hookSpecificOutput.additionalContext not injected into system prompt (Windows)
Status Fixed / completed
Reported on v2.1.177
Maintainer reply None cached
Activity 3 comments · opened Jun 21, 2026 · closed Jun 21, 2026
Bug Description
Plugin hooks that return hookSpecificOutput.additionalContext are executed successfully, but the content is NOT injected into the system prompt sent to the model.
Environment
- Claude Code version:
2.1.177 - Platform: Windows 11 (Git Bash)
- Shell:
/bin/bash.exe
Steps to Reproduce
- Install the
superpowersplugin (which has a SessionStart hook) - Start Claude Code with
claude --debug hooks - The hook executes successfully and returns
additionalContext(5632 chars) - Test injection: Modify the hook to add a unique marker (e.g.,
TESTMARKER_12345_67890) to theadditionalContextcontent - Start a new Claude Code session
- Ask the model: "Does your system prompt contain TESTMARKER_12345_67890?"
- Model responds: "No, I don't see that marker"
Expected Behavior
The additionalContext from the hook should be injected into the system prompt, and the model should be able to see it.
Actual Behavior
- Debug log shows:
Hook SessionStart provided additionalContext (5632 chars) - But the model cannot see the injected content
- No log entry confirms injection into the system prompt
Evidence
Debug log (b37dc0c7-d6fa-4fe6-8475-e956666f41f8.txt):
2026-06-21T08:58:16.347Z [DEBUG] Hook SessionStart:startup (SessionStart) success:
{
"hookSpecificOutput": {
"hookEventName": "SessionStart",
"additionalContext": "<EXTREMELY_IMPORTANT>\nYou have superpowers..."
}
}
2026-06-21T08:58:16.348Z [DEBUG] Hook SessionStart provided additionalContext (5632 chars)But when asked, the model reports no knowledge of the injected content.
Additional Context
This is a bug in the injection mechanism itself, not related to the model. The TESTMARKER test proves that additionalContext is not being added to the system prompt at all, regardless of which model is being used.
3 Comments
Update: Root Cause Identified - Not a Claude Code Bug
After thorough investigation, I've identified the root cause and confirmed this is not a Claude Code bug.
Key Finding
The hook execution is identical for both model configurations:
The Difference
| Config | Model | Superpowers |
|--------|-------|-------------|
| ark-code-latest | | ✅ Works |
| mimo | | ❌ Doesn't work |
The only difference is the API endpoint and model name. Claude Code's configuration (settings.json, hooks, plugins) is identical.
Root Cause
The issue is with the mimo proxy (), not Claude Code. The proxy either:
Evidence
Conclusion
This is a third-party proxy compatibility issue, not a Claude Code bug. Closing this issue.
Update: Root Cause Identified - Not a Claude Code Bug
After thorough investigation, I've identified the root cause and confirmed this is not a Claude Code bug.
Key Finding
The hook execution is identical for both model configurations:
The Difference
| Config | Model | Superpowers |
|--------|-------|-------------|
| ark-code-latest | ark-code-latest | Works |
| mimo | mimo-v2.5-pro[1m] | Does not work |
The only difference is the API endpoint and model name. Claude Code configuration (settings.json, hooks, plugins) is identical.
Root Cause
The issue is with the mimo proxy (token-plan-cn.xiaomimimo.com/anthropic), not Claude Code. The proxy either:
Evidence
Conclusion
This is a third-party proxy compatibility issue, not a Claude Code bug. Closing this issue.
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.