openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-10-30 19:18:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Configure memory consolidation service tiers independently (#57568)

Browse Source 
## Why

Memory consolidation inherits the session's service tier. Give background consolidation its own setting, defaulting to Standard.

## What changed

Add `memories.consolidation_service_tier` with a default of `"default"` and apply it to the consolidation agent. Normalize recognized tier aliases, including `"fast"` to `"priority"`, and expose the setting in the configuration schema.

## Testing

Add coverage for configuration parsing and alias normalization, Standard consolidation despite an Ultrafast session tier, and an explicit `"flex"` consolidation override.

GitOrigin-RevId: 58031ad56196152d212531d56e7fe9813f83317e
This commit is contained in:
mandal-OAI
2026-10-27 21:51:26 +00:00
committed by copyberry
parent f00c70f5d0
commit 02bc25c89f
5 changed files with 66 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/src/config/config_tests.rs
+3
View File
@@ -336,6 +336,7 @@ min_rollout_idle_hours = 24
min_rate_limit_remaining_percent = 12
extract_model = "gpt-5-mini"
consolidation_model = "gpt-5.2"
consolidation_service_tier = "fast"
"#;
let memories_cfg =
toml::from_str::<ConfigToml>(memories).expect("TOML deserialization should succeed");
@@ -355,6 +356,7 @@ consolidation_model = "gpt-5.2"
min_rate_limit_remaining_percent: Some(12),
extract_model: Some("gpt-5-mini".to_string()),
consolidation_model: Some("gpt-5.2".to_string()),
consolidation_service_tier: Some("fast".to_string()),
}),
memories_cfg.memories
);
@@ -383,6 +385,7 @@ consolidation_model = "gpt-5.2"
min_rate_limit_remaining_percent: 12,
extract_model: Some("gpt-5-mini".to_string()),
consolidation_model: Some("gpt-5.2".to_string()),
consolidation_service_tier: "priority".to_string(),
}
);