Skip to content

fix(codex): pin the Codex model explicitly (--ignore-user-config discards it) #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rschumann merged 1 commit into from
Aug 9, 2026
Merged

fix(codex): pin the Codex model explicitly (--ignore-user-config discards it) #9

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions lope/validators.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1668,6 +1668,14 @@ def validate(
# ─── Codex validator ───────────────────────────────────────────


# 2026-08-07: --ignore-user-config below discards ~/.codex/config.toml, so the user's default
# model never reached lope. Pin it explicitly instead. Reasoning stays "low" on purpose (see the
# comment in generate()): these are fast pass/fail gates, and xhigh would make every validation
# slow and expensive. For a heavyweight opinion call `codex exec` directly, which reads the user
# config (gpt-5.6-sol / xhigh). Override without editing this file: LOPE_CODEX_MODEL=<slug>.
CODEX_MODEL = os.environ.get("LOPE_CODEX_MODEL", "gpt-5.6-sol")


class CodexValidator(Validator):
"""Wraps `codex exec "<prompt>"` for validated review."""

Expand Down Expand Up @@ -1726,6 +1734,8 @@ def generate(
"--skip-git-repo-check",
"-s",
"workspace-write" if implementation_mode else "read-only",
"-m",
CODEX_MODEL,
"-c",
'model_reasoning_effort="low"',
],
Expand Down Expand Up @@ -1764,6 +1774,8 @@ def validate(
"--skip-git-repo-check",
"-s",
"read-only",
"-m",
CODEX_MODEL,
"-c",
'model_reasoning_effort="low"',
],
Expand Down
Loading