Add session-stable prompt_cache_key (patch 0006)

Main turns now set prompt_cache_key to the session/conv id. Responses
already sent that via the conv-id fallback; Chat Completions now puts
the same value in `user`. Recap and /btw keep sharing the parent
session key — not an agent-scoped suffix.

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

@@ -0,0 +1,134 @@
+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 4d9ce755a316ab0cca430aa3126d3ceb18e541b5..7c787b6dce09682445438274ed5a35008f242a6d 100644
+--- a/crates/codegen/xai-chat-state/src/actor/request_builder.rs
++++ b/crates/codegen/xai-chat-state/src/actor/request_builder.rs
+@@ -105,7 +105,10 @@ 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 604a121b4897d1e245a15f99318130af0ad02462..e9899af98ecf80eb541ce120f4aad489e0e25dae 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 982839bbe822874651bc37e257e4e4a7442f6f87..91d61f3a46524cdf5c11cb753c739abe8481f503 100644
+--- a/crates/codegen/xai-grok-sampling-types/src/conversation.rs
++++ b/crates/codegen/xai-grok-sampling-types/src/conversation.rs
+@@ -623,10 +623,29 @@ 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)
+@@ -2399,6 +2418,35 @@ 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..b80820fbbf3c96e348f44880c432361eb537817a 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
+@@ -295,7 +295,7 @@ impl From<ConversationRequest> for ChatCompletionRequest {
+             top_p: req.top_p,
+             frequency_penalty: None,
+             presence_penalty: None,
+-            user: None,
++            user: req.session_cache_key().map(str::to_owned),
+             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]