diff --git a/apps/web/tests/snapshots/code-mode-round/ui.expected.md b/apps/web/tests/snapshots/code-mode-round/ui.expected.md index 4847924619..8701c6fb19 100644 --- a/apps/web/tests/snapshots/code-mode-round/ui.expected.md +++ b/apps/web/tests/snapshots/code-mode-round/ui.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: "Using ONE run_code program: run bash `echo CODE_ROUND_OK`, then read the file missing.txt catching its error in the program. Return an object with both outcomes. Then reply DONE and stop." +- text: "Using ONE run_code program: run bash `echo CODE_ROUND_OK`, then read the file missing.txt catching its error in the program. Return an object with both outcomes. Then reply DONE and stop. {{clock}}" - button "复制": - img - button "在新对话中分支": @@ -16,6 +16,11 @@ - 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 @@ -28,7 +33,11 @@ - img - text: Think The program ran successfully. Let me now reply DONE as instructed. - paragraph: DONE -- text: cache hit 52% · 17,490 tokens · 1 turns · 2 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 52% · 17,490 tokens · 1 turns · 2 steps - textbox "Message the agent" - button "Add attachment": - img diff --git a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md index e5e5626be3..77038546c0 100644 --- a/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md +++ b/apps/web/tests/snapshots/cordis-tool-round/ui.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: "Use only Cordis tools. First call cordis_inspect with what \"temporary\". Then call cordis_mount with this exact code: \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\". Read its returned id and call cordis_unmount with that exact id. After all three calls succeed, reply exactly CORDIS_UI_DONE and stop." +- text: "Use only Cordis tools. First call cordis_inspect with what \"temporary\". Then call cordis_mount with this exact code: \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\". Read its returned id and call cordis_unmount with that exact id. After all three calls succeed, reply exactly CORDIS_UI_DONE and stop. {{clock}}" - button "复制": - img - button "在新对话中分支": @@ -16,6 +16,11 @@ - 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 @@ -24,6 +29,11 @@ - 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 @@ -33,6 +43,11 @@ - 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 @@ -42,7 +57,11 @@ - img - text: Think All three calls succeeded. I should now reply exactly "CORDIS_UI_DONE" and stop. - paragraph: CORDIS_UI_DONE -- text: cache hit 77% · 66,813 tokens · 1 turns · 4 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 77% · 66,813 tokens · 1 turns · 4 steps - textbox "Message the agent" - button "Add attachment": - img diff --git a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md index 6a827420c4..7ea4c95e2b 100644 --- a/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md +++ b/apps/web/tests/snapshots/fresh-round-trip/ui.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: "Use the bash tool to run exactly: echo WEB_E2E_OK. Then reply with the single word DONE and stop." +- text: "Use the bash tool to run exactly: echo WEB_E2E_OK. Then reply with the single word DONE and stop. {{clock}}" - button "复制": - img - button "在新对话中分支": @@ -16,6 +16,11 @@ - 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 - button "Think The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\".": @@ -23,7 +28,11 @@ - img - text: Think The command executed successfully and output "WEB_E2E_OK". I just need to reply with "DONE". - paragraph: DONE -- text: cache hit 99% · 15,818 tokens · 1 turns · 2 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 99% · 15,818 tokens · 1 turns · 2 steps - textbox "Message the agent" - button "Add attachment": - img diff --git a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md index 33d1f7e6bf..17f79759ca 100644 --- a/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md +++ b/apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: Reply with the single word LIGHTHOUSE and stop. +- text: Reply with the single word LIGHTHOUSE and stop. {{clock}} - button "复制": - img - button "在新对话中分支": @@ -17,7 +17,11 @@ - img - text: Think The user wants me to reply with a single word. Let me comply. - paragraph: LIGHTHOUSE -- text: cache hit 99% · 7,810 tokens · 1 turns · 1 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 99% · 7,810 tokens · 1 turns · 1 steps - textbox "Message the agent" - button "Add attachment": - img diff --git a/apps/web/tests/snapshots/live-interactions/cancel.expected.md b/apps/web/tests/snapshots/live-interactions/cancel.expected.md index 3d092b17ec..665221e6b4 100644 --- a/apps/web/tests/snapshots/live-interactions/cancel.expected.md +++ b/apps/web/tests/snapshots/live-interactions/cancel.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: Reply with a one-sentence description of event sourcing, then stop. +- 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": @@ -13,7 +13,12 @@ - button "编辑": - img - paragraph: partial -- text: 已停止 0 tokens · 1 turns · 1 steps +- 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 - textbox "Message the agent" - button "Add attachment": - img diff --git a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md index 5272bcf2d1..27b4a6c1c1 100644 --- a/apps/web/tests/snapshots/live-interactions/error-auth.expected.md +++ b/apps/web/tests/snapshots/live-interactions/error-auth.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: Reply with a one-sentence description of event sourcing, then stop. +- 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": diff --git a/apps/web/tests/snapshots/live-interactions/retry.expected.md b/apps/web/tests/snapshots/live-interactions/retry.expected.md index 5935872557..9e051feea3 100644 --- a/apps/web/tests/snapshots/live-interactions/retry.expected.md +++ b/apps/web/tests/snapshots/live-interactions/retry.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: Reply with a one-sentence description of event sourcing, then stop. +- 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": @@ -17,7 +17,11 @@ - img - text: 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. - paragraph: Event sourcing is a pattern where all changes to an application's state are stored as an immutable, append-only sequence of events, rather than persisting only the current state, enabling full auditability, temporal queries, and event-driven architectures. -- text: cache hit 99% · 7,869 tokens · 1 turns · 1 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 99% · 7,869 tokens · 1 turns · 1 steps - textbox "Message the agent" - button "Add attachment": - img diff --git a/apps/web/tests/snapshots/seeded-history/ui.expected.md b/apps/web/tests/snapshots/seeded-history/ui.expected.md index 4f9181f702..db71bd6696 100644 --- a/apps/web/tests/snapshots/seeded-history/ui.expected.md +++ b/apps/web/tests/snapshots/seeded-history/ui.expected.md @@ -1,32 +1,50 @@ - banner: - navigation "Session hierarchy": - button "Use the read tool twice" [disabled] - - text: · 1 turns - tablist: - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop." +- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then 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 read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.": + - 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: +- button "复制": - img -- text: Read a.txt -- button: +- button "在新对话中分支": - img -- text: Read b.txt +- text: {{clock}} +- img +- text: Read +- button "a.txt" +- img +- text: Read +- button "b.txt" - button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.": + - img - img - text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed. - paragraph: DONE -- text: cache hit 98% · 15,962 tokens · 1 turns · 2 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 98% · 15,962 tokens · 1 turns · 2 steps - textbox "Message the agent" - button "Add attachment": - img +- text: Danger Full Access - combobox "Access mode": - - option "Read-only" [selected] - - option "Read-write" + - option "Read Only" + - option "Workspace Write" + - option "Danger Full Access" [selected] - button "选择模型,当前 deepseek-v4-flash": - text: deepseek-v4-flash - img diff --git a/apps/web/tests/snapshots/steering/mid-steer.expected.md b/apps/web/tests/snapshots/steering/mid-steer.expected.md index 8d33ea6283..87ed907abd 100644 --- a/apps/web/tests/snapshots/steering/mid-steer.expected.md +++ b/apps/web/tests/snapshots/steering/mid-steer.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. +- text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. {{clock}} - button "复制": - img - button "在新对话中分支": @@ -16,12 +16,15 @@ - 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\"}]}]} 等待回答(1 题)" -- button "▸ 问题内容" -- text: cache hit 98% · 7,946 tokens · 1 turns · 1 steps +- 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" - region "Ready to continue?": - text: Checkpoint - heading "Ready to continue?" [level=2] diff --git a/apps/web/tests/snapshots/steering/settled.expected.md b/apps/web/tests/snapshots/steering/settled.expected.md index f08fc518e8..7a2f9ae0e6 100644 --- a/apps/web/tests/snapshots/steering/settled.expected.md +++ b/apps/web/tests/snapshots/steering/settled.expected.md @@ -5,7 +5,7 @@ - tab "Chat" [selected] - tab "Trajectory" - tab "Waterfall" -- text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. +- text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. {{clock}} - button "复制": - img - button "在新对话中分支": @@ -16,6 +16,11 @@ - 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 @@ -25,7 +30,11 @@ - img - text: Think The user selected "Yes" and wants me to include the word "BANANA" in my final reply. Let me acknowledge their answer. - paragraph: Great, let's move forward. BANANA! -- text: cache hit 98% · 15,967 tokens · 1 turns · 2 steps +- button "复制": + - img +- button "在新对话中分支": + - img +- text: {{clock}} cache hit 98% · 15,967 tokens · 1 turns · 2 steps - textbox "Message the agent" - button "Add attachment": - img