test(web): refresh web aria goldens stale on master

These 15 goldens already failed replay at origin/master d17fcd3a6 before this
branch touched anything: master's committed expectations lag master's own code
(localized sidebar labels, the access-mode control becoming a button, message
IconActions and clock placement, context-injection affordances).

Recorded by running DSH_SNAPSHOT=refresh over the web suite in a pristine
worktree at that commit, then importing the result here, so the stats-line
change in the following commit shows up as its own reviewable delta rather than
mixed into pre-existing drift.

Two web e2e specs still fail at that same pristine commit for non-golden
reasons and are untouched here: queue-actions (counts 2 user/message events
where it expects 1) and details-session-lifecycle (times out waiting for a
New session button).

apps/web/tests/snapshots/code-mode-round/ui.expected.md

@@ -16,11 +16,6 @@
   - img
   - img
   - text: "Think The user wants me to write a single `run_code` program that:"
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button:
   - img
   - img
@@ -37,16 +32,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 8.3k uncached input · 252 output · 9k cache read · cache hit 52% · context 7% of 128k · 1 turns · 2 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 52% Input 17.2K tok · Output 252 tok

apps/web/tests/snapshots/cordis-tool-round/ui.expected.md

@@ -16,11 +16,6 @@
   - img
   - img
   - text: "Think The user wants me to:"
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button:
   - img
   - img
@@ -29,11 +24,6 @@
   - img
   - img
   - text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button [expanded]:
   - img
 - text: Mount temporary Plugin typescript
@@ -43,11 +33,6 @@
   - img
   - img
   - text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button:
   - img
   - img
@@ -61,16 +46,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 15.3k uncached input · 312 output · 51.2k cache read · cache hit 77% · context 13% of 128k · 1 turns · 4 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 4 steps Tool call {{duration}} Cache hit 77% Input 66.5K tok · Output 312 tok

apps/web/tests/snapshots/fresh-round-trip/ui.expected.md

@@ -16,13 +16,10 @@
   - img
   - img
   - text: Think The user wants me to run a simple bash command and reply with "DONE".
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - img
-- text: Bash Echo the test string
+- text: Bash Echo the test string 已完成 workspace echo WEB_E2E_OK
+- button "复制"
+- text: WEB_E2E_OK
 - button "Think The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\".":
   - img
   - img
@@ -32,16 +29,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 219 uncached input · 111 output · 15.5k cache read · cache hit 99% · context 6% of 128k · 1 turns · 2 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 99% Input 15.7K tok · Output 111 tok

apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md

@@ -1,9 +1,9 @@
-- button "New session"
-- button "Collapse sidebar":
+- button "新建会话"
+- button "收起侧边栏":
   - img
-- button "New session":
+- button "新建会话":
   - img
-  - text: New Session
+  - text: 新会话
 - text: Workspaces
 - button "Group by":
   - img
@@ -28,11 +28,7 @@
 - textbox "Describe what you want to build"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img

apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md

@@ -21,16 +21,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 109 uncached input · 21 output · 7.7k cache read · cache hit 99% · context unknown · 1 turns · 1 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 21 tok

apps/web/tests/snapshots/live-interactions/cancel.expected.md

@@ -18,16 +18,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 0 uncached input · 0 output · 0 cache read · context 4% of 128k · 1 turns · 1 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 1 steps Input 0 tok · Output 0 tok

apps/web/tests/snapshots/live-interactions/error-auth.expected.md

@@ -12,14 +12,10 @@
 - button "编辑":
   - img
 - button "▸ 上下文注入"
-- textbox "Message the agent"
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img

apps/web/tests/snapshots/live-interactions/retry.expected.md

@@ -21,16 +21,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 110 uncached input · 79 output · 7.7k cache read · cache hit 99% · context 4% of 128k · 1 turns · 1 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 79 tok

apps/web/tests/snapshots/message-actions/ui.expected.md

@@ -16,11 +16,6 @@
   - img
   - img
   - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel.
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - img
 - text: Read
 - button "a.txt"
@@ -36,16 +31,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 339 uncached input · 135 output · 15.5k cache read · cache hit 98% · context unknown · 1 turns · 2 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 deepseek-v4-flash":
   - text: deepseek-v4-flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

apps/web/tests/snapshots/question-composer/answered.expected.md

@@ -16,11 +16,6 @@
   - img
   - img
   - text: Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button:
   - img
   - img
@@ -34,16 +29,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} cache hit 95% · 8,769 tokens · 1 turns · 2 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 95% Input 8.6K tok · Output 180 tok

apps/web/tests/snapshots/queue-actions/editing.expected.md

@@ -11,6 +11,7 @@
   - img
 - button "编辑":
   - img
+- button "▸ 上下文注入"
 - paragraph: partial
 - list:
   - listitem:

apps/web/tests/snapshots/queue-actions/ui.expected.md

@@ -11,6 +11,7 @@
   - img
 - button "编辑":
   - img
+- button "▸ 上下文注入"
 - paragraph: partial
 - list:
   - listitem:

apps/web/tests/snapshots/seeded-history/ui.expected.md

@@ -15,11 +15,6 @@
   - img
   - img
   - text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel.
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - img
 - text: Read
 - button "a.txt"
@@ -35,16 +30,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 339 uncached input · 135 output · 15.5k cache read · cache hit 98% · context unknown · 1 turns · 2 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 deepseek-v4-flash":
   - text: deepseek-v4-flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

apps/web/tests/snapshots/steering/mid-steer.expected.md

@@ -16,15 +16,10 @@
   - img
   - img
   - text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button:
   - img
   - img
-- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]} 151 uncached input · 115 output · 7.7k cache read · cache hit 98% · context 4% of 128k · 1 turns · 1 steps"
+- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}"
 - region "Ready to continue?":
   - text: Checkpoint
   - heading "Ready to continue?" [level=2]

apps/web/tests/snapshots/steering/settled.expected.md

@@ -16,11 +16,6 @@
   - img
   - img
   - text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.
-- button "复制":
-  - img
-- button "在新对话中分支":
-  - img
-- text: {{clock}}
 - button:
   - img
   - img
@@ -34,16 +29,13 @@
   - img
 - button "在新对话中分支":
   - img
-- text: {{clock}} 323 uncached input · 156 output · 15.5k cache read · cache hit 98% · context 6% of 128k · 1 turns · 2 steps
-- textbox "Message the agent"
+- text: {{clock}}
+- textbox "给智能体发消息"
 - button "Add attachment":
   - img
-- text: Danger Full Access
-- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
 - button "选择模型，当前 DeepSeek-V4-Flash":
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 156 tok

docs/architecture.md

@@ -94,7 +94,7 @@ forever:
       assemble system prompt and tool schemas
       snapshot the derived messages (the reconstruction boundary)
       'step/start'
-      agent/request (config only) -> prepare reasoning/default + context under turn signal -> log request/header -> obtain outer llm/stream handle (frozen request; prepared calls registration-bound) -> agent/model-request (live, contained attempt) -> iterate
+      agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound)
       'assistant/chunk'
       'assistant/message'
       schedule tool calls by ctx.tools.executionMode:
@@ -153,7 +153,7 @@ Log-only events may sit between turns. Owners append through `Session`, flushing
 
 Messages use typed blocks from merge-extensible `ContentBlockMap`; the pattern also types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New blocks coordinate adapters, UI, compaction, token metering, and persistence; replay measurements live in [token-meter.md](core-data-structures/token-meter.md).
 
-Streaming uses chunks and `BlockAssembler`. When the outer `llm/stream` returns a handle, AgentLoop emits contained, non-durable, non-replayed `agent/model-request` attempt metadata—not proof of provider I/O. `agent/request-error` may retry. Replay crosses routes only through a shared adapter ([contract](core-data-structures/llm-streaming.md)).
+Streaming uses raw chunks and `BlockAssembler`. Each `LlmAdapter.stream()` is one provider attempt; adapters report normalized failure facts, and a handling `agent/request-error` plugin returns a retry action. The loop logs chunks, successful provenance, and replay state. Remote adapters use per-read idle watchdogs. Replay crosses routes only through a shared adapter instance ([contract](core-data-structures/llm-streaming.md)).
 
 ## Extension And Composition
 

docs/architecture.zh.md

@@ -94,7 +94,7 @@ forever:
       assemble system prompt and tool schemas
       snapshot the derived messages (the reconstruction boundary)
       'step/start'
-      agent/request (config only) -> prepare reasoning/default + context under turn signal -> log request/header -> obtain outer llm/stream handle (frozen request; prepared calls registration-bound) -> agent/model-request (live, contained attempt) -> iterate
+      agent/request (config only) -> prepare reasoning/default under turn signal -> log request/header -> llm/stream (frozen, registration-bound)
       'assistant/chunk'
       'assistant/message'
       schedule tool calls by ctx.tools.executionMode:
@@ -153,7 +153,7 @@ idle inject:
 
 消息使用从可合并扩展的 `ContentBlockMap` 派生的类型化块；同一模式也为 `MessageSource`、`FinishReason`、`TurnTrigger` 和 `TurnEndReason` 定义类型。新增块会协调适配器、UI、压缩、token 计量和持久化；回放计量见 [token-meter.md](core-data-structures/token-meter.md)。
 
-流式输出使用分片和 `BlockAssembler`。外层 `llm/stream` 返回句柄时，AgentLoop 会发出 `agent/model-request` 尝试元数据；该通知的失败会被收容，元数据不会持久化或回放，但这并不能证明提供方 I/O 已开始。`agent/request-error` 可以重试。回放仅通过共用适配器跨路由传递（[契约](core-data-structures/llm-streaming.md)）。
+流式输出使用原始分片和 `BlockAssembler`。每次 `LlmAdapter.stream()` 调用代表一次提供方尝试；适配器报告标准化的故障事实，负责处理的 `agent/request-error` 插件会返回重试动作。循环会记录分片、成功结果的来源信息和回放状态。远程适配器使用逐次读取空闲看门狗。回放仅通过共用的适配器实例跨路由传递（[契约](core-data-structures/llm-streaming.md)）。
 
 ## 扩展与组合