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 and stash the returned memory block (when present) on the signal's tool_context under the key :__gralkor_memory__. The thread's session id is stashed alongside it under :session_id so in-turn tool calls (e.g. MemorySearch) key on the same session. The plugin does not mutate :query — the recalled memory is delivered to the LLM by a request transformer at prompt-build time (see Jido.AI.Reasoning.ReAct.RequestTransformer and Jido.AI.PromptBuilder), keeping :query the user's actual words everywhere downstream (buffer, request store, capture). 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. Because nothing in the turn mutates :query to add harness context, canonicalisation doesn't strip envelopes — the user message it persists is the user's actual words. 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.