{"version":"2.1.271","anchor":"teleport-relay-learns-about-forkedsubagent-loops","canonical_anchor":"teleport-relay-learns-about-forkedsubagent-loops","heading":"Teleport relay learns about forked\/subagent loops","tier":"internal","area":"Internals","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271\/e\/teleport-relay-learns-about-forkedsubagent-loops","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271","markdown":"### Teleport relay learns about forked\/subagent loops\n\nTeleport relay now distinguishes main-loop calls from forked\/subagent calls\n\n**What**\n\nThe \"teleport relay\" wrapper, which speeds up API calls by relaying them through a CCR session, now takes an explicit `loop` parameter marking whether the call comes from the \"main\" loop or a \"fork\" (such as a subagent). It uses different eligibility checks and different abort\/telemetry handling depending on which one it is, instead of applying the same checks to both.\n\n**Why**\n\nThis lets Claude Code apply relay rules that fit each kind of loop, so forked or subagent calls aren't forced through the same eligibility logic as the main conversation.\n\n- Area: Internals\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}