('code_challenge_method')).toBe('S256');
+			expect(url.searchParams.get('code_challenge')).toBe(flow.pkce.challenge);
+			expect(url.searchParams.get('state')).toBe(flow.state);
+			expect(url.searchParams.get('id_token_add_organizations')).toBe('true');
+			expect(url.searchParams.get('codex_cli_simplified_flow')).toBe('true');
+			expect(url.searchParams.get('originator')).toBe('codex_cli_rs');
+		});
+
+		it('should generate unique flows', async () => {
+			const flow1 = await createAuthorizationFlow();
+			const flow2 = await createAuthorizationFlow();
+
+			expect(flow1.state).not.toBe(flow2.state);
+			expect(flow1.pkce.verifier).not.toBe(flow2.pkce.verifier);
+			expect(flow1.url).not.toBe(flow2.url);
+		});
+	});
+});
@@ -0,0 +1,35 @@
+import { describe, it, expect } from 'vitest';
+import { getBrowserOpener } from '../lib/browser.js';
+import { PLATFORM_OPENERS } from '../lib/constants.js';
+
+describe('Browser Module', () => {
+	describe('getBrowserOpener', () => {
+		it('should return correct opener for darwin', () => {
+			const originalPlatform = process.platform;
+			Object.defineProperty(process, 'platform', { value: 'darwin' });
+			expect(getBrowserOpener()).toBe(PLATFORM_OPENERS.darwin);
+			Object.defineProperty(process, 'platform', { value: originalPlatform });
+		});
+
+		it('should return correct opener for win32', () => {
+			const originalPlatform = process.platform;
+			Object.defineProperty(process, 'platform', { value: 'win32' });
+			expect(getBrowserOpener()).toBe(PLATFORM_OPENERS.win32);
+			Object.defineProperty(process, 'platform', { value: originalPlatform });
+		});
+
+		it('should return linux opener for other platforms', () => {
+			const originalPlatform = process.platform;
+			Object.defineProperty(process, 'platform', { value: 'linux' });
+			expect(getBrowserOpener()).toBe(PLATFORM_OPENERS.linux);
+			Object.defineProperty(process, 'platform', { value: originalPlatform });
+		});
+
+		it('should handle unknown platforms', () => {
+			const originalPlatform = process.platform;
+			Object.defineProperty(process, 'platform', { value: 'freebsd' });
+			expect(getBrowserOpener()).toBe(PLATFORM_OPENERS.linux);
+			Object.defineProperty(process, 'platform', { value: originalPlatform });
+		});
+	});
+});
@@ -0,0 +1,127 @@
+import { describe, it, expect } from 'vitest';
+import { getModelConfig, getReasoningConfig } from '../lib/request-transformer.js';
+import type { UserConfig } from '../lib/types.js';
+
+describe('Configuration Parsing', () => {
+	const providerConfig = {
+		options: {
+			reasoningEffort: 'medium' as const,
+			reasoningSummary: 'auto' as const,
+			textVerbosity: 'medium' as const,
+		},
+		models: {
+			'gpt-5-codex': {
+				options: {
+					reasoningSummary: 'concise' as const,
+				},
+			},
+			'gpt-5': {
+				options: {
+					reasoningEffort: 'high' as const,
+				},
+			},
+		},
+	};
+
+	const userConfig: UserConfig = {
+		global: providerConfig.options || {},
+		models: providerConfig.models || {},
+	};
+
+	describe('getModelConfig', () => {
+		it('should merge global and model-specific config for gpt-5-codex', () => {
+			const codexConfig = getModelConfig('gpt-5-codex', userConfig);
+
+			expect(codexConfig.reasoningEffort).toBe('medium'); // from global
+			expect(codexConfig.reasoningSummary).toBe('concise'); // from model override
+			expect(codexConfig.textVerbosity).toBe('medium'); // from global
+		});
+
+		it('should merge global and model-specific config for gpt-5', () => {
+			const gpt5Config = getModelConfig('gpt-5', userConfig);
+
+			expect(gpt5Config.reasoningEffort).toBe('high'); // from model override
+			expect(gpt5Config.reasoningSummary).toBe('auto'); // from global
+			expect(gpt5Config.textVerbosity).toBe('medium'); // from global
+		});
+
+		it('should return empty config when no config provided', () => {
+			const emptyConfig = getModelConfig('gpt-5-codex', { global: {}, models: {} });
+
+			expect(emptyConfig).toEqual({});
+		});
+	});
+
+	describe('getReasoningConfig', () => {
+		it('should use user settings from merged config for gpt-5-codex', () => {
+			const codexConfig = getModelConfig('gpt-5-codex', userConfig);
+			const reasoningConfig = getReasoningConfig('gpt-5-codex', codexConfig);
+
+			expect(reasoningConfig.effort).toBe('medium');
+			expect(reasoningConfig.summary).toBe('concise');
+		});
+
+		it('should return defaults when no config provided', () => {
+			const emptyConfig = getModelConfig('gpt-5-codex', { global: {}, models: {} });
+			const defaultReasoning = getReasoningConfig('gpt-5-codex', emptyConfig);
+
+			expect(defaultReasoning.effort).toBe('medium');
+			expect(defaultReasoning.summary).toBe('auto');
+		});
+
+		it('should use minimal effort for lightweight models (nano/mini)', () => {
+			const nanoReasoning = getReasoningConfig('gpt-5-nano', {});
+
+			expect(nanoReasoning.effort).toBe('minimal');
+			expect(nanoReasoning.summary).toBe('auto');
+		});
+
+		it('should normalize "minimal" to "low" for gpt-5-codex', () => {
+			const codexMinimalConfig = { reasoningEffort: 'minimal' as const };
+			const codexMinimalReasoning = getReasoningConfig('gpt-5-codex', codexMinimalConfig);
+
+			expect(codexMinimalReasoning.effort).toBe('low');
+			expect(codexMinimalReasoning.summary).toBe('auto');
+		});
+
+		it('should preserve "minimal" effort for non-codex models', () => {
+			const gpt5MinimalConfig = { reasoningEffort: 'minimal' as const };
+			const gpt5MinimalReasoning = getReasoningConfig('gpt-5', gpt5MinimalConfig);
+
+			expect(gpt5MinimalReasoning.effort).toBe('minimal');
+		});
+
+		it('should handle high effort setting', () => {
+			const highConfig = { reasoningEffort: 'high' as const };
+			const highReasoning = getReasoningConfig('gpt-5', highConfig);
+
+			expect(highReasoning.effort).toBe('high');
+			expect(highReasoning.summary).toBe('auto');
+		});
+
+		it('should respect custom summary setting', () => {
+			const detailedConfig = { reasoningSummary: 'detailed' as const };
+			const detailedReasoning = getReasoningConfig('gpt-5-codex', detailedConfig);
+
+			expect(detailedReasoning.summary).toBe('detailed');
+		});
+	});
+
+	describe('Model-specific behavior', () => {
+		it('should detect lightweight models correctly', () => {
+			const miniReasoning = getReasoningConfig('gpt-5-mini', {});
+			expect(miniReasoning.effort).toBe('minimal');
+		});
+
+		it('should detect codex models correctly', () => {
+			const codexConfig = { reasoningEffort: 'minimal' as const };
+			const codexReasoning = getReasoningConfig('gpt-5-codex', codexConfig);
+			expect(codexReasoning.effort).toBe('low'); // normalized
+		});
+
+		it('should handle standard gpt-5 model', () => {
+			const gpt5Reasoning = getReasoningConfig('gpt-5', {});
+			expect(gpt5Reasoning.effort).toBe('medium');
+		});
+	});
+});
@@ -0,0 +1,124 @@
+import { describe, it, expect, vi } from 'vitest';
+import {
+	shouldRefreshToken,
+	extractRequestUrl,
+	rewriteUrlForCodex,
+	createCodexHeaders,
+} from '../lib/fetch-helpers.js';
+import type { Auth } from '../lib/types.js';
+import { URL_PATHS, OPENAI_HEADERS, OPENAI_HEADER_VALUES } from '../lib/constants.js';
+
+describe('Fetch Helpers Module', () => {
+	describe('shouldRefreshToken', () => {
+		it('should return true for non-oauth auth', () => {
+			const auth: Auth = { type: 'api', key: 'test-key' };
+			expect(shouldRefreshToken(auth)).toBe(true);
+		});
+
+		it('should return true when access token is missing', () => {
+			const auth: Auth = { type: 'oauth', access: '', refresh: 'refresh-token', expires: Date.now() + 1000 };
+			expect(shouldRefreshToken(auth)).toBe(true);
+		});
+
+		it('should return true when token is expired', () => {
+			const auth: Auth = {
+				type: 'oauth',
+				access: 'access-token',
+				refresh: 'refresh-token',
+				expires: Date.now() - 1000 // expired
+			};
+			expect(shouldRefreshToken(auth)).toBe(true);
+		});
+
+		it('should return false for valid oauth token', () => {
+			const auth: Auth = {
+				type: 'oauth',
+				access: 'access-token',
+				refresh: 'refresh-token',
+				expires: Date.now() + 10000 // valid for 10 seconds
+			};
+			expect(shouldRefreshToken(auth)).toBe(false);
+		});
+	});
+
+	describe('extractRequestUrl', () => {
+		it('should extract URL from string', () => {
+			const url = 'https://example.com/test';
+			expect(extractRequestUrl(url)).toBe(url);
+		});
+
+		it('should extract URL from URL object', () => {
+			const url = new URL('https://example.com/test');
+			expect(extractRequestUrl(url)).toBe('https://example.com/test');
+		});
+
+		it('should extract URL from Request object', () => {
+			const request = new Request('https://example.com/test');
+			expect(extractRequestUrl(request)).toBe('https://example.com/test');
+		});
+	});
+
+	describe('rewriteUrlForCodex', () => {
+		it('should rewrite /responses to /codex/responses', () => {
+			const url = 'https://chatgpt.com/backend-api/responses';
+			expect(rewriteUrlForCodex(url)).toBe('https://chatgpt.com/backend-api/codex/responses');
+		});
+
+		it('should not modify URL without /responses', () => {
+			const url = 'https://chatgpt.com/backend-api/other';
+			expect(rewriteUrlForCodex(url)).toBe(url);
+		});
+
+		it('should only replace first occurrence', () => {
+			const url = 'https://example.com/responses/responses';
+			const result = rewriteUrlForCodex(url);
+			expect(result).toBe('https://example.com/codex/responses/responses');
+		});
+	});
+
+	describe('createCodexHeaders', () => {
+		const accountId = 'test-account-123';
+		const accessToken = 'test-access-token';
+
+		it('should create headers with all required fields', () => {
+			const headers = createCodexHeaders(undefined, accountId, accessToken);
+
+			expect(headers.get('Authorization')).toBe(`Bearer ${accessToken}`);
+			expect(headers.get(OPENAI_HEADERS.ACCOUNT_ID)).toBe(accountId);
+			expect(headers.get(OPENAI_HEADERS.BETA)).toBe(OPENAI_HEADER_VALUES.BETA_RESPONSES);
+			expect(headers.get(OPENAI_HEADERS.ORIGINATOR)).toBe(OPENAI_HEADER_VALUES.ORIGINATOR_CODEX);
+			expect(headers.has(OPENAI_HEADERS.SESSION_ID)).toBe(true);
+		});
+
+		it('should remove x-api-key header', () => {
+			const init = { headers: { 'x-api-key': 'should-be-removed' } };
+			const headers = createCodexHeaders(init, accountId, accessToken);
+
+			expect(headers.has('x-api-key')).toBe(false);
+		});
+
+		it('should preserve other existing headers', () => {
+			const init = { headers: { 'Content-Type': 'application/json' } };
+			const headers = createCodexHeaders(init, accountId, accessToken);
+
+			expect(headers.get('Content-Type')).toBe('application/json');
+		});
+
+		it('should generate unique session IDs', () => {
+			const headers1 = createCodexHeaders(undefined, accountId, accessToken);
+			const headers2 = createCodexHeaders(undefined, accountId, accessToken);
+
+			expect(headers1.get(OPENAI_HEADERS.SESSION_ID)).not.toBe(
+				headers2.get(OPENAI_HEADERS.SESSION_ID)
+			);
+		});
+
+		it('should validate session ID format (UUID)', () => {
+			const headers = createCodexHeaders(undefined, accountId, accessToken);
+			const sessionId = headers.get(OPENAI_HEADERS.SESSION_ID);
+
+			// UUID v4 format: xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx
+			expect(sessionId).toMatch(/^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/);
+		});
+	});
+});
@@ -0,0 +1,43 @@
+import { describe, it, expect } from 'vitest';
+import { LOGGING_ENABLED, logRequest } from '../lib/logger.js';
+
+describe('Logger Module', () => {
+	describe('LOGGING_ENABLED constant', () => {
+		it('should be a boolean', () => {
+			expect(typeof LOGGING_ENABLED).toBe('boolean');
+		});
+
+		it('should default to false when env variable is not set', () => {
+			// This test verifies the default behavior
+			// In a real test environment, ENABLE_PLUGIN_REQUEST_LOGGING would not be set
+			const isEnabled = process.env.ENABLE_PLUGIN_REQUEST_LOGGING === '1';
+			expect(typeof isEnabled).toBe('boolean');
+		});
+	});
+
+	describe('logRequest function', () => {
+		it('should accept stage and data parameters', () => {
+			// This should not throw
+			expect(() => {
+				logRequest('test-stage', { data: 'test' });
+			}).not.toThrow();
+		});
+
+		it('should handle empty data object', () => {
+			expect(() => {
+				logRequest('test-stage', {});
+			}).not.toThrow();
+		});
+
+		it('should handle complex data structures', () => {
+			expect(() => {
+				logRequest('test-stage', {
+					nested: { data: 'value' },
+					array: [1, 2, 3],
+					number: 123,
+					boolean: true,
+				});
+			}).not.toThrow();
+		});
+	});
+});
@@ -0,0 +1,289 @@
+import { describe, it, expect } from 'vitest';
+import {
+	normalizeModel,
+	filterInput,
+	addToolRemapMessage,
+	transformRequestBody,
+} from '../lib/request-transformer.js';
+import { TOOL_REMAP_MESSAGE } from '../lib/codex.js';
+import type { RequestBody, UserConfig, InputItem } from '../lib/types.js';
+
+describe('Request Transformer Module', () => {
+	describe('normalizeModel', () => {
+		it('should normalize gpt-5-codex', () => {
+			expect(normalizeModel('gpt-5-codex')).toBe('gpt-5-codex');
+		});
+
+		it('should normalize gpt-5', () => {
+			expect(normalizeModel('gpt-5')).toBe('gpt-5');
+		});
+
+		it('should normalize variants containing "codex"', () => {
+			expect(normalizeModel('openai/gpt-5-codex')).toBe('gpt-5-codex');
+			expect(normalizeModel('custom-gpt-5-codex-variant')).toBe('gpt-5-codex');
+		});
+
+		it('should normalize variants containing "gpt-5"', () => {
+			expect(normalizeModel('gpt-5-mini')).toBe('gpt-5');
+			expect(normalizeModel('gpt-5-nano')).toBe('gpt-5');
+		});
+
+		it('should return gpt-5 as default for unknown models', () => {
+			expect(normalizeModel('unknown-model')).toBe('gpt-5');
+			expect(normalizeModel('gpt-4')).toBe('gpt-5');
+		});
+
+		it('should return gpt-5 for undefined', () => {
+			expect(normalizeModel(undefined)).toBe('gpt-5');
+		});
+	});
+
+	describe('filterInput', () => {
+		it('should keep items without IDs', () => {
+			const input: InputItem[] = [
+				{ type: 'message', role: 'user', content: 'hello' },
+			];
+			const result = filterInput(input);
+			expect(result).toEqual(input);
+		});
+
+		it('should remove items with rs_ IDs', () => {
+			const input: InputItem[] = [
+				{ id: 'rs_123', type: 'message', role: 'user', content: 'hello' },
+				{ id: 'msg_456', type: 'message', role: 'user', content: 'world' },
+			];
+			const result = filterInput(input);
+			expect(result).toHaveLength(1);
+			expect(result![0].id).toBe('msg_456');
+		});
+
+		it('should handle mixed items', () => {
+			const input: InputItem[] = [
+				{ type: 'message', role: 'user', content: '1' },
+				{ id: 'rs_stored', type: 'message', role: 'assistant', content: '2' },
+				{ id: 'msg_123', type: 'message', role: 'user', content: '3' },
+			];
+			const result = filterInput(input);
+			expect(result).toHaveLength(2);
+			expect(result![0].content).toBe('1');
+			expect(result![1].content).toBe('3');
+		});
+
+		it('should return undefined for undefined input', () => {
+			expect(filterInput(undefined)).toBeUndefined();
+		});
+
+		it('should return non-array input as-is', () => {
+			const notArray = { notAnArray: true };
+			expect(filterInput(notArray as any)).toBe(notArray);
+		});
+	});
+
+	describe('addToolRemapMessage', () => {
+		it('should prepend tool remap message when tools present', () => {
+			const input: InputItem[] = [
+				{ type: 'message', role: 'user', content: 'hello' },
+			];
+			const result = addToolRemapMessage(input, true);
+
+			expect(result).toHaveLength(2);
+			expect(result![0].role).toBe('developer');
+			expect(result![0].type).toBe('message');
+			expect((result![0].content as any)[0].text).toContain('apply_patch');
+		});
+
+		it('should not modify input when tools not present', () => {
+			const input: InputItem[] = [
+				{ type: 'message', role: 'user', content: 'hello' },
+			];
+			const result = addToolRemapMessage(input, false);
+			expect(result).toEqual(input);
+		});
+
+		it('should return undefined for undefined input', () => {
+			expect(addToolRemapMessage(undefined, true)).toBeUndefined();
+		});
+
+		it('should handle non-array input', () => {
+			const notArray = { notAnArray: true };
+			expect(addToolRemapMessage(notArray as any, true)).toBe(notArray);
+		});
+	});
+
+	describe('transformRequestBody', () => {
+		const codexInstructions = 'Test Codex Instructions';
+
+		it('should set required Codex fields', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+
+			expect(result.store).toBe(false);
+			expect(result.stream).toBe(true);
+			expect(result.instructions).toBe(codexInstructions);
+		});
+
+		it('should normalize model name', () => {
+			const body: RequestBody = {
+				model: 'gpt-5-mini',
+				input: [],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.model).toBe('gpt-5');
+		});
+
+		it('should apply default reasoning config', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+
+			expect(result.reasoning?.effort).toBe('medium');
+			expect(result.reasoning?.summary).toBe('auto');
+		});
+
+		it('should apply user reasoning config', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const userConfig: UserConfig = {
+				global: {
+					reasoningEffort: 'high',
+					reasoningSummary: 'detailed',
+				},
+				models: {},
+			};
+			const result = transformRequestBody(body, codexInstructions, userConfig);
+
+			expect(result.reasoning?.effort).toBe('high');
+			expect(result.reasoning?.summary).toBe('detailed');
+		});
+
+		it('should apply default text verbosity', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.text?.verbosity).toBe('medium');
+		});
+
+		it('should apply user text verbosity', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const userConfig: UserConfig = {
+				global: { textVerbosity: 'low' },
+				models: {},
+			};
+			const result = transformRequestBody(body, codexInstructions, userConfig);
+			expect(result.text?.verbosity).toBe('low');
+		});
+
+		it('should set default include for encrypted reasoning', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.include).toEqual(['reasoning.encrypted_content']);
+		});
+
+		it('should use user-configured include', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const userConfig: UserConfig = {
+				global: { include: ['custom_field', 'reasoning.encrypted_content'] },
+				models: {},
+			};
+			const result = transformRequestBody(body, codexInstructions, userConfig);
+			expect(result.include).toEqual(['custom_field', 'reasoning.encrypted_content']);
+		});
+
+		it('should filter input array', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [
+					{ id: 'rs_123', type: 'message', role: 'assistant', content: 'old' },
+					{ type: 'message', role: 'user', content: 'new' },
+				],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.input).toHaveLength(1);
+			expect(result.input![0].content).toBe('new');
+		});
+
+		it('should add tool remap message when tools present', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [{ type: 'message', role: 'user', content: 'hello' }],
+				tools: [{ name: 'test_tool' }],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.input![0].role).toBe('developer');
+		});
+
+		it('should not add tool remap message when tools absent', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [{ type: 'message', role: 'user', content: 'hello' }],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.input![0].role).toBe('user');
+		});
+
+		it('should remove unsupported parameters', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+				max_output_tokens: 1000,
+				max_completion_tokens: 2000,
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.max_output_tokens).toBeUndefined();
+			expect(result.max_completion_tokens).toBeUndefined();
+		});
+
+		it('should normalize minimal to low for gpt-5-codex', () => {
+			const body: RequestBody = {
+				model: 'gpt-5-codex',
+				input: [],
+			};
+			const userConfig: UserConfig = {
+				global: { reasoningEffort: 'minimal' },
+				models: {},
+			};
+			const result = transformRequestBody(body, codexInstructions, userConfig);
+			expect(result.reasoning?.effort).toBe('low');
+		});
+
+		it('should preserve minimal for non-codex models', () => {
+			const body: RequestBody = {
+				model: 'gpt-5',
+				input: [],
+			};
+			const userConfig: UserConfig = {
+				global: { reasoningEffort: 'minimal' },
+				models: {},
+			};
+			const result = transformRequestBody(body, codexInstructions, userConfig);
+			expect(result.reasoning?.effort).toBe('minimal');
+		});
+
+		it('should use minimal effort for lightweight models', () => {
+			const body: RequestBody = {
+				model: 'gpt-5-nano',
+				input: [],
+			};
+			const result = transformRequestBody(body, codexInstructions);
+			expect(result.reasoning?.effort).toBe('minimal');
+		});
+	});
+});
@@ -0,0 +1,114 @@
+import { describe, it, expect, vi } from 'vitest';
+import { ensureContentType, convertSseToJson } from '../lib/response-handler.js';
+
+describe('Response Handler Module', () => {
+	describe('ensureContentType', () => {
+		it('should preserve existing content-type', () => {
+			const headers = new Headers();
+			headers.set('content-type', 'application/json');
+			const result = ensureContentType(headers);
+			expect(result.get('content-type')).toBe('application/json');
+		});
+
+		it('should add default content-type if missing', () => {
+			const headers = new Headers();
+			const result = ensureContentType(headers);
+			expect(result.get('content-type')).toBe('text/event-stream; charset=utf-8');
+		});
+
+		it('should not modify original headers', () => {
+			const headers = new Headers();
+			const result = ensureContentType(headers);
+			expect(headers.has('content-type')).toBe(false);
+			expect(result.has('content-type')).toBe(true);
+		});
+	});
+
+	describe('convertSseToJson', () => {
+		it('should throw error if response has no body', async () => {
+			const response = new Response(null);
+			const headers = new Headers();
+
+			await expect(convertSseToJson(response, headers)).rejects.toThrow(
+				'Response has no body'
+			);
+		});
+
+		it('should parse SSE stream with response.done event', async () => {
+			const sseContent = `data: {"type":"response.started"}
+data: {"type":"response.done","response":{"id":"resp_123","output":"test"}}
+`;
+			const response = new Response(sseContent);
+			const headers = new Headers();
+
+			const result = await convertSseToJson(response, headers);
+			const body = await result.json();
+
+			expect(body).toEqual({ id: 'resp_123', output: 'test' });
+			expect(result.headers.get('content-type')).toBe('application/json; charset=utf-8');
+		});
+
+		it('should parse SSE stream with response.completed event', async () => {
+			const sseContent = `data: {"type":"response.started"}
+data: {"type":"response.completed","response":{"id":"resp_456","output":"done"}}
+`;
+			const response = new Response(sseContent);
+			const headers = new Headers();
+
+			const result = await convertSseToJson(response, headers);
+			const body = await result.json();
+
+			expect(body).toEqual({ id: 'resp_456', output: 'done' });
+		});
+
+		it('should return original text if no final response found', async () => {
+			const sseContent = `data: {"type":"response.started"}
+data: {"type":"chunk","delta":"text"}
+`;
+			const response = new Response(sseContent);
+			const headers = new Headers();
+
+			const result = await convertSseToJson(response, headers);
+			const text = await result.text();
+
+			expect(text).toBe(sseContent);
+		});
+
+		it('should skip malformed JSON in SSE stream', async () => {
+			const sseContent = `data: not-json
+data: {"type":"response.done","response":{"id":"resp_789"}}
+`;
+			const response = new Response(sseContent);
+			const headers = new Headers();
+
+			const result = await convertSseToJson(response, headers);
+			const body = await result.json();
+
+			expect(body).toEqual({ id: 'resp_789' });
+		});
+
+		it('should handle empty SSE stream', async () => {
+			const response = new Response('');
+			const headers = new Headers();
+
+			const result = await convertSseToJson(response, headers);
+			const text = await result.text();
+
+			expect(text).toBe('');
+		});
+
+		it('should preserve response status and statusText', async () => {
+			const sseContent = `data: {"type":"response.done","response":{"id":"x"}}`;
+			const response = new Response(sseContent, {
+				status: 200,
+				statusText: 'OK',
+			});
+			const headers = new Headers();
+
+			const result = await convertSseToJson(response, headers);
+
+			expect(result.status).toBe(200);
+			expect(result.statusText).toBe('OK');
+		});
+	});
+});
@@ -0,0 +1,33 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "module": "ES2022",
+    "lib": [
+      "ES2022"
+    ],
+    "moduleResolution": "bundler",
+    "outDir": "./dist",
+    "rootDir": "./",
+    "strict": true,
+    "esModuleInterop": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "resolveJsonModule": true,
+    "declaration": true,
+    "declarationMap": true,
+    "sourceMap": true,
+    "types": [
+      "node"
+    ]
+  },
+  "include": [
+    "index.ts",
+    "lib/**/*.ts"
+  ],
+  "exclude": [
+    "node_modules",
+    "dist",
+    "test",
+    "**/*.mjs"
+  ]
+}
@@ -0,0 +1,13 @@
+import { defineConfig } from 'vitest/config';
+
+export default defineConfig({
+  test: {
+    globals: true,
+    environment: 'node',
+    coverage: {
+      provider: 'v8',
+      reporter: ['text', 'json', 'html'],
+      exclude: ['node_modules/', 'dist/', 'test/'],
+    },
+  },
+});