Regenerate only native V3 Session/output oracles through the shipped headless and SDK profiles. These outputs retain system-message admission before users, bind request metadata before title fallback, and record real V3 delivery acknowledgments. Historical V0/V1/V2 replay inputs remain unchanged; pinned scenarios keep separate writer outputs. The upper headless/SDK refresh covered109 cases; the only initial failure used macOS system Python3.9 for the PTC Python scenario, which passed with the declared CPython3.14 PATH. No assertion or runtime behavior was changed to accommodate it.
21 lines
7.8 KiB
JSON
21 lines
7.8 KiB
JSON
{"type":"session","version":3,"id":"{{session:3}}","createdAt":1783951002000,"cwd":"{{cwd}}","parentSession":"{{session:1}}","isSeeded":false,"origin":"subagent","delegationDepth":1}
|
|
{"type":"sandbox/mode","data":{"mode":"danger-full-access","source":"delegation"}}
|
|
{"type":"approval/policy","data":{"policy":"never","source":"delegation"}}
|
|
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
|
|
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"You are one fresh worker in a foreground Ralph loop. You receive no parent conversation and no prior child session. Do not call the ralph tool: this round already is its worker.\n\nImmutable objective:\nProve two fresh Ralph rounds through the shipped headless app.\n\nRalph round: 2 of 2.\n\nThe shared workspace and its current working tree are the long-term memory and source of truth. Inspect them before acting, preserve existing work, perform concrete in-scope work, and verify what you change. Treat the previous report only as a bounded handoff; confirm it against the workspace.\n\nPrevious structured handoff:\n{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}\n\nReturn one report with exact normalized strings. Use status continue with at least one nextSteps entry while useful work remains; complete only with concrete evidence and no nextSteps; blocked only when no meaningful progress is possible without human input or an external-state change. blocker must be empty unless blocked."}],"source":{"kind":"user"},"role":"user","id":"{{message:12}}"}]}}
|
|
{"type":"turn/start","data":{"turn":1}}
|
|
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
|
|
{"type":"subagent/descriptor","data":{"version":3,"mode":"one-shot","provider":"spawn"}}
|
|
{"type":"step/start","data":{"turn":1,"step":1}}
|
|
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt"},"id":"{{message:13}}"}},"surfaceOp":"append"}
|
|
{"type":"user/message","data":{"content":[{"type":"text","text":"You are one fresh worker in a foreground Ralph loop. You receive no parent conversation and no prior child session. Do not call the ralph tool: this round already is its worker.\n\nImmutable objective:\nProve two fresh Ralph rounds through the shipped headless app.\n\nRalph round: 2 of 2.\n\nThe shared workspace and its current working tree are the long-term memory and source of truth. Inspect them before acting, preserve existing work, perform concrete in-scope work, and verify what you change. Treat the previous report only as a bounded handoff; confirm it against the workspace.\n\nPrevious structured handoff:\n{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}\n\nReturn one report with exact normalized strings. Use status continue with at least one nextSteps entry while useful work remains; complete only with concrete evidence and no nextSteps; blocked only when no meaningful progress is possible without human input or an external-state change. blocker must be empty unless blocked."}],"source":{"kind":"user"},"role":"user","id":"{{message:12}}"},"surfaceOp":"append"}
|
|
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"{{message:14}}"},"surfaceOp":"append"}
|
|
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}}
|
|
{"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
|
|
{"type":"session/title","data":{"title":"You are one fresh worker","messageSeqs":[9],"source":{"kind":"fallback"}}}
|
|
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"round-two-report","name":"structured_output","arguments":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:15}}"},"usage":{"inputTokens":40,"outputTokens":12},"stream":[{"type":"chunk","time":1788699412772,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1788699412772,"index":0,"dt":[],"id":"round-two-report","name":"structured_output","args":["{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"]},{"type":"chunk","time":1788699412772,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"round-two-report","name":"structured_output","arguments":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}},{"type":"chunk","time":1788699412772,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":12}}},{"type":"chunk","time":1788699412772,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}
|
|
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"round-two-report","name":"structured_output","arguments":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}
|
|
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"round-two-report"},"content":[{"type":"tool-result","toolCallId":"round-two-report","content":[{"type":"text","text":"Structured output recorded."}],"isError":false}],"role":"user","id":"{{message:16}}"}},"sourceEventSeqs":[15],"surfaceOp":"append"}
|
|
{"type":"step/end","data":{"turn":1,"step":1}}
|
|
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
|