fix(cli): keep model switches session-scoped

docs/users/configuration/auth.md

@@ -297,7 +297,7 @@ After launching Qwen Code, use the `/model` command to switch between all config
 /model
 ```
 
-The picker will show all models from your `modelProviders` configuration, grouped by their protocol (e.g. `openai`, `anthropic`, `gemini`). Your selection is persisted across sessions.
+The picker will show all models from your `modelProviders` configuration, grouped by their protocol (e.g. `openai`, `anthropic`, `gemini`). A selection from the ordinary `/model` picker applies only to the current session. To persist a selection for future sessions, use `/model --default <model-id>` or open the picker with `/model --default` and select a model.
 
 You can also switch models directly with a command-line argument, which is convenient when working across multiple terminals.
 

docs/users/configuration/model-providers.md

@@ -675,5 +675,5 @@ The snapshot:
 >
 > Define `modelProviders` in the user-scope `~/.qwen/settings.json` whenever possible and avoid persisting credential overrides in any scope. Keeping the provider catalog in user settings prevents merge/override conflicts between project and user scopes and ensures `/auth` and `/model` updates always write back to a consistent scope.
 
-- `/model` and `/auth` persist `model.name` (where applicable) and `security.auth.selectedType` to the closest writable scope that already defines `modelProviders`; otherwise they fall back to the user scope. This keeps workspace/user files in sync with the active provider catalog.
+- Plain `/model <model-id>` commands and selections from the ordinary `/model` picker apply only to the current session. `/model --default <model-id>` persists `model.name` (it selects by id only and clears any persisted `model.baseUrl` disambiguator; an explicit auth-type suffix also persists `security.auth.selectedType`). Selecting a model from the picker opened by `/model --default` additionally persists the disambiguating `model.baseUrl` and the selected provider's `security.auth.selectedType`. `/auth` continues to persist its selected authentication type. Persistent selections use the closest writable scope that already defines `modelProviders`; otherwise they fall back to the user scope.
 - Without `modelProviders`, the resolver mixes CLI/env/settings layers, creating Runtime Models. This is fine for single-provider setups but cumbersome when frequently switching. Define provider catalogs whenever multi-model workflows are common so that switches stay atomic, source-attributed, and debuggable.

docs/users/configuration/settings.md

@@ -163,7 +163,7 @@ Settings are organized into categories. Most settings should be placed within th
 | -------------------------------------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
 | `model.name`                                       | string  | The Qwen model to use for conversations.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `undefined` |
 | `model.reasoningEffort`                            | enum    | How hard reasoning-capable models think, applied across all providers. Set with the [`/effort`](../features/commands) command (`low`, `medium`, `high`, `xhigh`, `max`). Each provider maps and clamps this to what the active model supports (e.g. Gemini caps at `high`; Anthropic clamps tiers a model lacks). Leave unset to use the model/provider default.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `undefined` |
-| `model.baseUrl`                                    | string  | Persisted automatically by the model picker to disambiguate when multiple `modelProviders` entries share the same model id. Not intended to be set by hand — use the `/model` picker or a `modelProviders` entry instead; a stale hand-edited value can silently route requests to a different same-id provider.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `undefined` |
+| `model.baseUrl`                                    | string  | Persisted with a default model selection made through the picker opened with `/model --default` to disambiguate when multiple `modelProviders` entries share the same model id. The `/model --default <model-id>` argument form selects by id only and clears any persisted disambiguator. Plain model switches are session-scoped. Not intended to be set by hand — use the default-model picker or a `modelProviders` entry instead; a stale hand-edited value can silently route requests to a different same-id provider.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `undefined` |
 | `model.sessionTokenLimit`                          | number  | Maximum recorded prompt token count allowed before sending the next message. `-1` means unlimited; `0` is also treated as unlimited (unlike `model.maxToolCalls`, where `0` disallows all calls). When the recorded prompt count exceeds the limit, the next send is dropped (the session is not aborted).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | `-1`        |
 | `model.maxSessionTurns`                            | integer | Maximum number of user/model/tool turns to keep in a session. -1 means unlimited.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `-1`        |
 | `model.maxWallTimeSeconds`                         | number  | Wall-clock budget for headless / unattended runs, in seconds. `-1` means unlimited. Overridable per-invocation via `--max-wall-time`, which requires a positive duration (`90`, `30s`, `5m`, `1h`, `1.5h`); the minimum is 1 second — sub-second values (`500ms`, `0.5`) are rejected as typos. Omit the flag to fall back to this setting. Aborts with exit code 55 when exceeded.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | `-1`        |

docs/users/features/commands.md

@@ -96,7 +96,8 @@ Commands for managing AI tools and models.
 | → `auto-edit`         | Auto-approve edits (trusted environment)                                              | `/approval-mode auto-edit`                                                                                |
 | → `auto`              | Classifier-evaluated approval (autonomous)                                            | `/approval-mode auto`                                                                                     |
 | → `yolo`              | Auto-approve everything (quick prototyping)                                           | `/approval-mode yolo`                                                                                     |
-| `/model`              | Switch model used in current session                                                  | `/model`, `/model <model-id>` (switch immediately)                                                        |
+| `/model`              | Switch model used in current session (session-scoped, not persisted)                  | `/model`, `/model <model-id>` (switch immediately)                                                        |
+| → `--default`         | Persist the main model for future sessions                                            | `/model --default <model-id>`, `/model --default --project <model-id>`                                    |
 | `/model --fast`       | Set a lighter model for prompt suggestions                                            | `/model --fast qwen3-coder-flash`                                                                         |
 | `/model --voice`      | Set the model used for voice transcription                                            | `/model --voice <model-id>`                                                                               |
 | `/model --vision`     | Set the vision-bridge model used to transcribe images for a text-only main model      | `/model --vision <model-id>`                                                                              |

packages/cli/src/i18n/locales/ca.js

@@ -2539,6 +2539,10 @@ export default {
     "Persistir la selecció de model a la configuració del projecte (àmbit de l'espai de treball)",
   'Persist the model selection to the user settings (global scope)':
     "Persistir la selecció de model a la configuració d'usuari (àmbit global)",
+  'Persist to project settings (requires --default for the main model)':
+    'Persistir a la configuració del projecte (requereix --default per al model principal)',
+  'Persist to user settings (requires --default for the main model)':
+    "Persistir a la configuració d'usuari (requereix --default per al model principal)",
   'Select Fast Model': 'Selecciona el model ràpid',
   'Select Vision Model': 'Seleccionar el model de visió',
   'Select Voice Model': 'Seleccionar el model de veu',

packages/cli/src/i18n/locales/en.js

@@ -1502,6 +1502,8 @@ export default {
     'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, --project to persist to project settings, --global to persist to user settings, [model-id] to switch immediately, or [model-id] [prompt] to run a one-off prompt on another model; the inline prompt is sent verbatim without @file expansion).',
   'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, --compaction for chat compression model, --image for the image generation model, --project to persist to project settings, --global to persist to user settings, [model-id] to switch immediately, or [model-id] [prompt] to run a one-off prompt on another model; the inline prompt is sent verbatim without @file expansion).':
     'Switch the model for this session (--fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, --compaction for chat compression model, --image for the image generation model, --project to persist to project settings, --global to persist to user settings, [model-id] to switch immediately, or [model-id] [prompt] to run a one-off prompt on another model; the inline prompt is sent verbatim without @file expansion).',
+  'Switch the model for this session (--default to persist the main model for future sessions, --fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, --compaction for chat compression model, --image for the image generation model, --project to persist to project settings, --global to persist to user settings, [model-id] to switch immediately, or [model-id] [prompt] to run a one-off prompt on another model; the inline prompt is sent verbatim without @file expansion).':
+    'Switch the model for this session (--default to persist the main model for future sessions, --fast for suggestion model, --voice for voice transcription model, --vision for the vision bridge model, --compaction for chat compression model, --image for the image generation model, --project to persist to project settings, --global to persist to user settings, [model-id] to switch immediately, or [model-id] [prompt] to run a one-off prompt on another model; the inline prompt is sent verbatim without @file expansion).',
   "Inline one-shot override isn't supported in this mode — run '/model {{model}}' first, then send your prompt.":
     "Inline one-shot override isn't supported in this mode — run '/model {{model}}' first, then send your prompt.",
   "Inline one-shot override can't switch providers. '{{model}}' belongs to a different provider — run '/model {{model}}' first, then send your prompt.":
@@ -1523,6 +1525,10 @@ export default {
     'Persist the model selection to the project settings (workspace scope)',
   'Persist the model selection to the user settings (global scope)':
     'Persist the model selection to the user settings (global scope)',
+  'Persist to project settings (requires --default for the main model)':
+    'Persist to project settings (requires --default for the main model)',
+  'Persist to user settings (requires --default for the main model)':
+    'Persist to user settings (requires --default for the main model)',
   'Select Fast Model': 'Select Fast Model',
   'Select Vision Model': 'Select Vision Model',
   'Select Image Model': 'Select Image Model',

packages/cli/src/i18n/locales/fr.js

@@ -1339,6 +1339,10 @@ export default {
     'Persister la sélection du modèle dans les paramètres du projet (étendue workspace)',
   'Persist the model selection to the user settings (global scope)':
     'Persister la sélection du modèle dans les paramètres utilisateur (étendue globale)',
+  'Persist to project settings (requires --default for the main model)':
+    'Persister dans les paramètres du projet (nécessite --default pour le modèle principal)',
+  'Persist to user settings (requires --default for the main model)':
+    'Persister dans les paramètres utilisateur (nécessite --default pour le modèle principal)',
   'API Key': 'API Key',
   '(default)': '(par défaut)',
   '(not set)': '(non défini)',

packages/cli/src/i18n/locales/ja.js

@@ -1793,6 +1793,10 @@ export default {
     'モデルの選択をプロジェクト設定に永続化（ワークスペーススコープ）',
   'Persist the model selection to the user settings (global scope)':
     'モデルの選択をユーザー設定に永続化（グローバルスコープ）',
+  'Persist to project settings (requires --default for the main model)':
+    'プロジェクト設定に永続化（メインモデルには --default が必要）',
+  'Persist to user settings (requires --default for the main model)':
+    'ユーザー設定に永続化（メインモデルには --default が必要）',
   'API Key': 'API Key',
   '(default)': '(デフォルト)',
   '(not set)': '(未設定)',