Skip to content

armgit / ECC

Public Imported from GitHub
0

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

chore(codex): route sample roles to GPT-6 Sol and Luna

nguyenphivn1aea78011ba6
diff --git a/.codex/AGENTS.md b/.codex/AGENTS.md
index 847c7b317..9f6c5d28a 100644
--- a/.codex/AGENTS.md
+++ b/.codex/AGENTS.md
@@ -9,10 +9,10 @@ For repo navigation, surface ownership, and PR diff packet guidance, read
| Task Type | Recommended Model |
|-----------|------------------|
-| Routine coding, tests, formatting | GPT 5.5 |
-| Complex features, architecture | GPT 5.5 |
-| Debugging, refactoring | GPT 5.5 |
-| Security review | GPT 5.5 |
+| Routine coding, tests, formatting | GPT-6 Luna medium |
+| Complex features, architecture | GPT-6 Sol high |
+| Debugging, refactoring | GPT-6 Sol high |
+| Security review | GPT-6 Sol high |
## Skills Discovery
diff --git a/.codex/agents/docs-researcher.toml b/.codex/agents/docs-researcher.toml
index 4d6d8f479..5850a663e 100644
--- a/.codex/agents/docs-researcher.toml
+++ b/.codex/agents/docs-researcher.toml
@@ -1,4 +1,4 @@
-model = "gpt-5.5"
+model = "gpt-6-luna"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
diff --git a/.codex/agents/explorer.toml b/.codex/agents/explorer.toml
index 5665e2c87..0d2fec087 100644
--- a/.codex/agents/explorer.toml
+++ b/.codex/agents/explorer.toml
@@ -1,4 +1,4 @@
-model = "gpt-5.5"
+model = "gpt-6-luna"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
diff --git a/.codex/agents/reviewer.toml b/.codex/agents/reviewer.toml
index 4c27fdacb..24f1920f4 100644
--- a/.codex/agents/reviewer.toml
+++ b/.codex/agents/reviewer.toml
@@ -1,4 +1,4 @@
-model = "gpt-5.5"
+model = "gpt-6-sol"
model_reasoning_effort = "high"
sandbox_mode = "read-only"
diff --git a/tests/codex-config.test.js b/tests/codex-config.test.js
index 7d777d183..b0de7924a 100644
--- a/tests/codex-config.test.js
+++ b/tests/codex-config.test.js
@@ -112,6 +112,28 @@ if (
passed++;
else failed++;
+if (
+ test('sample Codex roles route research to GPT-6 Luna and review to GPT-6 Sol', () => {
+ const expected = {
+ 'explorer.toml': ['gpt-6-luna', 'medium'],
+ 'docs-researcher.toml': ['gpt-6-luna', 'medium'],
+ 'reviewer.toml': ['gpt-6-sol', 'high'],
+ };
+ for (const [roleFile, [model, effort]] of Object.entries(expected)) {
+ const roleConfig = fs.readFileSync(path.join(codexAgentsDir, roleFile), 'utf8');
+ assert.ok(roleConfig.includes(`model = "${model}"`), `${roleFile}: expected ${model}`);
+ assert.ok(
+ roleConfig.includes(`model_reasoning_effort = "${effort}"`),
+ `${roleFile}: expected ${effort} effort`,
+ );
+ }
+ const guidance = fs.readFileSync(path.join(repoRoot, '.codex', 'AGENTS.md'), 'utf8');
+ assert.ok(!/GPT 5\.5/.test(guidance), 'Expected model recommendations to be updated');
+ })
+)
+ passed++;
+else failed++;
+
console.log(`\nPassed: ${passed}`);
console.log(`Failed: ${failed}`);
process.exit(failed > 0 ? 1 : 0);