Jido plugin that replaces Jido.Memory.BasicPlugin with Gralkor-backed memory. Claims the :__memory__ slot so it is the only memory plugin attached to the agent.

session_id is the current Jido thread id, read from agent.state[:__thread__].id. One Jido thread per Gralkor session — the capture buffer rotates naturally when the thread rotates, and concurrent agents for the same principal never collide on the buffer. group_id is sanitize_group_id(agent.id) since memory graph partitioning is per-principal.

Recall fires on ai.react.query: if a thread is already committed in agent state, recall Gralkor for the current thread's session; inject the session id into the signal's tool_context so in-turn tool calls (e.g. MemorySearch) key on the same session. On the very first query of a fresh agent, ThreadAgent.append hasn't yet run (the ReAct strategy calls it inside @start, after the plugin hook), so there's nothing to recall against — the plugin passes the signal through unchanged and lets capture establish the session when the turn completes.

Capture fires on ai.request.completed / ai.request.failed: the full request trace and assistant answer are normalised via JidoGralkor.Canonical.to_messages/3 into Gralkor's canonical [%Gralkor.Message{role, content}] shape and shipped to the server, which keeps the rolling conversation buffer keyed by session_id. The <gralkor-memory>…</gralkor-memory> recall envelope this plugin prepended earlier in the turn is stripped during canonicalisation so recalled facts don't appear in the episode body and feed back through Graphiti extraction. Capture is skipped if the thread isn't present (first-turn failure with nothing committed) or if the canonical message list is empty.

Gralkor errors raise — the caller sees the real error, per the project's fail-fast rule.