test(snapshot): canonicalize Auto review PTC fixture

snapshots/session/ptc-python-turn/session.jsonl

@@ -19,7 +19,7 @@
 {"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}}}}
 {"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":6152,"outputTokens":214,"cacheReadTokens":0,"reasoningTokens":60}}}}
 {"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to write a single Python run_code program that:\n1. Calls bash tool twice: `echo CODE_ONE` and `echo CODE_TWO`\n2. print exactly `captured output`\n3. Return the two outputs joined with a plus sign\n\nLet me write this."},{"type":"tool-call","id":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:3}}"},"usage":{"inputTokens":6152,"outputTokens":214,"cacheReadTokens":0,"reasoningTokens":60}},"sourceEventSeqs":[[12,190]],"surfaceOp":"append"}
+{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to write a single Python run_code program that:\n1. Calls bash tool twice: `echo CODE_ONE` and `echo CODE_TWO`\n2. print exactly `captured output`\n3. Return the two outputs joined with a plus sign\n\nLet me write this."},{"type":"tool-call","id":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:3}}"},"usage":{"inputTokens":6152,"outputTokens":214,"cacheReadTokens":0,"reasoningTokens":60}},"sourceEventSeqs":[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],"surfaceOp":"append"}
 {"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}}
 {"type":"tool/code-dispatch-start","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:1","name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a job id immediately; read its output with `job_output` and stop it with `job_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]},"arguments":{"command":"echo CODE_ONE","description":"Print CODE_ONE"}}}
 {"type":"tool/code-dispatch","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"Print CODE_ONE"},"isError":false,"content":[{"type":"text","text":"CODE_ONE\n"}]}}
@@ -29,15 +29,13 @@
 {"type":"step/end","data":{"turn":1,"step":1}}
 {"type":"step/start","data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
-{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."}}}
-{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":""}}}
-{"type":"reasoning-chunks","data":{"turn":1,"step":2,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0],"texts":["","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","",""]}}
+{"type":"reasoning-chunks","data":{"turn":1,"step":2,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0],"texts":["The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only.","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","",""]}}
 {"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
 {"type":"text-chunks","data":{"turn":1,"step":2,"index":1,"dt":[0,0,0,0,0,0],"texts":["CODE","_","ONE","+","CODE","_T","WO"]}}
 {"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."}}}}
 {"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CODE_ONE+CODE_TWO"}}}}
 {"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":117,"outputTokens":50,"cacheReadTokens":6272,"reasoningTokens":42}}}}
 {"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:5}}"},"usage":{"inputTokens":117,"outputTokens":50,"cacheReadTokens":6272,"reasoningTokens":42}},"sourceEventSeqs":[[200,254]],"surfaceOp":"append"}
+{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:5}}"},"usage":{"inputTokens":117,"outputTokens":50,"cacheReadTokens":6272,"reasoningTokens":42}},"sourceEventSeqs":[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],"surfaceOp":"append"}
 {"type":"step/end","data":{"turn":1,"step":2}}
 {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}