openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-11-08 20:40:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Normalize image detail for the receiving model (#44249)

Browse Source 
## Why

Switching models can send images from conversation history with `detail: original` to a model that does not support it.

## What changed

Normalize image details on request copies using the receiving model's capabilities. Downgrade `original` to `high` when unsupported, covering user messages and function and custom tool outputs. Preserve stored image details so switching back to a supporting model retains `original`, and continue stripping details for Responses Lite.

## Testing

Expand unit coverage across image detail values and model capabilities. Extend integration coverage for model switches within and between turns, text-only models, and resumed and forked threads, including assertions that persisted tool outputs remain unchanged.

GitOrigin-RevId: 2561651ea74f045e00f708ae53771a41dcd49c94
This commit is contained in:
Abhinav
2026-09-09 17:56:06 +00:00
committed by copyberry
parent aa88a0333c
commit 6eecd04fc1
5 changed files with 199 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/src/client.rs
+1 -1
View File
@@ -897,7 +897,7 @@ impl ModelClient {
service_tier: Option<String>,
responses_metadata: &CodexResponsesMetadata,
) -> Result<ResponsesApiRequest> {
let mut input = prompt.get_formatted_input_for_request(model_info.use_responses_lite);
let mut input = prompt.get_formatted_input_for_request(model_info);
let is_openai = self.state.provider.info().is_openai();
let (instructions, tools) = if model_info.use_responses_lite {
// These prompt-only items are rebuilt on every request. Hash their visible payloads