Regression in muli-agent spawning in 0.113.0 #14288

Activity

1. randall-8080

   added

   bugSomething isn't workingSomething isn't working

   on Mar 11, 2026
2. github-actions

   added

   CLIIssues related to the Codex CLIIssues related to the Codex CLI

   tool-callsIssues related to tool callingIssues related to tool calling

   on Mar 11, 2026
3. github-actions commented on Mar 11, 2026

   

   github-actionsbot

   on Mar 11, 2026 – with GitHub Actions

   Contributor

   More actions

   Potential duplicates detected. Please review them and close your issue if it is a duplicate.

   • Forked Worker Inherits Parent User Intent and Misinterprets It as Direct Instruction (Recursive Delegation Attempt) #13491

   Powered by Codex Action
4. SproutSeeds commented on Mar 16, 2026

   

   SproutSeeds

   on Mar 16, 2026

   More actions

   I have a strong local root-cause candidate for this one, but I’d frame it narrowly.

   My current read is that the issue is likely in forked sub-agent handoff rather than generic multi-agent planning.

   What seems to be happening:

   • spawn_agent(..., fork_context=true) inherits parent rollout history into the child
   • the child also gets a synthetic handoff telling it to treat the next user message as its task
   • but the parent’s most recent live user directive can still remain in inherited history
   • if that parent directive is itself about delegation/orchestration, the child can reinterpret it as its own instruction and recurse

   This also seems consistent with the older related report in #13491.

   Locally, I patched the forked-spawn path to:

   • truncate inherited history before the parent’s last user message
   • preserve the parent spawn_agent function-call marker when needed
   • keep the synthetic fork handoff output

   That gives the child completed background context without the parent’s active directive.

   I added targeted regression coverage for:

   • unit-level forked spawn history shaping
   • rollout truncation before the last user message
   • integration coverage showing the child still receives earlier parent context, but not the current parent turn prompt

   Those targeted codex-core tests passed locally.

   I also ran a full workspace cargo test. It was not fully green on this machine, but the failures I hit were in unrelated EMFILE rollback-reconstruction tests and local seatbelt sandbox tests, not in the multi-agent fork path.

   👍React with 👍1Reacted by Ignat Remizov
5. jif-oai commented on Mar 16, 2026

   

   jif-oai

   on Mar 16, 2026

   Contributor

   More actions

   This is due to model behaviour. We will study this and see what's the best way to fix.
   Truncating in the parent history might actually be sub-optimal...
6. randall-8080 commented on Mar 16, 2026

   

   randall-8080

   on Mar 16, 2026

   Author

   More actions

   Created a new log file for a slightly different behavior that I just observed where the top-level agent spawned the three specialized agents. Each of the specialized agent spawn three additional specialized agents, for a total of ten agents.

   Log: 019cf8a6-81a4-7a22-bf56-98dcc64c270e
7. SproutSeeds commented on Mar 17, 2026

   

   SproutSeeds

   on Mar 17, 2026

   More actions

   Model behavior can still affect whether the child chooses to delegate again.
   The forked child history is also leaking a product-side instruction boundary.

   • spawn_agent(..., fork_context=true) snapshots parent rollout into the child
   • the child already receives its own task framing from the synthetic fork handoff and synthetic spawn_agent output
   • on clean upstream main, the second-generation fork test still fails at assert!(!body_contains(&grandchild_request, TURN_1_PROMPT)), so the grandchild request still contains the parent's live "spawn a child and continue" directive instead of only its own spawned task
   • in the targeted local tests, trimming inherited rollout before the newest surviving user-turn segment kept earlier completed context and spawn markers but removed the conflicting live delegation turn
   • that also removes the leaked parent TurnStarted scaffolding instead of cutting only at the raw user-message item
   • re-attaching the specific parent spawn_agent call and synthetic output keeps the fork handoff contract intact after trimming
   • the segment-based version still passes the same first-generation and second-generation fork tests locally

   The leaked boundary is the inherited live delegation turn, not generic background context.
   The strongest current fix shape is: drop the newest surviving user-turn segment from the forked rollout, then re-attach the specific parent spawn_agent call and synthetic output before handing control to the child.

   Patch I validated:
   SproutSeeds@a26e5df

   Full branch:
   https://github.com/SproutSeeds/codex/tree/sprout/issue-14288-fork-turn-segment
8. diogovalada

   added a commit that references this issue on Aug 26, 2026

   fix(core): scope inherited history for forked subagents

   ...

   8a2f27b