Sandbox takeover: the saved transcript loses everything the first host delivered before the restart
メンテナーはふだん 1 日以内に返信
@tombeckenham がすでに取り組んでいます。
2026年11月5日 から。
評価
この issue はまだ評価されていません。
説明
TanStack AI version
@tanstack/ai-sandbox 1.1.0 and main (644a780b0). @tanstack/ai 1.1.0 and main. @tanstack/ai-persistence 1.0.1. @tanstack/ai-claude-code 1.0.1.
Framework/Library version
Server only. chat() driven by sandboxRunDriver in a Node 24 route handler. No client framework is involved.
Describe the bug and the steps to reproduce it
A host restarted during a 40-second Bash call. sandboxRunDriver took over the run on another host and finished it. The saved transcript has the Bash tool result and the final text, but no assistant message with the Bash tool call. The live stream was correct, because the event log already held the first part of the run.
The transcript loses more than that one call. The successor's transcript is missing every chunk that the first host delivered before the restart: assistant text, complete tool calls, and the start of a tool call that was still running. A call that was still running leaves its result as an orphan role: 'tool' message with no call.
Expected: the saved transcript after a takeover is the same as the transcript of a run that did not restart.
Steps:
- Use
claudeCodeTextwithwithPersistenceandwithSandbox(sandbox, { instances, runs, durability }). - Start a run where the agent writes some text and then runs a slow tool.
- Stop the host while the tool runs. Let
sandboxRunDrivertake over the run on another host. - When the run finishes, load the thread from the message store. It holds only the chunks that the successor forwarded.
Suspected cause. On an attach, the harness adapter wraps its replay in alignedIfAttaching. alignToStoredLog suppresses the prefix that the event log already holds and yields only the rest. The wrap is inside the adapter's chatStream, so the suppressed chunks never reach the engine:
- The engine does not see the text of the prefix, so it does not add that text to the transcript.
withSandbox'sonChunkdoes not see theTOOL_CALL_START,TOOL_CALL_ARGSandTOOL_CALL_ENDof the prefix, so the tool-history recorder writes no call. The laterTOOL_CALL_RESULTarrives, and the recorder writes the result alone.
A comment in appendCall says that "a journal replay on takeover re-emits the whole stream". After alignment, that is not true.
Other effects. stripObservedToolCalls removes a result only when it also removed the result's call. So an orphan result stays in the model request of the next turn. claudeCodeText is not affected, because buildPrompt keeps only user and assistant text. I did not check the other harness adapters.
Not checked: whether withPersistence's snapshotStreaming option saves the first host's partial transcript in a form that the successor merges back.
Related: #2035 is a different takeover bug, where the reconnected client receives the rest of the run twice.
Your Minimal, Reproducible Example - (Sandbox Highly Recommended)
https://gist.github.com/adelrodriguez/4e34cfd7224b96dfe05d554e4c0dd1e0
The test runs one chat() with withPersistence(memoryPersistence()) and withSandbox(..., { runs, durability: { adapter: fakeLog(prefix), attach: true } }). Its adapter does what claudeCodeText does: it wraps a fixed replay in alignedIfAttaching. The log already holds the chunks up to the Bash call's TOOL_CALL_END, including a first text message. Place the file in packages/ai-sandbox/tests/ and run vitest run tests/takeover-transcript.repro.test.ts in packages/ai-sandbox. Both tests fail on main:
forwarded to engine: TOOL_CALL_RESULT, TEXT_MESSAGE_START, TEXT_MESSAGE_CONTENT, TEXT_MESSAGE_END, RUN_FINISHED
saved transcript:
{ "role": "user", "content": "Run the slow job" }
{ "role": "tool", "toolCallId": "bash-1", "content": "done" }
{ "role": "assistant", "content": "Finished.", ... }
× keeps the assistant tool call, not only its result
× keeps the text the first host streamed before the restart
AssertionError: expected 'Run the slow job done Finished.' to contain 'Starting the job.'
Tests 2 failed (2)
Do you intend to try to help solve this bug with your own PR?
Maybe, I'll investigate and start debugging
Terms & Code of Conduct
- I agree to follow this project's Code of Conduct
- I understand that if my bug cannot be reliable reproduced in a debuggable environment, it will probably not be fixed and this issue may even be closed.
🤖 Created with Claude Opus 5.5 in T3 Code
- 主要言語
- TypeScript
- スター
- 3.3k
- フォーク
- 378
- 平均マージ
- 1日 2時間
- マージ済み PR(30日)
- 254
環境構築
- Dockerfile・Docker Compose ファイルなし
- プルリクエストのテンプレートあり
- コントリビューションガイドを読む
はじめの一歩
- issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
- 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
- リポジトリをフォークし、ブランチを切って変更します。
- issue 番号を参照したプルリクエストを送ります。
TanStack/ai のほかの issue
-
openai-base: a Responses max_output_tokens cutoff ends as RUN_ERROR without usage instead of finishReason 'length'対応中かも @tombeckenham が 8 日前に担当しました。 オープンhas-pr waiting-on: maintainer
難易度 2/5 1〜3時間 初心者へのやさしさ 74/100
TanStack/ai#1916 · コメント 1 件 · 担当者 1 名 ·
メンテナーはふだん 1 日以内に返信
-
AG-UI TOOL_CALL_RESULT metadata is dropped in the live stream reducer対応中かも @c446984928 が今日担当しました。 オープン
難易度 2/5 1〜3時間 初心者へのやさしさ 35/100
メンテナーはふだん 1 日以内に返信
-
ai-sandbox: encrypt snapshot blobs at rest with an encrypting blob store wrapper対応中かも @AlemTuzlak が 1 日前に担当しました。 オープンwaiting-on: maintainer
メンテナーはふだん 1 日以内に返信
-
withSandbox: each run's save drops the harness tool calls of earlier runs対応中かも @tombeckenham が 1 日前に担当しました。 オープンhas-pr waiting-on: maintainer
メンテナーはふだん 1 日以内に返信
-
ai-compaction: checkpoint never reused when the store returns message keys in another order対応中かも @tombeckenham が 1 日前に担当しました。 オープンhas-pr waiting-on: maintainer
メンテナーはふだん 1 日以内に返信
似ている issue
-
The sample email preview's ResizeObserver is never disconnected and keeps raising errors after leaving Settings対応中かも このイシューにリンクされたプルリクエストがオープン中、またはマージ済みです。 オープンbug
難易度 2/5 1〜3時間 初心者へのやさしさ 82/100
メンテナーはふだん 1 日以内に返信
-
area:ui bug effort:S priority:P2
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
メンテナーはふだん 1 日以内に返信
-
Typo in WSL project description on Projects page対応中かも @akhil9tiet が今日担当しました。 オープン
難易度 1/5 1時間未満 初心者へのやさしさ 75/100
microsoft/opensource.microsoft.com#1066 · コメント 1 件 ·
-
ArcGIS Maps SDK for JavaScript c-carousel calcite-design-tokens enhancement impact - p3 - not time sensitive needs triage
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
Esri/calcite-design-system#15565 ·
メンテナーはふだん 1 日以内に返信
-
bug
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
linkwarden/linkwarden#1891 ·
メンテナーはふだん 1 日以内に返信