Merge pull request #557 from deepseek-harness/fix/web-zstd-session-logs

fix(web): compress session logs by default
2026-07-23 18:49:46 +08:00
parent 45a7f74145 8e3378d08f
commit c5f5b29588
5 changed files with 15 additions and 5 deletions
@@ -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
-2026-07-19-zstandard-jsonl-session-logs.md: ccfc81dd47504e6a9e9b19cda7c4b9fc40accecc
-2026-07-19-zstandard-jsonl-session-logs.zh.md: de5436a6eaefcb45e52e0ff4fea8592c7efcd127
+2026-07-19-zstandard-jsonl-session-logs.md: 74430624c771a265fb281e588e28733bc55d3eb6
+2026-07-19-zstandard-jsonl-session-logs.zh.md: b22275d1a7c54a743b11f4396318dd87e4f5b42a
@@ -36,7 +36,7 @@ EOF inside the final frame is a recoverable torn tail. Node's decoder is given t

 ### Consumers and verification

-The CLI, ACP, and stdio app bundles expose symmetric `persistenceCompression` pass-through configuration. Snapshot recording and replay compositions select `'none'` explicitly because committed fixtures are raw JSONL inputs to replay and normalization; ordinary runtime compositions use the compressed default.
+The CLI, ACP, and stdio app bundles expose symmetric `persistenceCompression` pass-through configuration. The web host assembly and ordinary app compositions omit the option and use the compressed default. Snapshot recording and replay compositions select `'none'` explicitly because committed fixtures are raw JSONL inputs to replay and normalization.

 The shared persistence and coordinator contracts run against both encodings. Backend tests cover standard framing and checksum interoperability, header-only listing, append rollback, encoding mismatch rejection, complete-frame corruption, and final-frame tears through headers, blocks, and checksum trailers. Default runtime, built-bin, headless, ACP, and Python smokes assert the compressed suffix and Zstandard magic or decode the header; raw-content tests opt out explicitly.

@@ -36,7 +36,7 @@ JSONL 持久化后端会逐字保留每个 `SessionEvent`，其中包括数量

 ### 消费方与验证

-CLI、ACP 与 stdio 应用包公开对称的 `persistenceCompression` 透传配置。快照录制与回放组合显式选择 `'none'`，因为提交的 fixture 是回放与规范化过程使用的原始 JSONL 输入；普通运行时组合使用压缩默认值。
+CLI、ACP 与 stdio 应用包公开对称的 `persistenceCompression` 透传配置。web 宿主装配与普通应用组合省略该选项并使用压缩默认值。快照录制与回放组合显式选择 `'none'`，因为提交的 fixture 是回放与规范化过程使用的原始 JSONL 输入。

 共享持久化契约与协调器契约会针对两种编码运行。后端测试覆盖标准帧与校验和互操作性、仅头部列举、追加回滚、编码不匹配拒绝、完整帧损坏，以及横跨头部、块和校验和尾部的最终帧撕裂。默认运行时、构建后二进制、headless、ACP 与 Python 冒烟测试会断言压缩后缀与 Zstandard 魔数，或解码头部；读取原始内容的测试则显式退出压缩。

@@ -98,7 +98,7 @@ export async function bootHost(options: BootHostOptions): Promise<HostHandle> {
  await ctx.plugin(TaskService)
  await ctx.plugin(AgentLoop, { agents: [] })
  await ctx.plugin(LlmDeepSeek, {})
-  await ctx.plugin(SessionPersistenceJsonl, { root: options.persistenceRoot, compression: 'none' })
+  await ctx.plugin(SessionPersistenceJsonl, { root: options.persistenceRoot })
  await ctx.plugin(LocalBashExecutor, {})
  // Tool suite mirroring the demo:repl composition (repl-agent/cordis.yml +
  // the agent-spine bundle) so web sessions get the same coding-agent tool
@@ -104,6 +104,16 @@ describe('bootHost / startHost', () => {
    await handle.dispose()
  })

+  it('uses the JSONL backend compressed default', async () => {
+    const handle: HostHandle = await bootHost({
+      persistenceRoot: mkdtempSync(join(tmpdir(), 'dsh-boot-zstd-')),
+      workspaceContext: false,
+    })
+    const session = handle.ctx.sessions.create()
+    expect(handle.ctx.sessionPersistence.locate(session.header)?.path).toMatch(/\.jsonl\.zstd$/)
+    await handle.dispose()
+  })
+
  it('startHost assembles api + handler over the same defaults and dedupes dispose', async () => {
    const running = await boot()
    expect(running.defaults).toMatchObject({ provider: 'scripted', model: 'test-model' })