feat: add gpt-6.1-terra and default exploration to high reasoning

.env.example

@@ -19,6 +19,10 @@ ARTEMIS_TOOL_FALLBACK_MAX_NO_PROGRESS_ATTEMPTS=3
 # default 表示不发送思考强度参数；接口不支持所选值时明确报错。
 OPENAI_REASONING_EFFORT=high
 
+# 探索独立默认值；网页已保存的探索配置优先，已创建会话保留快照。
+ARTEMIS_EXPLORATION_MODEL=gpt-6.1-terra
+ARTEMIS_EXPLORATION_REASONING_EFFORT=high
+
 # 1 跳过本次网页启动的 Codex MCP 与官方 artemis-use Skill 同步；默认自动安装/更新。
 ARTEMIS_SKIP_CODEX_SYNC=0
 

AGENTS.md

@@ -54,7 +54,7 @@ Windows 首次安装使用 `start.bat`，国内镜像使用 `start-cn.bat`。启
 - 历史压缩、视觉摘要与工具上下文调整须保留关键文件回执和来源，维护稳定的多轮前缀；缓存率使用实际用量加权统计，不把缓存输入当作消失的 token，也不承诺固定收益。
 - 设备动作回放已移除；只读历史步骤、截图和上下文回忆仍保留，不因 replay 命名误删这些能力。
 - 密钥仅通过网页或环境配置写入，读取配置不得回显；MCP 不接受密钥。全局配置修改影响后续任务，已保存配置优先于新安装默认值。
-- 新安装普通任务默认 `gpt-6-luna / high`，探索默认 `gpt-6.1-sol / high`；请求超时 300 秒、失败后重试 5 次、间隔 10 秒，视频分析与普通录屏关闭。接口不支持思考强度时明确报错，不静默降级。
+- 新安装普通任务默认 `gpt-6-luna / high`，探索默认 `gpt-6.1-terra / high`；请求超时 300 秒、失败后重试 5 次、间隔 10 秒，视频分析与普通录屏关闭。接口不支持思考强度时明确报错，不静默降级。
 - 业务环境恢复由任务提示词提出，不新增默认业务回滚流程；连接、录像、子进程和资源锁的运行时收尾仍然必需。
 
 ## Conventions

DESIGN.md

@@ -94,7 +94,7 @@ Flash 的最终 AI 判定与分析独立配置，默认关闭；首页功能配
 
 收藏保存独立模板与执行配置，用例复跑固定版本；删除原任务不破坏已保存模板。历史与导出的有效结论合并人工复验，不能用新裁定改写旧证据。
 
-普通任务新安装默认 `gpt-6-luna / high`，探索单独使用 `gpt-6.1-sol / high`，保留已有配置。上下文参照上限 300k、默认历史压缩预算 80k，均不表示整条任务累计 token 限额。优化稳定前缀时保留关键文件回执、路径、校验和来源；费用收益依实际网关用量及计价判断。
+普通任务新安装默认 `gpt-6-luna / high`，探索单独使用 `gpt-6.1-terra / high`，保留已有配置。上下文参照上限 300k、默认历史压缩预算 80k，均不表示整条任务累计 token 限额。优化稳定前缀时保留关键文件回执、路径、校验和来源；费用收益依实际网关用量及计价判断。
 
 普通 Pro 的计划全部完成后，执行循环返回既有收尾和最终验收流程，不要求额外设备动作；有新指导或验收反馈时先处理反馈，探索模式仍须交付完整报告。完成计划不等于测试通过。Operator 写入计划时拒绝新增或增加同名顶层里程碑，撤销该次写入并返回工具错误；局部替换不得夹带目标范围外的里程碑，已有重复项可继续整理，确需重复的阶段使用不同名称。
 

README.md

@@ -7,7 +7,7 @@
 ## 主要功能
 
 - **自然语言任务**：Flash 适合明确的操作流程，Pro 适合需要计划、分支探索和验证的任务。
-- **交互探索**：边执行边交流，也可录制人工示范；探索成功后生成一个可编辑、复跑的用例。默认使用独立的 `gpt-6.1-sol / high` 配置，超时暂停并保留进度。见 [探索模式](docs/exploration-mode.md)。
+- **交互探索**：边执行边交流，也可录制人工示范；探索成功后生成一个可编辑、复跑的用例。默认使用独立的 `gpt-6.1-terra / high` 配置，超时暂停并保留进度。见 [探索模式](docs/exploration-mode.md)。
 - **插件扩展**：在插件市场安装并启用电脑控制等能力，AI 在安卓任务中按需使用；手机、电脑的步骤与证据统一留档。见 [插件与跨端任务](docs/plugins.md)。
 - **可保存的模型配置**：支持自定义接口、模型、思考强度和超时重试，以及视频分析与录屏开关。
 - **批量测试**：按新版 Excel 模板导入提示词，每项可独立指定模型、模式和参数；任务可暂停、补充指导并继续。
@@ -57,7 +57,7 @@ cd Artemis-Eapil
 3. 输入任务目标，选择 Flash、Pro 或探索后执行；仅测试电脑时勾选输入区的“仅 PC”，无需手机或模拟器在线，但需已启用并授权的电脑观察插件。在工作区查看步骤、截图和结果。流程尚不明确时，选择探索并随时交流。
 4. 通过“报告与批量”导出报告或导入 Excel 用例；任务队列支持历史搜索。
 
-预设模型为 `gpt-6-luna`、`gpt-6.1-sol`、`gpt-6-astra`、`mimo-v2.6-pro`，主模型与兜底模型均可选择预设或填写自定义名称。新安装默认模型是 `gpt-6-luna`，思考强度默认 `high`（最高可选 `max`），单次请求超时 **300 秒**，失败后最多重试 **5 次**，间隔 **10 秒**。遇到 429 请求过多时改为每次等待 **60 秒**。连续 3 次没有有效工具调用时，本步骤改用 `gpt-6-luna`（high），兜底模型最多再尝试 3 次；下一步恢复首选模型。视频分析与录屏默认关闭。模型及思考参数是否可用取决于所配置网关；不支持时会明确报错。
+预设模型为 `gpt-6-luna`、`gpt-6.1-terra`、`gpt-6.1-sol`、`gpt-6-astra`、`mimo-v2.6-pro`，主模型与兜底模型均可选择预设或填写自定义名称。新安装默认模型是 `gpt-6-luna`，思考强度默认 `high`（最高可选 `max`），单次请求超时 **300 秒**，失败后最多重试 **5 次**，间隔 **10 秒**。遇到 429 请求过多时改为每次等待 **60 秒**。连续 3 次没有有效工具调用时，本步骤改用 `gpt-6-luna`（high），兜底模型最多再尝试 3 次；下一步恢复首选模型。视频分析与录屏默认关闭。模型及思考参数是否可用取决于所配置网关；不支持时会明确报错。
 
 也可在项目 `.env` 中设置 `OPENAI_API_KEY`、`OPENAI_BASE_URL` 和 `OPENAI_MODEL`，其他参数见 [.env.example](.env.example)。新安装默认接口地址为 `https://api-n-cd.playones.com/v1`；已保存的地址不变。直接编辑环境文件后需重启相应服务。不要提交自己的密钥。
 

apps/admin_console/services/model_settings_service.py

@@ -81,6 +81,7 @@ def get_model_settings() -> dict:
         "reasoning_effort": settings.OPENAI_REASONING_EFFORT,
         "model_presets": [
             "gpt-6-luna",
+            "gpt-6.1-terra",
             "gpt-6.1-sol",
             "gpt-6-astra",
             "mimo-v2.6-pro",

apps/showcase_ui/src/app/components/exploration-panel/exploration-panel.component.spec.ts

@@ -9,7 +9,7 @@ import { AgentStreamComponent } from '../agent-stream/agent-stream.component';
 @Component({selector:'app-agent-stream',standalone:true,template:'<ng-content></ng-content>'}) class StreamStub {conversationMessages=input<any[]>([]);demonstrations=input<any[]>([]);pendingQuestion=input('');useRecommendation=output<string>();}
 
 describe('Exploration conversation', () => {
-  const config = {model: 'gpt-6.1-sol', reasoning_effort: 'high', timeout_seconds: 1800, demonstration_timeout_seconds: 900, demonstration_warning_seconds: 60};
+  const config = {model: 'gpt-6.1-terra', reasoning_effort: 'high', timeout_seconds: 1800, demonstration_timeout_seconds: 900, demonstration_warning_seconds: 60};
   let current: ExplorationSession;
   let api: any;
   beforeEach(() => {

apps/showcase_ui/src/app/components/exploration-panel/exploration-panel.component.ts

@@ -44,7 +44,7 @@ export class ExplorationPanelComponent {
   private followsLatest = true;
   private requests = this.api.requests;
   private displayedId: string | null = null;
-  readonly models = ['gpt-6.1-sol', 'gpt-6-astra', 'gpt-6-luna', 'mimo-v2.6-pro', 'mimo-v2.6-flash'];
+  readonly models = ['gpt-6.1-terra', 'gpt-6.1-sol', 'gpt-6-astra', 'gpt-6-luna', 'mimo-v2.6-pro', 'mimo-v2.6-flash'];
   readonly efforts = ['default', 'none', 'minimal', 'low', 'medium', 'high', 'xhigh', 'max'];
 
   constructor() {

apps/showcase_ui/src/app/components/featured-tasks/featured-tasks.component.spec.ts

@@ -35,7 +35,7 @@ describe('Featured tasks',()=>{
     expect(fixture.nativeElement.textContent).not.toContain('旧任务部分配置缺失');
     fixture.nativeElement.querySelector('.configure').click();fixture.detectChanges();flushMicrotasks();
     const select:HTMLSelectElement=fixture.nativeElement.querySelector('app-model-selector select');
-    expect(Array.from(select.options,option=>option.value)).toEqual(['gpt-6-luna','gpt-6.1-sol','gpt-6-astra','mimo-v2.6-pro','__custom__']);
+    expect(Array.from(select.options,option=>option.value)).toEqual(['gpt-6-luna','gpt-6.1-terra', 'gpt-6.1-sol','gpt-6-astra','mimo-v2.6-pro','__custom__']);
     expect(select.value).toBe('__custom__');
     expect(fixture.nativeElement.querySelector('input[aria-label="复跑模型（自定义）"]').value).toBe('original-model');
     select.value='gpt-6-luna';select.dispatchEvent(new Event('change'));fixture.detectChanges();

apps/showcase_ui/src/app/components/model-settings/model-settings.component.spec.ts

@@ -11,7 +11,7 @@ describe('持久化模型与功能设置', () => {
     api_key_configured: true, timeout_seconds: 300, max_retries: 5, retry_interval_seconds: 10, reasoning_effort: 'high',
     rate_limit_retry_seconds: 60, tool_fallback_model: 'gpt-6-luna', tool_fallback_reasoning_effort: 'high',
     tool_fallback_max_retries: 3, tool_fallback_no_progress_attempts: 3,
-    model_presets: ['gpt-6-luna', 'gpt-6.1-sol', 'gpt-6-astra', 'mimo-v2.6-pro'], env_path: '/app/.env' };
+    model_presets: ['gpt-6-luna', 'gpt-6.1-terra', 'gpt-6.1-sol', 'gpt-6-astra', 'mimo-v2.6-pro'], env_path: '/app/.env' };
   beforeEach(() => {
     TestBed.configureTestingModule({ providers: [provideHttpClient(), provideHttpClientTesting()] });
     http = TestBed.inject(HttpTestingController);

apps/showcase_ui/src/app/core/model-presets.ts

@@ -1 +1 @@
-export const MODEL_PRESETS = ['gpt-6-luna', 'gpt-6.1-sol', 'gpt-6-astra', 'mimo-v2.6-pro'];
+export const MODEL_PRESETS = ['gpt-6-luna', 'gpt-6.1-terra', 'gpt-6.1-sol', 'gpt-6-astra', 'mimo-v2.6-pro'];

apps/showcase_ui/src/app/pages/home/home.component.html

@@ -1518,7 +1518,7 @@
               @if(explorationSettingsOpen()) {
                 <div class="exploration-settings-body">
                   <label class="model-label">探索模型<input list="explore-models" [(ngModel)]="config.model" [disabled]="explorationSettingsBusy()" /></label>
-                  <datalist id="explore-models"><option value="gpt-6.1-sol"></option><option value="gpt-6-astra"></option><option value="gpt-6-luna"></option><option value="mimo-v2.6-pro"></option></datalist>
+                  <datalist id="explore-models"><option value="gpt-6.1-terra"></option><option value="gpt-6.1-sol"></option><option value="gpt-6-astra"></option><option value="gpt-6-luna"></option><option value="mimo-v2.6-pro"></option></datalist>
                   <div class="exploration-fields">
                     <app-setting-slider label="思考强度" [(value)]="config.reasoning_effort" [values]="reasoningValues" [labels]="reasoningLabels" hint="越高越适合复杂推理，也可能等待更久。" [disabled]="explorationSettingsBusy()" />
                     <app-setting-slider label="每段执行时限" [(value)]="config.timeout_seconds" [values]="executionTimes" [labels]="executionTimeLabels" hint="到时暂停并保存进度，点击继续即可接着探索。" [disabled]="explorationSettingsBusy()" />

apps/showcase_ui/src/app/pages/home/home.component.spec.ts

@@ -10,7 +10,7 @@ import { TaskRecommendationService } from '../../core/services/task-recommendati
 
 describe('Homepage exploration entry',()=>{
   let api:any,agent:any,router:any,system:any;
-  const config={model:'gpt-6.1-sol',reasoning_effort:'high',timeout_seconds:1800,demonstration_timeout_seconds:900,demonstration_warning_seconds:60};
+  const config={model:'gpt-6.1-terra',reasoning_effort:'high',timeout_seconds:1800,demonstration_timeout_seconds:900,demonstration_warning_seconds:60};
   beforeEach(()=>{
     api={settings:jasmine.createSpy().and.resolveTo(config),create:jasmine.createSpy().and.resolveTo({id:'conversation'}),act:jasmine.createSpy().and.resolveTo({run:{id:'run'}})};
     agent={runTask:jasmine.createSpy(),selectSession:jasmine.createSpy(),fetchSessions:jasmine.createSpy(),fetchStatus:jasmine.createSpy()};router={navigate:jasmine.createSpy().and.resolveTo(true)};

artemis/config/exploration.py

@@ -8,7 +8,7 @@ from pydantic import BaseModel, ConfigDict, Field, model_validator
 class ExplorationConfig(BaseModel):
     model_config = ConfigDict(extra="forbid")
 
-    model: str = Field(default="gpt-6.1-sol", min_length=1, max_length=200)
+    model: str = Field(default="gpt-6.1-terra", min_length=1, max_length=200)
     reasoning_effort: Literal[
         "default", "none", "minimal", "low", "medium", "high", "xhigh", "max"
     ] = "high"

artemis/resources/config/artemis.jsonc

@@ -35,7 +35,7 @@
   },
   "agent": {
     "exploration": {
-      "model": "${env:ARTEMIS_EXPLORATION_MODEL:-gpt-6.1-sol}",
+      "model": "${env:ARTEMIS_EXPLORATION_MODEL:-gpt-6.1-terra}",
       "reasoning_effort": "${env:ARTEMIS_EXPLORATION_REASONING_EFFORT:-high}",
       "timeout_seconds": "${env:ARTEMIS_EXPLORATION_TIMEOUT_SECONDS:-1800}",
       "demonstration_timeout_seconds": "${env:ARTEMIS_DEMONSTRATION_TIMEOUT_SECONDS:-900}",

config/artemis.jsonc

@@ -35,7 +35,7 @@
   },
   "agent": {
     "exploration": {
-      "model": "${env:ARTEMIS_EXPLORATION_MODEL:-gpt-6.1-sol}",
+      "model": "${env:ARTEMIS_EXPLORATION_MODEL:-gpt-6.1-terra}",
       "reasoning_effort": "${env:ARTEMIS_EXPLORATION_REASONING_EFFORT:-high}",
       "timeout_seconds": "${env:ARTEMIS_EXPLORATION_TIMEOUT_SECONDS:-1800}",
       "demonstration_timeout_seconds": "${env:ARTEMIS_DEMONSTRATION_TIMEOUT_SECONDS:-900}",

docs/ai-automation.md

@@ -60,7 +60,7 @@ MCP 同步仅检查 `$CODEX_HOME/config.toml`；未设置或为空时使用当
 
 报告按任务或批次归档到 `artifacts/mcp_exports/`，包含本地路径及服务下载链接；删除批次时会清理对应导出副本。运行中导出是快照；执行完成不等于验证通过，报告会保留未验证、失败、跳过与中断状态。
 
-新安装模型默认使用 `gpt-6-luna`，预设 `gpt-6-luna`、`gpt-6.1-sol`、`gpt-6-astra`、`mimo-v2.6-pro`；首页、兜底模型与精选任务使用统一选择控件，也支持自定义模型名称。已保存的模型配置保留。思考强度最高支持 `max`，默认 `high`，选“由模型默认”不发送该参数；接口不支持时明确报错。单次请求 300 秒，首次失败后最多再试 5 次，普通错误每次等待 10 秒，429 每次等待 60 秒，SDK 不叠加重试。首选模型连续 3 次没有有效工具调用时，当前步骤改用 `gpt-6-luna`（high），最多再试 3 次；下一步重新使用首选模型。兜底模型及次数可通过 `.env.example` 中的 `OPENAI_TOOL_FALLBACK_*` 和 `ARTEMIS_TOOL_FALLBACK_MAX_NO_PROGRESS_ATTEMPTS` 配置。请求耗尽后沿用任务暂停/恢复机制，鉴权或非法参数立即失败。视频分析与录屏是独立开关，默认均关闭。每项批量用例可覆盖模式、模型、设备、录屏和超时等配置，不影响其他任务。暂停先返回 `pausing`，确认状态为 `task_paused` 才表示设备已释放；Pro 等待模型回复或只读诊断时可及时中断，恢复后重新观察设备。AI 可用 `mobile_manage_task(action="inject_instruction")` 提交指导并恢复；指导由执行器在安全检查点领取，可能中断当前模型等待并重新观察设备；接收回执不保证任务结束前已消费，已经开始的设备动作会安全结束。用 `guidance_history` 核对指导是否被领取、在任务流程中核对实际执行情况，或用 `resume` 单独恢复。
+新安装模型默认使用 `gpt-6-luna`，预设 `gpt-6-luna`、`gpt-6.1-terra`、`gpt-6.1-sol`、`gpt-6-astra`、`mimo-v2.6-pro`；首页、兜底模型与精选任务使用统一选择控件，也支持自定义模型名称。已保存的模型配置保留。思考强度最高支持 `max`，默认 `high`，选“由模型默认”不发送该参数；接口不支持时明确报错。单次请求 300 秒，首次失败后最多再试 5 次，普通错误每次等待 10 秒，429 每次等待 60 秒，SDK 不叠加重试。首选模型连续 3 次没有有效工具调用时，当前步骤改用 `gpt-6-luna`（high），最多再试 3 次；下一步重新使用首选模型。兜底模型及次数可通过 `.env.example` 中的 `OPENAI_TOOL_FALLBACK_*` 和 `ARTEMIS_TOOL_FALLBACK_MAX_NO_PROGRESS_ATTEMPTS` 配置。请求耗尽后沿用任务暂停/恢复机制，鉴权或非法参数立即失败。视频分析与录屏是独立开关，默认均关闭。每项批量用例可覆盖模式、模型、设备、录屏和超时等配置，不影响其他任务。暂停先返回 `pausing`，确认状态为 `task_paused` 才表示设备已释放；Pro 等待模型回复或只读诊断时可及时中断，恢复后重新观察设备。AI 可用 `mobile_manage_task(action="inject_instruction")` 提交指导并恢复；指导由执行器在安全检查点领取，可能中断当前模型等待并重新观察设备；接收回执不保证任务结束前已消费，已经开始的设备动作会安全结束。用 `guidance_history` 核对指导是否被领取、在任务流程中核对实际执行情况，或用 `resume` 单独恢复。
 
 429 等待、兜底模型及次数也可在网页“模型配置 → 稳定性与兜底模型”或通过已授权的 `mobile_config(section="model")` 配置。批次 ZIP 还收录每项任务已保存的步骤截图和录屏。
 

docs/exploration-mode.md

@@ -8,7 +8,7 @@
 
 ## 模型与超时
 
-探索独立保存模型配置，默认 `gpt-6.1-sol / high`，预设也提供 `gpt-6-astra`，允许自定义模型。执行、人工示范分析、用例提炼和结束后的讨论使用这套配置。修改默认值仅影响新探索；已创建会话保留配置快照，Flash/Pro 默认值不变。
+探索独立保存模型配置，默认 `gpt-6.1-terra / high`，预设也提供 `gpt-6-astra`，允许自定义模型。执行、人工示范分析、用例提炼和结束后的讨论使用这套配置。修改默认值仅影响新探索；已创建会话保留配置快照，Flash/Pro 默认值不变。
 
 默认每段主动执行 1800 秒。模型调用、设备动作、录像分析计入；排队、等待回答和人工示范不计入。到时保存进度并暂停，可点击「继续探索」开启下一段；不会仅因超时把测试判成失败，累计主动耗时仍保留。
 

mcp_server/README.md

@@ -61,7 +61,7 @@ The bridge discovers a live service from the same installation; `ARTEMIS_DAEMON_
 
 ## 🛠️ MCP Tools Overview
 
-* **`mobile_exploration`**: Guided exploration using the same queue and conversation as the web workspace. Create/start, exchange messages, pause/continue, record and analyze demonstrations, save immutable case versions, rerun with Flash/Pro, or add a batch draft. Writes use stable request IDs; reads never launch work. Defaults are independent (`gpt-6.1-sol / high`) and timeouts pause without marking the test failed. See the [exploration workflow](../docs/exploration-mode.md).
+* **`mobile_exploration`**: Guided exploration using the same queue and conversation as the web workspace. Create/start, exchange messages, pause/continue, record and analyze demonstrations, save immutable case versions, rerun with Flash/Pro, or add a batch draft. Writes use stable request IDs; reads never launch work. Defaults are independent (`gpt-6.1-terra / high`) and timeouts pause without marking the test failed. See the [exploration workflow](../docs/exploration-mode.md).
 * **`mobile_run_task`**: Asynchronously launches an autonomous mobile automation task (`Flash` or `Pro` model) with optional `device_serial` targeting. Pro runs can be tuned with `verification_level` (`off` | `final` | `checkpoints` | `strict` — how much the Checker audits) and `explorer_mode` (`flash` | `pro` | `ultra` — the Operator's perception depth).
 * **`mobile_manage_task`**: Manages task lifecycle (`status`, `stop`, `inject_instruction`), returning task state and assigned `device_serial`. Pass `release_loop=True` with `inject_instruction` to gracefully end a `[Loop:continuous]` monitoring task — this explicit signal (not "please stop" wording) is what unlocks the loop milestone's completion.
 * **`mobile_get_device_state`**: Real-time observer (`screenshot` or OCR+XML `hierarchy`) with optional `device_serial`.

mcp_server/catalog.json

@@ -437,7 +437,7 @@
     },
     {
       "name": "mobile_config",
-      "description": "Read configuration or explicitly save non-secret defaults for FUTURE tasks.\n\nOnly set persist_defaults=true when the user requests saved/global configuration.\nmodel changes: model (preset or custom), base_url, reasoning_effort\n(default/none/minimal/low/medium/high/xhigh/max), timeout_seconds, max_retries,\nretry_interval_seconds, rate_limit_retry_seconds, tool_fallback_model,\ntool_fallback_reasoning_effort, tool_fallback_max_retries,\ntool_fallback_no_progress_attempts. 'default' omits reasoning;\nunsupported values fail visibly.\ncapabilities: video_enabled and recording_enabled are independent; outputter_enabled,\nflash_final_check_enabled (false; Flash exit-only AI review),\nstep_summarizer_enabled, screenshot_limit_enabled, task_timeout_seconds (default 1800),\nobservation_timeout_seconds (60), observation_max_attempts (3),\ndevice_command_timeout_seconds (10), action_failure_attempts (3),\nworker_cleanup_timeout_seconds (30), adb_auto_connect (true),\nadb_discovery_interval_seconds (10), adb_discovery_timeout_seconds (5).\nreports: formats=['docx','xlsx'] (at least one).\nexploration: model (default gpt-6.1-sol), reasoning_effort (high), timeout_seconds\n(1800 active seconds), demonstration_timeout_seconds (900), demonstration_warning_seconds (60).\nAPI keys are never accepted or returned: use the Web UI or .env for credentials.\nSaving settings does not change an already running task. Flash/Pro are execution\nprofiles, not model names. Model retries do not repeat device test cases.\n",
+      "description": "Read configuration or explicitly save non-secret defaults for FUTURE tasks.\n\nOnly set persist_defaults=true when the user requests saved/global configuration.\nmodel changes: model (preset or custom), base_url, reasoning_effort\n(default/none/minimal/low/medium/high/xhigh/max), timeout_seconds, max_retries,\nretry_interval_seconds, rate_limit_retry_seconds, tool_fallback_model,\ntool_fallback_reasoning_effort, tool_fallback_max_retries,\ntool_fallback_no_progress_attempts. 'default' omits reasoning;\nunsupported values fail visibly.\ncapabilities: video_enabled and recording_enabled are independent; outputter_enabled,\nflash_final_check_enabled (false; Flash exit-only AI review),\nstep_summarizer_enabled, screenshot_limit_enabled, task_timeout_seconds (default 1800),\nobservation_timeout_seconds (60), observation_max_attempts (3),\ndevice_command_timeout_seconds (10), action_failure_attempts (3),\nworker_cleanup_timeout_seconds (30), adb_auto_connect (true),\nadb_discovery_interval_seconds (10), adb_discovery_timeout_seconds (5).\nreports: formats=['docx','xlsx'] (at least one).\nexploration: model (default gpt-6.1-terra), reasoning_effort (high), timeout_seconds\n(1800 active seconds), demonstration_timeout_seconds (900), demonstration_warning_seconds (60).\nAPI keys are never accepted or returned: use the Web UI or .env for credentials.\nSaving settings does not change an already running task. Flash/Pro are execution\nprofiles, not model names. Model retries do not repeat device test cases.\n",
       "inputSchema": {
         "properties": {
           "section": {
@@ -791,7 +791,7 @@
     },
     {
       "name": "mobile_exploration",
-      "description": "Explore ONE complex test with user guidance and produce a reusable case.\n\ndeletion_preview lists affected conversation runs; delete requires user_confirmed=true\nafter the user requests deletion. Independent validation runs are preserved.\nRead-only list/get/case never execute tasks. create stores {goal,config?,task_config?};\nstart/continue explicitly enqueue or resume Pro exploration. Independent defaults:\ngpt-6.1-sol/high, 1800 active seconds; timeout pauses, never fails by itself.\nmessage payload={text}; answer pending questions or guide without discarding history.\ndemonstrate payload={source:'android'|'computer'|'both'} pauses at a safe point and\nrecords while retaining the device/plugin lease. Wait for recording before the user\noperates. demo_finish analyzes the SAVED clip; demo_extend payload={seconds:900};\ndemo_cancel preserves evidence. Default 900s, warning 60s before expiry, auto-pause.\nsave_case payload={expected_version,case:{name,goal,preconditions?,evidence?}};\ngenerate payload={source_run_id,expected_version} starts evidence-based synthesis,\npoll get.generations for completion. validate payload={version,profile,task_config?}\nexplicitly runs the saved version in Flash/Pro; batch additionally accepts name and\ncreates a DRAFT batch, never starts it. Exploration pass and rerun pass are separate.\nUse stable request_id for every mutation except pause/stop/delete, reusing it on transport\nretries. No API keys; configure secrets in the Web UI. mobile_config(section='exploration')\ncontrols non-secret defaults. After errors call mobile_diagnose before resubmitting.\n",
+      "description": "Explore ONE complex test with user guidance and produce a reusable case.\n\ndeletion_preview lists affected conversation runs; delete requires user_confirmed=true\nafter the user requests deletion. Independent validation runs are preserved.\nRead-only list/get/case never execute tasks. create stores {goal,config?,task_config?};\nstart/continue explicitly enqueue or resume Pro exploration. Independent defaults:\ngpt-6.1-terra/high, 1800 active seconds; timeout pauses, never fails by itself.\nmessage payload={text}; answer pending questions or guide without discarding history.\ndemonstrate payload={source:'android'|'computer'|'both'} pauses at a safe point and\nrecords while retaining the device/plugin lease. Wait for recording before the user\noperates. demo_finish analyzes the SAVED clip; demo_extend payload={seconds:900};\ndemo_cancel preserves evidence. Default 900s, warning 60s before expiry, auto-pause.\nsave_case payload={expected_version,case:{name,goal,preconditions?,evidence?}};\ngenerate payload={source_run_id,expected_version} starts evidence-based synthesis,\npoll get.generations for completion. validate payload={version,profile,task_config?}\nexplicitly runs the saved version in Flash/Pro; batch additionally accepts name and\ncreates a DRAFT batch, never starts it. Exploration pass and rerun pass are separate.\nUse stable request_id for every mutation except pause/stop/delete, reusing it on transport\nretries. No API keys; configure secrets in the Web UI. mobile_config(section='exploration')\ncontrols non-secret defaults. After errors call mobile_diagnose before resubmitting.\n",
       "inputSchema": {
         "properties": {
           "action": {

mcp_server/tools/automation.py

@@ -200,7 +200,7 @@ async def mobile_config(
     worker_cleanup_timeout_seconds (30), adb_auto_connect (true),
     adb_discovery_interval_seconds (10), adb_discovery_timeout_seconds (5).
     reports: formats=['docx','xlsx'] (at least one).
-    exploration: model (default gpt-6.1-sol), reasoning_effort (high), timeout_seconds
+    exploration: model (default gpt-6.1-terra), reasoning_effort (high), timeout_seconds
     (1800 active seconds), demonstration_timeout_seconds (900), demonstration_warning_seconds (60).
     API keys are never accepted or returned: use the Web UI or .env for credentials.
     Saving settings does not change an already running task. Flash/Pro are execution

mcp_server/tools/exploration.py

@@ -43,7 +43,7 @@ async def mobile_exploration(
     after the user requests deletion. Independent validation runs are preserved.
     Read-only list/get/case never execute tasks. create stores {goal,config?,task_config?};
     start/continue explicitly enqueue or resume Pro exploration. Independent defaults:
-    gpt-6.1-sol/high, 1800 active seconds; timeout pauses, never fails by itself.
+    gpt-6.1-terra/high, 1800 active seconds; timeout pauses, never fails by itself.
     message payload={text}; answer pending questions or guide without discarding history.
     demonstrate payload={source:'android'|'computer'|'both'} pauses at a safe point and
     records while retaining the device/plugin lease. Wait for recording before the user

skills/artemis-use/references/exploration.md

@@ -6,7 +6,7 @@
 
 ## 模型与超时
 
-探索独立保存模型配置，默认 `gpt-6.1-sol / high`，预设也提供 `gpt-6-astra`，允许自定义模型。执行、人工示范分析、用例提炼和结束后的讨论使用这套配置。修改默认值仅影响新探索；已创建会话保留配置快照，Flash/Pro 默认值不变。
+探索独立保存模型配置，默认 `gpt-6.1-terra / high`，预设也提供 `gpt-6-astra`，允许自定义模型。执行、人工示范分析、用例提炼和结束后的讨论使用这套配置。修改默认值仅影响新探索；已创建会话保留配置快照，Flash/Pro 默认值不变。
 
 默认每段主动执行 1800 秒。模型调用、设备动作、录像分析计入；排队、等待回答和人工示范不计入。到时保存进度并暂停，可点击「继续探索」开启下一段；不会仅因超时把测试判成失败，累计主动耗时仍保留。
 

skills/artemis-use/references/modes.md

@@ -17,7 +17,7 @@
 ## 模式、模型与配置
 
 - `mobile_run_task.model` 取 `Flash` / `Pro`。API 模型名放 `runtime_overrides.model`；思考强度放 `runtime_overrides.reasoning_effort`。批次使用 `task_config.profile` 选择模式，`task_config.model` 选择 API 模型。
-- 探索独立配置，默认 `gpt-6.1-sol/high`，支持 `gpt-6-astra` 及已配置网关支持的自定义模型。执行、示范分析、提炼共用该探索配置；不改变 Flash/Pro 默认值。
+- 探索独立配置，默认 `gpt-6.1-terra/high`，支持 `gpt-6-astra` 及已配置网关支持的自定义模型。执行、示范分析、提炼共用该探索配置；不改变 Flash/Pro 默认值。
 - 默认 high、单次模型请求时限 300 秒。`default` 表示不发送思考强度，`none` 是显式关闭，不能混为一谈；接口不支持参数时如实报告，不擅自降级。
 - 请求时限与整任务主动执行时限不同。排队/用户暂停不计入任务主动执行；探索等待回答、人工示范也不计入。
 - 录屏 `record_video` 和 AI 视频分析 `analyze_video` 独立，默认关闭。需要可下载录像时明确启用录屏。

tests/unit/admin_console/test_model_settings.py

@@ -96,6 +96,7 @@ def test_model_presets_keep_supported_choices_without_restricting_custom_names()
     presets = service.get_model_settings()["model_presets"]
     assert presets == [
         "gpt-6-luna",
+        "gpt-6.1-terra",
         "gpt-6.1-sol",
         "gpt-6-astra",
         "mimo-v2.6-pro",

tests/unit/test_exploration_service.py

@@ -30,7 +30,7 @@ async def test_admission_uses_shared_queue_with_independent_model(service, monke
     await service.start(session["id"], "start")
     request = enqueue.call_args.args[0]
     assert request.profile == "pro"
-    assert request.runtime_overrides.model == "gpt-6.1-sol"
+    assert request.runtime_overrides.model == "gpt-6.1-terra"
     assert request.runtime_overrides.reasoning_effort == "high"
     assert request.runtime_overrides.verification_level == "final"
     assert request.conversation_id == session["id"]
@@ -193,7 +193,7 @@ def test_independent_saved_defaults_do_not_change_existing_sessions(service):
     session = service.create(CreateExploration(goal="探索设置", request_id="create"))
     service.save_settings(ExplorationConfig(model="gpt-6-astra", reasoning_effort="max"))
     later = service.create(CreateExploration(goal="另一次探索", request_id="later"))
-    assert service.repository.get(session["id"])["config"]["model"] == "gpt-6.1-sol"
+    assert service.repository.get(session["id"])["config"]["model"] == "gpt-6.1-terra"
     assert later["config"]["model"] == "gpt-6-astra"
 
 

tests/unit/test_exploration_store.py

@@ -187,7 +187,7 @@ def test_generated_case_cannot_borrow_another_sessions_evidence(repository):
 def test_exploration_config_defaults_and_rejects_credentials():
     config = ExplorationConfig()
     assert (config.model, config.reasoning_effort, config.timeout_seconds) == (
-        "gpt-6.1-sol",
+        "gpt-6.1-terra",
         "high",
         1800,
     )