admin/Linux_post_install
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

feat: pos ai server — llama.cpp local inference server
gates / consistency-and-conventions (push) Successful in 1m38s
Details

Browse Source 
Service manager (start/stop/status/models/logs) with systemd user
service generation, GPU auto-detection, model selection from pos ai hf
downloads. Provider adapter integrates with pos ai ask as --provider
llamacpp. Config extends existing ai scope with LLAMACPP_* keys.

87 test cases / 0 failed. make gen/check/lint 0 FAIL / 0 WARN.
This commit is contained in:
he
2026-09-04 12:40:50 -04:00
parent 99c033c6c6
commit 5e312b3207
7 changed files with 554 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bin/pos-ai
+5 -1
View File
@@ -3,7 +3,7 @@ set -euo pipefail
# POS: ai ask — AI assistant: ask, chat, sessions, capture, models, providers
# POS_SUBCMDS: ask chat sessions capture models providers
# POS_FLAGS: --provider --model --session --system --full --last --trust
# POS_CONFIG: ai | ai.env | AI_PROVIDER=:Provider (gemini or openrouter, default gemini) | @[AI_PROVIDER=gemini|] Gemini | *providers=gemini | @[AI_PROVIDER=openrouter] OpenRouter | *providers=openrouter | @General | AI_SYSTEM_PROMPT=:Custom system prompt (overrides built-in, empty to reset)
# POS_CONFIG: ai | ai.env | AI_PROVIDER=:Provider (gemini or openrouter, default gemini) | @[AI_PROVIDER=gemini|] Gemini | *providers=gemini | @[AI_PROVIDER=openrouter] OpenRouter | *providers=openrouter | llamacpp | *providers=llamacpp | @General | AI_SYSTEM_PROMPT=:Custom system prompt (overrides built-in, empty to reset) | LLAMACPP_PORT=:Server port (default 8088) | LLAMACPP_HOST=:Bind address (default 127.0.0.1) | LLAMACPP_MODEL=:Default model path (GGUF) | LLAMACPP_CTX_SIZE:num:Context window size (default 4096) | LLAMACPP_GPU_LAYERS:num:GPU layers (-1=auto, 0=CPU, default -1) | LLAMACPP_THREADS:num:CPU threads (default: nproc)
source "$(dirname "$0")/../lib/common.sh" 2>/dev/null || source "$(dirname "$0")/common.sh"
@@ -167,6 +167,7 @@ resolve_key() {
case "$p" in
gemini) [ -n "${AI_GEMINI_API_KEY:-}" ] && export AI_API_KEY="$AI_GEMINI_API_KEY" && return 0 ;;
openrouter) [ -n "${OPENROUTER_API_KEY:-}" ] && export AI_API_KEY="$OPENROUTER_API_KEY" && return 0 ;;
llamacpp) return 0 ;; # No API key needed for local server
esac
return 1
}
@@ -177,6 +178,7 @@ require_key() {
case "$p" in
gemini) err "No Gemini API key — run 'pos config ai' and set AI_GEMINI_API_KEY" ;;
openrouter) err "No OpenRouter API key — run 'pos config ai' and set OPENROUTER_API_KEY" ;;
llamacpp) ;; # No key needed for local server
esac
err "No API key for provider '$p' — run 'pos config ai'"
fi
@@ -193,6 +195,7 @@ resolve_model() {
case "$p" in
gemini) [ -n "${AI_GEMINI_MODEL:-}" ] && printf '%s' "$AI_GEMINI_MODEL" && return ;;
openrouter) [ -n "${OPENROUTER_MODEL:-}" ] && printf '%s' "$OPENROUTER_MODEL" && return ;;
llamacpp) [ -n "${LLAMACPP_MODEL:-}" ] && printf '%s' "$(basename "$LLAMACPP_MODEL")" && return ;;
esac
provider_default_model
fi
@@ -620,6 +623,7 @@ cmd_providers() {
case "$name" in
gemini) [ -n "${AI_GEMINI_API_KEY:-}" ] && configured="configured" ;;
openrouter) [ -n "${OPENROUTER_API_KEY:-}" ] && configured="configured" ;;
llamacpp) configured="configured" ;; # Local server — always configured
esac
current=""
[ "$name" = "$active" ] && current=" ← active"