github/codex
4
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-10-19 16:17:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Stop memory dual-write when v2 is selected (#55262)

Browse Source 
## Why

Dual-write prepares v2 memories while v1 is selected. Once v2 is selected, running the v1 pipeline is no longer needed.

## What changed

Run both memory pipelines only when `memories.dual_write` is enabled and `memories.version` selects v1. Run only v2 when it is selected, even if dual-write remains enabled. Update the configuration documentation and schema to describe this behavior.

## Testing

Extend the startup test to cover both selected versions, checking model request counts, versioned extraction and consolidation state, and the absence of v1 rollout summaries when v2 is selected.

GitOrigin-RevId: 1eb85bd67d7b32883b4ff086514a2acfb6b18f3a
This commit is contained in:
jif
2026-10-19 11:36:21 +00:00
committed by copyberry
parent c0ce901923
commit 71ab2ea77b
4 changed files with 113 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/config.schema.json
+1 -1
View File
@@ -2645,7 +2645,7 @@
"type": "boolean"
},
"dual_write": {
"description": "Generate both versions while the selected version supplies context.",
"description": "Generate both versions while v1 is selected; v2 runs alone after cutover.",
"type": "boolean"
},
"extract_model": {