DeepSeek/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(session): default JSONL writes to packed rows

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-26 23:44:52 +08:00
parent cad2af4741
commit 4ff496c65c
47 changed files with 521 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/core-data-structures/session.i18n.yaml
View File

@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write
session.md: d789ffcabb5cb0c744e265b61e322831c1d8a04f
session.zh.md: f4f102861db7403520e9f38cb56613e430718cbe
session.md: 2cbbac8042d04522fea0b1ed7a66c503e4b63f4e
session.zh.md: e932c8f99f684f1b8985b006ab4ddb145db966bd

2
docs/core-data-structures/session.md
View File

@@ -560,6 +560,6 @@ The hook bridges' `hook/invoked` / `hook/result` provenance pairs (from `@deepse
## Durability contract
What a persistence backend relies on: the durable log persists every event losslessly, **including** `assistant/chunk` — `seq` must stay contiguous, so chunks cannot be filtered out of the canonical log. A backend may choose its own storage encoding for an event batch as long as `load` returns the exact appended events (the JSONL backend's opt-in packed chunk rows are such an encoding — see [persistence.md](persistence.md)). All `event.data` must be JSON-serializable; `Session.append` enforces this at the source (throwing on non-serializable data), so a bad event never enters the log and `session.events` always equals what a backend can persist. Adding an event type that carries non-serializable data, or that breaks the turn/step nesting checked by the session invariant companion, is a breaking change to the on-disk format.
What a persistence backend relies on: the durable log persists every event losslessly, **including** `assistant/chunk` — `seq` must stay contiguous, so chunks cannot be filtered out of the canonical log. A backend may choose its own storage encoding for an event batch as long as `load` returns the exact appended events (the JSONL backend's default packed chunk rows are such an encoding — see [persistence.md](persistence.md)). All `event.data` must be JSON-serializable; `Session.append` enforces this at the source (throwing on non-serializable data), so a bad event never enters the log and `session.events` always equals what a backend can persist. Adding an event type that carries non-serializable data, or that breaks the turn/step nesting checked by the session invariant companion, is a breaking change to the on-disk format.
The backends that consume this contract are on [persistence.md](persistence.md).

2
docs/core-data-structures/session.zh.md
View File

@@ -564,6 +564,6 @@ interface TurnEndReasonMap {
## 持久性契约
持久化后端依赖的契约如下：持久日志无损保存每个事件，**包括** `assistant/chunk`；`seq` 必须连续，因此不能从规范日志中过滤分片。后端可以为事件批次选择自己的存储编码，只要 `load` 返回与追加时完全一致的事件即可（JSONL 后端可选启用的打包分片行就是此类编码；见 [persistence.md](persistence.md)）。所有 `event.data` 都必须可序列化为 JSON；`Session.append` 会从源头强制这一要求（遇到不可序列化数据时抛出），因此错误事件绝不会进入日志，`session.events` 始终与后端可持久化的内容一致。新增携带不可序列化数据的事件类型，或破坏会话不变式配套插件所检查的轮次/步骤嵌套，会构成磁盘格式的破坏性变更。
持久化后端依赖的契约如下：持久日志无损保存每个事件，**包括** `assistant/chunk`；`seq` 必须连续，因此不能从规范日志中过滤分片。后端可以为事件批次选择自己的存储编码，只要 `load` 返回与追加时完全一致的事件即可（JSONL 后端默认启用的打包分片行就是此类编码；见 [persistence.md](persistence.md)）。所有 `event.data` 都必须可序列化为 JSON；`Session.append` 会从源头强制这一要求（遇到不可序列化数据时抛出），因此错误事件绝不会进入日志，`session.events` 始终与后端可持久化的内容一致。新增携带不可序列化数据的事件类型，或破坏会话不变式配套插件所检查的轮次/步骤嵌套，会构成磁盘格式的破坏性变更。
消费此契约的后端见 [persistence.md](persistence.md)。