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

test(python): stabilize executable snapshot

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-29 22:56:14 +08:00
parent c0bd88430a
commit 5de69975f0
8 files changed
+468 -299
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/snapshots/python-sdk-single-exe/advanced/result.json
+438 -270
View File
@@ -30,7 +30,9 @@
],
"source": {
"kind": "user"
}
},
"role": "user",
"id": "{{messageId}}"
},
"surfaceOp": "append"
},
@@ -70,20 +72,15 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "initial"
@@ -176,17 +173,22 @@
"data": {
"turn": 1,
"step": 1,
"content": [
{
"type": "tool-call",
"id": "advanced-mount",
"name": "cordis_mount",
"arguments": "{\"code\": \"return (ctx) => {\\n harness.registerTool(ctx, harness.defineTool({\\n name: 'snapshot_double',\\n description: 'Double a number for executable snapshot verification.',\\n parameters: { value: { type: 'number', required: true } },\\n output: {\\n schema: { type: 'number' },\\n render(_args, value) {\\n return [{ type: 'text', text: String(value) }]\\n }\\n },\\n async execute(args) {\\n return args.value * 2\\n }\\n }))\\n}\\n\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-mount",
"name": "cordis_mount",
"arguments": "{\"code\": \"return (ctx) => {\\n harness.registerTool(ctx, harness.defineTool({\\n name: 'snapshot_double',\\n description: 'Double a number for executable snapshot verification.',\\n parameters: { value: { type: 'number', required: true } },\\n output: {\\n schema: { type: 'number' },\\n render(_args, value) {\\n return [{ type: 'text', text: String(value) }]\\n }\\n },\\n async execute(args) {\\n return args.value * 2\\n }\\n }))\\n}\\n\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -221,14 +223,27 @@
"data": {
"turn": 1,
"step": 1,
"callId": "advanced-mount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 is running (plugin \"<anonymous>\"; available until unmounted or DSH restarts)."
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-mount"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-mount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 is running (plugin \"<anonymous>\"; available until unmounted or DSH restarts)."
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
11
@@ -266,21 +281,16 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"snapshot_double",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "change"
@@ -373,17 +383,22 @@
"data": {
"turn": 1,
"step": 2,
"content": [
{
"type": "tool-call",
"id": "advanced-code",
"name": "run_code",
"arguments": "{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Run the temporary Plugin tool\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-code",
"name": "run_code",
"arguments": "{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Run the temporary Plugin tool\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -451,14 +466,27 @@
"data": {
"turn": 1,
"step": 2,
"callId": "advanced-code",
"content": [
{
"type": "text",
"text": "42"
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-code"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-code",
"content": [
{
"type": "text",
"text": "42"
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
22
@@ -570,17 +598,22 @@
"data": {
"turn": 1,
"step": 3,
"content": [
{
"type": "tool-call",
"id": "advanced-direct-child",
"name": "subagent",
"arguments": "{\"description\": \"Check direct child\", \"prompt\": \"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-direct-child",
"name": "subagent",
"arguments": "{\"description\": \"Check direct child\", \"prompt\": \"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -615,14 +648,27 @@
"data": {
"turn": 1,
"step": 3,
"callId": "advanced-direct-child",
"content": [
{
"type": "text",
"text": "DIRECT_CHILD_OK"
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-direct-child"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-direct-child",
"content": [
{
"type": "text",
"text": "DIRECT_CHILD_OK"
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
34
@@ -734,17 +780,22 @@
"data": {
"turn": 1,
"step": 4,
"content": [
{
"type": "tool-call",
"id": "advanced-workflow",
"name": "workflow",
"arguments": "{\"script\": \"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\", \"meta\": {\"name\": \"advanced-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-workflow",
"name": "workflow",
"arguments": "{\"script\": \"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\", \"meta\": {\"name\": \"advanced-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -779,14 +830,27 @@
"data": {
"turn": 1,
"step": 4,
"callId": "advanced-workflow",
"content": [
{
"type": "text",
"text": "workflow \"advanced-exe-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-workflow"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-workflow",
"content": [
{
"type": "text",
"text": "workflow \"advanced-exe-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
44
@@ -898,17 +962,22 @@
"data": {
"turn": 1,
"step": 5,
"content": [
{
"type": "tool-call",
"id": "advanced-unmount",
"name": "cordis_unmount",
"arguments": "{\"id\": \"dyn-1\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-unmount",
"name": "cordis_unmount",
"arguments": "{\"id\": \"dyn-1\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -943,14 +1012,27 @@
"data": {
"turn": 1,
"step": 5,
"callId": "advanced-unmount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 was unmounted and removed."
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-unmount"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-unmount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 was unmounted and removed."
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
54
@@ -988,20 +1070,15 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "change"
@@ -1090,15 +1167,20 @@
"data": {
"turn": 1,
"step": 6,
"content": [
{
"type": "text",
"text": "ADVANCED_EXECUTABLE_OK"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "text",
"text": "ADVANCED_EXECUTABLE_OK"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -1173,7 +1255,9 @@
],
"source": {
"kind": "user"
}
},
"role": "user",
"id": "{{messageId}}"
},
"surfaceOp": "append"
}
@@ -1231,20 +1315,15 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "initial"
@@ -1373,17 +1452,22 @@
"data": {
"turn": 1,
"step": 1,
"content": [
{
"type": "tool-call",
"id": "advanced-mount",
"name": "cordis_mount",
"arguments": "{\"code\": \"return (ctx) => {\\n harness.registerTool(ctx, harness.defineTool({\\n name: 'snapshot_double',\\n description: 'Double a number for executable snapshot verification.',\\n parameters: { value: { type: 'number', required: true } },\\n output: {\\n schema: { type: 'number' },\\n render(_args, value) {\\n return [{ type: 'text', text: String(value) }]\\n }\\n },\\n async execute(args) {\\n return args.value * 2\\n }\\n }))\\n}\\n\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-mount",
"name": "cordis_mount",
"arguments": "{\"code\": \"return (ctx) => {\\n harness.registerTool(ctx, harness.defineTool({\\n name: 'snapshot_double',\\n description: 'Double a number for executable snapshot verification.',\\n parameters: { value: { type: 'number', required: true } },\\n output: {\\n schema: { type: 'number' },\\n render(_args, value) {\\n return [{ type: 'text', text: String(value) }]\\n }\\n },\\n async execute(args) {\\n return args.value * 2\\n }\\n }))\\n}\\n\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -1430,14 +1514,27 @@
"data": {
"turn": 1,
"step": 1,
"callId": "advanced-mount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 is running (plugin \"<anonymous>\"; available until unmounted or DSH restarts)."
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-mount"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-mount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 is running (plugin \"<anonymous>\"; available until unmounted or DSH restarts)."
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
11
@@ -1493,21 +1590,16 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"snapshot_double",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "change"
@@ -1636,17 +1728,22 @@
"data": {
"turn": 1,
"step": 2,
"content": [
{
"type": "tool-call",
"id": "advanced-code",
"name": "run_code",
"arguments": "{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Run the temporary Plugin tool\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-code",
"name": "run_code",
"arguments": "{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Run the temporary Plugin tool\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -1738,14 +1835,27 @@
"data": {
"turn": 1,
"step": 2,
"callId": "advanced-code",
"content": [
{
"type": "text",
"text": "42"
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-code"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-code",
"content": [
{
"type": "text",
"text": "42"
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
22
@@ -1905,17 +2015,22 @@
"data": {
"turn": 1,
"step": 3,
"content": [
{
"type": "tool-call",
"id": "advanced-direct-child",
"name": "subagent",
"arguments": "{\"description\": \"Check direct child\", \"prompt\": \"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-direct-child",
"name": "subagent",
"arguments": "{\"description\": \"Check direct child\", \"prompt\": \"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -1995,7 +2110,9 @@
],
"source": {
"kind": "user"
}
},
"role": "user",
"id": "{{messageId}}"
},
"surfaceOp": "append"
}
@@ -2053,21 +2170,16 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"snapshot_double",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "initial"
@@ -2192,15 +2304,20 @@
"data": {
"turn": 1,
"step": 1,
"content": [
{
"type": "text",
"text": "DIRECT_CHILD_OK"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "text",
"text": "DIRECT_CHILD_OK"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -2278,14 +2395,27 @@
"data": {
"turn": 1,
"step": 3,
"callId": "advanced-direct-child",
"content": [
{
"type": "text",
"text": "DIRECT_CHILD_OK"
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-direct-child"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-direct-child",
"content": [
{
"type": "text",
"text": "DIRECT_CHILD_OK"
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
34
@@ -2445,17 +2575,22 @@
"data": {
"turn": 1,
"step": 4,
"content": [
{
"type": "tool-call",
"id": "advanced-workflow",
"name": "workflow",
"arguments": "{\"script\": \"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\", \"meta\": {\"name\": \"advanced-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-workflow",
"name": "workflow",
"arguments": "{\"script\": \"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\", \"meta\": {\"name\": \"advanced-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -2535,7 +2670,9 @@
],
"source": {
"kind": "user"
}
},
"role": "user",
"id": "{{messageId}}"
},
"surfaceOp": "append"
}
@@ -2593,21 +2730,16 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"snapshot_double",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "initial"
@@ -2732,15 +2864,20 @@
"data": {
"turn": 1,
"step": 1,
"content": [
{
"type": "text",
"text": "WORKFLOW_CHILD_OK"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "text",
"text": "WORKFLOW_CHILD_OK"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -2818,14 +2955,27 @@
"data": {
"turn": 1,
"step": 4,
"callId": "advanced-workflow",
"content": [
{
"type": "text",
"text": "workflow \"advanced-exe-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-workflow"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-workflow",
"content": [
{
"type": "text",
"text": "workflow \"advanced-exe-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
44
@@ -2985,17 +3135,22 @@
"data": {
"turn": 1,
"step": 5,
"content": [
{
"type": "tool-call",
"id": "advanced-unmount",
"name": "cordis_unmount",
"arguments": "{\"id\": \"dyn-1\"}"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "tool-call",
"id": "advanced-unmount",
"name": "cordis_unmount",
"arguments": "{\"id\": \"dyn-1\"}"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,
@@ -3042,14 +3197,27 @@
"data": {
"turn": 1,
"step": 5,
"callId": "advanced-unmount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 was unmounted and removed."
}
],
"isError": false
"message": {
"source": {
"kind": "tool",
"callId": "advanced-unmount"
},
"content": [
{
"type": "tool-result",
"toolCallId": "advanced-unmount",
"content": [
{
"type": "text",
"text": "Temporary Plugin dyn-1 was unmounted and removed."
}
],
"isError": false
}
],
"role": "user",
"id": "{{messageId}}"
}
},
"sourceEventSeqs": [
54
@@ -3105,20 +3273,15 @@
},
"system": "{{system}}",
"tools": [
"bash",
"cordis_inspect",
"cordis_mount",
"cordis_unmount",
"run_code",
"skill",
"subagent",
"task_kill",
"task_list",
"task_output",
"workflow"
],
"messagePrefix": [
"{{messagePrefix}}"
]
},
"reason": "change"
@@ -3243,15 +3406,20 @@
"data": {
"turn": 1,
"step": 6,
"content": [
{
"type": "text",
"text": "ADVANCED_EXECUTABLE_OK"
}
],
"provenance": {
"provider": "deepseek",
"model": "smoke-model"
"message": {
"role": "assistant",
"content": [
{
"type": "text",
"text": "ADVANCED_EXECUTABLE_OK"
}
],
"source": {
"kind": "model",
"provider": "deepseek",
"model": "smoke-model"
},
"id": "{{messageId}}"
},
"usage": {
"inputTokens": 3,