mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-09-12 04:01:20 +00:00
The minimal compositions serve the same models that trained against a one-shot `bash` tool; three surface differences remained visible to them. - Every settled command now appends `[Command finished with exit code N]`, including exit code 0, instead of `[exit code: N]` only on failure. A timeout appends `[Command timed out or OOM]` after the partial output. - Trailing newlines are all dropped before the status trailer rather than only the last one. - The `bash` description in the `minimal` preset and the `sdk-minimal` bundle replaces the two fixed network lines with a single environment- dependent line; the pwsh description is unchanged. Tests, READMEs, the web minimal-preset schema snapshot, and the packaged Python minimal model-visible snapshot follow the new wording. The standalone `persistent-tools` SDK replay fixture keeps its own copy of the old description since it is a per-launch customization, not the profile.
144 lines
4.8 KiB
JSON
144 lines
4.8 KiB
JSON
[
|
|
{
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "bash",
|
|
"description": "Run commands in a bash shell\n* When invoking this tool, the contents of the \"command\" parameter does NOT need to be XML-escaped.\n* Network access depends on the task environment. Prefer configured mirrors/proxies when they are available.\n* State is persistent across command calls and discussions with the user.\n* To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.\n* Please avoid commands that may produce a very large amount of output.\n* Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"command": {
|
|
"type": "string",
|
|
"description": "The bash command to run. Relative path is preferred in the command."
|
|
}
|
|
},
|
|
"required": [
|
|
"command"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"text": "You are a helpful software engineer assistant."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"text": "Exercise the packaged minimal agent's persistent shell."
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "bash",
|
|
"description": "Run commands in a bash shell\n* When invoking this tool, the contents of the \"command\" parameter does NOT need to be XML-escaped.\n* Network access depends on the task environment. Prefer configured mirrors/proxies when they are available.\n* State is persistent across command calls and discussions with the user.\n* To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.\n* Please avoid commands that may produce a very large amount of output.\n* Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"command": {
|
|
"type": "string",
|
|
"description": "The bash command to run. Relative path is preferred in the command."
|
|
}
|
|
},
|
|
"required": [
|
|
"command"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"text": "You are a helpful software engineer assistant."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"text": "Exercise the packaged minimal agent's persistent shell."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"toolCalls": [
|
|
{
|
|
"id": "minimal-bash-1",
|
|
"name": "bash"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"toolCallId": "minimal-bash-1",
|
|
"text": "{{tool-result}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "bash",
|
|
"description": "Run commands in a bash shell\n* When invoking this tool, the contents of the \"command\" parameter does NOT need to be XML-escaped.\n* Network access depends on the task environment. Prefer configured mirrors/proxies when they are available.\n* State is persistent across command calls and discussions with the user.\n* To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.\n* Please avoid commands that may produce a very large amount of output.\n* Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"command": {
|
|
"type": "string",
|
|
"description": "The bash command to run. Relative path is preferred in the command."
|
|
}
|
|
},
|
|
"required": [
|
|
"command"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"text": "You are a helpful software engineer assistant."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"text": "Exercise the packaged minimal agent's persistent shell."
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"toolCalls": [
|
|
{
|
|
"id": "minimal-bash-1",
|
|
"name": "bash"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"toolCallId": "minimal-bash-1",
|
|
"text": "{{tool-result}}"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"toolCalls": [
|
|
{
|
|
"id": "minimal-bash-2",
|
|
"name": "bash"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"toolCallId": "minimal-bash-2",
|
|
"text": "{{tool-result}}"
|
|
}
|
|
]
|
|
}
|
|
]
|