Files
mcpctl/stack/claude-vllm

179 lines
8.0 KiB
Plaintext
Raw Normal View History

feat(claude): claude-vllm — run Claude Code against the homelab LLM gateway The gateway at llm.ad.itaz.eu is LiteLLM in front of vLLM, and LiteLLM already serves the Anthropic Messages API on /v1/messages — verified with a real completion. So Claude Code needs no bridge: pointing ANTHROPIC_BASE_URL at it is the whole integration. `claude-vllm` exists only to stop you pasting four exports each time. It reuses what another agent is already configured with — ~/.pi/agent, ~/.prime/agent, then opencode's config, first hit wins — taking the base URL and the credential from the same source so one gateway's URL is never paired with another's key. Beyond the obvious ANTHROPIC_* vars it sets two that are easy to miss: - ANTHROPIC_SMALL_FAST_MODEL / ANTHROPIC_DEFAULT_HAIKU_MODEL, or the background and summarisation calls ask the gateway for a real Haiku it does not serve and every one 404s; - CLAUDE_CODE_MAX_CONTEXT_TOKENS from the provider's declared contextWindow, because Claude Code assumes 200k for models it has no table for — and deepseek-v4-* is 393k, so it would auto-compact at half capacity. On `claude-mcpctl`: mcpctl's LLM layer is a client, not a server. mcpd serves /api/v1/llms (management) and its adapters call out to providers for gating, prompt selection and agent chat; nothing serves /v1/messages. Routing Claude through mcpctl would mean adding an Anthropic-shaped passthrough that re-wraps LiteLLM — worth doing only if mcpctl in the LLM path buys something of its own (per-project gating of model calls, prompt audit, budgets), which is a mcpd endpoint rather than a wrapper script. Verified: `claude-vllm --model deepseek-v4-fast -- -p "..."` completes against deepseek on the homelab, with the unknown-model context warning gone. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BVwuCjuMoA13gmzYEfcrNP
2026-08-09 18:39:36 +01:00
#!/usr/bin/env bash
# claude-vllm — run Claude Code against the homelab LLM gateway instead of api.anthropic.com.
#
# The gateway (LiteLLM in front of vLLM) already speaks the Anthropic Messages
# API on /v1/messages, so no bridge or translation layer is needed — Claude Code
# talks to it directly once ANTHROPIC_BASE_URL points there. This script exists
# only to find the endpoint, credential and model you have already configured
# for another agent, instead of making you paste four exports every time.
#
# Discovery order (first hit wins, per field):
# 1. environment already set (ANTHROPIC_BASE_URL / ANTHROPIC_AUTH_TOKEN / ANTHROPIC_MODEL)
# 2. flags (--provider, --model)
# 3. ~/.pi/agent settings.json + models.json + auth.json
# 4. ~/.prime/agent settings.json + models.json + auth.json
# 5. ~/.config/opencode/opencode.jsonc (provider.<name>.options.{baseURL,apiKey})
#
# Usage:
# claude-vllm # default provider + model, then exec claude
# claude-vllm --model deepseek-v4-max
# claude-vllm --provider itaz --model deepseek-v4-fast -- -p "summarise this repo"
# claude-vllm --list # show discoverable providers/models and exit
# claude-vllm --print-env # print the exports and exit (don't run claude)
set -euo pipefail
PROVIDER=""
MODEL=""
LIST=0
PRINT_ENV=0
CLAUDE_ARGS=()
while [ $# -gt 0 ]; do
case "$1" in
--provider) PROVIDER="${2:?--provider needs a value}"; shift 2 ;;
--model) MODEL="${2:?--model needs a value}"; shift 2 ;;
--list) LIST=1; shift ;;
--print-env) PRINT_ENV=1; shift ;;
-h|--help) sed -n '2,25p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
--) shift; CLAUDE_ARGS+=("$@"); break ;;
*) CLAUDE_ARGS+=("$1"); shift ;;
esac
done
command -v jq >/dev/null || { echo "claude-vllm: jq is required" >&2; exit 1; }
PI_HOME="${PI_AGENT_HOME:-$HOME/.pi/agent}"
PRIME_HOME="${PRIME_AGENT_HOME:-$HOME/.prime/agent}"
OC_CONFIG="${XDG_CONFIG_HOME:-$HOME/.config}/opencode/opencode.jsonc"
# jq tolerates the // comments opencode.jsonc may contain only after we strip
# them; harmless for strict JSON.
read_json() { [ -f "$1" ] && sed 's://[^"]*$::' "$1" | jq -c . 2>/dev/null || echo '{}'; }
# ── discover ─────────────────────────────────────────────────────────────────
# Each agent home is tried in turn; the first one that yields a base URL wins,
# and the credential is taken from that same home so we never pair one gateway's
# URL with another's key.
discover_from_agent_home() {
local home="$1" settings models auth provider base key model
settings=$(read_json "$home/settings.json")
models=$(read_json "$home/models.json")
auth=$(read_json "$home/auth.json")
provider="$PROVIDER"
[ -n "$provider" ] || provider=$(jq -r '.defaultProvider // empty' <<<"$settings")
[ -n "$provider" ] || return 1
base=$(jq -r --arg p "$provider" '.providers[$p].baseUrl // empty' <<<"$models")
[ -n "$base" ] || return 1
# `apiKey` in models.json names an env var; the secret itself lives in auth.json.
key=$(jq -r --arg p "$provider" '.[$p].key // empty' <<<"$auth")
model="$MODEL"
[ -n "$model" ] || model=$(jq -r '.defaultModel // empty' <<<"$settings")
FOUND_PROVIDER="$provider"; FOUND_BASE="$base"; FOUND_KEY="$key"; FOUND_MODEL="$model"
FOUND_MODELS=$(jq -r --arg p "$provider" '.providers[$p].models[]?.id' <<<"$models")
FOUND_CONTEXT=$(jq -r --arg p "$provider" --arg m "$model" \
'.providers[$p].models[]? | select(.id==$m) | .contextWindow // empty' <<<"$models")
FOUND_SOURCE="$home"
return 0
}
discover_from_opencode() {
local cfg provider base key
cfg=$(read_json "$OC_CONFIG")
provider="$PROVIDER"
if [ -z "$provider" ]; then
provider=$(jq -r '(.model // "") | split("/")[0] // empty' <<<"$cfg")
fi
[ -n "$provider" ] || return 1
base=$(jq -r --arg p "$provider" '.provider[$p].options.baseURL // empty' <<<"$cfg")
[ -n "$base" ] || return 1
key=$(jq -r --arg p "$provider" '.provider[$p].options.apiKey // empty' <<<"$cfg")
FOUND_PROVIDER="$provider"; FOUND_BASE="$base"; FOUND_KEY="$key"
FOUND_MODEL="${MODEL:-$(jq -r '(.model // "") | split("/")[1] // empty' <<<"$cfg")}"
FOUND_MODELS=$(jq -r --arg p "$provider" '.provider[$p].models | keys[]?' <<<"$cfg")
FOUND_CONTEXT=$(jq -r --arg p "$provider" --arg m "$FOUND_MODEL" \
'.provider[$p].models[$m].limit.context // empty' <<<"$cfg")
FOUND_SOURCE="$OC_CONFIG"
return 0
}
FOUND_PROVIDER=""; FOUND_BASE=""; FOUND_KEY=""; FOUND_MODEL=""; FOUND_MODELS=""; FOUND_CONTEXT=""; FOUND_SOURCE=""
discover_from_agent_home "$PI_HOME" \
|| discover_from_agent_home "$PRIME_HOME" \
|| discover_from_opencode \
|| true
BASE="${ANTHROPIC_BASE_URL:-$FOUND_BASE}"
KEY="${ANTHROPIC_AUTH_TOKEN:-${ANTHROPIC_API_KEY:-$FOUND_KEY}}"
MODEL_ID="${MODEL:-${ANTHROPIC_MODEL:-$FOUND_MODEL}}"
if [ "$LIST" = 1 ]; then
echo "provider: ${FOUND_PROVIDER:-<none found>} (from ${FOUND_SOURCE:-nowhere})"
echo "endpoint: ${BASE:-<none found>}"
echo "credential: $([ -n "$KEY" ] && echo "found (${KEY:0:10}…)" || echo "<none found>")"
echo "default model: ${MODEL_ID:-<none>}${FOUND_CONTEXT:+ (context ${FOUND_CONTEXT})}"
echo "models:"
[ -n "$FOUND_MODELS" ] && printf ' %s\n' $FOUND_MODELS || echo " <none listed>"
exit 0
fi
if [ -z "$BASE" ]; then
echo "claude-vllm: no LLM endpoint found." >&2
echo " Looked in $PI_HOME, $PRIME_HOME and $OC_CONFIG." >&2
echo " Set ANTHROPIC_BASE_URL, or configure a provider in one of those." >&2
exit 1
fi
if [ -z "$KEY" ]; then
echo "claude-vllm: found $BASE but no credential for '${FOUND_PROVIDER}'." >&2
echo " Set ANTHROPIC_AUTH_TOKEN, or add the key to ${FOUND_SOURCE}/auth.json." >&2
exit 1
fi
# Claude Code appends /v1/messages itself, so the stored provider baseUrl's
# trailing /v1 (an OpenAI-style base) has to come off or requests go to
# /v1/v1/messages.
BASE="${BASE%/}"; BASE="${BASE%/v1}"
export ANTHROPIC_BASE_URL="$BASE"
# Both forms: the gateway accepts either, and which one Claude Code sends has
# changed between releases (Authorization: Bearer vs x-api-key).
export ANTHROPIC_AUTH_TOKEN="$KEY"
export ANTHROPIC_API_KEY="$KEY"
[ -n "$MODEL_ID" ] && export ANTHROPIC_MODEL="$MODEL_ID"
# Without a substitute, the background/summarisation calls ask the gateway for a
# real Haiku it does not serve, and every one of them 404s.
export ANTHROPIC_SMALL_FAST_MODEL="${ANTHROPIC_SMALL_FAST_MODEL:-${CLAUDE_VLLM_FAST_MODEL:-$MODEL_ID}}"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="${ANTHROPIC_DEFAULT_HAIKU_MODEL:-$ANTHROPIC_SMALL_FAST_MODEL}"
# Claude Code only knows the context window of models it ships a table for, and
# assumes 200k for anything else — so a 393k model would auto-compact at half
# its capacity. Tell it the real number when the provider config states one.
if [ -n "${FOUND_CONTEXT:-}" ] && [ -z "${CLAUDE_CODE_MAX_CONTEXT_TOKENS:-}" ]; then
export CLAUDE_CODE_MAX_CONTEXT_TOKENS="$FOUND_CONTEXT"
fi
# Beta headers the gateway does not implement make it reject otherwise fine
# requests.
export CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS="${CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS:-1}"
# Stops Claude Code phoning home about a non-Anthropic endpoint.
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC="${CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC:-1}"
if [ "$PRINT_ENV" = 1 ]; then
for v in ANTHROPIC_BASE_URL ANTHROPIC_MODEL ANTHROPIC_SMALL_FAST_MODEL \
ANTHROPIC_DEFAULT_HAIKU_MODEL CLAUDE_CODE_MAX_CONTEXT_TOKENS \
CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS \
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC; do
[ -n "${!v:-}" ] || continue
printf 'export %s=%q\n' "$v" "${!v}"
done
# Never printed: the credential. Use --list to confirm one was found.
echo 'export ANTHROPIC_AUTH_TOKEN=<redacted> # and ANTHROPIC_API_KEY'
exit 0
fi
command -v claude >/dev/null || { echo "claude-vllm: claude is not on PATH" >&2; exit 1; }
echo "claude-vllm: ${FOUND_PROVIDER:-custom} · ${ANTHROPIC_MODEL:-<gateway default>} · $ANTHROPIC_BASE_URL" >&2
exec claude "${CLAUDE_ARGS[@]}"