feat(claude-vllm): own config file instead of reading opencode's

claude-vllm read `~/.config/opencode/opencode.jsonc` directly. Same shape is
useful; sharing the actual file is not — a credential rotation in opencode would
silently change what Claude Code authenticates with, and it couples two tools'
configs for no reason.

It now has its own `$XDG_CONFIG_HOME/mcpctl/claude-vllm.jsonc`, shaped like
opencode's (`provider.<name>.options.{baseURL,apiKey}` plus a `models` map), and
takes priority. The pi and prime-agent homes stay as a fallback so the command
works before any config exists; reading opencode's file is dropped.

No key is stored in the tool. `apiKey` may be a literal in the 0600 file,
`${ENV_VAR}`, or a bare env var NAME (the form pi's models.json already uses),
so the secret can live in the environment instead of on disk. `--init` reads it
from stdin when `--api-key` is omitted — keeping it out of shell history and out
of the process table, where an argument is visible to every user via `ps`.
`--list` prints at most a 10-character prefix.

`--init` records the context window for every model it can see, not just the
active one: recording only the default meant `--model something-else` silently
fell back to Claude Code's assumed 200k on a 393k model.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BVwuCjuMoA13gmzYEfcrNP
This commit is contained in:
Michal
2026-08-09 20:07:07 +01:00
parent 888b72b26c
commit 80fa8a3c7e
3 changed files with 163 additions and 27 deletions

View File

@@ -258,15 +258,17 @@ The homelab gateway (LiteLLM in front of vLLM) already serves the Anthropic
Messages API, so Claude Code can talk to it directly — no bridge: Messages API, so Claude Code can talk to it directly — no bridge:
```bash ```bash
claude-vllm # reuse the provider/model/key pi or prime-agent already uses claude-vllm --init # write ~/.config/mcpctl/claude-vllm.jsonc (0600)
claude-vllm # use it
claude-vllm --model deepseek-v4-max claude-vllm --model deepseek-v4-max
claude-vllm --list # show what it would use claude-vllm --list # show what it would use
claude-vllm -- -p "summarise this repo" # args after -- go to claude claude-vllm -- -p "summarise this repo" # args after -- go to claude
``` ```
It discovers the endpoint, credential, model and context window from It reads its own config (shaped like `opencode.jsonc`, but a separate file),
`~/.pi/agent`, `~/.prime/agent` or opencode's config (first hit wins) and sets falling back to `~/.pi/agent` or `~/.prime/agent` so it works before you have
the `ANTHROPIC_*` environment Claude Code needs. written one. The key may be a literal in the 0600 file, `${ENV_VAR}`, or an env
var name — it is never stored in the tool.
See [docs/claude-vllm.md](docs/claude-vllm.md), including why routing this See [docs/claude-vllm.md](docs/claude-vllm.md), including why routing this
through mcpctl would add surface without adding capability. through mcpctl would add surface without adding capability.

View File

@@ -43,21 +43,60 @@ sake: per-project gating of model calls, audit of prompts, or budget
enforcement. Those are real features, but they are a passthrough endpoint in enforcement. Those are real features, but they are a passthrough endpoint in
mcpd, not a wrapper script. mcpd, not a wrapper script.
## What it discovers, and from where ## Its own config
`claude-vllm` exists only so you don't paste four exports each time. It reuses ```bash
whatever you already configured for another agent — first hit wins: claude-vllm --init # prompts for the key, writes 0600
claude-vllm --init --api-key '${MY_KEY}' # keep the secret in the environment instead
claude-vllm --init --base-url https://other-gateway/v1
```
Written to `$XDG_CONFIG_HOME/mcpctl/claude-vllm.jsonc` (`~/.config/…`), shaped
like `opencode.jsonc` — a `provider` map with `options.baseURL` /
`options.apiKey` and a `models` map:
```jsonc
{
"model": "itaz/deepseek-v4-think",
"provider": {
"itaz": {
"options": { "baseURL": "https://llm.ad.itaz.eu/v1", "apiKey": "${MY_LLM_KEY}" },
"models": { "deepseek-v4-fast": { "limit": { "context": 393216 } } }
}
}
}
```
**Same shape as opencode's config, but a separate file.** Reading opencode's own
config would mean a credential rotation there silently changing what Claude Code
authenticates with, and would couple two tools' configs for no reason.
### Keys are never stored in the tool
`apiKey` may be a literal (in a 0600 file), `${ENV_VAR}`, or a bare env var
NAME — so the secret can live in your environment or a password manager instead
of on disk. `--init` reads the key from **stdin** when `--api-key` is omitted,
keeping it out of shell history and out of the process table, where `--api-key`
would be visible to every user via `ps`. `--list` never prints more than a
10-character prefix.
### Discovery order
| Order | Source | Supplies | | Order | Source | Supplies |
|-------|--------|----------| |-------|--------|----------|
| 1 | environment (`ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN`, `ANTHROPIC_MODEL`) | anything already set is respected | | 1 | environment (`ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN`, `ANTHROPIC_MODEL`) | anything already set is respected |
| 2 | `--provider` / `--model` flags | provider, model | | 2 | `--provider` / `--model` flags | provider, model |
| 3 | `~/.pi/agent` | `settings.json` → default provider/model · `models.json` → base URL, context window · `auth.json` → key | | 3 | `~/.config/mcpctl/claude-vllm.jsonc` | its own config |
| 4 | `~/.prime/agent` | same shape | | 4 | `~/.pi/agent` | `settings.json` → default provider/model · `models.json` → base URL, context windows · `auth.json` → key |
| 5 | `~/.config/opencode/opencode.jsonc` | `provider.<name>.options.{baseURL,apiKey}` | | 5 | `~/.prime/agent` | same shape |
The base URL and the credential always come from the *same* source, so one The pi/prime homes remain a convenience fallback so `claude-vllm` works before
gateway's URL is never paired with another's key. you have written a config at all. The base URL and the credential always come
from the *same* source, so one gateway's URL is never paired with another's key.
`--init` records the context window for **every** model it can see, not just the
active one — otherwise `--model something-else` silently falls back to Claude
Code's assumed 200k.
## What it sets, and why each one ## What it sets, and why each one

View File

@@ -10,22 +10,37 @@
# Discovery order (first hit wins, per field): # Discovery order (first hit wins, per field):
# 1. environment already set (ANTHROPIC_BASE_URL / ANTHROPIC_AUTH_TOKEN / ANTHROPIC_MODEL) # 1. environment already set (ANTHROPIC_BASE_URL / ANTHROPIC_AUTH_TOKEN / ANTHROPIC_MODEL)
# 2. flags (--provider, --model) # 2. flags (--provider, --model)
# 3. ~/.pi/agent settings.json + models.json + auth.json # 3. its own config: $XDG_CONFIG_HOME/mcpctl/claude-vllm.jsonc (~/.config/...)
# 4. ~/.prime/agent settings.json + models.json + auth.json # 4. ~/.pi/agent settings.json + models.json + auth.json
# 5. ~/.config/opencode/opencode.jsonc (provider.<name>.options.{baseURL,apiKey}) # 5. ~/.prime/agent settings.json + models.json + auth.json
#
# The config file is shaped like opencode's — a `provider` map with
# `options.baseURL` / `options.apiKey` and a `models` map — but it is OUR file.
# Reading opencode's own config would mean a credential rotation there silently
# changing what Claude Code authenticates with, and would tie two tools' configs
# together for no reason. The pi/prime homes remain as a convenience fallback so
# `claude-vllm` works before you have written a config at all.
#
# NO KEY IS EVER STORED IN THIS SCRIPT. `apiKey` may be a literal (in a 0600
# config), or `\${ENV_VAR}` / a bare env var NAME, so the secret can live in your
# environment or a password manager instead of on disk.
# #
# Usage: # Usage:
# claude-vllm # default provider + model, then exec claude # claude-vllm # default provider + model, then exec claude
# claude-vllm --model deepseek-v4-max # claude-vllm --model deepseek-v4-max
# claude-vllm --provider itaz --model deepseek-v4-fast -- -p "summarise this repo" # claude-vllm --provider itaz --model deepseek-v4-fast -- -p "summarise this repo"
# claude-vllm --list # show discoverable providers/models and exit # claude-vllm --list # show what it would use (never prints the key)
# claude-vllm --print-env # print the exports and exit (don't run claude) # claude-vllm --print-env # print the exports and exit (don't run claude)
# claude-vllm --init --api-key ... # write the config file (0600); reads stdin if omitted
set -euo pipefail set -euo pipefail
PROVIDER="" PROVIDER=""
MODEL="" MODEL=""
LIST=0 LIST=0
INIT=0
PRINT_ENV=0 PRINT_ENV=0
API_KEY_ARG=""
BASE_URL_ARG=""
CLAUDE_ARGS=() CLAUDE_ARGS=()
while [ $# -gt 0 ]; do while [ $# -gt 0 ]; do
@@ -33,6 +48,9 @@ while [ $# -gt 0 ]; do
--provider) PROVIDER="${2:?--provider needs a value}"; shift 2 ;; --provider) PROVIDER="${2:?--provider needs a value}"; shift 2 ;;
--model) MODEL="${2:?--model needs a value}"; shift 2 ;; --model) MODEL="${2:?--model needs a value}"; shift 2 ;;
--list) LIST=1; shift ;; --list) LIST=1; shift ;;
--init) INIT=1; shift ;;
--api-key) API_KEY_ARG="${2:?--api-key needs a value}"; shift 2 ;;
--base-url) BASE_URL_ARG="${2:?--base-url needs a value}"; shift 2 ;;
--print-env) PRINT_ENV=1; shift ;; --print-env) PRINT_ENV=1; shift ;;
-h|--help) sed -n '2,25p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;; -h|--help) sed -n '2,25p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
--) shift; CLAUDE_ARGS+=("$@"); break ;; --) shift; CLAUDE_ARGS+=("$@"); break ;;
@@ -44,12 +62,27 @@ command -v jq >/dev/null || { echo "claude-vllm: jq is required" >&2; exit 1; }
PI_HOME="${PI_AGENT_HOME:-$HOME/.pi/agent}" PI_HOME="${PI_AGENT_HOME:-$HOME/.pi/agent}"
PRIME_HOME="${PRIME_AGENT_HOME:-$HOME/.prime/agent}" PRIME_HOME="${PRIME_AGENT_HOME:-$HOME/.prime/agent}"
OC_CONFIG="${XDG_CONFIG_HOME:-$HOME/.config}/opencode/opencode.jsonc" CONFIG="${CLAUDE_VLLM_CONFIG:-${XDG_CONFIG_HOME:-$HOME/.config}/mcpctl/claude-vllm.jsonc}"
# jq tolerates the // comments opencode.jsonc may contain only after we strip # jq tolerates the // comments opencode.jsonc may contain only after we strip
# them; harmless for strict JSON. # them; harmless for strict JSON.
read_json() { [ -f "$1" ] && sed 's://[^"]*$::' "$1" | jq -c . 2>/dev/null || echo '{}'; } read_json() { [ -f "$1" ] && sed 's://[^"]*$::' "$1" | jq -c . 2>/dev/null || echo '{}'; }
# Resolve an apiKey field that may be a literal, \${ENV_VAR}, or a bare env var
# NAME (the form pi's models.json uses). Keeping the indirection means the
# secret can live in the environment rather than on disk.
resolve_key() {
local raw="$1"
[ -n "$raw" ] || return 0
case "$raw" in
'${'*'}') local n="${raw#\$\{}"; n="${n%\}}"; printf '%s' "${!n:-}" ;;
# A bare ALL_CAPS token that names a set variable is an env var reference,
# not a key: no real API key looks like that.
[A-Z_][A-Z0-9_]*) if [ -n "${!raw:-}" ]; then printf '%s' "${!raw}"; else printf '%s' "$raw"; fi ;;
*) printf '%s' "$raw" ;;
esac
}
# ── discover ───────────────────────────────────────────────────────────────── # ── discover ─────────────────────────────────────────────────────────────────
# Each agent home is tried in turn; the first one that yields a base URL wins, # Each agent home is tried in turn; the first one that yields a base URL wins,
# and the credential is taken from that same home so we never pair one gateway's # and the credential is taken from that same home so we never pair one gateway's
@@ -74,45 +107,107 @@ discover_from_agent_home() {
FOUND_PROVIDER="$provider"; FOUND_BASE="$base"; FOUND_KEY="$key"; FOUND_MODEL="$model" FOUND_PROVIDER="$provider"; FOUND_BASE="$base"; FOUND_KEY="$key"; FOUND_MODEL="$model"
FOUND_MODELS=$(jq -r --arg p "$provider" '.providers[$p].models[]?.id' <<<"$models") FOUND_MODELS=$(jq -r --arg p "$provider" '.providers[$p].models[]?.id' <<<"$models")
# model -> context for ALL models, so --init records every limit rather than
# only the active one (Claude Code assumes 200k for anything it lacks).
FOUND_MODEL_LIMITS=$(jq -c --arg p "$provider" \
'[.providers[$p].models[]? | select(.contextWindow) | {(.id): {limit:{context:.contextWindow}}}] | add // {}' <<<"$models")
FOUND_CONTEXT=$(jq -r --arg p "$provider" --arg m "$model" \ FOUND_CONTEXT=$(jq -r --arg p "$provider" --arg m "$model" \
'.providers[$p].models[]? | select(.id==$m) | .contextWindow // empty' <<<"$models") '.providers[$p].models[]? | select(.id==$m) | .contextWindow // empty' <<<"$models")
FOUND_SOURCE="$home" FOUND_SOURCE="$home"
return 0 return 0
} }
discover_from_opencode() { # Our own config, shaped like opencode's but deliberately a separate file.
discover_from_config() {
local cfg provider base key local cfg provider base key
cfg=$(read_json "$OC_CONFIG") [ -f "$CONFIG" ] || return 1
cfg=$(read_json "$CONFIG")
provider="$PROVIDER" provider="$PROVIDER"
if [ -z "$provider" ]; then [ -n "$provider" ] || provider=$(jq -r '(.model // "") | split("/")[0] // empty' <<<"$cfg")
provider=$(jq -r '(.model // "") | split("/")[0] // empty' <<<"$cfg") [ -n "$provider" ] || provider=$(jq -r '.provider | keys[0] // empty' <<<"$cfg")
fi
[ -n "$provider" ] || return 1 [ -n "$provider" ] || return 1
base=$(jq -r --arg p "$provider" '.provider[$p].options.baseURL // empty' <<<"$cfg") base=$(jq -r --arg p "$provider" '.provider[$p].options.baseURL // empty' <<<"$cfg")
[ -n "$base" ] || return 1 [ -n "$base" ] || return 1
key=$(jq -r --arg p "$provider" '.provider[$p].options.apiKey // empty' <<<"$cfg") key=$(resolve_key "$(jq -r --arg p "$provider" '.provider[$p].options.apiKey // empty' <<<"$cfg")")
FOUND_PROVIDER="$provider"; FOUND_BASE="$base"; FOUND_KEY="$key" FOUND_PROVIDER="$provider"; FOUND_BASE="$base"; FOUND_KEY="$key"
FOUND_MODEL="${MODEL:-$(jq -r '(.model // "") | split("/")[1] // empty' <<<"$cfg")}" FOUND_MODEL="${MODEL:-$(jq -r '(.model // "") | split("/")[1] // empty' <<<"$cfg")}"
FOUND_MODELS=$(jq -r --arg p "$provider" '.provider[$p].models | keys[]?' <<<"$cfg") FOUND_MODELS=$(jq -r --arg p "$provider" '.provider[$p].models | keys[]?' <<<"$cfg")
FOUND_MODEL_LIMITS=$(jq -c --arg p "$provider" '.provider[$p].models // {}' <<<"$cfg")
FOUND_CONTEXT=$(jq -r --arg p "$provider" --arg m "$FOUND_MODEL" \ FOUND_CONTEXT=$(jq -r --arg p "$provider" --arg m "$FOUND_MODEL" \
'.provider[$p].models[$m].limit.context // empty' <<<"$cfg") '.provider[$p].models[$m].limit.context // empty' <<<"$cfg")
FOUND_SOURCE="$OC_CONFIG" FOUND_SOURCE="$CONFIG"
return 0 return 0
} }
FOUND_PROVIDER=""; FOUND_BASE=""; FOUND_KEY=""; FOUND_MODEL=""; FOUND_MODELS=""; FOUND_CONTEXT=""; FOUND_SOURCE="" FOUND_PROVIDER=""; FOUND_BASE=""; FOUND_KEY=""; FOUND_MODEL=""; FOUND_MODELS=""; FOUND_MODEL_LIMITS=""; FOUND_CONTEXT=""; FOUND_SOURCE=""
discover_from_agent_home "$PI_HOME" \ discover_from_config \
|| discover_from_agent_home "$PI_HOME" \
|| discover_from_agent_home "$PRIME_HOME" \ || discover_from_agent_home "$PRIME_HOME" \
|| discover_from_opencode \
|| true || true
# ── --init: write the config file ────────────────────────────────────────────
if [ "$INIT" = 1 ]; then
init_base="${BASE_URL_ARG:-${FOUND_BASE:-}}"
if [ -z "$init_base" ]; then
echo "claude-vllm --init: no endpoint known. Pass --base-url https://your-gateway/v1" >&2
exit 1
fi
init_key="$API_KEY_ARG"
if [ -z "$init_key" ]; then
# Read from stdin so the key never lands in shell history or the process
# table (where --api-key is visible to every user via `ps`).
if [ -t 0 ]; then
printf 'API key (input hidden, or pass ${ENV_VAR} to keep it out of the file): ' >&2
read -rs init_key; echo >&2
else
read -r init_key || true
fi
fi
[ -n "$init_key" ] || { echo "claude-vllm --init: no API key given" >&2; exit 1; }
init_provider="${PROVIDER:-${FOUND_PROVIDER:-default}}"
init_model="${MODEL:-${FOUND_MODEL:-}}"
# Every model's limit, not just the active one — switching with --model must
# not silently drop back to Claude Code's assumed 200k.
init_models_json=$(
if [ -n "$FOUND_MODELS" ]; then
known="${FOUND_MODEL_LIMITS:-{\}}"
for m in $FOUND_MODELS; do jq -n --arg m "$m" '{($m): {}}'; done \
| jq -s --argjson known "$known" 'add // {} | . * $known'
else
jq -n --arg m "$init_model" 'if $m == "" then {} else {($m): {}} end'
fi
)
mkdir -p "$(dirname "$CONFIG")"
umask 077
jq -n --arg p "$init_provider" --arg model "$init_model" --arg base "$init_base" \
--arg key "$init_key" --argjson models "$init_models_json" '
{
"//": "mcpctl claude-vllm config. Shaped like opencode.jsonc, but its own file. apiKey may be a literal, \"${ENV_VAR}\", or a bare env var NAME.",
model: (if $model == "" then null else "\($p)/\($model)" end),
provider: { ($p): { options: { baseURL: $base, apiKey: $key }, models: $models } }
} | del(..|nulls)' > "$CONFIG.tmp.$$"
mv "$CONFIG.tmp.$$" "$CONFIG"
chmod 600 "$CONFIG"
echo "Wrote $CONFIG (0600)" >&2
echo " provider: $init_provider endpoint: $init_base model: ${init_model:-<gateway default>}" >&2
case "$init_key" in
'${'*'}'|[A-Z_][A-Z0-9_]*) echo " apiKey: kept as an environment reference, not a literal" >&2 ;;
*) echo " apiKey: stored in the file — readable only by you" >&2 ;;
esac
exit 0
fi
BASE="${ANTHROPIC_BASE_URL:-$FOUND_BASE}" BASE="${ANTHROPIC_BASE_URL:-$FOUND_BASE}"
KEY="${ANTHROPIC_AUTH_TOKEN:-${ANTHROPIC_API_KEY:-$FOUND_KEY}}" KEY="${ANTHROPIC_AUTH_TOKEN:-${ANTHROPIC_API_KEY:-$FOUND_KEY}}"
MODEL_ID="${MODEL:-${ANTHROPIC_MODEL:-$FOUND_MODEL}}" MODEL_ID="${MODEL:-${ANTHROPIC_MODEL:-$FOUND_MODEL}}"
if [ "$LIST" = 1 ]; then if [ "$LIST" = 1 ]; then
echo "provider: ${FOUND_PROVIDER:-<none found>} (from ${FOUND_SOURCE:-nowhere})" echo "provider: ${FOUND_PROVIDER:-<none found>} (from ${FOUND_SOURCE:-nowhere})"
echo "config: $CONFIG $([ -f "$CONFIG" ] && echo '(present)' || echo '(absent — using fallback; run --init)')"
echo "endpoint: ${BASE:-<none found>}" echo "endpoint: ${BASE:-<none found>}"
echo "credential: $([ -n "$KEY" ] && echo "found (${KEY:0:10}…)" || echo "<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 "default model: ${MODEL_ID:-<none>}${FOUND_CONTEXT:+ (context ${FOUND_CONTEXT})}"