hope-voice-api

0 Fork 0

T

Shane ab6b5254ef feat: context compaction + skills system

Compaction:
- GemmaLLM.chat() truncates ChatContext to last 30 items (~15 turns)
  before sending to LLM, preventing context window overflow on long
  conversations. Preserves system prompt and removes orphaned tool calls.

Skills:
- agent/skills_mcp.py: MCP server with skill_save, skill_recall,
  skill_list, skill_update tools backed by .md files in /skills
- skills/ dir bind-mounted into container, git-trackable
- System prompt instructs Hope to save repeatable procedures as skills
  and recall them before performing tasks she's done before
- Distinct from memory (facts) — skills are learned *procedures*

2026-08-22 16:42:16 -04:00

agent

feat: context compaction + skills system

2026-08-22 16:42:16 -04:00

memory

feat: markdown memory system — Hope learns from conversations

2026-08-22 16:33:00 -04:00

skills

feat: context compaction + skills system

2026-08-22 16:42:16 -04:00

web

feat: name the agent Hope