Merge remote-tracking branch 'origin/master' into mergebot/pr711

# Conflicts: # apps/cli/README.i18n.yaml # apps/cli/README.md # apps/cli/README.zh.md # apps/cli/cordis.yml # apps/cli/package.json # docs/config-catalog.md # packages/client/runtime/README.i18n.yaml # packages/client/runtime/src/client/contract/sessions.ts # packages/client/test-runtime/src/sessions.ts # packages/client/ui-workspace/README.i18n.yaml # packages/client/ui-workspace/README.md # packages/client/ui-workspace/README.zh.md # packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx # packages/client/ui-workspace/src/client/tree.ts # packages/client/ui-workspace/tests/apply.spec.ts # packages/client/ui-workspace/tests/tree.spec.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/tests/client-handler.spec.ts # packages/host/apiproxy/tests/rpc-schemas.spec.ts # pnpm-lock.yaml
2026-07-31 01:28:15 +08:00
parent c9729b501d 37b68e1c31
commit ecbd8babc1
980 changed files with 30720 additions and 7127 deletions
--- a/apps/web/tests/snapshots/approval-composer/session.jsonl
+++ b/apps/web/tests/snapshots/approval-composer/session.jsonl
--- a/apps/web/tests/snapshots/approval-composer/ui.expected.md
+++ b/apps/web/tests/snapshots/approval-composer/ui.expected.md
@@ -0,0 +1,4 @@
+- text: 等待审批
+- group "审批详情": "escalate sandbox to workspace-write: Need to write the notes.txt file as requested by the user. echo 'tok63z tokc7y tokibx tokofw tokujv tok10nu tok16rt tok1cvs tok1izr tok1p3q tok1v7p tok21bo tok2a4 tok8e3 tokei2 tokkm1 tokqq0 tokwtz tok12xy tok191x tok1f5w tok1l9v tok1rdu tok1xht tok23ls tok4k8 tokao7 tokgs6 tokmw5 tokt04 tokz43 tok1582 tok1bc1 tok1hg0 tok1njz tok1tny tok1zrx tokqd tok6uc tokcyb tokj2a tokp69 tokva8 tok11e7 tok17i6 tok1dm5 tok1jq4 tok1pu3 tok1vy2 tok2221 tok30h tok94g tokf8f toklce tokrgd tokxkc tok13ob tok19sa tok1fw9 tok1m08 tok1s47 tok1y86 tok24c5 tok5al tokbek tokhij toknmi toktqh tokzug tok15yf tok1c2e tok1i6d tok1oac tok1ueb tok20ia tok1gq tok7kp tokdoo tokjsn tokpwm tokw0l tok124k tok188j tok1eci tok1kgh tok1qkg tok1wof tok22se tok3qu tok9ut tokfys tokm2r toks6q tokyap tok14eo tok1ain tok1gmm tok1mql tok1suk tok1yyj tok252i tok60y tokc4x toki8w tokocv tokugu tok10kt tok16os tok1csr tok1iwq tok1p0p tok1v4o tok218n tok273 tok8b2 tokef1 tokkj0 tokqmz tokwqy tok12ux tok18yw tok1f2v tok1l6u tok1rat tok1xes tok23ir tok4h7 tokal6 tokgp5 tokmt4 toksx3 tokz12 tok1551 tok1b90 tok1hcz tok1ngy tok1tkx tok1zow toknc tok6rb tokcva tokiz9 tokp38 tokv77 tok11b6 tok17f5 tok1dj4 tok1jn3 tok1pr2 tok1vv1 tok21z0 tok2xg tok91f tokf5e tokl9d tokrdc tokxhb tok13la tok19p9 tok1ft8 tok1lx7 tok1s16 tok1y55 tok2494 tok57k tokbbj tokhfi toknjh tokktng tokzrf tok15ve tok1bzd tok1i3c tok1o7b tok1uba tok20f9 tok1dp tok7ho tokdln tokjpm tokptl tokvxk tok121j tok185i tok1e9h tok1kdg tok1qhf tok1wle tok22pd tok3nt tok9rs tokfvr toklzq toks3p toky7o tok14bn tok1afm tok1gjl tok1mnk tok1srj tok1yvi tok24zh tok5xx tokc1w toki5v toko9u tokudt tok10hs tok16lr tok1cpq tok1itp tok1oxo tok1v1n tok215m tok242 tok881 tokec0 tokfz tokqjy tokwnx' > notes.txt"
+- button "拒绝"
+- button "允许一次"
--- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md
+++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md
@@ -11,16 +11,10 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - 'button "Think The user wants me to write a single `run_code` program that:"':
  - 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 +31,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 52% · 17,490 tokens · 1 turns · 2 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
+++ b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
@@ -11,16 +11,10 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "Think The user wants me to:":
  - 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 +23,6 @@
  - 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 +32,6 @@
  - 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 +45,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 77% · 66,813 tokens · 1 turns · 4 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
+++ b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
@@ -11,18 +11,14 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "Think The user wants me to run a simple bash command and reply with \"DONE\".":
  - 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 +28,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 99% · 15,818 tokens · 1 turns · 2 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
+++ b/apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
@@ -17,9 +17,9 @@
    - img
    - text: workspace 1 session
  - treeitem "New Session now" [selected]
- button "设置":
+- button "Settings":
  - img
-  - text: 设置
+  - text: Settings
 - text: Let's start building
 - button "Choose workspace":
  - img
@@ -28,12 +28,9 @@
 - 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 "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
 - button "Send message" [disabled]
--- a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
+++ b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
@@ -11,7 +11,6 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "Think The user wants me to reply with a single word. Let me comply.":
  - img
  - img
@@ -21,16 +20,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 99% · 7,810 tokens · 1 turns · 1 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/live-interactions/cancel.expected.md
+++ b/apps/web/tests/snapshots/live-interactions/cancel.expected.md
@@ -11,23 +11,20 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - paragraph: partial
 - text: 已停止
 - button "复制":
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} 0 tokens · 1 turns · 1 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
 - button "Send message" [disabled]
+- text: 1 turns · 1 steps Input 0 tok · Output 0 tok
--- a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md
+++ b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md
@@ -11,16 +11,12 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
  - text: DeepSeek-V4-Flash
  - img
 - button "Send message" [disabled]
--- a/apps/web/tests/snapshots/live-interactions/retry.expected.md
+++ b/apps/web/tests/snapshots/live-interactions/retry.expected.md
@@ -11,7 +11,6 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "Think The user is asking for a one-sentence description of event sourcing. This is a straightforward knowledge question that doesn't require any skill loading or tool calls.":
  - img
  - img
@@ -21,16 +20,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 99% · 7,869 tokens · 1 turns · 1 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/message-actions/fork.expected.md
+++ b/apps/web/tests/snapshots/message-actions/fork.expected.md
@@ -0,0 +1,7 @@
+- tree "Sessions":
+  - treeitem "Ungrouped 3 sessions" [expanded]:
+    - img
+    - text: Ungrouped 3 sessions
+  - treeitem "Use the read tool twice (2) now" [selected]
+  - treeitem "Use the read tool twice (1) now"
+  - treeitem "Use the read tool twice 1min"
--- a/apps/web/tests/snapshots/message-actions/ui.expected.md
+++ b/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 +31,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 98% · 15,962 tokens · 1 turns · 2 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 deepseek-v4-flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/plan-review/approved.expected.md
+++ b/apps/web/tests/snapshots/plan-review/approved.expected.md
@@ -0,0 +1,51 @@
+- banner:
+  - navigation "Session hierarchy":
+    - 'button "Plan a small change: add" [disabled]'
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- img
+- text: "/plan Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. Plan mode on. Use /plan off to leave. Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. {{clock}}"
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- button "编辑":
+  - img
+- 'button "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."':
+  - img
+  - img
+  - text: "Think The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."
+- paragraph:
+  - text: Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with
+  - code: exit_plan_mode
+  - text: .
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- text: {{clock}}
+- button:
+  - img
+  - img
+- text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"
+- 'button "Think The plan was approved. The user''s last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."':
+  - img
+  - img
+  - text: "Think The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."
+- paragraph: DONE
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- text: {{clock}}
+- textbox "Message the agent"
+- button "Add attachment":
+  - img
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Send message" [disabled]
+- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 51% Input 10.2K tok · Output 346 tok
--- a/apps/web/tests/snapshots/plan-review/review.expected.md
+++ b/apps/web/tests/snapshots/plan-review/review.expected.md
@@ -0,0 +1,44 @@
+- region "Approve this plan and leave plan mode?":
+  - text: Plan review
+  - heading "Add --greeting flag to CLI" [level=1]:
+    - text: Add
+    - code: "--greeting"
+    - text: flag to CLI
+  - list:
+    - listitem:
+      - strong: Locate the CLI entry point
+      - text: (e.g.,
+      - code: cli.py
+      - text: ","
+      - code: main.go
+      - text: ","
+      - code: index.js
+      - text: etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).
+    - listitem:
+      - strong: Register a new optional string argument
+      - text: named
+      - code: "--greeting"
+      - text: with a short alias (
+      - code: "-g"
+      - text: if available) and a sensible default value (e.g.,
+      - code: "\"Hello\""
+      - text: ).
+    - listitem:
+      - strong: Thread the parsed value
+      - text: through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).
+    - listitem:
+      - strong: Update the help text
+      - text: so
+      - code: "--help"
+      - text: or
+      - code: "-h"
+      - text: shows the new flag with its description.
+    - listitem:
+      - strong: No tests or config changes
+      - text: unless they already exist and directly validate the flag's presence.
+  - status
+  - button "Chat about it":
+    - img
+    - text: Chat about it
+  - button "Refuse"
+  - button "Approve"
--- a/apps/web/tests/snapshots/plan-review/session.jsonl
+++ b/apps/web/tests/snapshots/plan-review/session.jsonl
@@ -0,0 +1,39 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785406804293,"cwd":"{{cwd}}/workspace"}
+{"type":"command/run","seq":0,"time":1785406804350,"data":{"commandId":"cmd-228a60ef-1","name":"plan","args":" Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop.","source":{"kind":"user"}}}
+{"type":"plan/mode","seq":1,"time":1785406804350,"data":{"active":true}}
+{"type":"command/done","seq":2,"time":1785406804352,"data":{"commandId":"cmd-228a60ef-1","kind":"success","text":"Plan mode on. Use /plan off to leave."}}
+{"type":"turn/start","seq":3,"time":1785406804353,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
+{"type":"user/message","seq":4,"time":1785406804353,"data":{"content":[{"type":"text","text":"Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"a22bd0d2-15dc-4bfb-b978-0d5961459e57"},"surfaceOp":"append"}
+{"type":"session/title","seq":5,"time":1785406804354,"data":{"title":"Plan a small change: add","messageSeqs":[4],"source":{"kind":"fallback"}}}
+{"type":"step/start","seq":6,"time":1785406804355,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":7,"time":1785406804356,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"assistant/chunk","seq":8,"time":1785406805697,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":9,"time0":1785406805698,"data":{"turn":1,"step":1,"index":0,"dt":[151,31,0,0,0,0,18,1,0,0,0,31,1,0,0,0,1,23,0,0,0,19,0,0,37,1,0,0,0,0,12,1,0,0,28,0,1,0,24,1,0,0,0,0,26,1,0,0,26,1,22],"texts":["The"," user"," wants"," me"," to"," plan"," a"," small"," change"," to"," add"," a"," `","--","gre","eting","`"," flag"," to"," a"," CLI","."," They"," explicitly"," told"," me"," not"," to"," read"," or"," write"," any"," files",","," and"," to"," call"," exit","_","plan","_mode"," with"," a"," short"," plan","."," Let"," me"," do"," that"," directly","."]}}
+{"type":"assistant/chunk","seq":61,"time":1785406806155,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"text-chunks","seq0":62,"time0":1785406806156,"data":{"turn":1,"step":1,"index":1,"dt":[0,20,0,34,23,26,0,1,0,0,28,0,0,0,32,0,15,1,0,30,1,0,0,23,1,0,24,0,0,0],"texts":["Since"," the"," user"," has"," explicitly"," asked"," me"," not"," to"," read"," or"," write"," any"," files"," and"," to"," go"," straight"," to"," planning",","," I","'ll"," proceed"," with"," `","exit","_","plan","_mode","`."]}}
+{"type":"assistant/chunk","seq":93,"time":1785406806493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}}}
+{"type":"tool-call-chunks","seq0":94,"time0":1785406806493,"data":{"turn":1,"step":1,"index":2,"dt":[27,1,0,0,0,24,0,0,29,1,0,0,0,1,20,0,27,1,0,21,28,0,0,31,1,23,0,0,1,23,0,0,0,23,1,0,28,20,26,28,1,0,29,1,0,0,21,28,0,0,25,1,26,1,0,0,24,1,0,26,0,0,0,1,23,1,0,0,22,29,0,31,1,1,0,21,1,0,0,0,0,20,0,32,25,0,0,22,0,0,27,0,1,0,31,0,1,0,0,20,1,0,0,0,0,24,0,1,0,26,1,29,1,26,1,0,25,30,1,18,0,30,0,0,30,21,1,28,0,21,1,0,0,23,1,23,36,0,0,1,0,13,1,28,27,0,0,25,1,45,1,11,0,21,0,0,0,0,23,0,0,32,1,0,0,0,16,28,0,27,1,0,22,31,1,24,1,21,32,1,0,24,1,0,24],"id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","args":["","{","\"","plan","\"",": ","\"","#"," Add"," `","--","gre","eting","`"," flag"," to"," CLI","\\n\\n","-"," **","Loc","ate"," the"," CLI"," entry"," point","**"," (","e",".g",".,"," `","cli",".py","`,"," `","main",".go","`,"," `","index",".js","`"," etc",".)"," and"," find"," the"," argument"," parser"," definition"," (","arg","parse",","," click",","," cob","ra",","," y","args",","," or"," similar",").\\n","-"," **","Register"," a"," new"," optional"," string"," argument","**"," named"," `","--","gre","eting","`"," with"," a"," short"," alias"," (`","-","g","`"," if"," available",")"," and"," a"," sensible"," default"," value"," (","e",".g",".,"," `","\\\"","Hello","\\\"","`",").\\n","-"," **","Thread"," the"," parsed"," value","**"," through"," the"," main"," handler"," function"," so"," it"," is"," passed"," where"," the"," greeting"," string"," is"," used"," (","e",".g",".,"," the"," welcome","/","response"," message",").\\n","-"," **","Update"," the"," help"," text","**"," so"," `","--","help","`"," or"," `","-","h","`"," shows"," the"," new"," flag"," with"," its"," description",".\\n","-"," **","No"," tests"," or"," config"," changes","**"," unless"," they"," already"," exist"," and"," directly"," validate"," the"," flag","'s"," presence",".","\"","}"]}}
+{"type":"assistant/chunk","seq":280,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."}}}}
+{"type":"assistant/chunk","seq":281,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."}}}}
+{"type":"assistant/chunk","seq":282,"time":1785406808318,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}}}
+{"type":"assistant/chunk","seq":283,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}}}}
+{"type":"assistant/chunk","seq":284,"time":1785406808319,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":285,"time":1785406808324,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."},{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."},{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"b9e18116-68f6-4442-b5a5-a33277ef526c"},"usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52}},"sourceEventSeqs":[8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284],"surfaceOp":"append"}
+{"type":"tool/call","seq":286,"time":1785406808325,"data":{"turn":1,"step":1,"callId":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}
+{"type":"tool/result","seq":287,"time":1785406808720,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_TPh5fH8x5kRezK115kgx8155"},"content":[{"type":"tool-result","toolCallId":"call_00_TPh5fH8x5kRezK115kgx8155","content":[{"type":"text","text":"Plan approved — plan mode exited; carry out the plan starting with your next step."}],"isError":false}],"role":"user","id":"e7cf1f9f-e143-48df-b975-440a9d61a538"}},"sourceEventSeqs":[286],"surfaceOp":"append"}
+{"type":"step/end","seq":288,"time":1785406808721,"data":{"turn":1,"step":1}}
+{"type":"plan/mode","seq":289,"time":1785406808721,"data":{"active":false}}
+{"type":"step/start","seq":290,"time":1785406808723,"data":{"turn":1,"step":2}}
+{"type":"request/header","seq":291,"time":1785406808723,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
+{"type":"assistant/chunk","seq":292,"time":1785406809855,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"reasoning-chunks","seq0":293,"time0":1785406809855,"data":{"turn":1,"step":2,"index":0,"dt":[133,28,1,0,0,17,0,28,1,0,0,29,0,0,0,0,0,21,0,0,0,35,0,0,0,0,0,14,1,37,1,0,1,17,0,0,0,0,1],"texts":["The"," plan"," was"," approved","."," The"," user","'s"," last"," instruction"," says",":"," \"","Once"," the"," plan"," is"," approved",","," reply"," with"," the"," single"," word"," D","ONE"," and"," stop",".\""," So"," I"," should"," just"," reply"," with"," D","ONE"," and"," stop","."]}}
+{"type":"assistant/chunk","seq":333,"time":1785406810252,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":334,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
+{"type":"assistant/chunk","seq":335,"time":1785406810253,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
+{"type":"assistant/chunk","seq":336,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."}}}}
+{"type":"assistant/chunk","seq":337,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
+{"type":"assistant/chunk","seq":338,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}}}}
+{"type":"assistant/chunk","seq":339,"time":1785406810256,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":340,"time":1785406810257,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek","model":"deepseek-v4-flash"},"id":"2d9da552-d236-4166-9d06-dffa9bace4cd"},"usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}},"sourceEventSeqs":[292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339],"surfaceOp":"append"}
+{"type":"step/end","seq":341,"time":1785406810258,"data":{"turn":1,"step":2}}
+{"type":"turn/end","seq":342,"time":1785406810258,"data":{"turn":1,"reason":{"kind":"completed"}}}
--- a/apps/web/tests/snapshots/question-composer/answered.expected.md
+++ b/apps/web/tests/snapshots/question-composer/answered.expected.md
@@ -11,20 +11,14 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.":
  - 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
- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"color\", \"question\": \"Which color do you prefer?\", \"header\": \"Pick one\", \"options\": [{\"label\": \"Blue\", \"description\": \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\"}, {\"label\": \"Green\", \"description\": \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\"}]}]}"
+- text: Ask question 1/1 answered
 - button "Think The user answered \"Blue\". I should now reply with the single word DONE and stop.":
  - img
  - img
@@ -34,16 +28,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 95% · 8,769 tokens · 1 turns · 2 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/question-composer/ui.expected.md
+++ b/apps/web/tests/snapshots/question-composer/ui.expected.md
@@ -1,23 +1,17 @@
 - region "Which color do you prefer?":
  - text: Pick one
  - heading "Which color do you prefer?" [level=2]
-  - text: 1 / 1
-  - button "上一题" [disabled]:
-    - img
-  - button "下一题" [disabled]:
-    - img
-  - button "放弃整组问题":
+  - button "Dismiss all questions":
    - img
  - radiogroup:
-    - radio "Blue":
-      - text: 1 Blue A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.
-      - img
-    - radio "Green":
-      - text: 2 Green A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.
-      - img
-    - button "其他，请填写自定义答案":
-      - img
-      - text: 其他，请填写自定义答案
+    - radio "Blue": 1 Blue A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.
+    - radio "Green": 2 Green A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.
+    - textbox "Type your answer"
+  - button "Previous question" [disabled]:
+    - img
+  - text: 1 / 1
+  - button "Next question" [disabled]:
+    - img
  - status
-  - button "跳过本题"
-  - button "提交" [disabled]
+  - button "Skip this question"
+  - button "Submit" [disabled]
--- a/apps/web/tests/snapshots/queue-actions/collapsed.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/collapsed.expected.md
@@ -0,0 +1,24 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- button "编辑":
+  - img
+- paragraph: partial
+- button "2 条排队消息"
+- textbox "Message the agent"
+- button "Add attachment":
+  - img
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Stop generating"
--- a/apps/web/tests/snapshots/queue-actions/editing.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/editing.expected.md
@@ -0,0 +1,37 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- button "编辑":
+  - img
+- paragraph: partial
+- button "2 条排队消息" [disabled] [expanded]
+- list:
+  - listitem:
+    - text: Queue item to remove
+    - button "编辑排队消息":
+      - img
+    - button "删除排队消息":
+      - img
+  - listitem:
+    - textbox "编辑排队消息": Edited queue item
+    - button "保存排队消息":
+      - img
+    - button "取消编辑":
+      - img
+- textbox "Message the agent"
+- button "Add attachment":
+  - img
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Stop generating"
--- a/apps/web/tests/snapshots/queue-actions/ui.expected.md
+++ b/apps/web/tests/snapshots/queue-actions/ui.expected.md
@@ -0,0 +1,30 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "Reply with a one-sentence description" [disabled]
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
+- button "复制":
+  - img
+- button "在新对话中分支":
+  - img
+- button "编辑":
+  - img
+- paragraph: partial
+- list:
+  - listitem:
+    - text: Edited queue item
+    - button "编辑排队消息":
+      - img
+    - button "删除排队消息":
+      - img
+- textbox "Message the agent"
+- button "Add attachment":
+  - img
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Stop generating"
--- a/apps/web/tests/snapshots/seeded-history/ui.expected.md
+++ b/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 +30,18 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 98% · 15,962 tokens · 1 turns · 2 steps
+- text: {{clock}}
+- button "上下文注入":
+  - img
+  - img
+  - text: 上下文注入
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 deepseek-v4-flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/skill-invocation-policy/menu.expected.md
+++ b/apps/web/tests/snapshots/skill-invocation-policy/menu.expected.md
@@ -1,3 +1,3 @@
 - listbox "Trigger suggestions":
-  - text: 技能
+  - text: Skills
  - option "policy-shared Available to both model and user invocation" [selected]
--- a/apps/web/tests/snapshots/steering/mid-steer.expected.md
+++ b/apps/web/tests/snapshots/steering/mid-steer.expected.md
@@ -11,40 +11,28 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "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.":
  - 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\"}]}]} cache hit 98% · 7,946 tokens · 1 turns · 1 steps"
+- text: Ask question waiting
 - region "Ready to continue?":
  - text: Checkpoint
  - heading "Ready to continue?" [level=2]
-  - text: 1 / 1
-  - button "上一题" [disabled]:
-    - img
-  - button "下一题" [disabled]:
-    - img
-  - button "放弃整组问题":
+  - button "Dismiss all questions":
    - img
  - radiogroup:
-    - radio "Yes":
-      - text: 1 Yes
-      - img
-    - radio "No":
-      - text: 2 No
-      - img
-    - button "其他，请填写自定义答案":
-      - img
-      - text: 其他，请填写自定义答案
+    - radio "Yes": 1 Yes
+    - radio "No": 2 No
+    - textbox "Type your answer"
+  - button "Previous question" [disabled]:
+    - img
+  - text: 1 / 1
+  - button "Next question" [disabled]:
+    - img
  - status
-  - button "跳过本题"
-  - button "提交" [disabled]
+  - button "Skip this question"
+  - button "Submit" [disabled]
--- a/apps/web/tests/snapshots/steering/settled.expected.md
+++ b/apps/web/tests/snapshots/steering/settled.expected.md
@@ -11,20 +11,14 @@
  - img
 - button "编辑":
  - img
- button "▸ 上下文注入"
 - button "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.":
  - 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\"}]}]} 插话 Interjection: include the word BANANA in your final reply."
+- text: "Ask question 1/1 answered 插话 Interjection: include the word BANANA in your final reply."
 - button "Think The user selected \"Yes\" and wants me to include the word \"BANANA\" in my final reply. Let me acknowledge their answer.":
  - img
  - img
@@ -34,16 +28,14 @@
  - img
 - button "在新对话中分支":
  - img
- text: {{clock}} cache hit 98% · 15,967 tokens · 1 turns · 2 steps
+- text: {{clock}}
 - textbox "Message the agent"
 - button "Add attachment":
  - img
- text: Danger Full Access
- combobox "Access mode":
-  - option "Read Only"
-  - option "Workspace Write"
-  - option "Danger Full Access" [selected]
- button "选择模型，当前 DeepSeek-V4-Flash":
+- 'button "Access mode, current: Danger Full Access"': Danger Full Access
+- button "Plan mode off, press to turn on": Plan off
+- button "Select model, current 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
--- a/apps/web/tests/snapshots/workspace-management/directory-browser.expected.md
+++ b/apps/web/tests/snapshots/workspace-management/directory-browser.expected.md
@@ -1,10 +1,41 @@
- dialog "选择工作区目录":
-  - heading "选择工作区目录" [level=2]
+- dialog "Select Workspace Directory":
+  - heading "Select Workspace Directory" [level=2]
  - navigation:
-    - button "主目录"
+    - button "Home"
    - img
    - button "browse-golden"
-  - button "编辑路径"
+  - button "Edit path"
+  - list:
+    - listitem:
+      - button "adopted":
+        - img
+        - text: adopted
+        - img
+    - listitem:
+      - button "alpha-ws":
+        - img
+        - text: alpha-ws
+        - img
+    - listitem:
+      - button "beta-ws":
+        - img
+        - text: beta-ws
+        - img
+    - listitem:
+      - button "browse-golden":
+        - img
+        - text: browse-golden
+        - img
+    - listitem:
+      - button "same-name":
+        - img
+        - text: same-name
+        - img
+    - listitem:
+      - button "workspace":
+        - img
+        - text: workspace
+        - img
  - list:
    - listitem:
      - button "alpha":
@@ -16,8 +47,9 @@
        - img
        - text: beta
        - img
-  - button "新建文件夹":
+  - button "New folder":
    - img
-    - text: 新建文件夹
-  - button "取消"
-  - button "打开"
+    - text: New folder
+  - button "Show hidden files"
+  - button "Cancel"
+  - button "Open"