Remember
Store new memory with 3-layer architecture.
Issue #1 specification:
- Layer 1: summary (Embedding化、検索用)
- Layer 2: context_summary (文脈説明)
- Layer 3: content + details (完全詳細)
Request: { "summary": "認証エラー修正。JWTトークン有効期限チェック追加。", "context_summary": "ユーザーからログイン失敗の報告があり...", "content": "auth.pyのverify_token関数にexpired_atの検証を追加", "details": {"code_diff": "...", "test_results": "..."}, "type": "code", "importance": 0.8, "tags": ["python", "authentication"], "context": {"context_id": "my-context"} }
Response: { "status": "success", "memory_id": "uuid", "scope": "working", "persistence": { "scope": "working", "committed": true, "promotes_via": "sleep_consolidation", "consolidation_archive_min_age_days": 30, "detail": "..." } }
The memory is committed before this returns; scope selects the consolidation lifecycle, not whether it was stored. persistence describes that lifecycle for this deployment and is null when the scope cannot be classified. Its age floor is scoped to consolidation and is not a retention guarantee — see services.persistence.
Example: POST /api/v1/memory/remember Authorization: Bearer <session_token>
Request
- Base URL: https://memory.kagura-ai.com (the document declares no server; this is the origin it was published from)
- URL: https://memory.kagura-ai.com/api/v1/memory/remember
- Auth: none declared
Headers
Request body
Response
Successful Response
Changes
No recorded changes to this operation across all 1 revision of this API.