CommandCodeAI / CommandCodeAI/command-code

Background agent result causes “200 Failed to process successful response”

Open
#786 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
4k
Forks
350
PR merge metrics
No merged PRs in 30d

Description

Summary

I was running a session with two background agents. One finished normally, but the second one ran for a very long time and eventually stopped with an error.

When I continued the main session, it tried to retrieve the result of that agent with AGENT(output). The result actually appeared in the UI (... +12 lines), but immediately after that Command Code returned:

Error: 200 Failed to process successful response

Typing continue just brings me back to the same problem, so the session is effectively stuck.

Trace ID: bb9fe6a5d866dd91c2d545423130da57

The main model was GLM-5.3-Flash through Fireworks and was working normally before this happened. I’m attaching the session JSONL as well.

Expected Behavior

If a background agent finishes or fails, the main agent should be able to retrieve whatever result/status is available and continue working.

A failed background agent should not make the parent session unusable.

Actual Behavior

The background agent result seems to be available because AGENT(output) displays it in the UI, but Command Code then fails with:

200 Failed to process successful response

The current turn stops and continuing the session causes the same issue again.

Steps to reproduce the issue
  1. Start a session and let the main agent launch a background agent.
  2. In my case the background agent ran for a long time (~139 minutes) and eventually errored.
  3. Continue the parent session and ask it to retrieve the background agent result.
  4. Command Code calls AGENT(output).
  5. The agent output appears to be returned, but the parent turn immediately fails with 200 Failed to process successful response.
  6. Type continue and the session gets stuck on the same point again.
Command Code Version

1.39.3

Operating System

macOS

Terminal/IDE

Terminal

Shell

zsh

Session file (optional)

3075aad8-c5ec-4898-a3ec-7a736d98ad02.jsonl.zip
For context, the problematic background agent had run for ~139 minutes, used ~1.88M tokens over 23 turns, and then errored.

Fix prompt (optional)

No response

Additional context

OS: macOS Tahoe 26.6.2

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by inspecting the attached session JSONL around the AGENT(output) call and the subsequent Command Code error. Reproduce the long-running background-agent failure if possible, then trace how the returned result and failed status are processed. Done means the parent session can retrieve either result or status and continue without repeating the 200 error.

Written by the indexing model from the issue text.

Assessment

Domain
ai, cli
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.