Remove the GLM restriction for Codex subagents - #273
Merged
Conversation
Drop the `skip_arms` guard that kept a GLM routing decision from being applied to Codex subagent spawns, so GLM is routed like any other arm. Removes the now unused GLM_SUBAGENT_SKIP_MESSAGE constant and updates the corresponding test. Co-authored-by: Isaac
masonc08
force-pushed
the
masonc08/remove-glm-subagent-restriction
branch
from
August 5, 2026 20:34
570771d to
8c80e81
Compare
tt-le
approved these changes
Aug 5, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What & why
Drops the
skip_armsguard incodex_routing.route_pre_tool_usethat prevented a GLM routing decision from being applied to Codex subagent spawns. With it removed, GLM is routed like any other arm — the subagent'smodelis rewritten tosystem.ai.glm-5-2.Scope is deliberately minimal: only the guard, the now-unused
GLM_SUBAGENT_SKIP_MESSAGEconstant, and the one test that asserted the skip.Caveat worth flagging
The guard existed because Codex constrains a spawned subagent's model to its own model catalog, and GLM isn't in it — so a GLM-routed subagent may be rejected at spawn until GLM is present in the catalog (either via the gateway's model-list endpoint or a client-side catalog file). This PR removes the restriction on its own; the catalog side is tracked separately.
How do you know it works
test_spawn_glm_decision_applies_glm_modelreplaces the old skip test and asserts the GLM model is injected intoupdatedInput.This pull request and its description were written by Isaac.