Skip to content

chore(atm): luna runs gpt-6.1-luna in the cipher and lumen panes - #2288

Closed
randlee wants to merge 1 commit into
developfrom
fix/codex-6.1-luna
Closed

randlee wants to merge 1 commit into
developfrom
fix/codex-6.1-luna

Conversation

@randlee

@randlee randlee commented Oct 29, 2026

Copy link
Copy Markdown
Owner

The last 6.0 model pins in this config, now that terra moved to 6.1 (2026-10-27).

line 100  cipher   gpt-6-luna    -> gpt-6.1-luna   (with model_reasoning_effort=high)
line 144  lumen    gpt-6-luna    -> gpt-6.1-luna

After this every codex pane pins a 6.1 model: terra x4, luna x2, sol x1. Two lines, no behavioural change beyond the model.

The remaining 6.0 pins after terra moved to 6.1. Every codex pane in this
config now pins a 6.1 model: terra x4, luna x2 (cipher with high reasoning
effort, lumen), sol x1.
@randlee
randlee requested a review from rand-lee October 29, 2026 14:38
@randlee

randlee commented Oct 30, 2026

Copy link
Copy Markdown
Owner Author

Closing — the premise was wrong. gpt-6.1-luna is not a supported model: codex exec --model gpt-6.1-luna returns "The 'gpt-6.1-luna' model is not supported when using Codex with a ChatGPT account", while gpt-6-luna returns OK. Luna's current model is gpt-6-luna, so the 6.0 pins this PR 'fixed' were already correct. Verified matrix below.

No replacement PR needed — atm-core's luna panes are right as they stand.

@randlee randlee closed this Oct 30, 2026
@randlee
randlee deleted the fix/codex-6.1-luna branch October 30, 2026 06:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant