Auto-inject relevant memory facts into LLM context on every user turn.

Fork: 0

root / navi-1

Browse code Auto-inject relevant memory facts into LLM context on every user turn. Semantic search against the vector memory store runs in parallel with context provider collection. Number of injected facts scales with message length (1–3) to reduce noise on short queries. Guardrails: min length gate, per-turn deduplication, and structured logging at info level for observability. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> feature/navi-code master vmkdemo
1 parent dee2c9b commit de38f31632bb32955a1bb36a9607eafd6159a204 Eugene Sukhodolskiy authored on 12 May

Browse code

Semantic search against the vector memory store runs in parallel with
context provider collection. Number of injected facts scales with
message length (1–3) to reduce noise on short queries. Guardrails:
min length gate, per-turn deduplication, and structured logging at
info level for observability.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

feature/navi-code master vmkdemo

1 parent dee2c9b commit de38f31632bb32955a1bb36a9607eafd6159a204

Eugene Sukhodolskiy authored on 12 May

Patch

Unified Split

Showing 2 changed files

Ignore Space Show notes View navi/core/agent.py

Ignore Space Show notes View navi/core/context_builder.py

Show line notes below