jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-11-07 05:32:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix(cookbook): recover from stale llama-server shims

Browse Source 
Reconcile Odysseus-owned Python compatibility shims when llama_cpp.server is no longer available, allowing healthy native llama-server binaries in PATH to be discovered and executed without shadowing.

Fixes #6079
This commit is contained in:
Alexandre Teixeira
2026-08-17 00:59:13 +01:00
parent 517946d778
commit a7c03f85bf
3 changed files with 648 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
routes/cookbook_helpers.py
+127
View File
@@ -1030,6 +1030,133 @@ def _append_llama_cpp_linux_accel_build_lines(runner_lines: list[str]) -> None:
runner_lines.append(' fi # end _odysseus_have_prebuilt guard')
ODYSSEUS_LLAMA_SHIM_MARKER = "# Auto-generated by Odysseus Cookbook: a `llama-server` lookalike"
def _append_llama_server_shim_definition_lines(runner_lines: list[str]) -> None:
"""Define the helper shell function that generates the Odysseus compatibility shim."""
marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
runner_lines.append('_odysseus_create_llama_shim() {')
runner_lines.append(' local _target="$HOME/bin/llama-server"')
runner_lines.append(f' local _marker={marker}')
runner_lines.append(' if [ -e "$_target" ] || [ -L "$_target" ]; then')
runner_lines.append(' if [ -f "$_target" ] && [ ! -L "$_target" ] && grep -Fxq "$_marker" "$_target" 2>/dev/null; then')
runner_lines.append(' : # existing Odysseus shim — safe to replace')
runner_lines.append(' else')
runner_lines.append(' echo "[odysseus] WARNING: $_target already exists and is not an Odysseus-managed shim; leaving untouched." >&2')
runner_lines.append(' return 1')
runner_lines.append(' fi')
runner_lines.append(' fi')
runner_lines.append(' mkdir -p "$HOME/bin" || return 1')
runner_lines.append(' local _tmp')
runner_lines.append(' _tmp="$(mktemp "$HOME/bin/.llama-server.odysseus.tmp.XXXXXX")" || {')
runner_lines.append(' echo "[odysseus] ERROR: unable to create secure temporary llama-server shim in $HOME/bin" >&2')
runner_lines.append(' return 1')
runner_lines.append(' }')
runner_lines.append(" if ! cat > \"$_tmp\" <<'_ODY_LLAMA_SHIM_EOF'")
runner_lines.append('#!/usr/bin/env bash')
runner_lines.append(ODYSSEUS_LLAMA_SHIM_MARKER)
runner_lines.append('# that translates the native CLI to `python -m llama_cpp.server`.')
runner_lines.append('# Lets cookbook-generated launch commands run unchanged on hosts')
runner_lines.append('# where only the pip llama-cpp-python package is installed.')
runner_lines.append('ARGS=()')
runner_lines.append('while [ $# -gt 0 ]; do')
runner_lines.append(' case "$1" in')
runner_lines.append(' -ngl|--gpu-layers|--n-gpu-layers) ARGS+=(--n_gpu_layers "$2"); shift 2 ;;')
runner_lines.append(' -c|--ctx-size) ARGS+=(--n_ctx "$2"); shift 2 ;;')
runner_lines.append(' -b|--batch-size) ARGS+=(--n_batch "$2"); shift 2 ;;')
runner_lines.append(' -ub|--ubatch-size) shift 2 ;; # llama-cpp-python has no separate ubatch')
runner_lines.append(' --flash-attn) ARGS+=(--flash_attn true); shift 2 ;;')
runner_lines.append(' --cache-type-k) ARGS+=(--type_k "$2"); shift 2 ;;')
runner_lines.append(' --cache-type-v) ARGS+=(--type_v "$2"); shift 2 ;;')
runner_lines.append(' --n-cpu-moe) ARGS+=(--n_cpu_moe "$2"); shift 2 ;;')
runner_lines.append(' --mmproj) ARGS+=(--clip_model_path "$2"); shift 2 ;;')
runner_lines.append(' --image-max-tokens) shift 2 ;; # native-only')
runner_lines.append(' --no-mmap) ARGS+=(--no_mmap true); shift ;;')
runner_lines.append(' --no-warmup) shift ;; # native-only')
runner_lines.append(' --chat-template) ARGS+=(--chat_format "$2"); shift 2 ;;')
runner_lines.append(' --fit|--split-mode|--tensor-split|--main-gpu|--parallel) shift 2 ;; # native-only')
runner_lines.append(' --mlock) ARGS+=(--use_mlock true); shift ;;')
runner_lines.append(' *) ARGS+=("$1"); shift ;;')
runner_lines.append(' esac')
runner_lines.append('done')
runner_lines.append('exec python3 -m llama_cpp.server "${ARGS[@]}"')
runner_lines.append('_ODY_LLAMA_SHIM_EOF')
runner_lines.append(' then')
runner_lines.append(' rm -f -- "$_tmp"')
runner_lines.append(' return 1')
runner_lines.append(' fi')
runner_lines.append(' chmod +x "$_tmp" || { rm -f -- "$_tmp"; return 1; }')
runner_lines.append(' mv -f -- "$_tmp" "$_target" || { rm -f -- "$_tmp"; return 1; }')
runner_lines.append(' hash -r')
runner_lines.append(' echo "[odysseus] Created llama-server shim → python -m llama_cpp.server (no native binary needed)"')
runner_lines.append('}')
def _append_llama_server_shim_reconciliation_lines(runner_lines: list[str]) -> None:
"""Reconcile an existing ~/bin/llama-server if it is owned by Odysseus Cookbook.
Invariants:
- Never touch an arbitrary user-owned executable or symlink.
- If ~/bin/llama-server is an Odysseus generated shim:
- If a native llama-server is present and healthy elsewhere on PATH, remove the shim
so the native binary is used.
- If python3 -m llama_cpp.server is unavailable, remove the stale shim
and hash -r so the fallback/build path is triggered.
- If no healthy native server exists and llama_cpp.server is working, preserve it.
"""
marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
runner_lines.append('[ -r ~/.config/odysseus-llama-cpp-env ] && . ~/.config/odysseus-llama-cpp-env')
runner_lines.append(f'if [ -f "$HOME/bin/llama-server" ] && [ ! -L "$HOME/bin/llama-server" ] && grep -Fxq {marker} "$HOME/bin/llama-server" 2>/dev/null; then')
runner_lines.append(' _odysseus_has_native=""')
runner_lines.append(' _odysseus_saved_ifs="$IFS"')
runner_lines.append(' IFS=\':\'')
runner_lines.append(' read -r -a _odysseus_path_parts <<< "$PATH"')
runner_lines.append(' IFS="$_odysseus_saved_ifs"')
runner_lines.append(' for _dir in "${_odysseus_path_parts[@]}"; do')
runner_lines.append(' [ -n "$_dir" ] || continue')
runner_lines.append(' case "$_dir" in')
runner_lines.append(' "$HOME/bin"|"$HOME/bin/") continue ;;')
runner_lines.append(' esac')
runner_lines.append(' _candidate="$_dir/llama-server"')
runner_lines.append(' if [ -x "$_candidate" ] && "$_candidate" --version >/dev/null 2>&1; then')
runner_lines.append(' _odysseus_has_native=1')
runner_lines.append(' break')
runner_lines.append(' fi')
runner_lines.append(' done')
runner_lines.append(' if [ -n "$_odysseus_has_native" ]; then')
runner_lines.append(' echo "[odysseus] Native llama-server detected — retiring Odysseus compatibility shim in ~/bin"')
runner_lines.append(' rm -f "$HOME/bin/llama-server"')
runner_lines.append(' hash -r')
runner_lines.append(' elif ! python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' echo "[odysseus] Removing stale Odysseus llama-server shim (python3 -m llama_cpp.server unavailable)"')
runner_lines.append(' rm -f "$HOME/bin/llama-server"')
runner_lines.append(' hash -r')
runner_lines.append(' fi')
runner_lines.append('fi')
def _append_llama_server_finalization_lines(runner_lines: list[str], platform_hint: str = "") -> None:
"""Reconcile post-install launcher availability and enforce fail-closed invariant.
Guarantees that if python3 -m llama_cpp.server is usable but the `llama-server`
command is unresolvable, the compatibility launcher is created. If no usable
launcher exists after all build/install attempts, sets ODYSSEUS_PREFLIGHT_EXIT=127.
"""
err_msg = (
f"ERROR: llama.cpp serving is not available on {platform_hint} after install attempts."
if platform_hint
else "ERROR: llama.cpp serving is not available after install/build attempts."
)
runner_lines.append('if ! command -v llama-server >/dev/null 2>&1 && python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' _odysseus_create_llama_shim')
runner_lines.append('fi')
runner_lines.append('if ! command -v llama-server &>/dev/null; then')
runner_lines.append(f' echo "{err_msg}"')
runner_lines.append(' ODYSSEUS_PREFLIGHT_EXIT=127')
runner_lines.append('fi')
def _llama_cpp_rebuild_cmd(update_source: bool = False) -> str:
"""Shell command that clears the Cookbook-managed llama.cpp build.