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

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