claude-code - 💡(How to fix) Fix [BUG] Remote trigger run returns HTTP 200 but agent never executes [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#48888Fetched 2026-04-16 06:48:15
View on GitHub
Comments
1
Participants
2
Timeline
4
Reactions
0
Author
Participants
Timeline (top)
labeled ×3commented ×1

Error Message

Error Messages/Logs

No error messages are returned. This is part of the issue — the API returns HTTP 200 for every run call with no indication of failure. There are no error

Code Example

No error messages are returned. This is part of the issue — the API returns   
  HTTP 200 for every run call with no indication of failure. There are no error 
  logs visible from the CLI or API.                                            
                                                                                
  The only observable evidence that the agent is not running:
  - Connected GitHub repo has no new commits after multiple trigger runs (latest
   commit remains 815a935 Initial commit)                                       
  - Gmail MCP produces no drafts despite explicit instructions to do so         
  - No failure notifications or emails received
RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues and this hasn't been reported yet
  • This is a single bug report (please file separate reports for different bugs)
  • I am using the latest version of Claude Code

What's Wrong?

Environment:

  • Claude Code CLI
  • macOS
  • Triggers managed via terminal (not claude.ai UI)

Trigger details:

  • Trigger ID: trig_01W76V5iZuzY1LUeozi8VWCY (also trig_01EJtuPZSFdWRMqQEeXxwHsg — previous trigger, same behaviour)
  • Environment ID: env_01HgbPFzSAvh65oZNx1v1mwY
  • Cron: 0 22 * * *
  • Model: claude-sonnet-4-6
  • Git source: GitHub private repo
  • MCP: Gmail connector attached

What happens: Every call to POST /v1/code/triggers/{id}/run returns HTTP 200. However, no
agent execution occurs — no git commits are pushed to the connected repo, and no Gmail drafts are created, even with the simplest possible test prompt ("create a draft email" / "echo text and git commit").

What I've tried:

  • Multiple trigger configurations (different prompts, with/without Gmail MCP, different permitted_tools values)
  • Corrected Gmail MCP URL from https://gmail.mcp.claude.com/mcp to https://gmailmcp.googleapis.com/mcp/v1
  • Deleted and recreated the trigger from scratch via the UI
  • Reconnected and reauthorised the Gmail integration
  • Verified the GitHub token is valid (returns HTTP 200 from GitHub API)
  • Both scheduled runs and manual run calls — neither produce any output

Expected behaviour:
Agent executes, commits to repo, and/or creates Gmail draft.

Actual behaviour:
API returns 200, nothing happens.

What Should Happen?

Expected behaviour:
Agent executes, commits to repo, and/or creates Gmail draft.

Actual behaviour:
API returns 200, nothing happens.

Error Messages/Logs

No error messages are returned. This is part of the issue — the API returns   
  HTTP 200 for every run call with no indication of failure. There are no error 
  logs visible from the CLI or API.                                            
                                                                                
  The only observable evidence that the agent is not running:
  - Connected GitHub repo has no new commits after multiple trigger runs (latest
   commit remains 815a935 Initial commit)                                       
  - Gmail MCP produces no drafts despite explicit instructions to do so         
  - No failure notifications or emails received

Steps to Reproduce

  1. Create a remote trigger via the Claude Code CLI using RemoteTrigger with
    action: "create", attaching a GitHub repo source and Gmail MCP connector
  2. Call RemoteTrigger with action: "run" on the trigger — API returns HTTP 200
  3. Wait 5+ minutes
  4. Check the connected GitHub repo for new commits — none appear
  5. Check Gmail for drafts/emails — none appear
  6. Repeat with the simplest possible prompt ("create a draft email to X with
    subject Y") — same result
  7. Delete and recreate the trigger from the claude.ai UI at
    https://claude.ai/code/scheduled — same result with new trigger ID

Note: The trigger prompt instructs the agent to commit to a git repo AND create a Gmail draft regardless of success or failure, so at minimum a draft
should always appear. Neither does.

Claude Model

Sonnet (default)

Is this a regression?

I don't know

Last Working Version

No response

Claude Code Version

⏺ claude-sonnet-4-6

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

No response

extent analysis

TL;DR

The issue might be related to the trigger configuration or the interaction between the Claude Code CLI and the Anthropic API, and verifying the trigger setup and the API requests could help identify the root cause.

Guidance

  • Review the trigger configuration, especially the action and prompt fields, to ensure they are correctly set up for the desired behavior.
  • Check the API requests made by the Claude Code CLI to verify that they are correctly formatted and sent to the Anthropic API.
  • Investigate the Anthropic API documentation to see if there are any specific requirements or restrictions for the claude-sonnet-4-6 model or the Gmail MCP connector.
  • Try modifying the trigger prompt to a simpler action, such as just committing to the GitHub repo, to isolate the issue.

Example

No code example is provided as the issue seems to be related to the configuration and interaction between the Claude Code CLI and the Anthropic API.

Notes

The lack of error messages or logs makes it challenging to diagnose the issue. The fact that the API returns HTTP 200 but no action is taken suggests that the issue might be related to the trigger configuration or the API request.

Recommendation

Apply workaround: Try modifying the trigger configuration and prompt to isolate the issue and identify the root cause. This approach can help determine if the problem is related to the specific trigger setup or the interaction with the Anthropic API.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING