Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
test(claude-code-plugin): fit recall fixture within the full context budget (#6353)
z1gon0902110a011f
diff --git a/examples/claude-code-memory-plugin/scripts/auto-recall.test.mjs b/examples/claude-code-memory-plugin/scripts/auto-recall.test.mjsindex c199e24f9..048cdafd7 100644--- a/examples/claude-code-memory-plugin/scripts/auto-recall.test.mjs+++ b/examples/claude-code-memory-plugin/scripts/auto-recall.test.mjs@@ -247,8 +247,9 @@ test("hits that all fall under the score threshold are recorded as filtered_out"});test("the client-ranked fallback degrades past the budget to URI hints", async () => {- const first = "x".repeat(500);- const second = "y".repeat(500);+ // Leave room for the recall wrapper and both citations within the 200-token cap.+ const first = "x".repeat(300);+ const second = "y".repeat(300);const { stdout, state } = await recallTurn({env: { OPENVIKING_RECALL_TOKEN_BUDGET: "200" },routes: {