test(acp): clarify skill snapshot fixture
This commit is contained in:
Yichen Jiang committed
1 parent
b5b17a7f65
commit
0b20353424
7 files changed
+18
-51
No files matched your search
@@ -36,7 +36,7 @@ const SCENARIOS: Scenario[] = [
|
||||
{ name: 'tool-call-turn', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-terminal-card', hasModelTurn: true, recorded: true },
|
||||
{ name: 'todo-plan', hasModelTurn: true, recorded: true },
|
||||
{ name: 'skill-load', hasModelTurn: true, recorded: false, overridden: true, pinsHeader: true, headerClass: 'skill' },
|
||||
{ name: 'skill-load', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'skill' },
|
||||
{ name: 'workspace-edit', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-read', hasModelTurn: true, recorded: true },
|
||||
{ name: 'fs-write', hasModelTurn: true, recorded: true },
|
||||
|
||||
@@ -2,6 +2,6 @@
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Load the dsh-skill-creator skill with the skill tool, then reply DONE." }
|
||||
{ "op": "prompt", "text": "Load the snapshot-skill skill with the skill tool, then reply DONE." }
|
||||
]
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
[
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "reasoning" },
|
||||
{ "type": "reasoning-delta", "index": 0, "text": "Load the requested skill." },
|
||||
{ "type": "block-start", "index": 1, "blockType": "tool-call" },
|
||||
{ "type": "tool-call-delta", "index": 1, "id": "call_skill_load", "name": "skill", "argumentsDelta": "{\"name\":\"dsh-skill-creator\"}" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "reasoning", "text": "Load the requested skill." } },
|
||||
{ "type": "block-end", "index": 1, "block": { "type": "tool-call", "id": "call_skill_load", "name": "skill", "arguments": "{\"name\":\"dsh-skill-creator\"}" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 100, "outputTokens": 20, "cacheReadTokens": 0, "reasoningTokens": 5 } },
|
||||
{ "type": "finish", "reason": { "kind": "tool-calls" } }
|
||||
]
|
||||
},
|
||||
{
|
||||
"kind": "chunks",
|
||||
"chunks": [
|
||||
{ "type": "block-start", "index": 0, "blockType": "reasoning" },
|
||||
{ "type": "reasoning-delta", "index": 0, "text": "The skill is loaded." },
|
||||
{ "type": "block-start", "index": 1, "blockType": "text" },
|
||||
{ "type": "text-delta", "index": 1, "text": "DONE" },
|
||||
{ "type": "block-end", "index": 0, "block": { "type": "reasoning", "text": "The skill is loaded." } },
|
||||
{ "type": "block-end", "index": 1, "block": { "type": "text", "text": "DONE" } },
|
||||
{ "type": "usage", "usage": { "inputTokens": 180, "outputTokens": 10, "cacheReadTokens": 0, "reasoningTokens": 4 } },
|
||||
{ "type": "finish", "reason": { "kind": "stop" } }
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -1,19 +1,19 @@
|
||||
{"type":"session","version":0,"id":"9eb4181f-2d05-49d3-98fc-3711fe2f5664","createdAt":1783654655599,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW"}
|
||||
{"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the dsh-skill-creator skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.","tools":[{"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]`. 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 task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","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 task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before actingLine truncated
|
||||
{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.","tools":[{"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]`. 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 task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","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 task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before actingLine truncated
|
||||
{"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skill_load","name":"skill","argumentsDelta":"{\"name\":\"dsh-skill-creator\"}"}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skill_load","name":"skill","argumentsDelta":"{\"name\":\"snapshot-skill\"}"}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Load the requested skill."}}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"dsh-skill-creator\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":10,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":11,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"dsh-skill-creator\"}"}],"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"dsh-skill-creator\"}"}}
|
||||
{"type":"tool/result","seq":14,"time":1783654655610,"data":{"turn":1,"step":1,"callId":"call_skill_load","content":[{"type":"text","text":"<skill_content name=\"dsh-skill-creator\">\n<skill_resources>\nBase directory for this skill: /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW/.dsh/skills/dsh-skill-creator\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nUse this skill to write focused DeepSeek Harness skills.\n\nA skill is a directory `<name>/SKILL.md` or a flat `<name>.md` file with YAML frontmatter.\nFrontmatter must include kebab-case `name` and a concise `description` that tells the model when to load it.\nUse optional `whenToUse` for extra routing signal and `disableModelInvocation: true` for user-only skills.\nKeep the body procedural, evidence-oriented, and scoped to the workflow the skill owns.\n</skill_instructions>\n</skill_content>"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}
|
||||
{"type":"tool/result","seq":14,"time":1783654655610,"data":{"turn":1,"step":1,"callId":"call_skill_load","content":[{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":15,"time":1783654655610,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":16,"time":1783654655610,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":17,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
|
||||
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill dsh-skill-creator","kind":"read","status":"in_progress","rawInput":"dsh-skill-creator"}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<skill_content name=\"dsh-skill-creator\">\n<skill_resources>\nBase directory for this skill: {{cwd}}/.dsh/skills/dsh-skill-creator\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nUse this skill to write focused DeepSeek Harness skills.\n\nA skill is a directory `<name>/SKILL.md` or a flat `<name>.md` file with YAML frontmatter.\nFrontmatter must include kebab-case `name` and a concise `description` that tells the model when to load it.\nUse optional `whenToUse` for extra routing signal and `disableModelInvocation: true` for user-only skills.\nKeep the body procedural, evidence-oriented, and scoped to the workflow the skill owns.\n</skill_instructions>\n</skill_content>"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"<skill_content name=\"snapshot-skill\">\n<skill_resources>\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n</skill_instructions>\n</skill_content>"}}]}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The skill is loaded."}}}}
|
||||
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}}
|
||||
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
---
|
||||
name: dsh-skill-creator
|
||||
description: Create or update DeepSeek Harness SKILL.md instructions.
|
||||
whenToUse: Use when writing reusable agent instructions for DeepSeek Harness or adding system/project/user skills.
|
||||
---
|
||||
|
||||
Use this skill to write focused DeepSeek Harness skills.
|
||||
|
||||
A skill is a directory `<name>/SKILL.md` or a flat `<name>.md` file with YAML frontmatter.
|
||||
Frontmatter must include kebab-case `name` and a concise `description` that tells the model when to load it.
|
||||
Use optional `whenToUse` for extra routing signal and `disableModelInvocation: true` for user-only skills.
|
||||
Keep the body procedural, evidence-oriented, and scoped to the workflow the skill owns.
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: snapshot-skill
|
||||
description: Exercise project skill discovery and loading in snapshot tests.
|
||||
---
|
||||
|
||||
Follow these snapshot-only instructions.
|
||||
Resolve referenced resources relative to this skill directory.
|
||||
Reference in new issue
Block a user