Files
litellm/scripts/install.sh
T
Mateo Wang 20e453f698 feat(cli): per-agent lite claude / codex / opencode commands that wrap coding agents through the proxy (#29850)
* feat(cli): add `litellm-proxy run -- <agent>` to wrap coding agents through the proxy

Wraps Claude Code, Codex, OpenCode, and any other coding agent so all of its
LLM traffic routes through a LiteLLM proxy, with the agent-vault style of "just
works" DX: one `run -- <agent>` command, auto SSO login when interactive,
env-key "agent mode" for containers/CI, and a fail-fast key check against the
proxy so bad credentials error immediately instead of deep inside the agent.

The wrapped binary is detected by name to pick the right variables. Claude Code
gets ANTHROPIC_BASE_URL (the bare proxy root, so it appends /v1/messages) and
ANTHROPIC_AUTH_TOKEN, with any stray ANTHROPIC_API_KEY cleared so the proxy
token wins. Codex and OpenCode get OPENAI_BASE_URL (proxy + /v1) and
OPENAI_API_KEY. Unrecognized commands get both sets so they work either way.
`litellm-proxy claude-code` remains as a shortcut for `run -- claude`.

The core logic is split into dependency-injected helpers (agent_profile,
build_agent_env, verify_proxy_key, run_agent) so env wiring, the preflight, and
the launch handoff are unit-tested without monkeypatching, alongside CliRunner
tests for auth resolution, agent mode, and auto-login. Mutation-tested the env
profiles, preflight, and agent-mode branch to confirm the tests fail when the
behavior is broken.

https://claude.ai/code/session_0154VpLXW7mMvk5wfbgPRJa6

* Make each coding agent its own litellm-proxy command

Replace the `run -- <agent>` interface and the `claude-code` shortcut with
top-level commands generated per known agent, so launching is just
`litellm-proxy claude`, `litellm-proxy codex`, or `litellm-proxy opencode`,
with everything after the agent name forwarded straight to it. This drops the
ceremony of `run --` and cuts typing.

The `--model`/`--small-fast-model` wrapper flags are gone; pass the agent's
own model flag instead, or export the model env vars (the wrapper preserves
what you already have set), which keeps the surface minimal and avoids
intercepting flags the agent owns. Rename the module to agents.py to match.

* fix(cli): route `litellm-proxy codex` through the proxy via a custom provider

Codex ignores OPENAI_BASE_URL (it always dials api.openai.com over the
Responses WebSocket transport), so the OpenAI env profile alone left
`litellm-proxy codex` talking to OpenAI directly instead of the proxy. Point
Codex at the proxy with a custom provider passed as `-c` config overrides, and
force the HTTP/SSE Responses transport with supports_websockets=false since the
proxy does not speak the Responses WebSocket protocol. The provider reads its
key from OPENAI_API_KEY, which the agent env already exports.

The overrides are injected ahead of the user's args so they precede Codex's
subcommand. Claude Code and OpenCode are unaffected; they honor the exported
env vars. Adds regression tests for the per-agent launch args and the
injection ordering.

Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>

* Rename litellm-proxy CLI command to lite

The proxy management CLI was invoked as litellm-proxy, which is a lot to
type for an everyday command. Rename the console script entry point to
lite and update the in-CLI usage examples, help text, error messages and
docs to match.

* fix(sso): stop CLI auth success page from hanging on "Closing..."

The CLI opens the SSO success page with webbrowser.open, so the tab is
not script-opened and the browser refuses window.close(). The countdown
would end on "Closing..." and the tab would sit there forever.

Drop the countdown and just show "You can now close this window and
return to your terminal." from the start, while still attempting
window.close() once so the tab auto-closes in the rare case the browser
allows it. Add a regression test asserting the manual-close instruction
is always present and the misleading countdown/"Closing..." text is gone.

* fix(cli): reattach controlling terminal after SSO login, keep litellm-proxy alias

When the first `lite claude` has to log in via browser SSO, completing the login could
leave stdin detached from the terminal, so a TUI agent like Claude Code would start in
non-interactive mode and exit with "Input must be provided". The wrapper now reopens the
controlling terminal onto stdin just before handoff when the session started interactively;
piped or redirected input is detected up front and left alone, so agent-mode and
non-interactive use are unchanged.

Also keep the `litellm-proxy` console script as an alias for `lite` so existing scripts and
CI that invoke `litellm-proxy` keep working; both names map to the same CLI.

* feat(install): make the curl installer need only curl, not a pre-existing Python

The installer now lets uv provision a managed Python 3.13 when no suitable
interpreter is found, instead of aborting. The minimum is also bumped from
3.9 to 3.10 to match the package's requires-python (>=3.10), so a system
Python 3.9 is no longer selected only for uv tool install to reject it.

* feat(cli): add thin litellm[cli] install path (install-cli.sh + brew) for the lite CLI

On a developer laptop the `lite` CLI only needs `lite login` and running coding
agents through a proxy, but the sole install path was `litellm[proxy]`, which
drags in the whole server tree (fastapi, uvicorn, boto3, polars, cryptography,
litellm-enterprise). The CLI's heavy imports are all guarded, so it runs on the
base SDK plus just rich, pyyaml and requests.

Add a `cli` extra carrying exactly those three, a `scripts/install-cli.sh` curl
one-liner that installs `litellm[cli]`, and a `BerriAI/homebrew-litellm` tap
formula with a release runbook under `packaging/homebrew/`. The installer passes
no `--python`, so uv honours litellm's requires-python and provisions a managed
interpreter, skipping a too-old (3.9) or too-new (3.14+) system Python instead
of failing to resolve.

A pyproject thin-contract test asserts the `cli` extra keeps the deps the CLI
imports and never leaks a server-only dependency from `proxy`, so the laptop
install cannot silently re-bloat

* fix(install): let uv pick the Python via --python-preference system

Both installers detected a system Python with a floor-only check and forced it
with `uv tool install --python <interp>`. On a host whose only Python is outside
litellm's requires-python (a too-old 3.9 or, increasingly, a too-new 3.14) that
forced an incompatible interpreter and the resolve failed. Drop the detection and
pass `--python-preference system`: uv reuses a compatible system Python when
present and downloads a managed one otherwise, always honouring requires-python

* test(router): filter aiohttp unclosed-session gc noise in test_async_fallbacks

test_async_fallbacks asserts the last three captured log records are the
router's fallback messages. Under the litellm_router_testing job (pytest -k
router -n 4) many router tests share the module-level in_memory_llm_clients_cache
(max 200, ttl 3600s). Older cached OpenAI/Azure clients get evicted while their
aiohttp ClientSession is still open, and when the gc reclaims them aiohttp emits
"Unclosed client session"/"Unclosed connector" through the asyncio logger.
Those records land in caplog mid-test and push the expected router logs out of
the last-three window, so the assertion flips to failing non-deterministically.

These warnings are async cleanup noise, not router debug logs, so filter them
out exactly like the existing leaked-task warnings before asserting order. The
assertion on the three router fallback messages is unchanged.

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-06-10 13:52:26 -07:00

140 lines
6.4 KiB
Bash
Executable File

#!/usr/bin/env bash
# LiteLLM Installer
# Usage: curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh
#
# Needs only curl: uv is bootstrapped if missing, and uv provisions a compatible
# Python itself (reusing a suitable system one, else downloading a managed build).
#
# NOTE: set -e without pipefail for POSIX sh compatibility (dash on Ubuntu/Debian
# ignores the shebang when invoked as `sh` and does not support `pipefail`).
set -eu
# NOTE: before merging, this must stay as "litellm[proxy]" to install from PyPI.
LITELLM_PACKAGE="litellm[proxy]"
UV_VERSION="0.10.9"
# ── colours ────────────────────────────────────────────────────────────────
if [ -t 1 ]; then
BOLD='\033[1m'
GREEN='\033[38;2;78;186;101m'
GREY='\033[38;2;153;153;153m'
RESET='\033[0m'
else
BOLD='' GREEN='' GREY='' RESET=''
fi
info() { printf "${GREY} %s${RESET}\n" "$*"; }
success() { printf "${GREEN} ✔ %s${RESET}\n" "$*"; }
header() { printf "${BOLD} %s${RESET}\n" "$*"; }
die() { printf "\n Error: %s\n\n" "$*" >&2; exit 1; }
# ── banner ─────────────────────────────────────────────────────────────────
echo ""
cat << 'EOF'
██╗ ██╗████████╗███████╗██╗ ██╗ ███╗ ███╗
██║ ██║╚══██╔══╝██╔════╝██║ ██║ ████╗ ████║
██║ ██║ ██║ █████╗ ██║ ██║ ██╔████╔██║
██║ ██║ ██║ ██╔══╝ ██║ ██║ ██║╚██╔╝██║
███████╗██║ ██║ ███████╗███████╗███████╗██║ ╚═╝ ██║
╚══════╝╚═╝ ╚═╝ ╚══════╝╚══════╝╚══════╝╚═╝ ╚═╝
EOF
printf " ${BOLD}LiteLLM Installer${RESET} ${GREY}— unified gateway for 100+ LLM providers${RESET}\n\n"
# ── OS detection ───────────────────────────────────────────────────────────
OS="$(uname -s)"
ARCH="$(uname -m)"
case "$OS" in
Darwin) PLATFORM="macOS ($ARCH)" ;;
Linux) PLATFORM="Linux ($ARCH)" ;;
*) die "Unsupported OS: $OS. LiteLLM supports macOS and Linux." ;;
esac
info "Platform: $PLATFORM"
# ── uv detection / install ────────────────────────────────────────────────
UV_BIN=""
CURRENT_UV_VERSION=""
for candidate in uv "$HOME/.local/bin/uv"; do
if command -v "$candidate" >/dev/null 2>&1; then
UV_BIN="$(command -v "$candidate")"
break
elif [ -x "$candidate" ]; then
UV_BIN="$candidate"
break
fi
done
if [ -n "$UV_BIN" ]; then
CURRENT_UV_VERSION="$("$UV_BIN" --version 2>/dev/null | awk '{print $2}' | head -1 || true)"
fi
if [ -z "$UV_BIN" ] || [ "${CURRENT_UV_VERSION:-}" != "$UV_VERSION" ]; then
header "Installing uv…"
if [ -n "${CURRENT_UV_VERSION:-}" ]; then
info "Upgrading uv from ${CURRENT_UV_VERSION} to ${UV_VERSION}"
fi
curl -LsSf "https://astral.sh/uv/${UV_VERSION}/install.sh" | env UV_NO_MODIFY_PATH=1 sh \
|| die "uv installation failed. Try manually: curl -LsSf https://astral.sh/uv/${UV_VERSION}/install.sh | sh"
UV_BIN="$HOME/.local/bin/uv"
fi
# ── install ────────────────────────────────────────────────────────────────
echo ""
header "Installing litellm[proxy]…"
echo ""
# --python-preference system: reuse a compatible system Python when present,
# otherwise download a managed one. Either way uv honours litellm's requires-python,
# so a too-old (3.9) or too-new (3.14+) system Python is skipped, not forced.
"$UV_BIN" tool install --python-preference system --force "${LITELLM_PACKAGE}" \
|| die "uv tool install failed. Try manually: $UV_BIN tool install '${LITELLM_PACKAGE}'"
# ── find the litellm binary installed by uv tool ───────────────────────────
SCRIPTS_DIR="$("$UV_BIN" tool dir --bin)"
LITELLM_BIN="${SCRIPTS_DIR}/litellm"
if [ ! -x "$LITELLM_BIN" ]; then
die "litellm binary not found after install. Try: $UV_BIN tool install '${LITELLM_PACKAGE}'"
fi
# ── success banner ─────────────────────────────────────────────────────────
echo ""
success "LiteLLM installed"
installed_ver="$("$LITELLM_BIN" --version 2>&1 | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1 || true)"
[ -n "$installed_ver" ] && info "Version: $installed_ver"
# ── PATH hint ──────────────────────────────────────────────────────────────
if ! command -v litellm >/dev/null 2>&1; then
info "Note: add litellm to your PATH: export PATH=\"\$PATH:${SCRIPTS_DIR}\""
fi
# ── launch setup wizard ────────────────────────────────────────────────────
echo ""
printf " ${BOLD}Run the interactive setup wizard?${RESET} ${GREY}(Y/n)${RESET}: "
# /dev/tty may be unavailable in Docker/CI — default to yes if it can't be read
answer=""
if [ -r /dev/tty ]; then
read -r answer </dev/tty || answer=""
fi
if [ -z "$answer" ] || [ "$answer" = "y" ] || [ "$answer" = "Y" ]; then
echo ""
# Use /dev/tty for interactive input when available (stdin is a pipe from curl)
if [ -r /dev/tty ]; then
exec "$LITELLM_BIN" --setup </dev/tty
else
exec "$LITELLM_BIN" --setup
fi
else
echo ""
header "Quick start:"
echo ""
info " litellm --setup # interactive wizard"
info " litellm --model gpt-4o # single-model quickstart"
echo ""
info "Docs: https://docs.litellm.ai"
echo ""
fi