mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
jif
baddb5e686
## Why Responses WebSocket requests were encoded in two steps: first into a full `serde_json::Value`, then again into the JSON string sent over the socket. That walks the full request twice and keeps an extra JSON tree alive. These requests can contain the complete conversation history and tool schemas, so the extra work grows with the request size. ## What changed - serialize `ResponsesWsRequest` directly to the wire string - pass that string through the existing WebSocket stream and send path - keep the existing error mapping, tracing, send timeout, and telemetry behavior - compare the new wire JSON with the previous `to_value` payload in a focused test ## Performance I measured both paths in an optimized temporary test using a 6,324,180-byte request: 4 MiB of history plus 256 tools with 8 KiB descriptions. Each path ran 100 times. - previous `to_value` + `to_string`: 209 ms total, 2.09 ms per request - direct `to_string`: 174 ms total, 1.74 ms per request - difference: about 17% faster, or 0.35 ms per request The direct path also removes one full temporary `serde_json::Value` tree. For this mostly string-backed payload, that avoids roughly one payload-sized copy plus the JSON node overhead. The exact memory saving depends on the request shape. The temporary benchmark was removed before committing. ## Validation - `just test -p codex-api` — 125 passed - `just fix -p codex-api`
baddb5e686
·
2026-06-15 18:33:35 +02:00
History