Adds a memory store plugin with Holographic Reduced Representations (HRR)
for algebraic fact retrieval. Unlike embedding-based approaches, HRR uses
phase vectors (hashlib + numpy) with zero models, zero APIs, zero GPU.

Key capabilities:
- search: keyword matching via FTS5 + Jaccard + HRR 3-signal scoring
- probe: single-entity recall ("what about peppi?")
- related: structural adjacency ("what connects to Rust?")
- reason: multi-entity composition ("what connects peppi AND backend?")
  This is a vector-space JOIN — no embedding DB does this.

Also includes: trust scoring, entity resolution, temporal decay,
thread-safe SQLite, auto-extraction hook, memory bank monitoring.

81 tests (22 pure math + 59 integration).

Detects potentially contradictory facts by finding pairs with high
entity overlap but low content-vector similarity. Uses HRR phase
cosine to measure content divergence — no keyword heuristics.

Completes the algebraic action progression:
search → probe → related → reason → contradict

84 tests passing.

Test files now try ~/.hermes/plugins/ first (local dev), then fall
back to plugins/ in the repo root (CI). Fixes ImportError on fresh
runners where ~/.hermes doesn't exist.

…outer'

resolve_provider() in auth.py treated 'custom' and 'openrouter' as
identical, silently routing all custom provider traffic through
OpenRouter. This broke local LLM setups (Ollama, llama.cpp, LM Studio)
where users configured provider: custom with a local base_url.

Three changes:
- auth.py: return "custom" when requested provider is "custom"
- runtime_provider.py: _resolve_named_custom_runtime() returns
  provider: "custom" instead of "openrouter"
- runtime_provider.py: _resolve_openrouter_runtime() preserves
  "custom" in the provider field when that was the request

Fixes NousResearch#2562, fixes NousResearch#2281