Merge origin/master into fix/web-agent-runtime-context
This commit is contained in:
Tianyi Cui
10
apps/web/tests/snapshots/access-confirmation/ui.expected.md
Normal file
10
apps/web/tests/snapshots/access-confirmation/ui.expected.md
Normal file
@@ -0,0 +1,10 @@
|
||||
- dialog "确认启用 Full access？":
|
||||
- heading "确认启用 Full access？" [level=2]
|
||||
- button "Close":
|
||||
- img
|
||||
- img
|
||||
- paragraph: 启用 Full access 后，agent 将减少确认步骤，并且可以直接执行更多操作，包括敏感操作、文件修改或外部命令。仅建议在你信任当前任务时使用。
|
||||
- checkbox "我已了解风险，并愿意继续"
|
||||
- text: 我已了解风险，并愿意继续
|
||||
- button "取消"
|
||||
- button "启用 Full access" [disabled]
|
||||
64
apps/web/tests/snapshots/approval-composer/session.jsonl
Normal file
64
apps/web/tests/snapshots/approval-composer/session.jsonl
Normal file
File diff suppressed because one or more lines are too long
@@ -0,0 +1,4 @@
|
||||
- text: Waiting for approval
|
||||
- group "Approval details": "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 "Reject"
|
||||
- button "Allow once"
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1785013630411,"data":{"content":[{"type":"text","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."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785013630418,"data":{"title":"Using ONE run_code program: run","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785013630479,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785013630480,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1785013630480,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785013631481,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785013631481,"data":{"turn":1,"step":1,"index":0,"dt":[182,27,0,0,1,39,1,0,11,0,0,1,0,25,0,1,0,0,25,28,0,0,0,26,1,0,0,0,0,25,1,0,0,0,0,28,1,0,0,0,23,1,0,1,0,0,25,1,0,0,0,26,0,0,0,26,0,26,0,0,1,25,1,0,0,0,0,25,1,26,0,1,26,29],"texts":["The"," user"," wants"," me"," to"," write"," a"," single"," `","run","_code","`"," program"," that",":\n","1","."," Runs"," bash"," to"," echo"," \"","CODE","_RO","UND","_OK","\"\n","2","."," T","ries"," to"," read"," a"," file"," \"","missing",".txt","\""," and"," catches"," the"," error","\n","3","."," Returns"," an"," object"," with"," both"," outcomes","\n","4","."," They"," also"," want"," me"," to"," reply"," \"","D","ONE","\""," and"," stop"," after","\n\n","Let"," me"," write"," this"," program","."]}}
|
||||
{"type":"assistant/chunk","seq":81,"time":1785013632219,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/chunk","seq":202,"time":1785013633103,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_6VNoF1gDSerTBKoCfYSH3765","name":"run_code","arguments":"{\"description\": \"Run bash echo and catch missing file read\", \"code\": \"\\nconst bashResult = await tools.bash({\\n command: \\\"echo CODE_ROUND_OK\\\",\\n description: \\\"Echo CODE_ROUND_OK\\\"\\n});\\n\\nlet readError = null;\\ntry {\\n await tools.read({ file_path: \\\"missing.txt\\\" });\\n} catch (e) {\\n readError = {\\n toolName: e.toolName,\\n message: e.message\\n };\\n}\\n\\nreturn { bash: bashResult.stdout.text.trim(), readError };\\n\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":203,"time":1785013633104,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":8082,"outputTokens":235,"cacheReadTokens":384,"reasoningTokens":75}}}}
|
||||
{"type":"assistant/chunk","seq":204,"time":1785013633104,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":205,"time":1785013633108,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to write a single `run_code` program that:\n1. Runs bash to echo \"CODE_ROUND_OK\"\n2. Tries to read a file \"missing.txt\" and catches the error\n3. Returns an object with both outcomes\n4. They also want me to reply \"DONE\" and stop after\n\nLet me write this program."},{"type":"tool-call","id":"call_00_6VNoF1gDSerTBKoCfYSH3765","name":"run_code","arguments":"{\"description\": \"Run bash echo and catch missing file read\", \"code\": \"\\nconst bashResult = await tools.bash({\\n command: \\\"echo CODE_ROUND_OK\\\",\\n description: \\\"Echo CODE_ROUND_OK\\\"\\n});\\n\\nlet readError = null;\\ntry {\\n await tools.read({ file_path: \\\"missing.txt\\\" });\\n} catch (e) {\\n readError = {\\n toolName: e.toolName,\\n message: e.message\\n };\\n}\\n\\nreturn { bash: bashResult.stdout.text.trim(), readError };\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":8082,"outputTokens":235,"cacheReadTokens":384,"reasoningTokens":75}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":205,"time":1785013633108,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to write a single `run_code` program that:\n1. Runs bash to echo \"CODE_ROUND_OK\"\n2. Tries to read a file \"missing.txt\" and catches the error\n3. Returns an object with both outcomes\n4. They also want me to reply \"DONE\" and stop after\n\nLet me write this program."},{"type":"tool-call","id":"call_00_6VNoF1gDSerTBKoCfYSH3765","name":"run_code","arguments":"{\"description\": \"Run bash echo and catch missing file read\", \"code\": \"\\nconst bashResult = await tools.bash({\\n command: \\\"echo CODE_ROUND_OK\\\",\\n description: \\\"Echo CODE_ROUND_OK\\\"\\n});\\n\\nlet readError = null;\\ntry {\\n await tools.read({ file_path: \\\"missing.txt\\\" });\\n} catch (e) {\\n readError = {\\n toolName: e.toolName,\\n message: e.message\\n };\\n}\\n\\nreturn { bash: bashResult.stdout.text.trim(), readError };\\n\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":8082,"outputTokens":235,"cacheReadTokens":384,"reasoningTokens":75}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":206,"time":1785013633108,"data":{"turn":1,"step":1,"callId":"call_00_6VNoF1gDSerTBKoCfYSH3765","name":"run_code","arguments":"{\"description\": \"Run bash echo and catch missing file read\", \"code\": \"\\nconst bashResult = await tools.bash({\\n command: \\\"echo CODE_ROUND_OK\\\",\\n description: \\\"Echo CODE_ROUND_OK\\\"\\n});\\n\\nlet readError = null;\\ntry {\\n await tools.read({ file_path: \\\"missing.txt\\\" });\\n} catch (e) {\\n readError = {\\n toolName: e.toolName,\\n message: e.message\\n };\\n}\\n\\nreturn { bash: bashResult.stdout.text.trim(), readError };\\n\"}"}}
|
||||
{"type":"tool/code-dispatch-start","seq":207,"time":1785013633173,"data":{"parentCallId":"call_00_6VNoF1gDSerTBKoCfYSH3765","subCallId":"call_00_6VNoF1gDSerTBKoCfYSH3765:code:1","name":"bash","arguments":{"command":"echo CODE_ROUND_OK","description":"Echo CODE_ROUND_OK"}}}
|
||||
{"type":"tool/code-dispatch","seq":208,"time":1785013633196,"data":{"parentCallId":"call_00_6VNoF1gDSerTBKoCfYSH3765","subCallId":"call_00_6VNoF1gDSerTBKoCfYSH3765:code:1","name":"bash","arguments":{"command":"echo CODE_ROUND_OK","description":"Echo CODE_ROUND_OK"},"isError":false,"content":[{"type":"text","text":"CODE_ROUND_OK\n"}]}}
|
||||
@@ -30,6 +30,6 @@
|
||||
{"type":"assistant/chunk","seq":233,"time":1785013634223,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":234,"time":1785013634223,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":196,"outputTokens":17,"cacheReadTokens":8576,"reasoningTokens":14}}}}
|
||||
{"type":"assistant/chunk","seq":235,"time":1785013634223,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":236,"time":1785013634224,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The program ran successfully. Let me now reply DONE as instructed."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":196,"outputTokens":17,"cacheReadTokens":8576,"reasoningTokens":14}},"sourceEventSeqs":[214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":236,"time":1785013634224,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The program ran successfully. Let me now reply DONE as instructed."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":196,"outputTokens":17,"cacheReadTokens":8576,"reasoningTokens":14}},"sourceEventSeqs":[214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":237,"time":1785013634225,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":238,"time":1785013634225,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -1,32 +1,46 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- 'button "Using ONE run_code program: run" [disabled]'
|
||||
- text: · 1 turns
|
||||
- 'heading "Using ONE run_code program: run" [level=1]'
|
||||
- tablist:
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- 'button "Think The user wants me to write a single `run_code` program that:"':
|
||||
- img
|
||||
- text: "Think The user wants me to write a single `run_code` program that:"
|
||||
- button:
|
||||
- img
|
||||
- text: Code Run bash echo and catch missing file read Echo CODE_ROUND_OK
|
||||
- button
|
||||
- text: Read missing.txt
|
||||
- text: "Think The user wants me to write a single `run_code` program that:"
|
||||
- button "Code Run bash echo and catch missing file read":
|
||||
- img
|
||||
- img
|
||||
- text: Code Run bash echo and catch missing file read
|
||||
- img
|
||||
- text: Bash Echo CODE_ROUND_OK Failed
|
||||
- 'button "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"':
|
||||
- img
|
||||
- text: "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"
|
||||
- button "Think The program ran successfully. Let me now reply DONE as instructed.":
|
||||
- img
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Context 7% of 128K Cache hit 52% Input 17.2K tok · Output 252 tok
|
||||
|
||||
@@ -0,0 +1,25 @@
|
||||
# Composer draft scrolling (14-line cap, two text layers)
|
||||
|
||||
## At the start of the draft
|
||||
|
||||
- draft overflows the capped box: true
|
||||
- visible lines: 14
|
||||
- both layers share one scroll extent: true
|
||||
- all three layers wrap at one width: true
|
||||
- textarea scroll offset: 0px
|
||||
- glyph layer tracks it: true
|
||||
- first draft line is on screen: true
|
||||
- last draft line is on screen: false
|
||||
|
||||
## Scrolled to the end of the draft
|
||||
|
||||
- textarea moved: true
|
||||
- glyph layer tracks it: true
|
||||
- first draft line has scrolled out above: true
|
||||
- last draft line is on screen: true
|
||||
|
||||
## Draft ending in a newline, scrolled to the end
|
||||
|
||||
- both layers share one scroll extent: true
|
||||
- glyph layer tracks the caret: true
|
||||
- last draft line is on screen: true
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1785157562882,"data":{"content":[{"type":"text","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."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785157562883,"data":{"title":"Use only Cordis tools. First","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785157562937,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785157562938,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1785157562938,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","reasoningEffort":"high"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785157564667,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785157564667,"data":{"turn":1,"step":1,"index":0,"dt":[115,31,3,0,1,0,1,21,1,0,0,0,1,23,0,1,0,0,0,24,2,1,0,0,0,28,2,0,0,0,1,23,2,22,2,1,25,2,0,0,25,27,1,1,0,0,28,2,0,0,0,0,32,1,31,1,0,0,0,9,29,3,0,0,0,1,23,1,0,0,0,27,4,0,0,0,23,2,0,0],"texts":["The"," user"," wants"," me"," to",":\n","1","."," Call"," `","cord","is","_in","spect","`"," with"," `","what",":"," \"","t","emporary","\"`\n","2","."," Call"," `","cord","is","_m","ount","`"," with"," the"," exact"," code"," provided","\n","3","."," Read"," the"," returned"," id"," and"," call"," `","cord","is","_un","mount","`"," with"," that"," exact"," id","\n","4","."," Reply"," exactly"," \"","C","ORD","IS","_","UI","_D","ONE","\""," and"," stop","\n\n","Let"," me"," start"," with"," step"," ","1","."]}}
|
||||
{"type":"assistant/chunk","seq":87,"time":1785157565360,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/chunk","seq":100,"time":1785157565491,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_KZk918WtlKan9pHMULIT8794","name":"cordis_inspect","arguments":"{\"what\": \"temporary\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":101,"time":1785157565491,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":15137,"outputTokens":128,"cacheReadTokens":1280,"reasoningTokens":81}}}}
|
||||
{"type":"assistant/chunk","seq":102,"time":1785157565491,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":103,"time":1785157565495,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Call `cordis_inspect` with `what: \"temporary\"`\n2. Call `cordis_mount` with the exact code provided\n3. Read the returned id and call `cordis_unmount` with that exact id\n4. Reply exactly \"CORDIS_UI_DONE\" and stop\n\nLet me start with step 1."},{"type":"tool-call","id":"call_00_KZk918WtlKan9pHMULIT8794","name":"cordis_inspect","arguments":"{\"what\": \"temporary\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":15137,"outputTokens":128,"cacheReadTokens":1280,"reasoningTokens":81}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":103,"time":1785157565495,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Call `cordis_inspect` with `what: \"temporary\"`\n2. Call `cordis_mount` with the exact code provided\n3. Read the returned id and call `cordis_unmount` with that exact id\n4. Reply exactly \"CORDIS_UI_DONE\" and stop\n\nLet me start with step 1."},{"type":"tool-call","id":"call_00_KZk918WtlKan9pHMULIT8794","name":"cordis_inspect","arguments":"{\"what\": \"temporary\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":15137,"outputTokens":128,"cacheReadTokens":1280,"reasoningTokens":81}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":104,"time":1785157565496,"data":{"turn":1,"step":1,"callId":"call_00_KZk918WtlKan9pHMULIT8794","name":"cordis_inspect","arguments":"{\"what\": \"temporary\"}"}}
|
||||
{"type":"tool/result","seq":105,"time":1785157565500,"data":{"turn":1,"step":1,"callId":"call_00_KZk918WtlKan9pHMULIT8794","content":[{"type":"text","text":"## Temporary Plugins\nNo temporary Plugins are running. Temporary Plugins created with cordis_mount disappear when DSH restarts."}],"isError":false},"sourceEventSeqs":[104],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":106,"time":1785157565503,"data":{"turn":1,"step":1}}
|
||||
@@ -25,7 +25,7 @@
|
||||
{"type":"assistant/chunk","seq":157,"time":1785157567041,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_OyrlxqqpnvzTe11sN5Oy2361","name":"cordis_mount","arguments":"{\"code\": \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":158,"time":1785157567042,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":72,"outputTokens":82,"cacheReadTokens":16512,"reasoningTokens":22}}}}
|
||||
{"type":"assistant/chunk","seq":159,"time":1785157567042,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":160,"time":1785157567043,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."},{"type":"tool-call","id":"call_00_OyrlxqqpnvzTe11sN5Oy2361","name":"cordis_mount","arguments":"{\"code\": \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":72,"outputTokens":82,"cacheReadTokens":16512,"reasoningTokens":22}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":160,"time":1785157567043,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."},{"type":"tool-call","id":"call_00_OyrlxqqpnvzTe11sN5Oy2361","name":"cordis_mount","arguments":"{\"code\": \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":72,"outputTokens":82,"cacheReadTokens":16512,"reasoningTokens":22}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":161,"time":1785157567043,"data":{"turn":1,"step":2,"callId":"call_00_OyrlxqqpnvzTe11sN5Oy2361","name":"cordis_mount","arguments":"{\"code\": \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\"}"}}
|
||||
{"type":"tool/result","seq":162,"time":1785157567049,"data":{"turn":1,"step":2,"callId":"call_00_OyrlxqqpnvzTe11sN5Oy2361","content":[{"type":"text","text":"Temporary Plugin dyn-1 is running (plugin \"snapshot-noop\"; available until unmounted or DSH restarts)."}],"isError":false},"sourceEventSeqs":[161],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":163,"time":1785157567050,"data":{"turn":1,"step":2}}
|
||||
@@ -38,7 +38,7 @@
|
||||
{"type":"assistant/chunk","seq":204,"time":1785157568279,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_e38S6zeYdZGvbhecUCil6659","name":"cordis_unmount","arguments":"{\"id\": \"dyn-1\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":205,"time":1785157568279,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":63,"outputTokens":72,"cacheReadTokens":16640,"reasoningTokens":23}}}}
|
||||
{"type":"assistant/chunk","seq":206,"time":1785157568279,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":207,"time":1785157568280,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."},{"type":"tool-call","id":"call_00_e38S6zeYdZGvbhecUCil6659","name":"cordis_unmount","arguments":"{\"id\": \"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":63,"outputTokens":72,"cacheReadTokens":16640,"reasoningTokens":23}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":207,"time":1785157568280,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."},{"type":"tool-call","id":"call_00_e38S6zeYdZGvbhecUCil6659","name":"cordis_unmount","arguments":"{\"id\": \"dyn-1\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":63,"outputTokens":72,"cacheReadTokens":16640,"reasoningTokens":23}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":208,"time":1785157568280,"data":{"turn":1,"step":3,"callId":"call_00_e38S6zeYdZGvbhecUCil6659","name":"cordis_unmount","arguments":"{\"id\": \"dyn-1\"}"}}
|
||||
{"type":"tool/result","seq":209,"time":1785157568281,"data":{"turn":1,"step":3,"callId":"call_00_e38S6zeYdZGvbhecUCil6659","content":[{"type":"text","text":"Temporary Plugin dyn-1 was unmounted and removed."}],"isError":false},"sourceEventSeqs":[208],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":210,"time":1785157568282,"data":{"turn":1,"step":3}}
|
||||
@@ -51,6 +51,6 @@
|
||||
{"type":"assistant/chunk","seq":244,"time":1785157569551,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CORDIS_UI_DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":245,"time":1785157569551,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":29,"outputTokens":30,"cacheReadTokens":16768,"reasoningTokens":22}}}}
|
||||
{"type":"assistant/chunk","seq":246,"time":1785157569551,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":247,"time":1785157569553,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"All three calls succeeded. I should now reply exactly \"CORDIS_UI_DONE\" and stop."},{"type":"text","text":"CORDIS_UI_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":29,"outputTokens":30,"cacheReadTokens":16768,"reasoningTokens":22}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":247,"time":1785157569553,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"All three calls succeeded. I should now reply exactly \"CORDIS_UI_DONE\" and stop."},{"type":"text","text":"CORDIS_UI_DONE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":29,"outputTokens":30,"cacheReadTokens":16768,"reasoningTokens":22}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":248,"time":1785157569554,"data":{"turn":1,"step":4}}
|
||||
{"type":"turn/end","seq":249,"time":1785157569554,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -1,48 +1,61 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use only Cordis tools. First" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Use only Cordis tools. First" [level=1]
|
||||
- tablist:
|
||||
- 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."
|
||||
- button "复制":
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "在新对话中分支":
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "编辑":
|
||||
- button "Context injection":
|
||||
- img
|
||||
- button "▸ 上下文注入"
|
||||
- img
|
||||
- text: Context injection
|
||||
- button "Think The user wants me to:":
|
||||
- img
|
||||
- text: "Think The user wants me to:"
|
||||
- button:
|
||||
- img
|
||||
- text: Inspect temporary
|
||||
- text: "Think The user wants me to:"
|
||||
- button "Inspect temporary":
|
||||
- img
|
||||
- img
|
||||
- text: Inspect temporary
|
||||
- 'button "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."':
|
||||
- img
|
||||
- text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."
|
||||
- button [expanded]:
|
||||
- img
|
||||
- text: Mount temporary Plugin typescript
|
||||
- button "复制"
|
||||
- text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."
|
||||
- 'button "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }" [expanded]':
|
||||
- img
|
||||
- text: "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }"
|
||||
- text: typescript
|
||||
- button "Copy"
|
||||
- code: "return { name: \"snapshot-noop\", apply(ctx) {} }"
|
||||
- text: OUT Temporary Plugin dyn-1 is running (plugin "snapshot-noop"; available until unmounted or DSH restarts).
|
||||
- button "Inspect"
|
||||
- 'button "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."':
|
||||
- img
|
||||
- text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."
|
||||
- button:
|
||||
- img
|
||||
- text: Unmount temporary Plugin dyn-1
|
||||
- text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."
|
||||
- button "Unmount temporary Plugin dyn-1":
|
||||
- img
|
||||
- img
|
||||
- text: Unmount temporary Plugin dyn-1
|
||||
- button "Think All three calls succeeded. I should now reply exactly \"CORDIS_UI_DONE\" and stop.":
|
||||
- img
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 4 steps Tool call {{duration}} Context 13% of 128K Cache hit 77% Input 66.5K tok · Output 312 tok
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
# AppFrame drag handles
|
||||
|
||||
## sidebar
|
||||
|
||||
- hit strip present: true
|
||||
- cursor: col-resize
|
||||
- pill generated: false
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1784973850103,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo WEB_E2E_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1784973850105,"data":{"title":"Use the bash tool to","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1784973850164,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1784973850165,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1784973850165,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1784973850888,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1784973850889,"data":{"turn":1,"step":1,"index":0,"dt":[199,1,0,0,0,18,1,0,0,0,0,27,0,1,0,0],"texts":["The"," user"," wants"," me"," to"," run"," a"," simple"," bash"," command"," and"," reply"," with"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":23,"time":1784973851217,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/chunk","seq":52,"time":1784973851493,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_BYXlxjFaalMg95YVqEeF2495","name":"bash","arguments":"{\"command\": \"echo WEB_E2E_OK\", \"description\": \"Echo the test string\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":53,"time":1784973851493,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":122,"outputTokens":85,"cacheReadTokens":7680,"reasoningTokens":17}}}}
|
||||
{"type":"assistant/chunk","seq":54,"time":1784973851493,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":55,"time":1784973851498,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and reply with \"DONE\"."},{"type":"tool-call","id":"call_00_BYXlxjFaalMg95YVqEeF2495","name":"bash","arguments":"{\"command\": \"echo WEB_E2E_OK\", \"description\": \"Echo the test string\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":122,"outputTokens":85,"cacheReadTokens":7680,"reasoningTokens":17}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":55,"time":1784973851498,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and reply with \"DONE\"."},{"type":"tool-call","id":"call_00_BYXlxjFaalMg95YVqEeF2495","name":"bash","arguments":"{\"command\": \"echo WEB_E2E_OK\", \"description\": \"Echo the test string\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":122,"outputTokens":85,"cacheReadTokens":7680,"reasoningTokens":17}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":56,"time":1784973851499,"data":{"turn":1,"step":1,"callId":"call_00_BYXlxjFaalMg95YVqEeF2495","name":"bash","arguments":"{\"command\": \"echo WEB_E2E_OK\", \"description\": \"Echo the test string\"}"}}
|
||||
{"type":"tool/result","seq":57,"time":1784973851515,"data":{"turn":1,"step":1,"callId":"call_00_BYXlxjFaalMg95YVqEeF2495","content":[{"type":"text","text":"WEB_E2E_OK\n"}],"isError":false},"sourceEventSeqs":[56],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":58,"time":1784973851517,"data":{"turn":1,"step":1}}
|
||||
@@ -26,6 +26,6 @@
|
||||
{"type":"assistant/chunk","seq":88,"time":1784973852460,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":89,"time":1784973852460,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":97,"outputTokens":26,"cacheReadTokens":7808,"reasoningTokens":23}}}}
|
||||
{"type":"assistant/chunk","seq":90,"time":1784973852460,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":91,"time":1784973852461,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":26,"cacheReadTokens":7808,"reasoningTokens":23}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":91,"time":1784973852461,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":26,"cacheReadTokens":7808,"reasoningTokens":23}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":92,"time":1784973852461,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":93,"time":1784973852462,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
You are an AI agent powered by the DeepSeek Harness SDK.
|
||||
|
||||
Your own source code is the checkout at {{sourceRoot}}; you can read it there to learn how dsh works and how to extend it.
|
||||
The DeepSeek Harness implementation checkout is at {{sourceRoot}}. The checkout location and current working directory are separate values and may differ; never infer the working directory from this path. Use pwd to determine the current working directory. Use this checkout only to inspect or extend DSH itself.
|
||||
|
||||
You are interacting with the user through the DeepSeek Harness Web GUI. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context.
|
||||
|
||||
|
||||
@@ -1,28 +1,41 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use the bash tool to" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Use the bash tool to" [level=1]
|
||||
- tablist:
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- 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".
|
||||
- text: Echo the test string
|
||||
- button "Bash Echo the test string":
|
||||
- img
|
||||
- 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\".":
|
||||
- img
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 99% Input 15.7K tok · Output 111 tok
|
||||
|
||||
8
apps/web/tests/snapshots/goal-bar/active.expected.md
Normal file
8
apps/web/tests/snapshots/goal-bar/active.expected.md
Normal file
@@ -0,0 +1,8 @@
|
||||
- img
|
||||
- text: Ongoing Goal guard rapid clear clicks
|
||||
- button "Pause goal":
|
||||
- img
|
||||
- button "Edit goal":
|
||||
- img
|
||||
- button "Clear goal":
|
||||
- img
|
||||
@@ -0,0 +1,7 @@
|
||||
- listbox "Trigger suggestions":
|
||||
- text: Commands
|
||||
- option "compact Compact older conversation history" [selected]
|
||||
- option "goal set or view the goal for a long-running task"
|
||||
- option "permission Switch the permission preset (sandbox mode + approval policy)"
|
||||
- option "plan Enter or leave plan mode"
|
||||
- option "model Select the model for this conversation"
|
||||
@@ -1,3 +1,4 @@
|
||||
- button "New session"
|
||||
- button "Collapse sidebar":
|
||||
- img
|
||||
- button "New session":
|
||||
@@ -6,7 +7,7 @@
|
||||
- text: Workspaces
|
||||
- button "Group by":
|
||||
- img
|
||||
- button "Create workspace":
|
||||
- button "Add workspace":
|
||||
- img
|
||||
- button "Search sessions":
|
||||
- img
|
||||
@@ -15,25 +16,23 @@
|
||||
- treeitem "workspace 1 session" [expanded]:
|
||||
- img
|
||||
- text: workspace 1 session
|
||||
- treeitem "New Session now" [selected]
|
||||
- button "设置":
|
||||
- treeitem "New Session" [selected]
|
||||
- button "Settings":
|
||||
- img
|
||||
- text: 设置
|
||||
- text: Settings
|
||||
- text: Let's start building
|
||||
- button "Choose workspace":
|
||||
- img
|
||||
- text: workspace
|
||||
- img
|
||||
- textbox "Describe what you want to build"
|
||||
- button "Add attachment":
|
||||
- button "Commands":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 详情
|
||||
- button "关闭详情"
|
||||
- text: 点击消息流中的工具行查看详情
|
||||
- text: Details
|
||||
- button "Close details"
|
||||
- text: Click a tool row in the message flow to view its details
|
||||
|
||||
@@ -0,0 +1,39 @@
|
||||
- button "New session"
|
||||
- button "Collapse sidebar":
|
||||
- img
|
||||
- button "New session":
|
||||
- img
|
||||
- text: New Session
|
||||
- text: Workspaces
|
||||
- button "Group by":
|
||||
- img
|
||||
- button "Add workspace":
|
||||
- img
|
||||
- button "Search sessions":
|
||||
- img
|
||||
- textbox "Search name, keywords..."
|
||||
- tree "Sessions":
|
||||
- treeitem "workspace 1 session" [expanded]:
|
||||
- img
|
||||
- text: workspace 1 session
|
||||
- treeitem "New Session" [selected]
|
||||
- button "Settings":
|
||||
- img
|
||||
- text: Settings
|
||||
- text: Let's start building
|
||||
- button "Choose workspace":
|
||||
- img
|
||||
- text: workspace
|
||||
- img
|
||||
- textbox "Describe what you want to build"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Plan mode on, press to turn off": Plan
|
||||
- button "Select model, current deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: Details
|
||||
- button "Close details"
|
||||
- text: Click a tool row in the message flow to view its details
|
||||
@@ -1,24 +1,33 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Reply with the single word" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Reply with the single word" [level=1]
|
||||
- tablist:
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- button "Think The user wants me to reply with a single word. Let me comply.":
|
||||
- img
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 21 tok
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1785015039292,"data":{"content":[{"type":"text","text":"Reply with the single word LIGHTHOUSE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785015039294,"data":{"title":"Reply with the single word","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785015039362,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785015039363,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1785015039363,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785015039930,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785015039930,"data":{"turn":1,"step":1,"index":0,"dt":[162,28,1,0,0,46,1,0,0,0,11,0,0,30],"texts":["The"," user"," wants"," me"," to"," reply"," with"," a"," single"," word","."," Let"," me"," comply","."]}}
|
||||
{"type":"assistant/chunk","seq":21,"time":1785015040209,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
@@ -12,6 +12,6 @@
|
||||
{"type":"assistant/chunk","seq":28,"time":1785015040242,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"LIGHTHOUSE"}}}}
|
||||
{"type":"assistant/chunk","seq":29,"time":1785015040242,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":109,"outputTokens":21,"cacheReadTokens":7680,"reasoningTokens":15}}}}
|
||||
{"type":"assistant/chunk","seq":30,"time":1785015040242,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":31,"time":1785015040244,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with a single word. Let me comply."},{"type":"text","text":"LIGHTHOUSE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":109,"outputTokens":21,"cacheReadTokens":7680,"reasoningTokens":15}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":31,"time":1785015040244,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with a single word. Let me comply."},{"type":"text","text":"LIGHTHOUSE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":109,"outputTokens":21,"cacheReadTokens":7680,"reasoningTokens":15}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":32,"time":1785015040246,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":33,"time":1785015040247,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -1,21 +1,30 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Reply with a one-sentence description" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- tab "Waterfall"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop.
|
||||
- paragraph: partial
|
||||
- text: 已停止 0 tokens · 1 turns · 1 steps
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- paragraph: partial
|
||||
- text: Stopped
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- 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
|
||||
|
||||
@@ -1,19 +1,25 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Reply with a one-sentence description" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- tab "Waterfall"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop.
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- status:
|
||||
- text: This turn failedAPI key is invalid
|
||||
- code: AUTH
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
- banner:
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- paragraph: partial
|
||||
- status: Deep diving...
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Stop generating"
|
||||
@@ -1,24 +1,35 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Reply with a one-sentence description" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- group:
|
||||
- status: Retried model request (1/2) · {{duration}}
|
||||
- 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
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 79 tok
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1784998084454,"data":{"content":[{"type":"text","text":"Reply with a one-sentence description of event sourcing, then stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1784998084457,"data":{"title":"Reply with a one-sentence description","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1784998084519,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1784998084520,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1784998084520,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1784998084900,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1784998084900,"data":{"turn":1,"step":1,"index":0,"dt":[153,3,0,29,1,0,0,28,0,1,0,0,0,28,0,0,0,29,1,0,29,0,0,29,0,0,36,0,21,29],"texts":["The"," user"," is"," asking"," for"," a"," one","-s","entence"," description"," of"," event"," sourcing","."," This"," is"," a"," straightforward"," knowledge"," question"," that"," doesn","'t"," require"," any"," skill"," loading"," or"," tool"," calls","."]}}
|
||||
{"type":"assistant/chunk","seq":37,"time":1784998085318,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
@@ -12,6 +12,6 @@
|
||||
{"type":"assistant/chunk","seq":86,"time":1784998085814,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"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."}}}}
|
||||
{"type":"assistant/chunk","seq":87,"time":1784998085814,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":110,"outputTokens":79,"cacheReadTokens":7680,"reasoningTokens":31}}}}
|
||||
{"type":"assistant/chunk","seq":88,"time":1784998085814,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":89,"time":1784998085818,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"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."},{"type":"text","text":"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."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":110,"outputTokens":79,"cacheReadTokens":7680,"reasoningTokens":31}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":89,"time":1784998085818,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"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."},{"type":"text","text":"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."}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":110,"outputTokens":79,"cacheReadTokens":7680,"reasoningTokens":31}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":90,"time":1784998085820,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":91,"time":1784998085821,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -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"
|
||||
44
apps/web/tests/snapshots/message-actions/ui.expected.md
Normal file
44
apps/web/tests/snapshots/message-actions/ui.expected.md
Normal file
@@ -0,0 +1,44 @@
|
||||
- banner:
|
||||
- heading "Use the read tool twice" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- 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. 7/25 {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- tooltip "Copy"
|
||||
- button "Branch into a new conversation":
|
||||
- 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 "Read a.txt":
|
||||
- img
|
||||
- img
|
||||
- text: Read
|
||||
- button "a.txt"
|
||||
- button "Read b.txt":
|
||||
- img
|
||||
- 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
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: 7/25 {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- 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
|
||||
@@ -0,0 +1,20 @@
|
||||
- dialog "设置":
|
||||
- navigation:
|
||||
- text: 设置
|
||||
- button "通用设置":
|
||||
- img
|
||||
- text: 通用设置
|
||||
- button "模型":
|
||||
- img
|
||||
- text: 模型
|
||||
- button "关闭":
|
||||
- img
|
||||
- text: 关闭
|
||||
- heading "模型" [level=2]
|
||||
- paragraph: 填入各提供方的 API 密钥即可使用其模型。
|
||||
- list:
|
||||
- listitem:
|
||||
- text: minimax-cn
|
||||
- button "编辑"
|
||||
- button "删除"
|
||||
- button "+ 添加提供方"
|
||||
@@ -0,0 +1,7 @@
|
||||
- dialog "删除模型提供方？":
|
||||
- heading "删除模型提供方？" [level=2]
|
||||
- button "关闭":
|
||||
- img
|
||||
- paragraph: 删除此模型提供方会移除其配置。在重新添加前，你将无法继续使用其模型。
|
||||
- button "取消"
|
||||
- button "删除提供方"
|
||||
60
apps/web/tests/snapshots/models-settings/empty.expected.md
Normal file
60
apps/web/tests/snapshots/models-settings/empty.expected.md
Normal file
@@ -0,0 +1,60 @@
|
||||
- dialog "设置":
|
||||
- navigation:
|
||||
- text: 设置
|
||||
- button "通用设置":
|
||||
- img
|
||||
- text: 通用设置
|
||||
- button "模型":
|
||||
- img
|
||||
- text: 模型
|
||||
- button "关闭":
|
||||
- img
|
||||
- text: 关闭
|
||||
- heading "模型" [level=2]
|
||||
- paragraph: 填入各提供方的 API 密钥即可使用其模型。
|
||||
- list
|
||||
- text: 提供方
|
||||
- combobox "提供方":
|
||||
- option "amazon-bedrock"
|
||||
- option "ant-ling"
|
||||
- option "anthropic"
|
||||
- option "azure-openai-responses"
|
||||
- option "cerebras"
|
||||
- option "cloudflare-ai-gateway"
|
||||
- option "cloudflare-workers-ai"
|
||||
- option "deepseek"
|
||||
- option "fireworks"
|
||||
- option "github-copilot"
|
||||
- option "google"
|
||||
- option "google-vertex"
|
||||
- option "groq"
|
||||
- option "huggingface"
|
||||
- option "kimi-coding"
|
||||
- option "minimax"
|
||||
- option "minimax-cn" [selected]
|
||||
- option "mistral"
|
||||
- option "moonshotai"
|
||||
- option "moonshotai-cn"
|
||||
- option "nvidia"
|
||||
- option "openai"
|
||||
- option "openai-codex"
|
||||
- option "opencode"
|
||||
- option "opencode-go"
|
||||
- option "openrouter"
|
||||
- option "qwen-token-plan"
|
||||
- option "qwen-token-plan-cn"
|
||||
- option "together"
|
||||
- option "vercel-ai-gateway"
|
||||
- option "xai"
|
||||
- option "xiaomi"
|
||||
- option "xiaomi-token-plan-ams"
|
||||
- option "xiaomi-token-plan-cn"
|
||||
- option "xiaomi-token-plan-sgp"
|
||||
- option "zai"
|
||||
- option "zai-coding-cn"
|
||||
- text: API 密钥
|
||||
- textbox "API 密钥":
|
||||
- /placeholder: 输入 API 密钥
|
||||
- group: 自定义设置
|
||||
- button "取消"
|
||||
- button "保存"
|
||||
@@ -1,5 +0,0 @@
|
||||
- text: bash
|
||||
- button "关闭详情"
|
||||
- text: Input
|
||||
- code: "{ \"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\" }"
|
||||
- text: Output NAVIGATION_OK
|
||||
@@ -0,0 +1,2 @@
|
||||
- tree "Search results":
|
||||
- 'treeitem "{{workspace}} {{workspace}} ## Navigation Summary - alpha nav - beta nav ``` echo WATERFALL ```"'
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1785011380490,"data":{"content":[{"type":"text","text":"NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785011380492,"data":{"title":"NavScenario: first run bash to","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785011380549,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785011380550,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1785011380550,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785011380917,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785011380917,"data":{"turn":1,"step":1,"index":0,"dt":[110,25,1,0,0,25,1,0,26,0,1,0,27,1,0,0,0,26,1,0,0,26,0,0,0,0,1,25,0,0,25,0,1,0,0,0,26,1,0,25,0,0,27,1,0,0,0,0,25,28,0,1,0,0,0,27,0,0,0,25,1,24,1,0,25],"texts":["The"," user"," wants"," me"," to"," follow"," a"," specific"," navigation"," scenario","."," Let"," me",":\n\n","1","."," Run"," bash"," to"," print"," \"","NA","V","IG","ATION","_OK","\"\n","2","."," Read"," nav","-a",".md"," and"," nav","-b",".md"," in"," two"," read"," calls"," in"," ONE"," message","\n","3","."," Reply"," with"," \"","FIR","ST","_D","ONE","\"\n\n","Let"," me"," start"," with"," the"," bash"," command"," and"," the"," reads","."]}}
|
||||
{"type":"assistant/chunk","seq":72,"time":1785011381556,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -18,7 +18,7 @@
|
||||
{"type":"assistant/chunk","seq":130,"time":1785011382087,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":3,"block":{"type":"tool-call","id":"call_02_k8Z6wGirxfnW96Iv8mkz9224","name":"read","arguments":"{\"file_path\": \"nav-b.md\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":131,"time":1785011382087,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":140,"outputTokens":197,"cacheReadTokens":7680,"reasoningTokens":66}}}}
|
||||
{"type":"assistant/chunk","seq":132,"time":1785011382087,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":133,"time":1785011382091,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to follow a specific navigation scenario. Let me:\n\n1. Run bash to print \"NAVIGATION_OK\"\n2. Read nav-a.md and nav-b.md in two read calls in ONE message\n3. Reply with \"FIRST_DONE\"\n\nLet me start with the bash command and the reads."},{"type":"tool-call","id":"call_00_kFKHaEXcTYEex0iDZw0C2432","name":"bash","arguments":"{\"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\"}"},{"type":"tool-call","id":"call_01_tK4hIIRVTMgAvdzs7m9j6212","name":"read","arguments":"{\"file_path\": \"nav-a.md\"}"},{"type":"tool-call","id":"call_02_k8Z6wGirxfnW96Iv8mkz9224","name":"read","arguments":"{\"file_path\": \"nav-b.md\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":140,"outputTokens":197,"cacheReadTokens":7680,"reasoningTokens":66}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":133,"time":1785011382091,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to follow a specific navigation scenario. Let me:\n\n1. Run bash to print \"NAVIGATION_OK\"\n2. Read nav-a.md and nav-b.md in two read calls in ONE message\n3. Reply with \"FIRST_DONE\"\n\nLet me start with the bash command and the reads."},{"type":"tool-call","id":"call_00_kFKHaEXcTYEex0iDZw0C2432","name":"bash","arguments":"{\"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\"}"},{"type":"tool-call","id":"call_01_tK4hIIRVTMgAvdzs7m9j6212","name":"read","arguments":"{\"file_path\": \"nav-a.md\"}"},{"type":"tool-call","id":"call_02_k8Z6wGirxfnW96Iv8mkz9224","name":"read","arguments":"{\"file_path\": \"nav-b.md\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":140,"outputTokens":197,"cacheReadTokens":7680,"reasoningTokens":66}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":134,"time":1785011382092,"data":{"turn":1,"step":1,"callId":"call_00_kFKHaEXcTYEex0iDZw0C2432","name":"bash","arguments":"{\"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\"}"}}
|
||||
{"type":"tool/result","seq":135,"time":1785011382105,"data":{"turn":1,"step":1,"callId":"call_00_kFKHaEXcTYEex0iDZw0C2432","content":[{"type":"text","text":"NAVIGATION_OK\n"}],"isError":false},"sourceEventSeqs":[134],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":136,"time":1785011382105,"data":{"turn":1,"step":1,"callId":"call_01_tK4hIIRVTMgAvdzs7m9j6212","name":"read","arguments":"{\"file_path\": \"nav-a.md\"}"}}
|
||||
@@ -35,7 +35,7 @@
|
||||
{"type":"assistant/chunk","seq":200,"time":1785011383090,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST_DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":201,"time":1785011383090,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":349,"outputTokens":56,"cacheReadTokens":7808,"reasoningTokens":51}}}}
|
||||
{"type":"assistant/chunk","seq":202,"time":1785011383090,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":203,"time":1785011383091,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"All three calls succeeded:\n1. bash printed \"NAVIGATION_OK\"\n2. nav-a.md contains \"# alpha nav\"\n3. nav-b.md contains \"# beta nav\"\n\nNow I need to reply with the single word \"FIRST_DONE\"."},{"type":"text","text":"FIRST_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":349,"outputTokens":56,"cacheReadTokens":7808,"reasoningTokens":51}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":203,"time":1785011383091,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"All three calls succeeded:\n1. bash printed \"NAVIGATION_OK\"\n2. nav-a.md contains \"# alpha nav\"\n3. nav-b.md contains \"# beta nav\"\n\nNow I need to reply with the single word \"FIRST_DONE\"."},{"type":"text","text":"FIRST_DONE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":349,"outputTokens":56,"cacheReadTokens":7808,"reasoningTokens":51}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":204,"time":1785011383091,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":205,"time":1785011383092,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
{"type":"turn/start","seq":206,"time":1785011383106,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user","rpcId":"{{rpcId}}"}}}}
|
||||
@@ -49,6 +49,6 @@
|
||||
{"type":"assistant/chunk","seq":247,"time":1785011383903,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"## Navigation Summary\n\n- alpha nav\n- beta nav\n\n```\necho WATERFALL\n```"}}}}
|
||||
{"type":"assistant/chunk","seq":248,"time":1785011383903,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":141,"outputTokens":36,"cacheReadTokens":8064,"reasoningTokens":16}}}}
|
||||
{"type":"assistant/chunk","seq":249,"time":1785011383903,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":250,"time":1785011383904,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with a specific format. Let me do that."},{"type":"text","text":"## Navigation Summary\n\n- alpha nav\n- beta nav\n\n```\necho WATERFALL\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":141,"outputTokens":36,"cacheReadTokens":8064,"reasoningTokens":16}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":250,"time":1785011383904,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with a specific format. Let me do that."},{"type":"text","text":"## Navigation Summary\n\n- alpha nav\n- beta nav\n\n```\necho WATERFALL\n```"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":141,"outputTokens":36,"cacheReadTokens":8064,"reasoningTokens":16}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":251,"time":1785011383904,"data":{"turn":2,"step":1}}
|
||||
{"type":"turn/end","seq":252,"time":1785011383904,"data":{"turn":2,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
- text: Done {{workspace}} echo NAVIGATION_OK
|
||||
- button "Copy"
|
||||
- text: NAVIGATION_OK
|
||||
@@ -1 +1,53 @@
|
||||
- text: "Turn 1 Message {{duration}} #1 User NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop. +{{duration}} Step 1 {{duration}} bash read×2 #2 Tool bash · {\"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\"} +{{duration}} #3 Tool read · {\"file_path\": \"nav-a.md\"} +{{duration}} #4 Tool read · {\"file_path\": \"nav-b.md\"} +{{duration}} Step 2 {{duration}} #5 Message FIRST_DONE 349 56 51 +{{duration}} Turn 2 Message {{duration}} #6 User Reply in markdown with: a level-2 heading \"Navigation Summary\", a bulleted list of exactly two items, and a fenced code block containing echo WATERFALL. Then stop. +{{duration}} Step 1 {{duration}} #7 Message ## Navigation Summary - alpha nav - beta nav ``` echo WATERFALL ``` 141 36 16 +{{duration}}"
|
||||
- toolbar "Trajectory toolbar":
|
||||
- button "Use actual duration": Duration
|
||||
- button "Collapse turns": Turns
|
||||
- button "Collapse calls": Calls
|
||||
- img
|
||||
- searchbox "Search trajectory"
|
||||
- region "Trajectory timeline"
|
||||
- table:
|
||||
- rowgroup:
|
||||
- row "SYSTEM, Initial System Prompt":
|
||||
- cell "SYSTEM"
|
||||
- cell "Initial System Prompt"
|
||||
- 'row "USER, NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop."':
|
||||
- cell "Turn 1 USER": USER
|
||||
- 'cell "NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop."'
|
||||
- 'row "Request 1, ASSISTANT, The user wants me to follow a specific navigation scenario. Let me: Run bash to print \"NAVIGATION_OK\" Read nav-a.md and nav-b.md in two read calls in ONE message Reply with \"FIRST_DONE\" Let me start with the bash command and the reads."':
|
||||
- 'cell "Request #1 ASSISTANT"':
|
||||
- 'button "Request #1"'
|
||||
- text: ASSISTANT
|
||||
- 'cell "The user wants me to follow a specific navigation scenario. Let me: Run bash to print \"NAVIGATION_OK\" Read nav-a.md and nav-b.md in two read calls in ONE message Reply with \"FIRST_DONE\" Let me start with the bash command and the reads."'
|
||||
- 'row "TOOL, bash {\"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\"}" [selected]':
|
||||
- cell "TOOL"
|
||||
- 'cell "bash{\"command\": \"echo NAVIGATION_OK\", \"description\": \"Print NAVIGATION_OK\"} → NAVIGATION_OK"'
|
||||
- 'row "TOOL, read {\"file_path\": \"nav-a.md\"}"':
|
||||
- cell "TOOL"
|
||||
- 'cell "read{\"file_path\": \"nav-a.md\"} → <path>{{cwd}}/nav-a.md</path> <type>file</type> <content> 1: # alpha nav (End of file - total 1 lines) </content>"'
|
||||
- 'row "TOOL, read {\"file_path\": \"nav-b.md\"}"':
|
||||
- cell "TOOL"
|
||||
- 'cell "read{\"file_path\": \"nav-b.md\"} → <path>{{cwd}}/nav-b.md</path> <type>file</type> <content> 1: # beta nav (End of file - total 1 lines) </content>"'
|
||||
- row "Request 2, ASSISTANT, FIRST_DONE":
|
||||
- 'cell "Request #2 ASSISTANT"':
|
||||
- 'button "Request #2"'
|
||||
- text: ASSISTANT
|
||||
- cell "FIRST_DONE"
|
||||
- 'row "USER, Reply in markdown with: a level-2 heading \"Navigation Summary\", a bulleted list of exactly two items, and a fenced code block containing echo WATERFALL. Then stop."':
|
||||
- cell "Turn 2 USER": USER
|
||||
- 'cell "Reply in markdown with: a level-2 heading \"Navigation Summary\", a bulleted list of exactly two items, and a fenced code block containing echo WATERFALL. Then stop."'
|
||||
- row "Request 3, ASSISTANT, Navigation Summary alpha nav beta nav echo WATERFALL":
|
||||
- 'cell "Request #3 ASSISTANT"':
|
||||
- 'button "Request #3"'
|
||||
- text: ASSISTANT
|
||||
- cell "Navigation Summary alpha nav beta nav echo WATERFALL"
|
||||
- complementary "Event details":
|
||||
- separator "Resize event details"
|
||||
- text: TOOL Turn 1 · Step 1
|
||||
- button "Close details"
|
||||
- tablist "Event details":
|
||||
- tab "Summary"
|
||||
- tab "Payload"
|
||||
- tab "Result" [selected]
|
||||
- tab "Schema"
|
||||
- tab "Timing"
|
||||
- tabpanel "Result": NAVIGATION_OK
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
- text: 3 turns · 3 steps · 3 tool calls turn 0 turn 1 turn 2
|
||||
@@ -0,0 +1,5 @@
|
||||
- region "添加一个 API Key 开始使用":
|
||||
- heading "添加一个 API Key 开始使用" [level=2]
|
||||
- paragraph: 配置 DeepSeek 官方模型，即可开始使用。
|
||||
- button "稍后配置"
|
||||
- button "前往配置"
|
||||
@@ -0,0 +1,9 @@
|
||||
- region "内测声明":
|
||||
- heading "内测声明" [level=2]
|
||||
- paragraph: 感谢您愿意拨冗试用 DeepSeek Harness。当前版本仍处于内部测试阶段，功能仍待完善，体验难免有些粗糙。
|
||||
- blockquote: “如切如磋，如琢如磨。” 产品的成长，离不开一次次真实的碰撞与坦诚的反馈。您在真实使用中发现的问题，也可能促使我们重新审视，甚至推翻已有的设计。
|
||||
- paragraph:
|
||||
- text: 为了帮助我们更准确地还原您真实使用中的问题，内测版本默认会上传所有 Session Log；如需关闭，可以设置环境变量 DSH_TELEMETRY_DISABLED=1。另外，
|
||||
- strong: 如果您有任何反馈与建议，请在企业微信群中留言告诉我们
|
||||
- text: 。每一条反馈，都会帮助我们把它打磨得更好。
|
||||
- button "继续"
|
||||
124
apps/web/tests/snapshots/permission-policy-context/session.jsonl
Normal file
124
apps/web/tests/snapshots/permission-policy-context/session.jsonl
Normal file
File diff suppressed because one or more lines are too long
46
apps/web/tests/snapshots/plan-review/approved.expected.md
Normal file
46
apps/web/tests/snapshots/plan-review/approved.expected.md
Normal file
@@ -0,0 +1,46 @@
|
||||
- banner:
|
||||
- 'heading "Plan a small change: add" [level=1]'
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- img
|
||||
- text: "plan 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- '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 "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"':
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Context 4% of 128K Cache hit 51% Input 10.2K tok · Output 346 tok
|
||||
44
apps/web/tests/snapshots/plan-review/review.expected.md
Normal file
44
apps/web/tests/snapshots/plan-review/review.expected.md
Normal file
@@ -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"
|
||||
39
apps/web/tests/snapshots/plan-review/session.jsonl
Normal file
39
apps/web/tests/snapshots/plan-review/session.jsonl
Normal file
@@ -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"}}}
|
||||
@@ -1,36 +1,41 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use the ask_user_question tool to" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Use the ask_user_question tool to" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- tab "Waterfall"
|
||||
- text: "Use the ask_user_question tool to ask me exactly one question with id \"color\", question \"Which color do you prefer?\", header \"Pick one\", and two options: label \"Blue\" with description \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\", and label \"Green\" with description \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\" After I answer, reply with the single word DONE and stop."
|
||||
- button "复制":
|
||||
- text: "Use the ask_user_question tool to ask me exactly one question with id \"color\", question \"Which color do you prefer?\", header \"Pick one\", and two options: label \"Blue\" with description \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\", and label \"Green\" with description \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\" After I answer, reply with the single word DONE and stop. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "在新对话中分支":
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "编辑":
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- button "Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.":
|
||||
- img
|
||||
- text: Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.
|
||||
- button:
|
||||
- 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: Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.
|
||||
- button "Ask question 1/1 answered":
|
||||
- img
|
||||
- img
|
||||
- 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
|
||||
- text: Think The user answered "Blue". I should now reply with the single word DONE and stop.
|
||||
- paragraph: DONE
|
||||
- text: cache hit 95% · 8,769 tokens · 1 turns · 2 steps
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Context 3% of 128K Cache hit 95% Input 8.6K tok · Output 180 tok
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1785150167925,"data":{"content":[{"type":"text","text":"Use the ask_user_question tool to ask me exactly one question with id \"color\", question \"Which color do you prefer?\", header \"Pick one\", and two options: label \"Blue\" with description \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\", and label \"Green\" with description \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\" After I answer, reply with the single word DONE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785150167927,"data":{"title":"Use the ask_user_question tool to","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785150167928,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785150167929,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1785150167929,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785150168452,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785150168452,"data":{"turn":1,"step":1,"index":0,"dt":[87,26,1,0,0,0,38,0,0,0,0,1,12,27,0,27,0,0,1,25,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," ask","_user","_","question"," tool"," with"," specific"," parameters","."," Let"," me"," do"," exactly"," that","."]}}
|
||||
{"type":"assistant/chunk","seq":28,"time":1785150168775,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/chunk","seq":128,"time":1785150169308,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Cijldc88LYmVPCXYUsRq1617","name":"ask_user_question","arguments":"{\"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.\"}]}]}"}}}}
|
||||
{"type":"assistant/chunk","seq":129,"time":1785150169308,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":113,"outputTokens":158,"cacheReadTokens":4096,"reasoningTokens":22}}}}
|
||||
{"type":"assistant/chunk","seq":130,"time":1785150169308,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":131,"time":1785150169311,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that."},{"type":"tool-call","id":"call_00_Cijldc88LYmVPCXYUsRq1617","name":"ask_user_question","arguments":"{\"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.\"}]}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":113,"outputTokens":158,"cacheReadTokens":4096,"reasoningTokens":22}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":131,"time":1785150169311,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that."},{"type":"tool-call","id":"call_00_Cijldc88LYmVPCXYUsRq1617","name":"ask_user_question","arguments":"{\"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.\"}]}]}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":113,"outputTokens":158,"cacheReadTokens":4096,"reasoningTokens":22}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":132,"time":1785150169312,"data":{"turn":1,"step":1,"callId":"call_00_Cijldc88LYmVPCXYUsRq1617","name":"ask_user_question","arguments":"{\"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.\"}]}]}"}}
|
||||
{"type":"tool/result","seq":133,"time":1785150169787,"data":{"turn":1,"step":1,"callId":"call_00_Cijldc88LYmVPCXYUsRq1617","content":[{"type":"text","text":"{\"answers\":[{\"id\":\"color\",\"selected\":[\"Blue\"]}]}"}],"isError":false},"sourceEventSeqs":[132],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":134,"time":1785150169790,"data":{"turn":1,"step":1}}
|
||||
@@ -26,6 +26,6 @@
|
||||
{"type":"assistant/chunk","seq":160,"time":1785150170856,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":161,"time":1785150170856,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":284,"outputTokens":22,"cacheReadTokens":4096,"reasoningTokens":19}}}}
|
||||
{"type":"assistant/chunk","seq":162,"time":1785150170856,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":163,"time":1785150170857,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user answered \"Blue\". I should now reply with the single word DONE and stop."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":284,"outputTokens":22,"cacheReadTokens":4096,"reasoningTokens":19}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":163,"time":1785150170857,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user answered \"Blue\". I should now reply with the single word DONE and stop."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":284,"outputTokens":22,"cacheReadTokens":4096,"reasoningTokens":19}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":164,"time":1785150170858,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":165,"time":1785150170858,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -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]
|
||||
|
||||
25
apps/web/tests/snapshots/queue-actions/collapsed.expected.md
Normal file
25
apps/web/tests/snapshots/queue-actions/collapsed.expected.md
Normal file
@@ -0,0 +1,25 @@
|
||||
- banner:
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- paragraph: partial
|
||||
- status: Deep diving...
|
||||
- button "2 queued messages"
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Stop generating"
|
||||
38
apps/web/tests/snapshots/queue-actions/editing.expected.md
Normal file
38
apps/web/tests/snapshots/queue-actions/editing.expected.md
Normal file
@@ -0,0 +1,38 @@
|
||||
- banner:
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- paragraph: partial
|
||||
- status: Deep diving...
|
||||
- button "2 queued messages" [disabled] [expanded]
|
||||
- list:
|
||||
- listitem:
|
||||
- text: Queue item to remove
|
||||
- button "Edit queued message":
|
||||
- img
|
||||
- button "Remove queued message":
|
||||
- img
|
||||
- listitem:
|
||||
- textbox "Edit queued message": Edited queue item
|
||||
- button "Save queued message":
|
||||
- img
|
||||
- button "Cancel editing":
|
||||
- img
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Stop generating"
|
||||
43
apps/web/tests/snapshots/queue-actions/preserved.expected.md
Normal file
43
apps/web/tests/snapshots/queue-actions/preserved.expected.md
Normal file
@@ -0,0 +1,43 @@
|
||||
- banner:
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- paragraph: partial
|
||||
- text: Stopped
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}} Edited queue item {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- paragraph: partial
|
||||
- status: Deep diving...
|
||||
- list:
|
||||
- listitem:
|
||||
- text: Queue item preserved after stop
|
||||
- button "Edit queued message":
|
||||
- img
|
||||
- button "Remove queued message":
|
||||
- img
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Stop generating"
|
||||
- text: 1 turns · 1 steps Input 0 tok · Output 0 tok
|
||||
31
apps/web/tests/snapshots/queue-actions/ui.expected.md
Normal file
31
apps/web/tests/snapshots/queue-actions/ui.expected.md
Normal file
@@ -0,0 +1,31 @@
|
||||
- banner:
|
||||
- heading "Reply with a one-sentence description" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- paragraph: partial
|
||||
- status: Deep diving...
|
||||
- list:
|
||||
- listitem:
|
||||
- text: Edited queue item
|
||||
- button "Edit queued message":
|
||||
- img
|
||||
- button "Remove queued message":
|
||||
- img
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Stop generating"
|
||||
27
apps/web/tests/snapshots/search-card/grep-card.expected.txt
Normal file
27
apps/web/tests/snapshots/search-card/grep-card.expected.txt
Normal file
@@ -0,0 +1,27 @@
|
||||
kind=matches
|
||||
summary=显示 9 / 共 42 处匹配 · 3 个文件
|
||||
file=packages/client/ui-primitives/src/SearchBlock.tsx3
|
||||
file=packages/client/ui-conversation/src/client/toolviews/search-row.tsx4
|
||||
line=16: export const DEFAULT_SEARCH_MAX_LINES = 16
|
||||
line=138: export function SearchBlock(props: SearchBlockProps) {
|
||||
line=141: const [collapsed, setCollapsed] = useState<ReadonlySet<number>>(() => new Set())
|
||||
line=35: const search = searchCardModel(block)
|
||||
line=52: search={search}
|
||||
line=73: ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow)
|
||||
expand=… 其余 4 行
|
||||
recovery=Found 9 of 42 matches
|
||||
|
||||
packages/client/ui-primitives/src/SearchBlock.tsx
|
||||
Line 16: export const DEFAULT_SEARCH_MAX_LINES = 16
|
||||
Line 138: export function SearchBlock(props: SearchBlockProps) {
|
||||
Line 141: const [collapsed, setCollapsed] = useState<ReadonlySet<number>>(() => new Set())
|
||||
packages/client/ui-conversation/src/client/contract/search-card-model.ts
|
||||
Line 24: export const CHAT_SEARCH_MAX_LINES = 8
|
||||
Line 60: export function searchCardModel(block: ToolCallBlock): SearchCardModel | null {
|
||||
packages/client/ui-conversation/src/client/toolviews/search-row.tsx
|
||||
Line 33: export function SearchRow({ toolName, block, inspect, t }: SearchRowProps) {
|
||||
Line 35: const search = searchCardModel(block)
|
||||
Line 52: search={search}
|
||||
Line 73: ctx.slots.register({ name: 'conversation.chat.toolview', key: 'grep', locale: NS }, SearchRow)
|
||||
|
||||
(Full grep result stored at: fixture://spill/grep-66. Read it to see every match.)
|
||||
@@ -0,0 +1,52 @@
|
||||
- banner:
|
||||
- heading "Use the read tool twice" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- 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. 7/25 {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- 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 "Read a.txt":
|
||||
- img
|
||||
- img
|
||||
- text: Read
|
||||
- button "a.txt"
|
||||
- button "Read b.txt":
|
||||
- img
|
||||
- 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
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: 7/25 {{clock}}
|
||||
- button "Context compacted View compaction summary":
|
||||
- img
|
||||
- text: Context compacted View compaction summary
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- img
|
||||
- text: permission preset read-only
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Read Only"': Read Only
|
||||
- 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
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1784974100759,"data":{"content":[{"type":"text","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."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1784974100761,"data":{"title":"Use the read tool twice","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1784974100827,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1784974100828,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1784974100828,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1784974101296,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1784974101297,"data":{"turn":1,"step":1,"index":0,"dt":[125,30,0,1,0,0,30,1,0,0,0,0,30,1,0,0,30,0,0,0,0,1,30,1,0,0],"texts":["The"," user"," wants"," me"," to"," read"," a",".txt"," and"," b",".txt",","," then"," reply"," with"," \"","D","ONE","\"."," Let"," me"," do"," both"," reads"," in"," parallel","."]}}
|
||||
{"type":"assistant/chunk","seq":33,"time":1784974101666,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -15,7 +15,7 @@
|
||||
{"type":"assistant/chunk","seq":61,"time":1784974101974,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_01_Hw6AQjhf9gjxnOtppcGx0725","name":"read","arguments":"{\"file_path\": \"b.txt\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":62,"time":1784974101974,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":124,"outputTokens":103,"cacheReadTokens":7680,"reasoningTokens":27}}}}
|
||||
{"type":"assistant/chunk","seq":63,"time":1784974101974,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":64,"time":1784974101978,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel."},{"type":"tool-call","id":"call_00_OsndvlcKnCcUmae7QXal8633","name":"read","arguments":"{\"file_path\": \"a.txt\"}"},{"type":"tool-call","id":"call_01_Hw6AQjhf9gjxnOtppcGx0725","name":"read","arguments":"{\"file_path\": \"b.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":124,"outputTokens":103,"cacheReadTokens":7680,"reasoningTokens":27}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":64,"time":1784974101978,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel."},{"type":"tool-call","id":"call_00_OsndvlcKnCcUmae7QXal8633","name":"read","arguments":"{\"file_path\": \"a.txt\"}"},{"type":"tool-call","id":"call_01_Hw6AQjhf9gjxnOtppcGx0725","name":"read","arguments":"{\"file_path\": \"b.txt\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":124,"outputTokens":103,"cacheReadTokens":7680,"reasoningTokens":27}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":65,"time":1784974101979,"data":{"turn":1,"step":1,"callId":"call_00_OsndvlcKnCcUmae7QXal8633","name":"read","arguments":"{\"file_path\": \"a.txt\"}"}}
|
||||
{"type":"tool/call","seq":66,"time":1784974101981,"data":{"turn":1,"step":1,"callId":"call_01_Hw6AQjhf9gjxnOtppcGx0725","name":"read","arguments":"{\"file_path\": \"b.txt\"}"}}
|
||||
{"type":"tool/result","seq":67,"time":1784974101985,"data":{"turn":1,"step":1,"callId":"call_00_OsndvlcKnCcUmae7QXal8633","content":[{"type":"text","text":"<path>{{cwd}}/workspace/a.txt</path>\n<type>file</type>\n<content>\n1: alpha\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"}
|
||||
@@ -31,6 +31,6 @@
|
||||
{"type":"assistant/chunk","seq":105,"time":1784974102749,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":106,"time":1784974102750,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":215,"outputTokens":32,"cacheReadTokens":7808,"reasoningTokens":29}}}}
|
||||
{"type":"assistant/chunk","seq":107,"time":1784974102750,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":108,"time":1784974102750,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":215,"outputTokens":32,"cacheReadTokens":7808,"reasoningTokens":29}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":108,"time":1784974102750,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":215,"outputTokens":32,"cacheReadTokens":7808,"reasoningTokens":29}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":109,"time":1784974102751,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":110,"time":1784974102751,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -1,33 +1,50 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use the read tool twice" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Use the read tool twice" [level=1]
|
||||
- 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. 7/25 {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- 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 "Read a.txt":
|
||||
- img
|
||||
- text: Read a.txt
|
||||
- button:
|
||||
- img
|
||||
- text: Read b.txt
|
||||
- text: Read
|
||||
- button "a.txt"
|
||||
- button "Read b.txt":
|
||||
- img
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: 7/25 {{clock}}
|
||||
- button "Context compacted View compaction summary":
|
||||
- img
|
||||
- text: Context compacted View compaction summary
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- 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
|
||||
|
||||
@@ -1,12 +0,0 @@
|
||||
{
|
||||
"initial": {
|
||||
"sidebar": "Fixture 历史会话",
|
||||
"breadcrumb": "Fixture 历史会话",
|
||||
"documentTitle": "Fixture 历史会话 — DeepSeek Harness"
|
||||
},
|
||||
"revised": {
|
||||
"sidebar": "Fixture 修订标题",
|
||||
"breadcrumb": "Fixture 修订标题",
|
||||
"documentTitle": "Fixture 修订标题 — DeepSeek Harness"
|
||||
}
|
||||
}
|
||||
@@ -10,11 +10,11 @@
|
||||
- button "关闭":
|
||||
- img
|
||||
- text: 关闭
|
||||
- text: 权限 选择默认权限模式
|
||||
- button "Read only" [disabled]:
|
||||
- text: Read only
|
||||
- text: 权限 选择新会话的默认权限模式
|
||||
- button "Workspace Write":
|
||||
- text: Workspace Write
|
||||
- img
|
||||
- text: 工具调用 Schema mode Traditional function calling — invoke tools one at a time Code mode Chain multiple tools with code — multi-step orchestration 语言
|
||||
- text: 语言
|
||||
- button "中文":
|
||||
- text: 中文
|
||||
- img
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
# Sidebar session list scrollbar
|
||||
|
||||
## Light palette
|
||||
|
||||
- scrollbar-gutter: stable
|
||||
- ::-webkit-scrollbar width: 8px
|
||||
- ::-webkit-scrollbar-track background: rgba(0, 0, 0, 0)
|
||||
- scrollbar-width: auto
|
||||
- scrollbar-color: auto
|
||||
- ::-webkit-scrollbar-thumb:hover declarations: var(--dsh-scrollbar-thumb-hover)
|
||||
- --dsh-scrollbar-thumb: rgb(229, 229, 229)
|
||||
- --dsh-scrollbar-thumb-hover: rgb(212, 212, 212)
|
||||
- list overflows: true
|
||||
- reserved band: 8px
|
||||
- relative time covered by the bar: 0px
|
||||
- relative time ends inside the content area: true
|
||||
- content area ends before the border box: true
|
||||
|
||||
## Dark palette
|
||||
|
||||
- scrollbar-gutter: stable
|
||||
- ::-webkit-scrollbar width: 8px
|
||||
- ::-webkit-scrollbar-track background: rgba(0, 0, 0, 0)
|
||||
- scrollbar-width: auto
|
||||
- scrollbar-color: auto
|
||||
- ::-webkit-scrollbar-thumb:hover declarations: var(--dsh-scrollbar-thumb-hover)
|
||||
- --dsh-scrollbar-thumb: rgb(60, 60, 61)
|
||||
- --dsh-scrollbar-thumb-hover: rgb(84, 85, 87)
|
||||
- list overflows: true
|
||||
- reserved band: 8px
|
||||
- relative time covered by the bar: 0px
|
||||
- relative time ends inside the content area: true
|
||||
- content area ends before the border box: true
|
||||
@@ -0,0 +1,3 @@
|
||||
- listbox "Trigger suggestions":
|
||||
- text: Skills
|
||||
- option "policy-shared Available to both model and user invocation" [selected]
|
||||
@@ -1,39 +1,41 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use the ask_user_question tool to" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Use the ask_user_question tool to" [level=1]
|
||||
- tablist:
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- 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
|
||||
- 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: 请在原客户端处理（web 端作答后续里程碑提供） cache hit 98% · 7,946 tokens · 1 turns · 1 steps
|
||||
- text: Running
|
||||
- button "Ask question waiting":
|
||||
- img
|
||||
- img
|
||||
- text: Ask question waiting
|
||||
- status: Deep diving...
|
||||
- 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]
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
{"type":"user/message","seq":1,"time":1785004180030,"data":{"content":[{"type":"text","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."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785004180033,"data":{"title":"Use the ask_user_question tool to","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785004180105,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785004180106,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"request/header","seq":4,"time":1785004180106,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785004180696,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785004180697,"data":{"turn":1,"step":1,"index":0,"dt":[88,29,1,0,0,0,28,0,0,1,0,0,30,1,27,0,0,0,0,28,1,0,30,0,0,0,28,1],"texts":["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","."]}}
|
||||
{"type":"assistant/chunk","seq":35,"time":1785004181077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
@@ -12,7 +12,7 @@
|
||||
{"type":"assistant/chunk","seq":85,"time":1785004181401,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sAvjivLShvnWVk0sPQPV7661","name":"ask_user_question","arguments":"{\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}"}}}}
|
||||
{"type":"assistant/chunk","seq":86,"time":1785004181401,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":151,"outputTokens":115,"cacheReadTokens":7680,"reasoningTokens":29}}}}
|
||||
{"type":"assistant/chunk","seq":87,"time":1785004181402,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":88,"time":1785004181406,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"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."},{"type":"tool-call","id":"call_00_sAvjivLShvnWVk0sPQPV7661","name":"ask_user_question","arguments":"{\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":151,"outputTokens":115,"cacheReadTokens":7680,"reasoningTokens":29}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":88,"time":1785004181406,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"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."},{"type":"tool-call","id":"call_00_sAvjivLShvnWVk0sPQPV7661","name":"ask_user_question","arguments":"{\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":151,"outputTokens":115,"cacheReadTokens":7680,"reasoningTokens":29}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":89,"time":1785004181407,"data":{"turn":1,"step":1,"callId":"call_00_sAvjivLShvnWVk0sPQPV7661","name":"ask_user_question","arguments":"{\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}"}}
|
||||
{"type":"tool/result","seq":90,"time":1785004181867,"data":{"turn":1,"step":1,"callId":"call_00_sAvjivLShvnWVk0sPQPV7661","content":[{"type":"text","text":"{\"answers\":[{\"id\":\"checkpoint\",\"selected\":[\"Yes\"]}]}"}],"isError":false},"sourceEventSeqs":[89],"surfaceOp":"append"}
|
||||
{"type":"steering/message","seq":91,"time":1785004181867,"data":{"turn":1,"content":[{"type":"text","text":"Interjection: include the word BANANA in your final reply."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
@@ -26,6 +26,6 @@
|
||||
{"type":"assistant/chunk","seq":137,"time":1785004182893,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Great, let's move forward. BANANA!"}}}}
|
||||
{"type":"assistant/chunk","seq":138,"time":1785004182893,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":172,"outputTokens":41,"cacheReadTokens":7808,"reasoningTokens":29}}}}
|
||||
{"type":"assistant/chunk","seq":139,"time":1785004182893,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":140,"time":1785004182894,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user selected \"Yes\" and wants me to include the word \"BANANA\" in my final reply. Let me acknowledge their answer."},{"type":"text","text":"Great, let's move forward. BANANA!"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":172,"outputTokens":41,"cacheReadTokens":7808,"reasoningTokens":29}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":140,"time":1785004182894,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user selected \"Yes\" and wants me to include the word \"BANANA\" in my final reply. Let me acknowledge their answer."},{"type":"text","text":"Great, let's move forward. BANANA!"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":172,"outputTokens":41,"cacheReadTokens":7808,"reasoningTokens":29}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":141,"time":1785004182895,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":142,"time":1785004182895,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
|
||||
@@ -1,30 +1,42 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use the ask_user_question tool to" [disabled]
|
||||
- text: · 1 turns
|
||||
- heading "Use the ask_user_question tool to" [level=1]
|
||||
- tablist:
|
||||
- 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 "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- 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
|
||||
- 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:
|
||||
- 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: 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 "Ask question 1/1 answered":
|
||||
- img
|
||||
- img
|
||||
- text: Ask question 1/1 answered
|
||||
- text: "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
|
||||
- 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
|
||||
- textbox "Message the agent"
|
||||
- button "Add attachment":
|
||||
- button "Copy":
|
||||
- img
|
||||
- combobox "Access mode":
|
||||
- option "Read-only" [selected]
|
||||
- option "Read-write"
|
||||
- button "选择模型，当前 deepseek-v4-flash":
|
||||
- text: deepseek-v4-flash
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 98% Input 15.8K tok · Output 156 tok
|
||||
|
||||
12
apps/web/tests/snapshots/web-search-round/session.jsonl
Normal file
12
apps/web/tests/snapshots/web-search-round/session.jsonl
Normal file
@@ -0,0 +1,12 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785456000000,"cwd":"{{cwd}}"}
|
||||
{"type":"user/message","seq":0,"time":1785456000001,"data":{"content":[{"type":"text","text":"Use web_search to search exactly \"DeepSeek Harness snapshot search\". Then reply exactly SEARCH_DONE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"assistant/chunk","seq":1,"time":1785456000002,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1785456000003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_web_search","name":"web_search","argumentsDelta":"{\"query\":\"DeepSeek Harness snapshot search\"}"}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1785456000004,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_web_search","name":"web_search","arguments":"{\"query\":\"DeepSeek Harness snapshot search\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1785456000005,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785456000006,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1785456000007,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1785456000008,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"SEARCH_DONE"}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1785456000009,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SEARCH_DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1785456000010,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2}}}}
|
||||
{"type":"assistant/chunk","seq":10,"time":1785456000011,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
33
apps/web/tests/snapshots/web-search-round/ui.expected.md
Normal file
33
apps/web/tests/snapshots/web-search-round/ui.expected.md
Normal file
@@ -0,0 +1,33 @@
|
||||
- banner:
|
||||
- heading "Use web_search to search exactly" [level=1]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Use web_search to search exactly "DeepSeek Harness snapshot search". Then reply exactly SEARCH_DONE and stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
- text: Context injection
|
||||
- button "Search DeepSeek Harness snapshot search":
|
||||
- img
|
||||
- img
|
||||
- text: Search DeepSeek Harness snapshot search
|
||||
- paragraph: SEARCH_DONE
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Workspace Write"': Workspace Write
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Context 0% of 128K Cache hit 0% Input 22 tok · Output 7 tok
|
||||
@@ -0,0 +1,55 @@
|
||||
- dialog "Select Workspace Directory":
|
||||
- heading "Select Workspace Directory" [level=2]
|
||||
- navigation:
|
||||
- button "Home"
|
||||
- img
|
||||
- button "browse-golden"
|
||||
- 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":
|
||||
- img
|
||||
- text: alpha
|
||||
- img
|
||||
- listitem:
|
||||
- button "beta":
|
||||
- img
|
||||
- text: beta
|
||||
- img
|
||||
- button "New folder":
|
||||
- img
|
||||
- text: New folder
|
||||
- button "Show hidden files"
|
||||
- button "Cancel"
|
||||
- button "Open"
|
||||
Reference in New Issue
Block a user