external-model-delegation

External Model Delegation Pattern

A UserPromptSubmit hook classifies every user prompt into one of six cost/performance tiers. The hook injects additionalContext instructing Claude to run a specific delegation script and return the output.

Tier routing table

Delegation script pattern

Each script is a self-contained executable in ~/bin/ that accepts a prompt and writes the response to stdout:

~/bin/
├── qwen3      # Shell: curl to local Ollama API
├── kimi       # Shell: execs Kimi CLI binary
├── deepseek   # Python: httpx to DeepSeek Anthropic-compat API
└── route-task # Shell + qwen3: classifies prompt into tier

Script contract

1. Accept prompt as first argument: qwen3 "what is 2+2"
2. Support --flash / --pro model flags (deepseek)
3. Support --quiet mode flag (kimi)
4. Write response to stdout, errors to stderr
5. Exit 0 on success, non-zero on error

Writing a new delegation script

#!/bin/bash
# Minimal delegator template
PROMPT="$1"
API_KEY="${EXTERNAL_API_KEY:-}"
# Call external API, write result to stdout
curl -s https://api.example.com/chat \
  -H "Authorization: Bearer $API_KEY" \
  -d "$(jq -n --arg p "$PROMPT" '{prompt: $p}')" \
  | jq -r '.response'

Routing hook flow

User types prompt
    ↓
UserPromptSubmit hook fires
    ↓
qwen3 classifies into tier (QWEN|DEEPSEEK_FLASH|DEEPSEEK_PRO|KIMI|CODEX|CLAUDE)
    ↓
Hook injects additionalContext: "Run: <delegation-command>"
    ↓
Claude reads context, spawns delegation script, returns output
    ↓
User sees response from the delegated model