Add Codex Mini support

AGENTS.md

@@ -4,7 +4,7 @@ This file provides coding guidance for AI agents (including Claude Code, Codex,
 
 ## Overview
 
-This is an **opencode plugin** that enables OAuth authentication with OpenAI's ChatGPT Plus/Pro Codex backend. It allows users to access `gpt-5-codex` and `gpt-5` models through their ChatGPT subscription instead of using OpenAI Platform API credits.
+This is an **opencode plugin** that enables OAuth authentication with OpenAI's ChatGPT Plus/Pro Codex backend. It allows users to access `gpt-5-codex`, `gpt-5-codex-mini`, and `gpt-5` models through their ChatGPT subscription instead of using OpenAI Platform API credits.
 
 **Key architecture principle**: 7-step fetch flow that intercepts opencode's OpenAI SDK requests, transforms them for the ChatGPT backend API, and handles OAuth token management.
 
@@ -41,7 +41,7 @@ The main entry point orchestrates a **7-step fetch flow**:
 1. **Token Management**: Check token expiration, refresh if needed
 2. **URL Rewriting**: Transform OpenAI Platform API URLs → ChatGPT backend API (`https://chatgpt.com/backend-api/codex/responses`)
 3. **Request Transformation**:
-   - Normalize model names (all variants → `gpt-5` or `gpt-5-codex`)
+   - Normalize model names (all variants → `gpt-5`, `gpt-5-codex`, or `codex-mini-latest`)
    - Inject Codex system instructions from latest GitHub release
    - Apply reasoning configuration (effort, summary, verbosity)
    - Add CODEX_MODE bridge prompt (default) or tool remap message (legacy)
@@ -99,8 +99,9 @@ The main entry point orchestrates a **7-step fetch flow**:
 
 **4. Model Normalization**:
 - All `gpt-5-codex` variants → `gpt-5-codex`
+- All `gpt-5-codex-mini*` or `codex-mini-latest` variants → `codex-mini-latest`
 - All `gpt-5` variants → `gpt-5`
-- `minimal` effort auto-normalized to `low` for gpt-5-codex (API limitation)
+- `minimal` effort auto-normalized to `low` for gpt-5-codex (API limitation) and clamped to `medium` (or `high` when requested) for Codex Mini
 
 **5. Codex Instructions Caching**:
 - Fetches from latest release tag (not main branch)

CHANGELOG.md

@@ -2,6 +2,14 @@
 
 All notable changes to this project are documented here. Dates use the ISO format (YYYY-MM-DD).
 
+## [3.1.0] - 2025-11-11
+### Added
+- Codex Mini support end-to-end: normalization to the `codex-mini-latest` slug, proper reasoning defaults, and two new presets (`gpt-5-codex-mini-medium` / `gpt-5-codex-mini-high`).
+- Documentation & configuration updates describing the Codex Mini tier (200k input / 100k output tokens) plus refreshed totals (11 presets, 160+ unit tests).
+
+### Fixed
+- Prevented Codex Mini from inheriting the lightweight (`minimal`) reasoning profile used by `gpt-5-mini`/`nano`, ensuring the API always receives supported effort levels.
+
 ## [3.0.0] - 2025-11-04
 ### Added
 - Codex-style usage-limit messaging that mirrors the 5-hour and weekly windows reported by the Codex CLI.

CONTRIBUTING.md

@@ -36,7 +36,7 @@ All contributions MUST:
 ## Code Standards
 
 - **TypeScript:** All code must be TypeScript with strict type checking
-- **Testing:** Include tests for new functionality (we maintain 159+ unit tests)
+- **Testing:** Include tests for new functionality (we maintain 160+ unit tests)
 - **Documentation:** Update README.md for user-facing changes
 - **Modular design:** Keep functions focused and under 40 lines
 - **No external dependencies:** Minimize dependencies (currently only @openauthjs/openauth)

README.md

@@ -33,7 +33,7 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an
 ## Features
 
 - ✅ **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
+- ✅ **11 pre-configured model variants** - Includes Codex Mini (medium/high) alongside all gpt-5 and gpt-5-codex presets
 - ✅ **Zero external dependencies** - Lightweight with only @openauthjs/openauth
 - ✅ **Auto-refreshing tokens** - Handles token expiration automatically
 - ✅ **Prompt caching** - Reuses responses across turns via stable `prompt_cache_key`
@@ -43,7 +43,7 @@ Follow me on [X @nummanthinks](https://x.com/nummanthinks) for future updates an
 - ✅ **Automatic tool remapping** - Codex tools → opencode tools
 - ✅ **Configurable reasoning** - Control effort, summary verbosity, and text output
 - ✅ **Usage-aware errors** - Shows clear guidance when ChatGPT subscription limits are reached
-- ✅ **Type-safe & tested** - Strict TypeScript with 159 unit tests + 14 integration tests
+- ✅ **Type-safe & tested** - Strict TypeScript with 160+ unit tests + 14 integration tests
 - ✅ **Modular architecture** - Easy to maintain and extend
 
 ## Installation
@@ -123,6 +123,38 @@ For the complete experience with all reasoning variants matching the official Co
             "store": false
           }
         },
+        "gpt-5-codex-mini-medium": {
+          "name": "GPT 5 Codex Mini Medium (OAuth)",
+          "limit": {
+            "context": 200000,
+            "output": 100000
+          },
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
+        "gpt-5-codex-mini-high": {
+          "name": "GPT 5 Codex Mini High (OAuth)",
+          "limit": {
+            "context": 200000,
+            "output": 100000
+          },
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
         "gpt-5-minimal": {
           "name": "GPT 5 Minimal (OAuth)",
           "limit": {
@@ -228,8 +260,9 @@ For the complete experience with all reasoning variants matching the official Co
    **Global config**: `~/.config/opencode/opencode.json`
    **Project config**: `<project>/.opencode.json`
 
-   This gives you 9 model variants with different reasoning levels:
+   This gives you 11 model variants with different reasoning levels:
    - **gpt-5-codex** (low/medium/high) - Code-optimized reasoning
+   - **gpt-5-codex-mini** (medium/high) - Cheaper Codex tier with 200k/100k tokens
    - **gpt-5** (minimal/low/medium/high) - General-purpose reasoning
    - **gpt-5-mini** and **gpt-5-nano** - Lightweight variants
 
@@ -316,6 +349,8 @@ When using [`config/full-opencode.json`](./config/full-opencode.json), you get t
 | `gpt-5-codex-low` | GPT 5 Codex Low (OAuth) | Low | Fast code generation |
 | `gpt-5-codex-medium` | GPT 5 Codex Medium (OAuth) | Medium | Balanced code tasks |
 | `gpt-5-codex-high` | GPT 5 Codex High (OAuth) | High | Complex code & tools |
+| `gpt-5-codex-mini-medium` | GPT 5 Codex Mini Medium (OAuth) | Medium | Cheaper Codex tier (200k/100k) |
+| `gpt-5-codex-mini-high` | GPT 5 Codex Mini High (OAuth) | High | Codex Mini with maximum reasoning |
 | `gpt-5-minimal` | GPT 5 Minimal (OAuth) | Minimal | Quick answers, simple tasks |
 | `gpt-5-low` | GPT 5 Low (OAuth) | Low | Faster responses with light reasoning |
 | `gpt-5-medium` | GPT 5 Medium (OAuth) | Medium | Balanced general-purpose tasks |
@@ -326,6 +361,8 @@ When using [`config/full-opencode.json`](./config/full-opencode.json), you get t
 **Usage**: `--model=openai/<CLI Model ID>` (e.g., `--model=openai/gpt-5-codex-low`)
 **Display**: TUI shows the friendly name (e.g., "GPT 5 Codex Low (OAuth)")
 
+> **Note**: All `gpt-5-codex-mini*` presets normalize to the ChatGPT slug `codex-mini-latest` (200k input / 100k output tokens).
+
 All accessed via your ChatGPT Plus/Pro subscription.
 
 ### Using in Custom Commands
@@ -365,7 +402,7 @@ These defaults match the official Codex CLI behavior and can be customized (see
 ### Recommended: Use Pre-Configured File
 
 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
+- 11 pre-configured model variants matching Codex CLI presets
 - Optimal settings for each reasoning level
 - All variants visible in the opencode model selector
 

config/README.md

@@ -28,7 +28,7 @@ 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)
+- All supported model variants (gpt-5-codex, gpt-5-codex-mini, gpt-5, gpt-5-mini, gpt-5-nano)
 
 ## Usage
 

config/full-opencode.json

@@ -63,6 +63,38 @@
             "store": false
           }
         },
+        "gpt-5-codex-mini-medium": {
+          "name": "GPT 5 Codex Mini Medium (OAuth)",
+          "limit": {
+            "context": 200000,
+            "output": 100000
+          },
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
+        "gpt-5-codex-mini-high": {
+          "name": "GPT 5 Codex Mini High (OAuth)",
+          "limit": {
+            "context": 200000,
+            "output": 100000
+          },
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium",
+            "include": [
+              "reasoning.encrypted_content"
+            ],
+            "store": false
+          }
+        },
         "gpt-5-minimal": {
           "name": "GPT 5 Minimal (OAuth)",
           "limit": {

docs/README.md

@@ -28,7 +28,7 @@ This plugin bridges two different systems with careful engineering:
 4. **15-Minute Caching** - Prevents GitHub API rate limit exhaustion
 5. **Per-Model Configuration** - Enables quality presets with quick switching
 
-**Testing**: 159 unit tests + 14 integration tests with actual API verification
+**Testing**: 160+ unit tests + 14 integration tests with actual API verification
 
 ---
 

docs/configuration.md

@@ -57,7 +57,9 @@ Controls computational effort for reasoning.
 - `medium` - Balanced (default)
 - `high` - Maximum code quality
 
-**Note**: `minimal` auto-converts to `low` for gpt-5-codex (API limitation)
+**Notes**:
+- `minimal` auto-converts to `low` for gpt-5-codex (API limitation)
+- `gpt-5-codex-mini*` only supports `medium` or `high`; lower settings are clamped to `medium`
 
 **Example:**
 ```json
@@ -379,7 +381,7 @@ CODEX_MODE=1 opencode run "task"  # Temporarily enable
 ## Configuration Files
 
 **Provided Examples:**
-- [config/full-opencode.json](../config/full-opencode.json) - Complete with 9 variants
+- [config/full-opencode.json](../config/full-opencode.json) - Complete with 11 variants (adds Codex Mini presets)
 - [config/minimal-opencode.json](../config/minimal-opencode.json) - Minimal setup
 
 > **Why choose the full config?** OpenCode's auto-compaction and usage widgets rely on the per-model `limit` metadata present only in `full-opencode.json`. Use the minimal config only if you don't need those UI features.

docs/development/ARCHITECTURE.md

@@ -262,8 +262,8 @@ let include: Vec<String> = if reasoning.is_some() {
    └─ tools: [...]
 
 2. Model Normalization
-   ├─ Detect codex/gpt-5 variants
-   └─ Normalize to "gpt-5" or "gpt-5-codex"
+   ├─ Detect codex/gpt-5/codex-mini variants
+   └─ Normalize to "gpt-5", "gpt-5-codex", or "codex-mini-latest"
 
 3. Config Merging
    ├─ Global options (provider.openai.options)
@@ -314,7 +314,7 @@ let include: Vec<String> = if reasoning.is_some() {
 | **store Parameter** | `false` (ChatGPT) | `false` | ✅ |
 | **Message IDs** | Stripped in stateless | Stripped | ✅ |
 | **reasoning.encrypted_content** | ✅ Included | ✅ Included | ✅ |
-| **Model Normalization** | "gpt-5" / "gpt-5-codex" | Same | ✅ |
+| **Model Normalization** | "gpt-5" / "gpt-5-codex" / "codex-mini-latest" | Same | ✅ |
 | **Reasoning Effort** | medium (default) | medium (default) | ✅ |
 | **Text Verbosity** | medium (codex), low (gpt-5) | Same | ✅ |
 

docs/development/TESTING.md

@@ -577,6 +577,8 @@ opencode
 normalizeModel("gpt-5-codex")          // → "gpt-5-codex" ✅
 normalizeModel("gpt-5-codex-low")      // → "gpt-5-codex" ✅
 normalizeModel("GPT-5-CODEX-HIGH")     // → "gpt-5-codex" ✅
+normalizeModel("gpt-5-codex-mini-high")// → "codex-mini-latest" ✅
+normalizeModel("codex-mini-latest")    // → "codex-mini-latest" ✅
 normalizeModel("my-codex-model")       // → "gpt-5-codex" ✅
 normalizeModel("gpt-5")                // → "gpt-5" ✅
 normalizeModel("gpt-5-mini")           // → "gpt-5" ✅
@@ -590,17 +592,25 @@ normalizeModel("random-model")         // → "gpt-5" ✅ (fallback)
 ```typescript
 export function normalizeModel(model: string | undefined): string {
   if (!model) return "gpt-5";
-  if (model.includes("codex")) return "gpt-5-codex";  // Check codex first
-  if (model.includes("gpt-5")) return "gpt-5";        // Then gpt-5
-  return "gpt-5";  // Safe fallback
+  const normalized = model.toLowerCase();
+  if (normalized.includes("codex-mini") || normalized.includes("codex-mini-latest")) {
+    return "codex-mini-latest";
+  }
+  if (normalized.includes("codex")) {
+    return "gpt-5-codex";
+  }
+  if (normalized.includes("gpt-5") || normalized.includes("gpt 5")) {
+    return "gpt-5";
+  }
+  return "gpt-5";
 }
 ```
 
 **Why this works:**
-- ✅ Case-insensitive (`.includes()` works with any case)
+- ✅ Case-insensitive (`.toLowerCase()` + `.includes()`)
 - ✅ Pattern-based (works with any naming)
 - ✅ Safe fallback (unknown models → `gpt-5`)
-- ✅ Codex priority (checks "codex" before "gpt-5")
+- ✅ Codex priority with explicit Codex Mini support (`codex-mini*` → `codex-mini-latest`)
 
 ---
 
@@ -657,12 +667,14 @@ describe('normalizeModel', () => {
   test('handles all default models', () => {
     expect(normalizeModel('gpt-5')).toBe('gpt-5')
     expect(normalizeModel('gpt-5-codex')).toBe('gpt-5-codex')
+    expect(normalizeModel('gpt-5-codex-mini')).toBe('codex-mini-latest')
     expect(normalizeModel('gpt-5-mini')).toBe('gpt-5')
     expect(normalizeModel('gpt-5-nano')).toBe('gpt-5')
   })
 
   test('handles custom preset names', () => {
     expect(normalizeModel('gpt-5-codex-low')).toBe('gpt-5-codex')
+    expect(normalizeModel('openai/gpt-5-codex-mini-high')).toBe('codex-mini-latest')
     expect(normalizeModel('gpt-5-high')).toBe('gpt-5')
   })
 
@@ -672,6 +684,7 @@ describe('normalizeModel', () => {
 
   test('handles edge cases', () => {
     expect(normalizeModel(undefined)).toBe('gpt-5')
+    expect(normalizeModel('codex-mini-latest')).toBe('codex-mini-latest')
     expect(normalizeModel('random')).toBe('gpt-5')
   })
 })

docs/getting-started.md

@@ -28,7 +28,7 @@ OpenCode automatically installs plugins - no `npm install` needed!
 
 #### Option A: Full Configuration (Recommended)
 
-Get 9 pre-configured model variants with optimal settings.
+Get 11 pre-configured model variants with optimal settings (including Codex Mini).
 
 Add this to `~/.config/opencode/opencode.json`:
 
@@ -88,6 +88,34 @@ Add this to `~/.config/opencode/opencode.json`:
             "store": false
           }
         },
+        "gpt-5-codex-mini-medium": {
+          "name": "GPT 5 Codex Mini Medium (OAuth)",
+          "limit": {
+            "context": 200000,
+            "output": 100000
+          },
+          "options": {
+            "reasoningEffort": "medium",
+            "reasoningSummary": "auto",
+            "textVerbosity": "medium",
+            "include": ["reasoning.encrypted_content"],
+            "store": false
+          }
+        },
+        "gpt-5-codex-mini-high": {
+          "name": "GPT 5 Codex Mini High (OAuth)",
+          "limit": {
+            "context": 200000,
+            "output": 100000
+          },
+          "options": {
+            "reasoningEffort": "high",
+            "reasoningSummary": "detailed",
+            "textVerbosity": "medium",
+            "include": ["reasoning.encrypted_content"],
+            "store": false
+          }
+        },
         "gpt-5-minimal": {
           "name": "GPT 5 Minimal (OAuth)",
           "limit": {
@@ -181,7 +209,9 @@ Add this to `~/.config/opencode/opencode.json`:
 **What you get:**
 - ✅ GPT-5 Codex (Low/Medium/High reasoning)
 - ✅ GPT-5 (Minimal/Low/Medium/High reasoning)
-- ✅ gpt-5-mini, gpt-5-nano (lightweight variants)
+- ✅ gpt-5-codex-mini (medium/high) plus gpt-5-mini & gpt-5-nano (lightweight variants)
+
+> Codex Mini presets normalize to the ChatGPT slug `codex-mini-latest` (200k input / 100k output tokens).
 - ✅ 272k context + 128k output window for every preset
 - ✅ All visible in OpenCode model selector
 - ✅ Optimal settings for each reasoning level
@@ -230,7 +260,7 @@ opencode run "write hello world to test.txt" --model=openai/gpt-5-codex
 opencode
 ```
 
-If using full config, you'll see all 9 variants in the model selector!
+If using full config, you'll see all 11 variants (including Codex Mini) in the model selector!
 
 ---
 

docs/index.md

@@ -82,11 +82,11 @@ opencode run "write hello world to test.txt" --model=openai/gpt-5-codex
 ## Features
 
 ✅ **OAuth Authentication** - Secure ChatGPT Plus/Pro login
-✅ **Multiple Models** - gpt-5, gpt-5-codex, gpt-5-mini, gpt-5-nano
+✅ **Multiple Models** - gpt-5, gpt-5-codex, gpt-5-codex-mini, gpt-5-mini, gpt-5-nano
 ✅ **Per-Model Configuration** - Different reasoning effort, verbosity for each variant
 ✅ **Multi-Turn Conversations** - Full conversation history with stateless backend
 ✅ **Backwards Compatible** - Works with old and new config formats
-✅ **Comprehensive Testing** - 159 unit tests + 14 integration tests
+✅ **Comprehensive Testing** - 160+ unit tests + 14 integration tests
 
 ---
 

lib/request/request-transformer.ts

@@ -1,13 +1,13 @@
+import { logDebug, logWarn } from "../logger.js";
 import { TOOL_REMAP_MESSAGE } from "../prompts/codex.js";
 import { CODEX_OPENCODE_BRIDGE } from "../prompts/codex-opencode-bridge.js";
 import { getOpenCodeCodexPrompt } from "../prompts/opencode-codex.js";
-import { logDebug, logWarn } from "../logger.js";
 import type {
-	UserConfig,
 	ConfigOptions,
+	InputItem,
 	ReasoningConfig,
 	RequestBody,
-	InputItem,
+	UserConfig,
 } from "../types.js";
 
 /**
@@ -18,12 +18,18 @@ import type {
 export function normalizeModel(model: string | undefined): string {
 	if (!model) return "gpt-5";
 
+	const normalized = model.toLowerCase();
+
+	if (normalized.includes("codex-mini")) {
+		return "codex-mini-latest";
+	}
+
 	// Case-insensitive check for "codex" anywhere in the model name
-	if (model.toLowerCase().includes("codex")) {
+	if (normalized.includes("codex")) {
 		return "gpt-5-codex";
 	}
 	// Case-insensitive check for "gpt-5" or "gpt 5" (with space)
-	if (model.toLowerCase().includes("gpt-5") || model.toLowerCase().includes("gpt 5")) {
+	if (normalized.includes("gpt-5") || normalized.includes("gpt 5")) {
 		return "gpt-5";
 	}
 
@@ -64,18 +70,37 @@ export function getReasoningConfig(
 	originalModel: string | undefined,
 	userConfig: ConfigOptions = {},
 ): ReasoningConfig {
+	const normalizedOriginal = originalModel?.toLowerCase() ?? "";
+	const isCodexMini =
+		normalizedOriginal.includes("codex-mini") ||
+		normalizedOriginal.includes("codex mini") ||
+		normalizedOriginal.includes("codex_mini") ||
+		normalizedOriginal.includes("codex-mini-latest");
+	const isCodex = normalizedOriginal.includes("codex") && !isCodexMini;
 	const isLightweight =
-		originalModel?.includes("nano") || originalModel?.includes("mini");
-	const isCodex = originalModel?.includes("codex");
+		!isCodexMini &&
+		(normalizedOriginal.includes("nano") ||
+			normalizedOriginal.includes("mini"));
 
 	// Default based on model type (Codex CLI defaults)
-	const defaultEffort: "minimal" | "low" | "medium" | "high" = isLightweight
-		? "minimal"
-		: "medium";
+	const defaultEffort: "minimal" | "low" | "medium" | "high" = isCodexMini
+		? "medium"
+		: isLightweight
+			? "minimal"
+			: "medium";
 
 	// Get user-requested effort
 	let effort = userConfig.reasoningEffort || defaultEffort;
 
+	if (isCodexMini) {
+		if (effort === "minimal" || effort === "low") {
+			effort = "medium";
+		}
+		if (effort !== "high") {
+			effort = "medium";
+		}
+	}
+
 	// Normalize "minimal" to "low" for gpt-5-codex
 	// Codex CLI does not provide a "minimal" preset for gpt-5-codex
 	// (only low/medium/high - see model_presets.rs:20-40)
@@ -293,10 +318,13 @@ export async function transformRequestBody(
 	const modelConfig = getModelConfig(lookupModel, userConfig);
 
 	// Debug: Log which config was resolved
-	logDebug(`Model config lookup: "${lookupModel}" → normalized to "${normalizedModel}" for API`, {
-		hasModelSpecificConfig: !!userConfig.models?.[lookupModel],
-		resolvedConfig: modelConfig,
-	});
+	logDebug(
+		`Model config lookup: "${lookupModel}" → normalized to "${normalizedModel}" for API`,
+		{
+			hasModelSpecificConfig: !!userConfig.models?.[lookupModel],
+			resolvedConfig: modelConfig,
+		},
+	);
 
 	// Normalize model name for API call
 	body.model = normalizedModel;
@@ -307,23 +335,33 @@ export async function transformRequestBody(
 	body.stream = true;
 	body.instructions = codexInstructions;
 
-    // Prompt caching relies on the host providing a stable prompt_cache_key
-    // (OpenCode passes its session identifier). We no longer synthesize one here.
+	// Prompt caching relies on the host providing a stable prompt_cache_key
+	// (OpenCode passes its session identifier). We no longer synthesize one here.
 
 	// Filter and transform input
 	if (body.input && Array.isArray(body.input)) {
 		// Debug: Log original input message IDs before filtering
-		const originalIds = body.input.filter(item => item.id).map(item => item.id);
+		const originalIds = body.input
+			.filter((item) => item.id)
+			.map((item) => item.id);
 		if (originalIds.length > 0) {
-			logDebug(`Filtering ${originalIds.length} message IDs from input:`, originalIds);
+			logDebug(
+				`Filtering ${originalIds.length} message IDs from input:`,
+				originalIds,
+			);
 		}
 
 		body.input = filterInput(body.input);
 
 		// Debug: Verify all IDs were removed
-		const remainingIds = (body.input || []).filter(item => item.id).map(item => item.id);
+		const remainingIds = (body.input || [])
+			.filter((item) => item.id)
+			.map((item) => item.id);
 		if (remainingIds.length > 0) {
-			logWarn(`WARNING: ${remainingIds.length} IDs still present after filtering:`, remainingIds);
+			logWarn(
+				`WARNING: ${remainingIds.length} IDs still present after filtering:`,
+				remainingIds,
+			);
 		} else if (originalIds.length > 0) {
 			logDebug(`Successfully removed all ${originalIds.length} message IDs`);
 		}

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "opencode-openai-codex-auth",
-  "version": "3.0.0",
+  "version": "3.1.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "opencode-openai-codex-auth",
-      "version": "3.0.0",
+      "version": "3.1.0",
       "license": "MIT",
       "dependencies": {
         "@openauthjs/openauth": "^0.4.3",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-openai-codex-auth",
-  "version": "3.0.0",
+  "version": "3.1.0",
   "description": "OpenAI ChatGPT (Codex backend) OAuth auth plugin for opencode - use your ChatGPT Plus/Pro subscription instead of API credits",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",

test/config.test.ts

@@ -52,10 +52,10 @@ describe('Configuration Parsing', () => {
 		});
 	});
 
-	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);
+		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');
@@ -99,13 +99,37 @@ describe('Configuration Parsing', () => {
 			expect(highReasoning.summary).toBe('auto');
 		});
 
-		it('should respect custom summary setting', () => {
-			const detailedConfig = { reasoningSummary: 'detailed' as const };
-			const detailedReasoning = getReasoningConfig('gpt-5-codex', detailedConfig);
+			it('should respect custom summary setting', () => {
+				const detailedConfig = { reasoningSummary: 'detailed' as const };
+				const detailedReasoning = getReasoningConfig('gpt-5-codex', detailedConfig);
 
-			expect(detailedReasoning.summary).toBe('detailed');
+				expect(detailedReasoning.summary).toBe('detailed');
+			});
+
+			it('should default codex-mini to medium effort', () => {
+				const codexMiniReasoning = getReasoningConfig('gpt-5-codex-mini', {});
+				expect(codexMiniReasoning.effort).toBe('medium');
+			});
+
+			it('should clamp codex-mini minimal/low to medium', () => {
+				const minimal = getReasoningConfig('gpt-5-codex-mini', {
+					reasoningEffort: 'minimal',
+				});
+				const low = getReasoningConfig('gpt-5-codex-mini-high', {
+					reasoningEffort: 'low',
+				});
+
+				expect(minimal.effort).toBe('medium');
+				expect(low.effort).toBe('medium');
+			});
+
+			it('should keep codex-mini high effort when requested', () => {
+				const high = getReasoningConfig('codex-mini-latest', {
+					reasoningEffort: 'high',
+				});
+				expect(high.effort).toBe('high');
+			});
 		});
-	});
 
 	describe('Model-specific behavior', () => {
 		it('should detect lightweight models correctly', () => {

test/request-transformer.test.ts

@@ -63,6 +63,18 @@ describe('Request Transformer Module', () => {
 				expect(normalizeModel('gpt-5-codex-low')).toBe('gpt-5-codex');
 				expect(normalizeModel('my-gpt-5-codex-model')).toBe('gpt-5-codex');
 			});
+
+			it('should normalize codex mini presets to codex-mini-latest', async () => {
+				expect(normalizeModel('gpt-5-codex-mini')).toBe('codex-mini-latest');
+				expect(normalizeModel('gpt-5-codex-mini-medium')).toBe('codex-mini-latest');
+				expect(normalizeModel('gpt-5-codex-mini-high')).toBe('codex-mini-latest');
+				expect(normalizeModel('openai/gpt-5-codex-mini-high')).toBe('codex-mini-latest');
+			});
+
+			it('should normalize raw codex-mini-latest slug to codex-mini-latest', async () => {
+				expect(normalizeModel('codex-mini-latest')).toBe('codex-mini-latest');
+				expect(normalizeModel('openai/codex-mini-latest')).toBe('codex-mini-latest');
+			});
 		});
 
 		// NEW: Edge case tests
@@ -70,6 +82,7 @@ describe('Request Transformer Module', () => {
 			it('should handle uppercase model names', async () => {
 				expect(normalizeModel('GPT-5-CODEX')).toBe('gpt-5-codex');
 				expect(normalizeModel('GPT-5-HIGH')).toBe('gpt-5');
+				expect(normalizeModel('CODEx-MINI-LATEST')).toBe('codex-mini-latest');
 			});
 
 			it('should handle mixed case', async () => {