newgrok/patches/0006-Pin-a-session-stable-prompt_cache_key-on-main-turns.patch

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: iceBear67 <icebear67@sfclub.cc>
Date: Sun, 16 Aug 2026 03:13:22 +0000
Subject: [PATCH] Pin a session-stable prompt_cache_key on main turns

Main turns already reached the Responses wire as prompt_cache_key via
the x_grok_conv_id fallback. Set the field explicitly so Chat Completions
can put the same session id in `user`, and so recap /btw keep sharing
one key. Do not agent-scope: that would split the prefix those side
calls are built to ride.

diff --git a/crates/codegen/xai-chat-state/src/actor/request_builder.rs b/crates/codegen/xai-chat-state/src/actor/request_builder.rs
index 64f497a0b0419b167faea18e35b32b941080620e..109a97521e590dc1f14d367c3d349600001558f8 100644
--- a/crates/codegen/xai-chat-state/src/actor/request_builder.rs
+++ b/crates/codegen/xai-chat-state/src/actor/request_builder.rs
@@ -106,7 +106,10 @@ impl ChatStateActor {
             x_grok_deployment_id: None,
             x_grok_user_id: None,
             trace,
-            prompt_cache_key: None,
+            // Same session id the Responses mapping already fell back to via
+            // `x_grok_conv_id`. Set it explicitly so Chat Completions `user`
+            // and side-calls share one key without depending on that fallback.
+            prompt_cache_key: Some(conv_id.clone()),
             reasoning_effort: self.state.sampling_config.reasoning_effort,
             json_schema: None,
         }
diff --git a/crates/codegen/xai-chat-state/src/actor/tests.rs b/crates/codegen/xai-chat-state/src/actor/tests.rs
index 07d581d48e78a7c69e78a7f0d8d2ce1844a3190b..dee7b542755b8d97dfcc4e621d01bb809488d017 100644
--- a/crates/codegen/xai-chat-state/src/actor/tests.rs
+++ b/crates/codegen/xai-chat-state/src/actor/tests.rs
@@ -1576,6 +1576,7 @@ async fn build_request_includes_all_messages() {
     assert_eq!(request.items.len(), 2);
     assert_eq!(request.x_grok_conv_id, Some("conv-1".to_string()));
     assert_eq!(request.x_grok_req_id, Some("req-1".to_string()));
+    assert_eq!(request.prompt_cache_key, Some("conv-1".to_string()));
 }
 
 #[tokio::test]
diff --git a/crates/codegen/xai-grok-sampling-types/src/conversation.rs b/crates/codegen/xai-grok-sampling-types/src/conversation.rs
index 7bd0cd870c5400ef4d3fb2ba6ce50cfc53ffd62c..db582daced370d89cc1158d5cbbf81b7a156ba4f 100644
--- a/crates/codegen/xai-grok-sampling-types/src/conversation.rs
+++ b/crates/codegen/xai-grok-sampling-types/src/conversation.rs
@@ -627,10 +627,29 @@ pub struct ConversationRequest {
     /// JSON Schema for structured output (strict mode).
     pub json_schema: Option<serde_json::Value>,
     /// Sticky routing key for prompt-cache reuse; overrides `x_grok_conv_id` for routing.
+    ///
+    /// Session-scoped, not agent-scoped: recap and `/btw` replay the parent
+    /// conversation under this key. A per-agent suffix would split the prefix
+    /// cache those side-calls are built to share. Only the Responses mapping
+    /// puts this field on the wire; Chat Completions surfaces the same value
+    /// as `user` (see [`Self::session_cache_key`]).
     pub prompt_cache_key: Option<String>,
 }
 
 impl ConversationRequest {
+    /// Session-stable key for prompt-cache sticky routing.
+    ///
+    /// Prefer an explicit [`Self::prompt_cache_key`], then session id, then
+    /// conv id. Callers that share a conversation prefix (main turn, recap,
+    /// `/btw`) must resolve to the same string.
+    pub fn session_cache_key(&self) -> Option<&str> {
+        self.prompt_cache_key
+            .as_deref()
+            .or(self.x_grok_session_id.as_deref())
+            .or(self.x_grok_conv_id.as_deref())
+            .filter(|s| !s.is_empty())
+    }
+
     /// Strip every image; returns the stripped URLs.
     pub fn strip_images(&mut self) -> Vec<Arc<str>> {
         strip_images_where(&mut self.items, |_| true)
@@ -2416,6 +2435,35 @@ mod tests {
     use crate::tool_overrides::*;
     use assert_matches::assert_matches;
 
+    #[test]
+    fn session_cache_key_prefers_explicit_then_session_then_conv() {
+        let mut req = ConversationRequest {
+            x_grok_conv_id: Some("conv".into()),
+            x_grok_session_id: Some("session".into()),
+            prompt_cache_key: Some("explicit".into()),
+            ..Default::default()
+        };
+        assert_eq!(req.session_cache_key(), Some("explicit"));
+        req.prompt_cache_key = None;
+        assert_eq!(req.session_cache_key(), Some("session"));
+        req.x_grok_session_id = None;
+        assert_eq!(req.session_cache_key(), Some("conv"));
+        req.x_grok_conv_id = Some(String::new());
+        assert_eq!(req.session_cache_key(), None);
+    }
+
+    #[test]
+    fn chat_completions_user_carries_session_cache_key() {
+        let req = ConversationRequest {
+            items: vec![ConversationItem::user("hi")],
+            model: Some("test-model".into()),
+            prompt_cache_key: Some("sess-1".into()),
+            ..Default::default()
+        };
+        let mapped = ChatCompletionRequest::from(req);
+        assert_eq!(mapped.user.as_deref(), Some("sess-1"));
+    }
+
     /// Keeps `forwards_prompt_cache_key()` honest against each mapping: a key that never reaches the wire looks like a 0% cache hit, not a bug.
     #[test]
     fn prompt_cache_key_reaches_the_wire_only_where_the_backend_claims() {
diff --git a/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions.rs b/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions.rs
index dac77d82f7f96836f5f4ed26f2e12eb13164e4f5..05a683317ae774f3ba674202ff12ae3ae50f56ec 100644
--- a/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions.rs
+++ b/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions.rs
@@ -251,6 +251,8 @@ impl From<ChatResponseMessage> for ConversationItem {
 
 impl From<ConversationRequest> for ChatCompletionRequest {
     fn from(req: ConversationRequest) -> Self {
+        // Copy before any field moves — `session_cache_key` borrows `req`.
+        let user = req.session_cache_key().map(str::to_owned);
         let messages: Vec<ChatRequestMessage> = conversation_to_chat_messages(req.items);
 
         let tools_is_empty = req.tools.is_empty();
@@ -295,7 +297,7 @@ impl From<ConversationRequest> for ChatCompletionRequest {
             top_p: req.top_p,
             frequency_penalty: None,
             presence_penalty: None,
-            user: None,
+            user,
             tools,
             tool_choice,
             search_parameters: None,
diff --git a/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions_tests.rs b/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions_tests.rs
index 8d2afa36362471676804bfa8676d0294ca56049d..1a29113ca0e467b9a5e39faa06cd468d4f45a242 100644
--- a/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions_tests.rs
+++ b/crates/codegen/xai-grok-sampling-types/src/conversation/chat_completions_tests.rs
@@ -52,6 +52,7 @@ fn test_conversation_request_to_chat_completion() {
     assert_eq!(chat_req.model, Some("grok-3".to_string()));
     assert_eq!(chat_req.temperature, Some(0.7));
     assert_eq!(chat_req.messages.len(), 2);
+    assert_eq!(chat_req.user, None);
 }
 
 #[test]