Strip unsupported images from prompt history to guard against model switch

codex-rs/core/src/codex.rs

@@ -4010,7 +4010,11 @@ pub(crate) async fn run_turn(
         }
 
         // Construct the input that we will send to the model.
-        let sampling_request_input: Vec<ResponseItem> = { sess.clone_history().await.for_prompt() };
+        let sampling_request_input: Vec<ResponseItem> = {
+            sess.clone_history()
+                .await
+                .for_prompt(&turn_context.model_info.input_modalities)
+        };
 
         let sampling_request_input_messages = sampling_request_input
             .iter()
@@ -6923,7 +6927,9 @@ mod tests {
         rollout_items.push(RolloutItem::ResponseItem(assistant1.clone()));
 
         let summary1 = "summary one";
-        let snapshot1 = live_history.clone().for_prompt();
+        let snapshot1 = live_history
+            .clone()
+            .for_prompt(&reconstruction_turn.model_info.input_modalities);
         let user_messages1 = collect_user_messages(&snapshot1);
         let rebuilt1 =
             compact::build_compacted_history(initial_context.clone(), &user_messages1, summary1);
@@ -6964,7 +6970,9 @@ mod tests {
         rollout_items.push(RolloutItem::ResponseItem(assistant2.clone()));
 
         let summary2 = "summary two";
-        let snapshot2 = live_history.clone().for_prompt();
+        let snapshot2 = live_history
+            .clone()
+            .for_prompt(&reconstruction_turn.model_info.input_modalities);
         let user_messages2 = collect_user_messages(&snapshot2);
         let rebuilt2 =
             compact::build_compacted_history(initial_context.clone(), &user_messages2, summary2);
@@ -7004,7 +7012,10 @@ mod tests {
         );
         rollout_items.push(RolloutItem::ResponseItem(assistant3));
 
-        (rollout_items, live_history.for_prompt())
+        (
+            rollout_items,
+            live_history.for_prompt(&reconstruction_turn.model_info.input_modalities),
+        )
     }
 
     #[tokio::test]

codex-rs/core/src/compact.rs

@@ -112,7 +112,9 @@ async fn run_compact_task_inner(
 
     loop {
         // Clone is required because of the loop
-        let turn_input = history.clone().for_prompt();
+        let turn_input = history
+            .clone()
+            .for_prompt(&turn_context.model_info.input_modalities);
         let turn_input_len = turn_input.len();
         let prompt = Prompt {
             input: turn_input,

codex-rs/core/src/compact_remote.rs

@@ -87,7 +87,7 @@ async fn run_remote_compact_task_inner_impl(
         .collect();
 
     let prompt = Prompt {
-        input: history.for_prompt(),
+        input: history.for_prompt(&turn_context.model_info.input_modalities),
         tools: vec![],
         parallel_tool_calls: false,
         base_instructions,

codex-rs/core/src/context_manager/history.rs

@@ -15,6 +15,7 @@ use codex_protocol::models::FunctionCallOutputBody;
 use codex_protocol::models::FunctionCallOutputContentItem;
 use codex_protocol::models::FunctionCallOutputPayload;
 use codex_protocol::models::ResponseItem;
+use codex_protocol::openai_models::InputModality;
 use codex_protocol::protocol::TokenUsage;
 use codex_protocol::protocol::TokenUsageInfo;
 use std::ops::Deref;
@@ -79,9 +80,11 @@ impl ContextManager {
     }
 
     /// Returns the history prepared for sending to the model. This applies a proper
-    /// normalization and drop un-suited items.
-    pub(crate) fn for_prompt(mut self) -> Vec<ResponseItem> {
-        self.normalize_history();
+    /// normalization and drops un-suited items. When `input_modalities` does not
+    /// include `InputModality::Image`, images are stripped from messages and tool
+    /// outputs.
+    pub(crate) fn for_prompt(mut self, input_modalities: &[InputModality]) -> Vec<ResponseItem> {
+        self.normalize_history(input_modalities);
         self.items
             .retain(|item| !matches!(item, ResponseItem::GhostSnapshot { .. }));
         self.items
@@ -309,12 +312,16 @@ impl ContextManager {
     /// This function enforces a couple of invariants on the in-memory history:
     /// 1. every call (function/custom) has a corresponding output entry
     /// 2. every output has a corresponding call entry
-    fn normalize_history(&mut self) {
+    /// 3. when images are unsupported, image content is stripped from messages and tool outputs
+    fn normalize_history(&mut self, input_modalities: &[InputModality]) {
         // all function/tool calls must have a corresponding output
         normalize::ensure_call_outputs_present(&mut self.items);
 
         // all outputs must have a corresponding function/tool call
         normalize::remove_orphan_outputs(&mut self.items);
+
+        // strip images when model does not support them
+        normalize::strip_images_when_unsupported(input_modalities, &mut self.items);
     }
 
     fn process_item(&self, item: &ResponseItem, policy: TruncationPolicy) -> ResponseItem {