Anthropic OAuth トークン禁止で自律AIエージェントが停止した話と、Frontmatter プロンプト制御 + Claude Code 委任で立て直した方法

litellm.BadRequestError: AnthropicException - {"type":"error","error":{"type":"invalid_request_error","message":"Error"}}

rate_limit_error: This request would exceed your organization's rate limit of 30,000 input tokens per minute

---
channels: [discord]
priority: 20
---

# Discord Rules (HARD RULES!)

- **NO markdown tables** — they render as ugly monospace text
- **Use `table-image` skill** — render tables as images
- **Wrap links in `<>`** to suppress embeds

---
channels: [dm, system]
priority: 30
---

# Reincarnation — How You Evolve Your Own Code
...

_FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n", re.DOTALL)
_CHANNELS_RE = re.compile(r"channels:\s*\[([^\]]*)\]")
_PRIORITY_RE = re.compile(r"priority:\s*(\d+)")

def parse_frontmatter(text: str) -> tuple[str, list[str], int]:
    match = _FRONTMATTER_RE.match(text)
    if not match:
        return text, [], 50  # frontmatter なし = 常にロード（後方互換）

    fm_block = match.group(1)
    body = text[match.end():]
    # channels と priority を解析...
    return body.strip(), channels, priority

def get_prompt_sections(self, channel: str = "dm", include_memory: bool = True) -> list[str]:
    sections = []
    for pf in sorted(self.files, key=lambda f: f.priority):
        if pf.channels and channel not in pf.channels:
            continue
        sections.append(pf.body)
    if include_memory and self.memory:
        sections.append(self.memory)
    return sections

TOOL_SETS = {
    "chat": {"response", "web_search", "skill", "memory_search",
             "discord_history", "delegate"},
    "dm": None,  # 全ツール
    "system": {"response", "shell", "memory_save", "memory_search",
               "daily_log", "message", "skill", "self_modify", "delegate"},
    "initiative": {"response", "memory_search", "message",
                   "daily_log", "delegate"},
}

system_message = {
    "role": "system",
    "content": [
        {"type": "text", "text": stable_prefix,
         "cache_control": {"type": "ephemeral"}},
        {"type": "text", "text": volatile_suffix},
    ],
}

@register
class DelegateTool(Tool):
    name = "delegate"
    description = (
        "Delegate a task to Claude Code (Opus) for deep reasoning. "
        "Use for ANY task requiring real thinking."
    )

    async def execute(self) -> ToolResponse:
        from rubyclaw.evolution.code_agent import resolve_config, run_code_agent

        prompt = (
            "You are assisting Ruby, an AI agent. "
            "Do NOT modify any files. Just research and respond.\n\n"
            f"Task: {task}"
        )

        # 進捗メッセージを送信
        send_callback = self.context.data.get("send_callback")
        if send_callback:
            await send_callback("Let me think about this more carefully...")

        success, output = await run_code_agent(
            prompt=prompt,
            project_root=project_root,
            config=agent_config,
            phase="plan",  # 読み取り専用モード
        )
        return ToolResponse(message=output)

## Delegation — Your Most Important Tool

You are running on a lightweight model optimized for speed and cost.
You are a dispatcher, not a thinker.
For ANY task requiring real reasoning, use the `delegate` tool.

**Always delegate:**
- Complex questions, research, analysis
- All scheduled/cron tasks
- Strategic decisions, code review

**Respond directly (no delegation):**
- Simple greetings ("hi", "thanks")
- Acknowledgments ("ok", "got it")
- Relaying delegate results to the user

tool:delegate args={'task': 'Analyze the rubyclaw codebase...'}
Delegation completed (1735 chars)