Runtime: MCP servers not fully loaded on session start and session unrecoverable after interrupt
まだ誰も着手していません。
評価
- 難易度
- 4/5
- 見積もり時間
- 3〜5日
- 初心者へのやさしさ
- 35/100
- issue の種類
- バグ
- 明瞭さ
- おおむね明確
- 活発さ
- 静か
- 技術スタック
- electron, typescript
- 領域
- desktop-dev, devtools
調査の方向性
Start by examining the harness-home canonical projection path for codepilot_runtime, then trace how that runtime discovers MCP servers and handles interrupts. Use the referenced main log and the settings.local.json permissions entry to compare expected and observed behavior. Done means the missing MCP server is loaded and an interrupted session can continue without Tool result is missing errors.
索引モデルが issue の本文から書いたものです。
説明
Summary
When using the Codepilot Runtime (codepilot_runtime), two distinct issues are observed:
-
MCP server loading is incomplete: Only a subset of configured MCP servers are synced to the agent loop. The third-party MCP server (
codepilot-image-gen) is consistently missing from the tool list, while onlyplaywrightandpencilare loaded. -
Session becomes unrecoverable after interrupt: Interrupting the agent mid-response causes the session to enter a permanently broken state, with
Tool result is missingerrors persisting across all subsequent turns.
Environment
- Codepilot version: 0.64.0 (upgraded from 0.63.0 on this session start)
- OS: Windows 11 Pro 10.0.22621
- Runtime mode:
codepilot_runtime(pinned in session) - Project path:
C:\Users\Administrator\codepilot
Issue 1: MCP servers not fully loaded
Observed behavior
Every agent loop turn logs the same line:
[agent-loop] Syncing 2 MCP servers: playwright, pencil
Only 2 MCP servers are synced. The tool list for the agent contains 58 tools total, consisting of built-in tools + Playwright MCP tools + Pencil MCP tools. No tools from the codepilot-image-gen MCP server are present.
Evidence
Log excerpt (repeated across all 7 turns in the session):
[agent-loop] Syncing 2 MCP servers: playwright, pencil
[agent-loop] Session 5857d9d0e7910ef2d8eebd4286c78124: model=deepseek-v4-flash, tools=[Read, Write, Edit, Bash, Glob, Grep, Skill, Agent, codepilot_dashboard_pin, ..., mcp__playwright__*, mcp__pencil__*] (58 total)
The codepilot-image-gen MCP tools are consistently absent from all 58-tool listings across all turns (lines 96, 120, 137, 181, 203, 222, 247, 272, 299, 317 of the log).
Related error
Every turn also logs:
[harness-home] Canonical projection failed { runtimeId: 'codepilot_runtime', reason: 'r is not a function' }
This error occurs on every single request (7 occurrences in the session log). It precedes the tool listing and may be related to the MCP loading failure.
Comparison: Claude Code Runtime works correctly
Under the same working directory, same MCP configuration, and same machine, using the Claude Code CLI Runtime:
codepilot-image-genMCP server is loaded automatically on session start- Agent can directly invoke
codepilot_generate_imagewithout any searching or manual configuration - MCP log confirms successful tool execution:
Tool 'codepilot_generate_image' completed successfully in 34s
Issue 2: Session unrecoverable after interrupt
Observed behavior
When the user interrupts the agent mid-response, the session enters a state where all subsequent turns fail with:
[agent-loop] streamText error: Tool result is missing for tool call call_7718bc899ed247aea103f200.
[agent-loop] Error: No output generated. Check the stream for errors.
Evidence
Interrupt log:
[codex.runtime] interrupt (route) — no active turn for 5857d9d0e7910ef2d8eebd4286c78124
[interrupt] fan-out { sessionId: '5857d9d0...', attempted: { native: true, codex_runtime: true, sdk: false } }
After the interrupt, the user sent 6 more messages. All of them failed with the same Tool result is missing error. Even switching the model (from deepseek-v4-flash to doubao-seed-2.1-turbo to claude-sonnet-5) and provider did not recover the session. The error persisted across model changes, and the sdk_session_id was repeatedly cleared and reset.
The session eventually became so broken that the user had to open a new session (478f123a...), but even that new session showed the same MCP loading issue (only 2 MCP servers synced).
Root cause analysis (speculative)
The recurring [harness-home] Canonical projection failed { runtimeId: 'codepilot_runtime', reason: 'r is not a function' } error suggests:
- The
harness-homemodule (likely responsible for resolving the home directory / config path for the agent harness) is failing duringcanonical projection— a path normalization operation - The error
'r is not a function'indicates a JavaScript runtime error, possibly a function reference that was expected but not found (e.g., a callback, a method on a config object, or a module export) - This failure may prevent the MCP configuration from being fully discovered and loaded, since MCP server definitions typically reside in the home directory config
Suggested investigation areas
-
harness-homemodule: Examine thecanonical projectionfunction for theruntimeId: 'codepilot_runtime'code path. The'r is not a function'error suggests a variableris expected to be a function but isundefinedor of a different type. -
MCP server discovery: Compare how the Codepilot Runtime discovers MCP servers vs. the Claude Code Runtime. The Codepilot Runtime may be using a different config resolution strategy that doesn't pick up all MCP servers.
-
Interrupt recovery: The
interrupthandler attempts recovery vianativeandcodex_runtimebut neither succeeds. TheTool result is missingerror suggests the interrupt left the tool call state machine in an inconsistent state. -
MCP server definition location: The
codepilot-image-genMCP server is only referenced in the project'ssettings.local.jsonpermissions list. ItsmcpServersdefinition may be in a non-standard location that the Codepilot Runtime doesn't check.
Configuration files
Project settings.local.json:
{
"permissions": {
"allow": [
"mcp__codepilot-image-gen__codepilot_generate_image"
]
}
}
Global ~/.claude/settings.json: Contains env vars, plugin config, theme, and permissions — but no mcpServers section relevant to codepilot-image-gen.
Log reference
- Session ID:
5857d9d0e7910ef2d8eebd4286c78124(broken session) - Log file:
%APPDATA%\codepilot\logs\codepilot-main.log - MCP log (working):
%LOCALAPPDATA%\claude-cli-nodejs\Cache\C--Users-Administrator-codepilot\mcp-logs-codepilot-image-gen\2026-08-03T05-34-03-041Z.jsonl
- 主要言語
- TypeScript
- スター
- 6.5k
- フォーク
- 697
- PR マージ指標
- 30日以内にマージされた PR はありません
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なし
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。
op7418/CodePilot のほかの issue
-
发生错误时提醒Error:successオープンbug P0-crash-or-interrupt
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
-
bug
難易度 2/5 1〜3時間 初心者へのやさしさ 75/100
-
難易度 2/5 1〜3時間 初心者へのやさしさ 65/100
-
Effort selector dropdown hidden for GLM models — blocks access to GLM-5.2 High/Max effort tiersオープン
難易度 2/5 1〜3時間 初心者へのやさしさ 68/100
-
bug P0-crash-or-interrupt
難易度 4/5 3〜5日 初心者へのやさしさ 48/100
op7418/CodePilot の issue をすべて見る
似ている issue
-
難易度 2/5 1〜3時間 初心者へのやさしさ 70/100
backnotprop/plannotator#2914 ·
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 78/100
microsoft/vscode-containers#655 ·
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 78/100
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 77/100
メンテナーはふだん 1 日以内に返信
-
難易度 2/5 1〜3時間 初心者へのやさしさ 72/100
dsh-tauri-desk/deepseek-harness-desktop#1477 · コメント 1 件 ·