3 Commits

Author	SHA1	Message	Date
he	5e312b3207	feat: pos ai server — llama.cpp local inference server ... 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.	2026-09-04 12:40:50 -04:00
Your Name	e0c9ba384a	feat: dynamic provider config — pos config ai auto-discovers provider keys ... - lib/ai-providers/*.sh declare # PROVIDER_CONFIG: headers - lib/config-ui.sh: _cfg_provider_keys() scans providers at runtime - bin/pos-ai: POS_CONFIG uses *providers marker (no hardcoded keys) - Adding a new provider auto-populates config UI — no main tool edits needed	2026-08-26 02:58:45 -04:00
Your Name	4f79ce123f	refactor: ai — merge gemini/openrouter into unified plugin architecture ... - bin/pos-ai: single provider-agnostic tool (ask/chat/sessions/capture/models/providers) - lib/ai-providers/gemini.sh: Gemini adapter (59 ln) - lib/ai-providers/openrouter.sh: OpenRouter adapter (59 ln) - bin/pos-ai-gemini/openrouter: thin forwarders for backward compat - Provider adapter interface: provider_name/default_model/generate/models_list - Unified session format (OpenAI messages), auto-migrate old gemini contents - Config: AI_PROVIDER/AI_API_KEY/AI_MODEL/AI_SYSTEM_PROMPT in ai.env - Config fallback: AI_API_KEY → provider-specific env var → error - Default system prompt configurable via AI_SYSTEM_PROMPT - New subcommand: pos ai providers (lists providers + config status) - Shell hook (pos-ai-hook.sh) for auto-capture	2026-08-25 09:57:10 -04:00