mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-09-05 17:43:49 +08:00

Files

Yige bdaaa44ce1 fix(skills): 提高智能体管理能力最低客户端版本 (#91 )

## 中文

- create-agent 2.6.1：最低客户端提高到 10.0.108（smartRouting + avatarImage）
- update-agent 3.2.1：最低客户端提高到 10.0.108
- clone-agent 1.0.1：最低客户端提高到 10.0.115（补偿、fixed route 与 Provider ceiling）
- action→Skill ID 映射仍不绑定版本

### 验证
- i18n validator
- translation freshness
- public information boundary review

## English

- create-agent 2.6.1 now requires client 10.0.108 for smartRouting and
avatarImage
- update-agent 3.2.1 now requires client 10.0.108
- clone-agent 1.0.1 now requires client 10.0.115 for compensation,
fixed-route, and Provider-ceiling guarantees
- The action-to-Skill-ID mapping remains versionless

### Verification
- i18n validator
- translation freshness
- public information boundary review

2026-08-25 17:25:42 +08:00

9.9 KiB

Raw Blame History

name, description, version, type, risk_level, status, disable-model-invocation, tags, metadata, market

name

description

version

type

risk_level

status

disable-model-invocation

create-agent skill

L0: One-Sentence Summary

Collect requirements through natural-language conversation and call the ManageAgent builtin tool to create a specialized digital Agent.

L1: Overview

Meta-skill: gather requirements over multi-turn conversation → generate persona/principles → land via ManageAgent(action='create'). Use it to raise a domain specialist (legal advisor, financial analyst), deploy a customized business Agent quickly, or produce a prototype from a template. The created repo conforms to the AgentFS v2 spec and is version-managed by git (governable, traceable). Its value is what the tool can't give: domain-tailored persona/principles generation + a pre-create preview confirmation.

L2: Detailed Spec

Flow: intent recognition → requirement gathering → content generation → user confirmation → creation → receipt.

Stage 1: Intent Recognition

Trigger (any): user explicitly says "create an Agent / make me an assistant"; describes a domain-specific need the current Agent lacks; asks "can you raise a …". Confirm intent, then move to requirement gathering.

Stage 2: Requirement Gathering

Required (parenthesized = example prompt question): name ("what to name it?"), role ("what does it mainly do?"), target_users ("who will use it?"), domain ("what expertise does it need?").
Optional: style (communication tone), boundaries (red lines), language (default Chinese) — defaults derived from the domain template.
Strategy: prefer inferring from the user's natural description; only ask for missing required fields; you decide how many to ask and the pacing.

Stage 3: Content Generation

Organize persona and principles as structured fields (do not emit raw markdown; present field-by-field). Leave uncollected fields empty for the system to fill with defaults:

persona: L0 one-sentence core identity; L1 role / personality (array of trait tags) / communication_style; L2 specialty, values, decision preferences (free-form).
principles: L0 one-sentence top principle; L1 must_do / must_not (safety red lines) / priority; L2 governance principles, escalation rules (free-form).

Domain matching reference (recommend personality and red lines by domain):

Domain	Recommended personality	Default must_not
Legal / contract	Professional, rigorous, prudent	No litigation representation; not a substitute for formal legal advice
Finance / accounting / investment	Precise, analytical, conservative	No investment advice; no real transactions
Code / development / architecture	Logical, pragmatic, direct	No direct production access; no credential storage
General / other	Friendly, helpful	Standard safety norms

Stage 4: User Confirmation

Present the preview in natural language / tables (name, description, persona, principles; no raw markdown source), e.g.:

About to create "Legal Advisor Assistant" — focused on contract review and legal risk assessment. Persona: digital legal advisor; professional, rigorous, prudent; uses legal terms accurately with plain-language explanations. Principles: user interest first, not a substitute for formal legal advice; must — cite statutes / mark uncertainty / recommend consulting a lawyer; must not — litigation representation / leaking consultations; priority: user safety > accuracy > efficiency. Confirm creation? (Confirm / Modify / Cancel)

If the user picks "Modify": ask which field → re-collect that field → update the preview → show and confirm again.

Stage 5: Create via ManageAgent

Structured call (persona/principles also accept markdown strings; unprovided fields are auto-filled):

ManageAgent({
  "action": "create",
  "name": "Legal Advisor Assistant",
  "description": "A digital Agent focused on contract review and legal risk assessment",
  "persona": { "L0": "…", "L1": { "role": "…", "personality": ["professional","rigorous","prudent"], "communication_style": "…" } },
  "principles": { "L0": "…", "L1": { "must_do": ["…"], "must_not": ["…"], "priority": "user safety > accuracy > efficiency" } }
})

Minimal create needs only { "action": "create", "name": "My Assistant" } (everything else auto-generated).
Basic create { "action": "create", "name": "Legal Advisor", "description": "contract review" } — with just name + description, the description auto-fills persona's L0.
Optional id (kebab-case slug; core / desirecore are reserved core identifiers and cannot be used, including when the slug auto-generated from name collides), config, smartRouting, and avatarImage. See the contracts below. Sensitive fields such as mcp_servers and tool_permissions are rejected and must be adjusted through the UI after creation.
The Agent is registered and usable immediately; the returned ID works directly with ManageTeam / Delegate. If the tool errors (already exists / reserved identifier / non-whitelisted config field, etc.), explain the reason and retry after adjusting per the hint.

Creation Parameter Guide

Smart routing: new Agents default to the Smart flagship tier. When responsibilities require an explicit tier, pass smartRouting:

{
  "tier": "balanced",
  "requiredCapabilities": ["vision", "tool_use"],
  "reasoning": "high"
}

tier accepts lightweight, balanced, or flagship; reasoning accepts auto, off, minimal, low, medium, high, xhigh, or max.
Omitting tier defaults to flagship. This expresses workload and capability intent, not a concrete Provider or model.
Fixed model, Provider, and Smart/fixed selection are governed by the human model selector and cannot be changed through ManageAgent.
Natural-language requests such as "deepest/highest/max it out" normally map to xhigh; use max only when the user explicitly names it and the model supports it.

Configuration patch: config supports only llm and declarative avatar settings. It is normally unnecessary during creation; use it only when the Agent needs a different default reasoning behavior:

{
  "llm": {
    "reasoning": "high",
    "maxRetryDelayMs": 30000
  },
  "avatar": {
    "char": "L",
    "color": "purple"
  }
}

config.llm currently exposes only reasoning, thinkingBudgets, and maxRetryDelayMs. Do not pass model, provider, providerId, or routingMode.

Image avatar: use the separate avatarImage parameter; do not place image data in config:

{ "source": "dc-media://<mediaId>" }

source may be a media ID from the current turn or a PNG/JPEG/WebP file inside the working directory. URLs and base64 are rejected. The service crops to 512×512 WebP and removes EXIF automatically. Avatar failure does not roll back an otherwise successful Agent creation; retry only the avatar operation according to the receipt.

Stage 6: Receipt

Present in a user-friendly way (no internal paths / technical details): confirm success and suggest next steps — start chatting, add skills, adjust persona or rules.

Background and Constraints

AgentFS structure, troubleshooting, and protected paths: see _agentfs-background.md and _protected-paths.yaml.
Always create via ManageAgent; never use curl / HTTP or write AgentFS directories directly. Requires client ≥ 10.0.90.

9.9 KiB Raw Blame History Unescape Escape