Duplicate Item Errors #3558

Activity

1. psulightning

   added

   triage

   on May 28, 2026
2. psulightning

   added the

   Bug

   issue type on May 28, 2026
3. examon

   added

   area:modelsModel selection, availability, switching, rate limits, and model-specific behaviorModel selection, availability, switching, rate limits, and model-specific behavior

   area:context-memoryContext window, memory, compaction, checkpoints, and instruction loadingContext window, memory, compaction, checkpoints, and instruction loading

   on May 28, 2026
4. github-actions

   removed

   triage

   on May 28, 2026
5. tjaensch commented on May 28, 2026

   

   tjaensch

   on May 28, 2026

   More actions

   Confirming this from a different setup. Reliably reproducing today (2026-05-28) against models gpt-5.5 and gpt-5.4 in a GitHub Actions runner via Copilot CLI invoking a custom skill. Error fires on the very first skill(...) tool call, after two transient_bad_request retries. Three back-to-back runs, three different fc_call_* IDs, same Duplicate item found outcome each time. No prompt / agent / skill changes vs. a successful run on 2026-05-19, so the trigger appears to be entirely server-side.

   👍React with 👍2Reacted by Collin Barrett and WilsonHeres
6. collinbarrett commented on May 28, 2026

   

   collinbarrett

   on May 28, 2026

   Last edited by collinbarrett

   More actions

   I'm suspecting this is linked to a Copilot outage here based on when we started seeing the same issue: https://www.githubstatus.com/incidents/rhqcgg8lg6mm

   But, perhaps Copilot CLI could be patched to show a more useful error message if it's a cloud issue in the future.

   👍React with 👍2Reacted by Troy Jones and WilsonHeres
7. yuriyp commented on May 28, 2026

   

   yuriyp

   on May 28, 2026

   More actions

   I’m seeing the same issue on Windows with Copilot CLI 1.0.54.

   I fully reset local state by deleting %LOCALAPPDATA%\copilot and reproduced it again from a clean start, so this does not seem to be caused by stale session data on disk.

   I also did not install any extra plugins or custom MCP servers. The logs only show the built-in remote github-mcp-server.

   In my case, the failure happens during task/subagent execution, and after the first error the CLI retries with the same exact fc_call_* id (fc_call_hQX8mWYeH4kmsw1OFJWCHKec).

   That makes it look like a CLI runtime/retry bug where an already-used tool/function-call item is being re-sent from in-memory agent state.

   If useful, I can share the relevant log excerpt showing repeated WebSocket 400 errors for the same fc_call_* id.
8. eavidan commented on Jun 14, 2026

   

   eavidan

   on Jun 14, 2026

   More actions

   I am seeing the same issue via the Python Copilot SDK

   async with await client.create_session(session_config) as session: 
     for prompt in prompts: 
       response = await session.send_and_wait({"prompt": prompt}, timeout=6000)
   

   This failed for me when the session config had {"streaming": True}
   The same sequential same-session flow appears to work after changing to {"streaming": False}
9. patniko

   marked Frequent websocket_error: Duplicate item found (fc_call_* replay from session-state) #3559 as a duplicate of this issue on Oct 26, 2026