37 lines
11 KiB
JSON
37 lines
11 KiB
JSON
[
|
||
{
|
||
"type": "message",
|
||
"role": "developer",
|
||
"content": [
|
||
{
|
||
"type": "input_text",
|
||
"text": "<permissions instructions>\nFilesystem sandboxing defines which files can be read or written. `sandbox_mode` is `workspace-write`: The sandbox permits reading files, and editing files in `cwd` and `writable_roots`. Editing files in other directories requires approval. Network access is restricted.\n# Escalation Requests\n\nCommands are run outside the sandbox if they are approved by the user, or match an existing rule that allows it to run unrestricted. The command string is split into independent command segments at shell control operators, including but not limited to:\n\n- Pipes: |\n- Logical operators: &&, ||\n- Command separators: ;\n- Subshell boundaries: (...), $(...)\n\nEach resulting segment is evaluated independently for sandbox restrictions and approval requirements.\n\nExample:\n\ngit pull | tee output.txt\n\nThis is treated as two command segments:\n\n[\"git\", \"pull\"]\n\n[\"tee\", \"output.txt\"]\n\nCommands that use more advanced shell features like redirection (>, >>, <), substitutions ($(...), ...), environment variables (FOO=bar), or wildcard patterns (*, ?) will not be evaluated against rules, to limit the scope of what an approved rule allows.\n\n## How to request escalation\n\nIMPORTANT: To request approval to execute a command that will require escalated privileges:\n\n- Provide the `sandbox_permissions` parameter with the value `\"require_escalated\"`\n- Include a short question asking the user if they want to allow the action in `justification` parameter. e.g. \"Do you want to download and install dependencies for this project?\"\n- Optionally suggest a `prefix_rule` - this will be shown to the user with an option to persist the rule approval for future sessions.\n\nIf you run a command that is important to solving the user's query, but it fails because of sandboxing or with a likely sandbox-related network error (for example DNS/host resolution, registry/index access, or dependency download failure), rerun the command with \"require_escalated\". ALWAYS proceed to use the `justification` parameter - do not message the user before requesting approval for the command.\n\n## When to request escalation\n\nWhile commands are running inside the sandbox, here are some scenarios that will require escalation outside the sandbox:\n\n- You need to run a command that writes to a directory that requires it (e.g. running tests that write to /var)\n- You need to run a GUI app (e.g., open/xdg-open/osascript) to open browsers or files.\n- If you run a command that is important to solving the user's query, but it fails because of sandboxing or with a likely sandbox-related network error (for example DNS/host resolution, registry/index access, or dependency download failure), rerun the command with `require_escalated`. ALWAYS proceed to use the `sandbox_permissions` and `justification` parameters. do not message the user before requesting approval for the command.\n- You are about to take a potentially destructive action such as an `rm` or `git reset` that the user did not explicitly ask for.\n- Be judicious with escalating, but if completing the user's request requires it, you should do so - don't try and circumvent approvals by using other tools.\n\n## prefix_rule guidance\n\nWhen choosing a `prefix_rule`, request one that will allow you to fulfill similar requests from the user in the future without re-requesting escalation. It should be categorical and reasonably scoped to similar capabilities. You should rarely pass the entire command into `prefix_rule`.\n\n### Banned prefix_rules \nAvoid requesting overly broad prefixes that the user would be ill-advised to approve. For example, do not request [\"python3\"], [\"python\", \"-\"], or other similar prefixes that would allow arbitrary scripting.\nNEVER provide a prefix_rule argument for destructive commands like rm.\nNEVER provide a prefix_rule if your command uses a heredoc or herestring. \n\n### Examples\nGood examples of prefixes:\n- [\"npm\", \"run\", \"dev\"]\n- [\"gh\", \"pr\", \"check\"]\n- [\"cargo\", \"test\"]\n The writable roots are `/home/wolves/.codex/memories`, `/home/wolves/project/codebuddy2api`, `/tmp`.\n</permissions instructions>"
|
||
},
|
||
{
|
||
"type": "input_text",
|
||
"text": "<skills_instructions>\n## Skills\nA skill is a set of local instructions to follow that is stored in a `SKILL.md` file. Below is the list of skills that can be used. Each entry includes a name, description, and file path so you can open the source for full instructions when using a specific skill.\n### Available skills\n- imagegen: Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas. (file: /home/wolves/.codex/skills/.system/imagegen/SKILL.md)\n- openai-docs: Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains. (file: /home/wolves/.codex/skills/.system/openai-docs/SKILL.md)\n- plugin-creator: Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata. (file: /home/wolves/.codex/skills/.system/plugin-creator/SKILL.md)\n- skill-creator: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations. (file: /home/wolves/.codex/skills/.system/skill-creator/SKILL.md)\n- skill-installer: Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos). (file: /home/wolves/.codex/skills/.system/skill-installer/SKILL.md)\n- Agent Browser: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. (file: /home/wolves/.codex/skills/agent-browser/SKILL.md)\n- find-skills-in-tencent-skillhub: Search, install, upgrade, and manage agent skills using skillhub CLI. Use when you need to discover new skills, install skills by slug, upgrade installed skills, list available skills, or self-upgrade the skillhub CLI. (file: /home/wolves/.codex/skills/find-skills-in-tencent-skillhub/SKILL.md)\n- skillhub-preference: Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capability extension. (file: /home/wolves/.codex/skills/skillhub-preference/SKILL.md)\n- ui-ux-pro-max: UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples. (file: /home/wolves/.codex/skills/ui-ux-pro-max/SKILL.md)\n### How to use skills\n- Discovery: The list above is the skills available in this session (name + description + file path). Skill bodies live on disk at the listed paths.\n- Trigger rules: If the user names a skill (with `$SkillName` or plain text) OR the task clearly matches a skill's description shown above, you must use that skill for that turn. Multiple mentions mean use them all. Do not carry skills across turns unless re-mentioned.\n- Missing/blocked: If a named skill isn't in the list or the path can't be read, say so briefly and continue with the best fallback.\n- How to use a skill (progressive disclosure):\n 1) After deciding to use a skill, open its `SKILL.md`. Read only enough to follow the workflow.\n 2) When `SKILL.md` references relative paths (e.g., `scripts/foo.py`), resolve them relative to the skill directory listed above first, and only consider other paths if needed.\n 3) If `SKILL.md` points to extra folders such as `references/`, load only the specific files needed for the request; don't bulk-load everything.\n 4) If `scripts/` exist, prefer running or patching them instead of retyping large code blocks.\n 5) If `assets/` or templates exist, reuse them instead of recreating from scratch.\n- Coordination and sequencing:\n - If multiple skills apply, choose the minimal set that covers the request and state the order you'll use them.\n - Announce which skill(s) you're using and why (one short line). If you skip an obvious skill, say why.\n- Context hygiene:\n - Keep context small: summarize long sections instead of pasting them; only load extra files when needed.\n - Avoid deep reference-chasing: prefer opening only files directly linked from `SKILL.md` unless you're blocked.\n - When variants exist (frameworks, providers, domains), pick only the relevant reference file(s) and note that choice.\n- Safety and fallback: If a skill can't be applied cleanly (missing files, unclear instructions), state the issue, pick the next-best approach, and continue.\n</skills_instructions>"
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"type": "message",
|
||
"role": "user",
|
||
"content": [
|
||
{
|
||
"type": "input_text",
|
||
"text": "<environment_context>\n <cwd>/home/wolves/project/codebuddy2api</cwd>\n <shell>bash</shell>\n <current_date>2026-04-23</current_date>\n <timezone>Asia/Shanghai</timezone>\n</environment_context>"
|
||
}
|
||
]
|
||
},
|
||
{
|
||
"type": "message",
|
||
"role": "user",
|
||
"content": [
|
||
{
|
||
"type": "input_text",
|
||
"text": "请只回复 ok，不要解释。"
|
||
}
|
||
]
|
||
}
|
||
]
|