refactor(llm-deepseek)!: rename the provider route to deepseek-official

The native adapter's route was named deepseek, colliding with pi-ai's
catalog provider of the same name, so the two DeepSeek paths could never
be mounted side by side. The web settings page needs both configurable at
once. Compositions, fixtures, goldens, scaffolding defaults, and docs all
move together (pre-release, no shim); TUI/session-query-spill/
missing-credential goldens re-recorded through their keyless refresh
modes because provider-name length shifts box padding and spill
truncation points.

docs/user/guide/config.md

@@ -28,7 +28,7 @@ A minimal configuration is a list of plugin entries:
 - id: tui-agent
   name: '@deepseek-ai/dsh-tui-demo'
   config:
-    provider: deepseek
+    provider: deepseek-official
     model: deepseek-v4-flash
     workspaceContext: false
 ```

docs/user/guide/config.zh.md

@@ -28,7 +28,7 @@ Harness 使用 `cordis.yml` 描述 Agent 加载哪些插件以及每个插件的
 - id: tui-agent
   name: '@deepseek-ai/dsh-tui-demo'
   config:
-    provider: deepseek
+    provider: deepseek-official
     model: deepseek-v4-flash
     workspaceContext: false
 ```

docs/user/guide/index.md

@@ -17,7 +17,7 @@ Harness implements every capability an AI agent needs—including LLM calls, too
 # Select the interactive application
 - name: '@deepseek-ai/dsh-tui-demo'
   config:
-    provider: deepseek
+    provider: deepseek-official
     model: deepseek-v4-flash
     workspaceContext: false
 ```

docs/user/guide/index.zh.md

@@ -17,7 +17,7 @@ Harness 将一个 AI Agent（智能体） 所需要的所有能力——LLM 调
 # Select the interactive application
 - name: '@deepseek-ai/dsh-tui-demo'
   config:
-    provider: deepseek
+    provider: deepseek-official
     model: deepseek-v4-flash
     workspaceContext: false
 ```