stratagate-dsh 0.2.37 → 0.2.39

package/docs/ARCHITECTURE.md

@@ -241,4 +241,4 @@ The adapter preserves these invariants:
 - forget is reversible unless an application explicitly implements irreversible deletion;
 - usage receipts are idempotent for one answer turn through a unique `receiptId`.
 
-SQLite schema v9 includes normalized Block processing state and persisted summary/extraction retry jobs in addition to graph, element, provenance, receipt, decay-anchor, and lift-source data. Opening a schema-v1 through v8 database migrates it in one transaction and preserves existing namespaces, Blocks, Events, jobs, and receipts. Existing pre-v9 Blocks are treated as ready because their persisted L0-L5 layers were already accepted by the older engine. Schema-v5 turn anchors are converted to per-thread Block positions; schema-v6 lift timestamps retain an unknown legacy source. Pre-v5 Blocks retain no inferred thread ownership, so they remain archival provenance without being attached to a new session. SQLite uses WAL, foreign keys, and per-namespace optimistic concurrency. It does not provide encryption at rest. Search still uses the reference in-memory ranking after hydration, so enabling persistence does not silently change retrieval semantics. Database-native lexical/vector indexes and a Postgres implementation remain separate future work.
+SQLite schema v10 includes durable external-memory import jobs and per-candidate progress, in addition to the normalized Block processing state, summary/extraction retry jobs, graph, element, provenance, receipt, decay-anchor, and lift-source data introduced earlier. Opening a schema-v1 through v9 database migrates it in one transaction and preserves existing namespaces, Blocks, Events, jobs, and receipts. Existing pre-v9 Blocks are treated as ready because their persisted L0-L5 layers were already accepted by the older engine. Schema-v5 turn anchors are converted to per-thread Block positions; schema-v6 lift timestamps retain an unknown legacy source. Pre-v5 Blocks retain no inferred thread ownership, so they remain archival provenance without being attached to a new session. SQLite uses WAL, foreign keys, and per-namespace optimistic concurrency. It does not provide encryption at rest. Search still uses the reference in-memory ranking after hydration, so enabling persistence does not silently change retrieval semantics. Database-native lexical/vector indexes and a Postgres implementation remain separate future work.

package/docs/DSH.md

@@ -133,7 +133,7 @@ Open DSH Settings and select **StrataGate-AgentMemory**. The page provides:
 
 Events, graph facts, and source messages cannot be edited, deleted, or approved in the UI. The UI can still change memory state in three explicit ways: manually expand a Block, import memory exported by another AI, and use Advanced Settings to change the completed turns per Block or the global Block decay coefficient λ. When the Block size changes, the UI explains their relationship and suggests a λ that preserves the decay rate per conversation turn; the user decides whether to adopt it. Saved settings immediately apply to every existing workspace, become the defaults for future workspaces, and survive restarts. Existing sealed Blocks are never repartitioned.
 
-The current UI import is intentionally simple: it validates the pasted `stratagate.external-memory.v2` JSON and adds each valid candidate as a new Event. It does not yet merge, supersede, mark conflicts, or remove duplicates against existing Events. Common token and credential patterns are redacted in message content and structured tool traces before they leave the local server. The SQLite database remains the source of truth.
+The UI validates and previews pasted `stratagate.external-memory.v2` JSON before writing. Malformed input uses a model-backed recovery fallback whose candidates always require review. Exact duplicates are ignored deterministically; the configured model adjudicates other candidates against Top-K local Events as add, merge, supersede, conflict, or ignore. Analysis jobs persist per-candidate progress in SQLite, resume after the import page is reopened, and let users choose the action for low-confidence decisions. High-confidence decisions remain automatic, and a committed import can be undone as one batch. Common token and credential patterns are redacted in message content and structured tool traces before they leave the local server. The SQLite database remains the source of truth.
 
 ## Configuration
 

package/docs/DSH.zh-CN.md

@@ -130,7 +130,7 @@ ID、`blockId`、角色、轮次和有界摘录。`narrative`、`quotes`、来
 
 界面不允许直接编辑、删除或批准 Event、图谱事实和来源消息，但可以通过三种明确操作改变记忆状态：手动展开 Block、导入其他 AI 的记忆，以及在“高级设置”中修改每个 Block 包含的完整对话轮数或全局 Block 衰减系数 λ。修改轮数时，界面会解释两者关系并给出保持单位对话衰减速度的建议 λ，是否采用由用户决定。保存后设置立即应用到所有已有工作区，同时成为新工作区默认值，并在重启后保持；已封存 Block 不会重新切分。
 
-当前界面的导入流程有意保持简单：它会校验粘贴的 `stratagate.external-memory.v2` JSON，并把每条有效候选新增为 Event；暂时不会与已有 Event 自动合并、取代、标记冲突或去重。消息内容和结构化工具轨迹中的常见令牌及凭证格式，会在离开本地服务器前被脱敏。SQLite 数据库始终是唯一可信数据源。
+当前界面会在写入前校验并预览粘贴的 `stratagate.external-memory.v2` JSON：不合格内容会进入模型兜底恢复，恢复候选全部需要人工确认。完全重复项会被确定性忽略，其余候选由当前模型结合 Top-K 本地 Event 判断新增、合并、取代、冲突或忽略。分析任务和逐条进度持久化到 SQLite，关闭并重新打开页面后会恢复进度；高置信度判断自动采用，低置信度项可由用户选择具体动作；提交后可按批次撤销。消息内容和结构化工具轨迹中的常见令牌及凭证格式，会在离开本地服务器前被脱敏。SQLite 数据库始终是唯一可信数据源。
 
 ## 配置
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "stratagate-dsh",
-  "version": "0.2.37",
+  "version": "0.2.39",
   "description": "Automatic local-first cross-session memory for DeepSeek Harness with source-traceable recall",
   "type": "module",
   "main": "./dist/index.js",