Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

test(ralph): snapshot fresh-agent rounds in headless app

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-20 18:18:08 +08:00
parent 94a6a95c8e
commit 9f6f87cf69
11 changed files with 157 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/headless-agent/tests/snapshots/ralph-loop/input.json
+8
View File
@@ -0,0 +1,8 @@
{
"steps": [
{
"op": "prompt",
"text": "Run a two-round fresh-agent Ralph loop to prove the shipped headless integration."
}
]
}
examples/headless-agent/tests/snapshots/ralph-loop/replay.override.json
+22
View File
@@ -0,0 +1,22 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "tool-call" },
{ "type": "tool-call-delta", "index": 0, "id": "call_ralph", "name": "ralph", "argumentsDelta": "{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}" },
{ "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_ralph", "name": "ralph", "arguments": "{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}" } },
{ "type": "usage", "usage": { "inputTokens": 20, "outputTokens": 8 } },
{ "type": "finish", "reason": { "kind": "tool-calls" } }
]
},
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "RALPH SNAPSHOT COMPLETE" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "RALPH SNAPSHOT COMPLETE" } },
{ "type": "usage", "usage": { "inputTokens": 30, "outputTokens": 4 } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
}
]
examples/headless-agent/tests/snapshots/ralph-loop/session.1.jsonl
+6
View File
@@ -0,0 +1,6 @@
{"type":"session","version":0,"id":"42222222-2222-4222-8222-222222222222","createdAt":1783951001000,"cwd":"/tmp/ralph-headless","parentSession":"41111111-1111-4111-8111-111111111111"}
{"type":"assistant/chunk","seq":0,"time":1783951001001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":1,"time":1783951001002,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"round-one-report","name":"structured_output","argumentsDelta":"{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}"}}}
{"type":"assistant/chunk","seq":2,"time":1783951001003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"round-one-report","name":"structured_output","arguments":"{\"status\":\"continue\",\"summary\":\"ROUND_ONE_HANDOFF\",\"evidence\":[\"Round one inspected the workspace.\"],\"nextSteps\":[\"Finish the snapshot objective.\"],\"blocker\":\"\"}"}}}}
{"type":"assistant/chunk","seq":3,"time":1783951001004,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":12}}}}
{"type":"assistant/chunk","seq":4,"time":1783951001005,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
examples/headless-agent/tests/snapshots/ralph-loop/session.2.jsonl
+6
View File
@@ -0,0 +1,6 @@
{"type":"session","version":0,"id":"43333333-3333-4333-8333-333333333333","createdAt":1783951002000,"cwd":"/tmp/ralph-headless","parentSession":"41111111-1111-4111-8111-111111111111"}
{"type":"assistant/chunk","seq":0,"time":1783951002001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":1,"time":1783951002002,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"round-two-report","name":"structured_output","argumentsDelta":"{\"status\":\"complete\",\"summary\":\"The Ralph snapshot objective is complete.\",\"evidence\":[\"Two fresh rounds completed through the shipped app.\"],\"nextSteps\":[],\"blocker\":\"\"}"}}}
{"type":"assistant/chunk","seq":2,"time":1783951002003,"data":{"turn":1,"step":1,"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":"assistant/chunk","seq":3,"time":1783951002004,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":40,"outputTokens":12}}}}
{"type":"assistant/chunk","seq":4,"time":1783951002005,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
examples/headless-agent/tests/snapshots/ralph-loop/session.jsonl
+1
View File
@@ -0,0 +1 @@
{"type":"session","version":0,"id":"41111111-1111-4111-8111-111111111111","createdAt":1783951000000,"cwd":"/tmp/ralph-headless"}
examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl
+23
View File
@@ -0,0 +1,23 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run a two-round fresh-agent Ralph loop to prove the shipped headless integration."}],"source":{"kind":"user"}},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_ralph","name":"ralph","argumentsDelta":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":20,"outputTokens":8}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_ralph","name":"ralph","arguments":"{\"objective\":\"Prove two fresh Ralph rounds through the shipped headless app.\",\"maxRounds\":2}"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_ralph","content":[{"type":"text","text":"Ralph worker reported completion after 2 rounds.\nFinal report:\n{\n \"status\": \"complete\",\n \"summary\": \"The Ralph snapshot objective is complete.\",\n \"evidence\": [\n \"Two fresh rounds completed through the shipped app.\"\n ],\n \"nextSteps\": [],\n \"blocker\": \"\"\n}"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"RALPH SNAPSHOT COMPLETE"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RALPH SNAPSHOT COMPLETE"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":30,"outputTokens":4}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"RALPH SNAPSHOT COMPLETE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":30,"outputTokens":4}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":20,"time":0,"data":{"turn":1,"step":2}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":21,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}}
{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"RALPH SNAPSHOT COMPLETE","reason":{"kind":"completed"},"usage":{"inputTokens":50,"outputTokens":12}}