v0.7.7

- Add batch processing function to tools like TODO
            - Optimize part of UI display to avoid icon display anomalies and terminal jitter
            - Update Gemini thinking strength parameters
            - Persistent context information
            - Enhance robustness of `/btw` command
            - Remove outdated API setting parameters

Author: MayDay-wpf

.github/workflows/publish.yml

@@ -56,7 +56,12 @@ jobs:
 
             ### What's New
 
-            - Fixed some known bugs
+            - Add batch processing function to tools like TODO
+            - Optimize part of UI display to avoid icon display anomalies and terminal jitter
+            - Update Gemini thinking strength parameters
+            - Persistent context information
+            - Enhance robustness of `/btw` command
+            - Remove outdated API setting parameters
 
             ### Installation
             ```bash

docs/usage/en/02.First Time Configuration.md

@@ -426,40 +426,6 @@ When selecting the `OpenAI Responses` request method, the following configuratio
 - Setting too high will increase response time and cost
 - Recommend setting reasonably based on actual needs
 
-#### Edit Similarity Threshold (Advanced Option, Change with Caution)
-
-**Purpose**: Controls matching precision when AI modifies files, affecting code editing accuracy
-
-**Default**: 0.75
-
-**Range**: 0.1 - 1.0 (decimal)
-
-**Configuration Method**:
-
-- Press Enter to enter edit mode
-- Input decimal number (e.g., 0.75, 0.8)
-- Supports backspace deletion
-- Press Enter to confirm
-
-**Explanation**:
-
-- **Higher threshold**: Stricter matching, only very similar code will be modified, reducing risk of incorrect modifications
-- **Lower threshold**: Looser matching, allows more differences (like indentation, whitespace), increasing flexibility
-- **Default 0.75**: Balances precision and flexibility, suitable for most scenarios
-
-**Recommendations**:
-
-- Keep default value unless encountering specific issues
-- If AI frequently can't find code to modify, slightly decrease (e.g., 0.6-0.7)
-- If AI incorrectly modifies similar but different code, slightly increase (e.g., 0.8-0.85)
-- Not recommended to set below 0.6 or above 0.9
-
-**Important Notes**:
-
-- This configuration affects all code editing operations
-- Changes take effect immediately without restart
-- Incorrect settings may cause code editing failures or incorrect modifications
-
 ## Configuration Interface Operations
 
 ### Basic Operations

docs/usage/en/21.Custom StatusLine Guide.md

@@ -182,7 +182,7 @@ Each render item supports the following fields:
 			thinkingBudgetTokens: 4096,
 			thinkingEffort: 'medium',
 			geminiThinkingEnabled: false,
-			geminiThinkingBudget: 4096,
+			geminiThinkingLevel: 'high',
 			responsesReasoningEnabled: false,
 			responsesReasoningEffort: 'medium',
 			responsesFastMode: false,
@@ -195,7 +195,6 @@ Each render item supports the following fields:
 			streamIdleTimeoutSec: 180,
 			systemPromptId: ['default'],
 			customHeadersSchemeId: 'default',
-			editSimilarityThreshold: 0.75,
 			toolResultTokenLimit: 100000,
 			streamingDisplay: false,
 		},
@@ -225,7 +224,7 @@ Available fields under `system`:
 - `system.codebase`: codebase indexing state, including `indexing` and `progress`
 - `system.watcher`: file watcher state, including `enabled` and `fileUpdateNotification`
 - `system.clipboard`: most recent copy feedback, including `text`, `isError`, `timestamp`
-- `system.profile`: current profile full configuration, including `currentName`, `baseUrl`, `requestMethod`, `advancedModel`, `basicModel`, `maxContextTokens`, `maxTokens`, `anthropicBeta`, `anthropicCacheTTL`, `thinkingEnabled`, `thinkingType`, `thinkingBudgetTokens`, `thinkingEffort`, `geminiThinkingEnabled`, `geminiThinkingBudget`, `responsesReasoningEnabled`, `responsesReasoningEffort`, `responsesFastMode`, `responsesVerbosity`, `anthropicSpeed`, `enablePromptOptimization`, `enableAutoCompress`, `autoCompressThreshold`, `showThinking`, `streamIdleTimeoutSec`, `systemPromptId`, `customHeadersSchemeId`, `editSimilarityThreshold`, `toolResultTokenLimit`, `streamingDisplay` (excluding `apiKey`)
+- `system.profile`: current profile full configuration, including `currentName`, `baseUrl`, `requestMethod`, `advancedModel`, `basicModel`, `maxContextTokens`, `maxTokens`, `anthropicBeta`, `anthropicCacheTTL`, `thinkingEnabled`, `thinkingType`, `thinkingBudgetTokens`, `thinkingEffort`, `geminiThinkingEnabled`, `geminiThinkingLevel`, `responsesReasoningEnabled`, `responsesReasoningEffort`, `responsesFastMode`, `responsesVerbosity`, `anthropicSpeed`, `enablePromptOptimization`, `enableAutoCompress`, `autoCompressThreshold`, `showThinking`, `streamIdleTimeoutSec`, `systemPromptId`, `customHeadersSchemeId`, `toolResultTokenLimit`, `streamingDisplay` (excluding `apiKey`)
 - `system.compression`: auto-compression state, including `blockToast`
 
 ## Example 1: Real Clock Plugin

docs/usage/zh/02.首次配置.md

@@ -426,40 +426,6 @@
 - 设置过大会增加响应时间和成本
 - 建议根据实际需求合理设置
 
-#### 文件编辑相似度阈值（高级选项，非必要不修改）
-
-**作用**：控制 AI 在修改文件时的匹配精度，影响代码编辑的准确性
-
-**默认值**：0.75
-
-**取值范围**：0.1 - 1.0（小数）
-
-**配置方式**：
-
-- 按回车键进入编辑模式
-- 输入数字，支持小数（如 0.75, 0.8）
-- 支持退格删除
-- 按回车键确认
-
-**说明**：
-
-- **阈值越高**：匹配越严格，只有非常相似的代码才会被修改，降低误修改风险
-- **阈值越低**：匹配越宽松，允许更多的差异（如缩进、空格），提高灵活性
-- **默认值 0.75**：在精确性和灵活性之间取得平衡，适用于大多数场景
-
-**建议**：
-
-- 保持默认值即可，除非遇到特殊问题
-- 如果 AI 经常找不到要修改的代码，可以适当降低（如 0.6-0.7）
-- 如果 AI 误修改了相似但不同的代码，可以适当提高（如 0.8-0.85）
-- 不建议设置低于 0.6 或高于 0.9
-
-**注意事项**：
-
-- 此配置影响所有代码编辑操作
-- 修改后立即生效，无需重启
-- 错误的设置可能导致代码编辑失败或误修改
-
 ## 配置界面操作说明
 
 ### 基本操作

docs/usage/zh/21.自定义StatusLine指南.md

@@ -182,7 +182,7 @@ export default {
 			thinkingBudgetTokens: 4096,
 			thinkingEffort: 'medium',
 			geminiThinkingEnabled: false,
-			geminiThinkingBudget: 4096,
+			geminiThinkingLevel: 'high',
 			responsesReasoningEnabled: false,
 			responsesReasoningEffort: 'medium',
 			responsesFastMode: false,
@@ -195,7 +195,6 @@ export default {
 			streamIdleTimeoutSec: 180,
 			systemPromptId: ['default'],
 			customHeadersSchemeId: 'default',
-			editSimilarityThreshold: 0.75,
 			toolResultTokenLimit: 100000,
 			streamingDisplay: false,
 		},
@@ -225,7 +224,7 @@ export default {
 - `system.codebase`：代码库索引状态，包含 `indexing` 和 `progress`
 - `system.watcher`：文件监视器状态，包含 `enabled` 和 `fileUpdateNotification`
 - `system.clipboard`：最近一次复制提示，包含 `text`、`isError`、`timestamp`
-- `system.profile`：当前 Profile 完整配置信息，包含 `currentName`、`baseUrl`、`requestMethod`、`advancedModel`、`basicModel`、`maxContextTokens`、`maxTokens`、`anthropicBeta`、`anthropicCacheTTL`、`thinkingEnabled`、`thinkingType`、`thinkingBudgetTokens`、`thinkingEffort`、`geminiThinkingEnabled`、`geminiThinkingBudget`、`responsesReasoningEnabled`、`responsesReasoningEffort`、`responsesFastMode`、`responsesVerbosity`、`anthropicSpeed`、`enablePromptOptimization`、`enableAutoCompress`、`autoCompressThreshold`、`showThinking`、`streamIdleTimeoutSec`、`systemPromptId`、`customHeadersSchemeId`、`editSimilarityThreshold`、`toolResultTokenLimit`、`streamingDisplay`（不含 `apiKey`）
+- `system.profile`：当前 Profile 完整配置信息，包含 `currentName`、`baseUrl`、`requestMethod`、`advancedModel`、`basicModel`、`maxContextTokens`、`maxTokens`、`anthropicBeta`、`anthropicCacheTTL`、`thinkingEnabled`、`thinkingType`、`thinkingBudgetTokens`、`thinkingEffort`、`geminiThinkingEnabled`、`geminiThinkingLevel`、`responsesReasoningEnabled`、`responsesReasoningEffort`、`responsesFastMode`、`responsesVerbosity`、`anthropicSpeed`、`enablePromptOptimization`、`enableAutoCompress`、`autoCompressThreshold`、`showThinking`、`streamIdleTimeoutSec`、`systemPromptId`、`customHeadersSchemeId`、`toolResultTokenLimit`、`streamingDisplay`（不含 `apiKey`）
 - `system.compression`：自动压缩提示，包含 `blockToast`
 
 ## 示例 1：真实可用的时钟插件

package-lock.json

@@ -1,6 +1,6 @@
 {
 	"name": "snow-ai",
-	"version": "0.7.6",
+	"version": "0.7.7",
 	"description": "Agentic coding in your terminal",
 	"license": "MIT",
 	"bin": {

package.json

@@ -499,7 +499,7 @@ export async function* createStreamingGeminiCompletion(
 			if (config.geminiThinking?.enabled && !options.disableThinking) {
 				requestBody.generationConfig = {
 					thinkingConfig: {
-						thinkingBudget: config.geminiThinking.budget,
+						thinkingLevel: config.geminiThinking.thinkingLevel || 'high',
 					},
 				};
 			}

source/api/gemini.ts

@@ -181,27 +181,37 @@ export async function fetchAvailableModels(): Promise<Model[]> {
 	try {
 		let models: Model[];
 
+		const defaultOpenAiBaseUrl = 'https://api.openai.com/v1';
+		const trimmedBaseUrl = config.baseUrl.replace(/\/$/, '');
+		const isDefaultBaseUrl =
+			!trimmedBaseUrl || trimmedBaseUrl === defaultOpenAiBaseUrl;
+
 		switch (config.requestMethod) {
-			case 'gemini':
+			case 'gemini': {
 				if (!config.apiKey) {
 					throw new Error('API key is required for Gemini API');
 				}
-				models = await fetchGeminiModels(
-					config.baseUrl.replace(/\/$/, ''),
-					config.apiKey,
-				);
+				const geminiBaseUrl = isDefaultBaseUrl
+					? 'https://generativelanguage.googleapis.com/v1beta'
+					: trimmedBaseUrl;
+				models = await fetchGeminiModels(geminiBaseUrl, config.apiKey);
 				break;
+			}
 
-			case 'anthropic':
+			case 'anthropic': {
 				if (!config.apiKey) {
 					throw new Error('API key is required for Anthropic API');
 				}
+				const anthropicBaseUrl = isDefaultBaseUrl
+					? 'https://api.anthropic.com/v1'
+					: trimmedBaseUrl;
 				models = await fetchAnthropicModels(
-					config.baseUrl.replace(/\/$/, ''),
+					anthropicBaseUrl,
 					config.apiKey,
 					customHeaders,
 				);
 				break;
+			}
 
 			case 'chat':
 			case 'responses':

source/api/models.ts

@@ -182,6 +182,10 @@ export const en: TranslationKeys = {
 		enablePromptOptimization: 'Enable Prompt Optimization:',
 		enableAutoCompress: 'Enable Auto Compression:',
 		autoCompressThreshold: 'Auto Compress Threshold (%):',
+		autoCompressThresholdHint:
+			'Algorithm: maxContextTokens × {percentage}% = {actualThreshold} tokens',
+		autoCompressThresholdDesc:
+			'Triggers compression when context exceeds this threshold (recommended 60-80%, too low impacts performance, too high defeats purpose)',
 		showThinking: 'Show Thinking Process:',
 		streamingDisplay: 'Streaming Line Display:',
 		thinkingEnabled: 'Thinking Enabled:',
@@ -191,7 +195,7 @@ export const en: TranslationKeys = {
 		thinkingBudgetTokens: 'Thinking Budget Tokens:',
 		thinkingEffort: 'Thinking Effort:',
 		geminiThinkingEnabled: 'Gemini Thinking Enabled:',
-		geminiThinkingBudget: 'Gemini Thinking Budget:',
+		geminiThinkingLevel: 'Gemini Thinking Level:',
 		responsesReasoningEnabled: 'Responses Reasoning Enabled:',
 		responsesReasoningEffort: 'Responses Reasoning Effort:',
 		responsesVerbosity: 'Responses Verbosity:',
@@ -206,8 +210,6 @@ export const en: TranslationKeys = {
 			'Algorithm: maxContextTokens × {percentage}% = {actualLimit} tokens',
 		toolResultTokenLimitDesc:
 			'Limits tool result as % of context window (recommended 20-40%, too low truncates, too high fills context)',
-		editSimilarityThreshold:
-			'Edit Similarity Threshold(0-1, change with caution):',
 		notSet: 'Not set',
 		enabled: '[✓] Enabled',
 		disabled: '[ ] Disabled',