jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-11-05 12:42:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix(cookbook): launch validated llama-server candidate and handle PATH precedence

Browse Source 
Ensure the native candidate that passed the health check is prioritized and executed when an earlier broken candidate exists on PATH.

Reconcile Odysseus-owned shims safely, invalidate command hash cache, and verify launchability rather than command existence before serve dispatch.

Fixes #6079
This commit is contained in:
Alexandre Teixeira
2026-10-30 13:15:40 +00:00
parent 5c542d03ac
commit 6037707430
3 changed files with 299 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
routes/cookbook_helpers.py
+63 -30
View File
@@ -1033,8 +1033,59 @@ def _append_llama_cpp_linux_accel_build_lines(runner_lines: list[str]) -> None:
ODYSSEUS_LLAMA_SHIM_MARKER = "# Auto-generated by Odysseus Cookbook: a `llama-server` lookalike"
def _append_llama_server_resolution_definition_lines(runner_lines: list[str]) -> None:
"""Define the helper shell function that discovers, reconciles and prioritizes llama-server."""
marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
runner_lines.append('_odysseus_resolve_llama_server() {')
runner_lines.append(' _odysseus_llama_bin=""')
runner_lines.append(f' local _marker={marker}')
runner_lines.append(' local _saved_ifs="$IFS"')
runner_lines.append(" IFS=':'")
runner_lines.append(' local -a _parts')
runner_lines.append(' read -r -a _parts <<< "$PATH"')
runner_lines.append(' IFS="$_saved_ifs"')
runner_lines.append(' local _dir _cand')
runner_lines.append(' for _dir in "${_parts[@]}"; do')
runner_lines.append(' [ -n "$_dir" ] || continue')
runner_lines.append(' _cand="$_dir/llama-server"')
runner_lines.append(' [ -x "$_cand" ] || continue')
runner_lines.append(' if [ -f "$_cand" ] && [ ! -L "$_cand" ] && grep -Fxq "$_marker" "$_cand" 2>/dev/null; then')
runner_lines.append(' continue')
runner_lines.append(' fi')
runner_lines.append(' if "$_cand" --version >/dev/null 2>&1; then')
runner_lines.append(' _odysseus_llama_bin="$_cand"')
runner_lines.append(' break')
runner_lines.append(' fi')
runner_lines.append(' done')
runner_lines.append(' if [ -f "$HOME/bin/llama-server" ] && [ ! -L "$HOME/bin/llama-server" ] && grep -Fxq "$_marker" "$HOME/bin/llama-server" 2>/dev/null; then')
runner_lines.append(' if [ -n "$_odysseus_llama_bin" ]; then')
runner_lines.append(' echo "[odysseus] Native llama-server detected — retiring Odysseus compatibility shim in ~/bin"')
runner_lines.append(' rm -f "$HOME/bin/llama-server"')
runner_lines.append(' hash -r')
runner_lines.append(' elif python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' _odysseus_llama_bin="$HOME/bin/llama-server"')
runner_lines.append(' else')
runner_lines.append(' echo "[odysseus] Removing stale Odysseus llama-server shim (python3 -m llama_cpp.server unavailable)"')
runner_lines.append(' rm -f "$HOME/bin/llama-server"')
runner_lines.append(' hash -r')
runner_lines.append(' fi')
runner_lines.append(' fi')
runner_lines.append(' if [ -n "$_odysseus_llama_bin" ]; then')
runner_lines.append(' local _cand_dir')
runner_lines.append(' _cand_dir="$(dirname "$_odysseus_llama_bin")"')
runner_lines.append(' if [ "${PATH%%:*}" != "$_cand_dir" ]; then')
runner_lines.append(' export PATH="$_cand_dir:$PATH"')
runner_lines.append(' fi')
runner_lines.append(' hash -r')
runner_lines.append(' return 0')
runner_lines.append(' fi')
runner_lines.append(' return 1')
runner_lines.append('}')
def _append_llama_server_shim_definition_lines(runner_lines: list[str]) -> None:
"""Define the helper shell function that generates the Odysseus compatibility shim."""
_append_llama_server_resolution_definition_lines(runner_lines)
marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
runner_lines.append('_odysseus_create_llama_shim() {')
runner_lines.append(' local _target="$HOME/bin/llama-server"')
@@ -1104,36 +1155,14 @@ def _append_llama_server_shim_reconciliation_lines(runner_lines: list[str]) -> N
- If python3 -m llama_cpp.server is unavailable, remove the stale shim
and hash -r so the fallback/build path is triggered.
- If no healthy native server exists and llama_cpp.server is working, preserve it.
- If a healthy native candidate exists on PATH (even later in PATH), prioritize it and
ensure the launched executable is the validated candidate.
"""
marker = f"'{_bash_squote(ODYSSEUS_LLAMA_SHIM_MARKER)}'"
runner_lines.append('[ -r ~/.config/odysseus-llama-cpp-env ] && . ~/.config/odysseus-llama-cpp-env')
runner_lines.append(f'if [ -f "$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('if ! declare -F _odysseus_resolve_llama_server >/dev/null 2>&1; then')
_append_llama_server_resolution_definition_lines(runner_lines)
runner_lines.append('fi')
runner_lines.append('_odysseus_resolve_llama_server || true')
def _append_llama_server_finalization_lines(runner_lines: list[str], platform_hint: str = "") -> None:
@@ -1148,10 +1177,14 @@ def _append_llama_server_finalization_lines(runner_lines: list[str], platform_hi
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('if ! declare -F _odysseus_resolve_llama_server >/dev/null 2>&1; then')
_append_llama_server_resolution_definition_lines(runner_lines)
runner_lines.append('fi')
runner_lines.append('if ! command -v llama-server &>/dev/null; then')
runner_lines.append('if [ -z "$_odysseus_llama_bin" ] && python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' _odysseus_create_llama_shim')
runner_lines.append(' _odysseus_resolve_llama_server || true')
runner_lines.append('fi')
runner_lines.append('if [ -z "$_odysseus_llama_bin" ]; then')
runner_lines.append(f' echo "{err_msg}"')
runner_lines.append(' ODYSSEUS_PREFLIGHT_EXIT=127')
runner_lines.append('fi')
routes/cookbook_routes.py
+3 -2
View File
@@ -2259,7 +2259,7 @@ def setup_cookbook_routes() -> APIRouter:
runner_lines.append(' CMAKE_ARGS="-DGGML_BLAS=OFF -DGGML_LLAMAFILE=OFF" pip install \'llama-cpp-python[server]\' --no-build-isolation --no-cache-dir 2>&1 || true')
runner_lines.append(' fi')
_append_llama_server_finalization_lines(runner_lines, platform_hint="Termux")
runner_lines.append('elif ! command -v llama-server &>/dev/null; then')
runner_lines.append('elif [ -z "$_odysseus_llama_bin" ]; then')
runner_lines.append(' echo "Native llama-server not found — building from source (one-time, may take a few minutes)..."')
runner_lines.append(' mkdir -p ~/bin')
runner_lines.append(' cd ~ && [ -d llama.cpp ] || git clone --depth 1 https://github.com/ggml-org/llama.cpp')
@@ -2300,8 +2300,9 @@ def setup_cookbook_routes() -> APIRouter:
runner_lines.append(' fi')
runner_lines.append(' fi')
runner_lines.append(' fi')
runner_lines.append(' _odysseus_resolve_llama_server || true')
# If the native build failed, fall back to the Python bindings.
runner_lines.append(' if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' if [ -z "$_odysseus_llama_bin" ] && ! python3 -c "import llama_cpp.server" 2>/dev/null; then')
runner_lines.append(' echo "llama-server build failed — installing Python bindings as fallback..."')
runner_lines.append(f" {_pip_install_fallback_chain('llama-cpp-python[server]', python_cmd='pip')} || true")
runner_lines.append(' fi')