stratagate-dsh 0.3.5 → 0.3.6

package/docs/DSH.md

@@ -201,7 +201,9 @@ Topic Projection has an independent output bound of 32,768 tokens. Advertised mo
 
 Topic technical details and task details in `/api/stratagate/overview` distinguish `max-tokens`, `schema-invalid`, `validation-failed`, `timeout`, `provider-failed`, `worker-failed`, and `source-changed`. Diagnostics retain only safe validation rules and numeric/runtime metadata, never raw chat, Event/Topic prose, full model responses, or reasoning. `requested-unverified` means off was requested, not that the provider honored it; observed reasoning is marked separately.
 
-Only explicit `finish=max-tokens` splits a failed batch in half, with at most four levels and three attempts per singleton. Each historical child still consumes the shared Bootstrap allowance, without trimming Event evidence. Other failures keep bounded retry and backoff. After automatic attempts are exhausted, the directory retry action (`POST /api/stratagate/topics/retry`, with namespace, jobId and expectedRevision) or `POST /api/stratagate/jobs/retry?namespace=...&kind=topic-projection&jobId=...` queues a fresh job ID. Both paths enforce source versions, reject old results, and persist across restart. Upgrades never automatically revive historical terminal failures.
+Once an invalid overview has been observed, retries must supply valid replacements; dropping the offending entries or clearing overview cannot report success. Jobs persist `overviewRepairRequirements` separately: only legal source IDs, kinds and minimum replacement counts, without model prose. Structured retries, task retries, restarts and splits inherit the relevant constraints. Known legacy overview field failures without paragraph identities require at least one valid replacement; ordinary first-call empty overviews remain legal. Settled failures retain their original historical status but leave current fault counts. The directory, Dashboard and task details include only valid unfinished failures, and manual retry processes only remaining Events.
+
+Only explicit `finish=max-tokens` splits a failed batch in half, with at most four levels and three attempts per singleton. Each historical child still consumes the shared Bootstrap allowance, without trimming Event evidence. Other failures keep bounded retry and backoff. After automatic attempts are exhausted, the directory retry action (`POST /api/stratagate/topics/retry`, with namespace, jobId and expectedRevision) or `POST /api/stratagate/jobs/retry?namespace=...&kind=topic-projection&jobId=...` queues a fresh job ID. Both paths enforce source versions, reject old results, and persist across restart. The version containing the #119 fix uses a separate, persistent Recovery Version on the first writer initialization to queue one new cycle of at most three task attempts for current terminal Topic failures with unfinished work. This cycle consumes the existing historical allowance. Successful work, stale sources and retired history are excluded. The recovery marker and queued jobs commit together; restarts, refreshes and repeated initialization never reset attempts again. If the new cycle fails, partial progress, error details and manual retry remain available. Only fully validated current work reports `completed`; exhausted outstanding work reports `failed`.
 
 `blockTurnSize` and `blockDecayLambda` are initial fallbacks. Once changed in **Advanced Settings**, persisted UI values take precedence. λ defaults to `0.3`; smaller values forget more slowly and consume more tokens, and values above `0.4` are not recommended.
 

package/docs/DSH.zh-CN.md

@@ -100,6 +100,8 @@ DSH_HOME/stratagate/memory.db
 
 其余行为与普通 Event 一致：agent 记录会投影进 Knowledge Graph，跨会话持久保存，走同样的 turn 衰减与引用强化生命周期（`memory_assess` → `memory_record_use`），也可以通过该生命周期遗忘。检索为两个池各开一条独立的 top-k 通道 —— 被动池与 agent 池分别独立排序，再按加权 RRF 融合，任何一方都无法把另一方挤出结果窗口。agent 通道的占比由 `agentMemoryRetrievalWeight` 配置（默认 `1` = 平权；`0` = 记录保留但不再浮现；更大值提升 agent 记录的排序权重），卡片带 `source: 'agent-recorded'` 标记。记忆面板通过 `/api/stratagate/agent-memories`（查询参数 `session` 与 `includeArchived=true`）展示这些记录。可用 `agentMemoryEnabled: false` 整体关闭该功能，同时注销对应工具。
 
+主动 Event 可直接引用真实开放尾部消息，因此可能没有 `sourceBlockId`；搜索卡片仅在该字段存在时返回它。检索返回的原始结构必须通过 DSH 的无损 JSON 规则后，才登记可评估的证据批次；无效返回不会留下未解决批次。此处理不删除 Event 或改写来源，排序、证据引用和后续采用强化沿用原有流程。
+
 插件注册以下工具：
 
 记忆目录默认提供约 400 词元的导航。`memory_list_topics` 可分类分页或查询主题，`memory_expand_topic` 展开有来源的概览；这两个工具不生成证据批次，也不强化记忆。概览中的事实需用 `memory_search_events` 的 `topic_id` 参数查证，再走证据评估和采用流程。后台从已有事件小批量整理，失败或尚未整理时仍保留事件入口。详见[记忆目录与主题整合](MEMORY_TOPICS.zh-CN.md)。
@@ -176,7 +178,9 @@ Topic Projection 使用独立的 32,768 token 输出上限；若宿主公布了
 
 Topic 技术详情及 `/api/stratagate/overview` 的任务详情会区分 `max-tokens`、`schema-invalid`、`validation-failed`、`timeout`、`provider-failed`、`worker-failed` 和 `source-changed`。诊断仅记录安全校验规则、数量、估算 token、请求预算、finish reason、reasoning off 请求/回退状态和尝试次数，不记录原始聊天、Event/Topic 正文、完整模型响应或 reasoning。`requested-unverified` 表示发送了 off 请求，不能证明 provider 实际关闭了 reasoning；若仍观察到 reasoning，会明确标记。
 
-只有明确的 `finish=max-tokens` 才会二分失败批次，最多四层，单条批次最多尝试三次；每个历史子批次仍受共用 Bootstrap 额度约束，不裁剪 Event 证据。其他错误维持原有有限重试与退避。自动尝试耗尽后，可通过目录“重新整理这 N 条”（`POST /api/stratagate/topics/retry`，携带 namespace、jobId 和 expectedRevision），或 `POST /api/stratagate/jobs/retry?namespace=...&kind=topic-projection&jobId=...` 重新排队。两条路径均开启新 jobId 周期，检查来源版本并拒绝旧结果，状态在重启后保留。升级不会自动复活历史终态失败。
+模型已经生成不合格 overview 时，后续请求必须提供合法替代，不能删除错误段落或清空 overview 后显示成功。任务单独持久化 `overviewRepairRequirements`：仅保存合法来源编号、类型及最低替代数量，不保存段落正文；结构化重试、任务重试、重启和拆批均继承对应约束。已知旧 overview 字段失败没有段落身份时，至少要求一个合法替代；首次正常空 overview 仍合法。已成功完成的失败记录保留原失败历史并退出当前故障统计；目录、Dashboard 和任务详情都只展示仍有效且存在未完成工作的失败，人工重试只处理剩余 Event。
+
+只有明确的 `finish=max-tokens` 才会二分失败批次，最多四层，单条批次最多尝试三次；每个历史子批次仍受共用 Bootstrap 额度约束，不裁剪 Event 证据。其他错误维持原有有限重试与退避。自动尝试耗尽后，可通过目录“重新整理这 N 条”（`POST /api/stratagate/topics/retry`，携带 namespace、jobId 和 expectedRevision），或 `POST /api/stratagate/jobs/retry?namespace=...&kind=topic-projection&jobId=...` 重新排队。两条路径均开启新 jobId 周期，检查来源版本并拒绝旧结果，状态在重启后保留。包含 #119 修复的版本在首次 writer 初始化时，使用独立的持久化 Recovery Version 为当前有效、仍有未完成工作的 Topic 终态失败任务自动开启一次新的最多三次任务尝试，仍消耗已有历史额度。已成功、来源过期及失效的历史记录不重跑；恢复标记与新任务一起提交，重启、刷新和重复初始化不再次清零。本轮再次失败后保留部分完成进度、错误详情和人工重试入口。只有当前应完成工作全部通过校验才返回 `completed`，仅剩终态失败时返回 `failed`。
 
 配置文件中的 `blockTurnSize` 和 `blockDecayLambda` 是初始后备值；一旦在“高级设置”中修改，持久化的界面值优先生效。λ 默认值为 `0.3`；数字越小，记忆遗忘越慢、消耗 token 越多，不建议大于 `0.4`。
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "stratagate-dsh",
-  "version": "0.3.5",
+  "version": "0.3.6",
   "description": "Recent conversations stay vivid. Older ones fade into summaries, not oblivion. StrataGate gives DeepSeek Harness six-layer, time-decaying memory, while lasting events and relationships settle into a knowledge graph. Bring your memories from other AIs with you—no need to start over.",
   "type": "module",
   "main": "./dist/index.js",