In-process (.NET, Windows): access violation in copilot_runtime_connection_write when responding to runtime requests
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 43/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- csharp, typescript
调研方向
Start by tracing the .NET in-process response path from FfiRuntimeHost.SendFrame through JsonRpc.SendResultResponseAsync, then inspect the native copilot_runtime_connection_write implementation and its connection lifecycle. Try to reproduce on Windows x64 with parallel MCP tool calls using the reported SDK/runtime versions; done means writes either succeed or report a managed error without crashing the host.
由索引模型根据 Issue 内容生成。
描述
Summary
With in-process hosting (RuntimeConnection.ForInProcess()) on Windows x64, the host process dies with an access violation (0xC0000005) inside the native copilot_runtime_connection_write while the .NET SDK writes a response frame. It happens mid-turn in long agent sessions and takes down the whole host application.
Versions
GitHub.Copilot.SDK1.0.16 (runtime 1.0.89) and 1.0.17 (runtime 1.0.93); reproduced on both- .NET 10, win-x64, self-contained WPF app, in-process hosting
- Session config:
OnPreToolUsehook (synchronous, returns allow),OnPermissionRequesthandler (synchronous allow),OnUserInputRequest,OnElicitationRequest, an HTTP MCP server with many tools,AskUserVariant.Elicitation, a custom provider pointed at a loopback HTTP endpoint
Stack (1.0.17)
Fatal error.
0xC0000005
at GitHub.Copilot.FfiRuntimeHost.<ConnectionWrite>g____PInvoke|55_0(UInt32, Byte*, UIntPtr)
at GitHub.Copilot.FfiRuntimeHost.SendFrame(System.ReadOnlySpan`1<Byte>)
at GitHub.Copilot.JsonRpc+<SendMessageAsync>d__35`1[[System.__Canon, ...]].MoveNext()
at GitHub.Copilot.JsonRpc+<SendResultResponseAsync>d__46.MoveNext()
at GitHub.Copilot.JsonRpc.SendResultResponseAsync(System.Text.Json.JsonElement, System.Object, System.Type, System.Threading.CancellationToken)
at GitHub.Copilot.JsonRpc+<HandleIncomingMethodAsync>d__41.MoveNext()
at GitHub.Copilot.JsonRpc+<ReadLoopAsync>d__37.MoveNext()
...
at GitHub.Copilot.JsonRpc+<ReadMessageAsync>d__39.MoveNext()
...
at GitHub.Copilot.FfiRuntimeHost+CallbackReceiveStream+<ReadAsync>d__4.MoveNext()
...
at GitHub.Copilot.FfiRuntimeHost+CallbackReceiveStream+<ReadCoreAsync>d__5.MoveNext()
at System.Threading.ThreadPoolWorkQueue.Dispatch()
at System.Threading.PortableThreadPool+WorkerThread.WorkerThreadStart()
On 1.0.16 the same fault came through JsonRpc.SendMessageAsync from CopilotSession.HandlePendingPermissionRequestAsync.
Pattern
Both crashes happened right after the model issued two MCP tool calls in parallel. The host log shows two preToolUse approvals, then two permission-request approvals, then an MCP HTTP call returning 200, and then the fault while writing a response frame back to the runtime. FfiRuntimeHost.SendFrame already holds _lifecycleLock and checks _disposed and _connectionId, so the managed side does not seem to be writing concurrently or after close. The fault appears to be in the native write path.
Frequency: about 1 crash in 15–20 multi-tool conversations when replaying real user sessions (each 1–4 turns, 10–60 tool calls). Single-turn tests and a 40-turn sequential stress run did not reproduce it, so concurrency between parallel tool calls looks like a factor.
Possibly related: on 1.0.16 we also saw one turn hang forever. The session's events.jsonl had hook.start for preToolUse with no matching hook.end, even though our hook returns synchronously.
Expected
A response write to an open connection either succeeds or fails with a managed error. It should never crash the host process.
Happy to run a build with extra native logging if that helps.
- 主要语言
- Java
- 星标
- 10.7k
- 派生
- 1.5k
- PR 合并指标
- 30 天内没有已合并 PR
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 没有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
github/copilot-sdk 的其他 Issue
-
Rust: ElicitationRequest drops the tool call id from elicitation.requested可能重新可做 关联的 PR 已关闭且未合并。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
github/copilot-sdk#2900 ·
-
难度 1/5 1 小时以内 新手友好度 84/100
github/copilot-sdk#2876 · 1 条评论 · 1 个 reaction ·
-
Python ModelLimits drops max_output_tokens from model metadata可能重新可做 关联的 PR 已关闭且未合并。 未关闭bug
难度 2/5 1-3 小时 新手友好度 78/100
github/copilot-sdk#2798 · 1 条评论 ·
-
难度 2/5 1-3 小时 新手友好度 65/100
github/copilot-sdk#2759 ·
-
docs/AGENTS.md is repo authoring guidance, but everything in docs/ gets published可能重新可做 关联的 PR 已关闭且未合并。 未关闭documentation
难度 1/5 1 小时以内 新手友好度 85/100
github/copilot-sdk#2758 ·
查看 github/copilot-sdk 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 75/100
ls1intum/thesis-management#1473 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 76/100
LunaDeerMC/Dominion#301 · 1 条评论 ·
-
[FEATURE] Expose external refresh, node-level translog and warmer stats可能已有人在做 关联的 PR 仍在进行中或已合并。 未关闭untriaged
难度 2/5 1-3 小时 新手友好度 68/100
opensearch-project/opensearch-prometheus-exporter#680 ·
维护者通常 2 天内回复
-
难度 2/5 1-3 小时 新手友好度 85/100
-
难度 2/5 1-3 小时 新手友好度 66/100
维护者通常 2 天内回复