v0.2.35

CHANGELOG.md

@@ -3,7 +3,13 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
-## [0.2.32] - 2026-07-22
+## [0.2.35] - 2026-07-23
+
+### Fixed
+- **Streaming Pipeline System Prompt Merging**: Fixed system prompt injection in `run_stream` so configured model system prompts and reasoning suppression directives are properly passed into streaming requests.
+- **CMF Reasoning Mode Compatibility**: Fully integrated with `cortiq-engine` v0.5.17 for sampler-level logit bias reasoning token suppression and zero-token thinking bypass.
+
+## [0.2.34] - 2026-07-23
 
 ### Added
 - **Responsive mobile admin console**: Added a hamburger navigation drawer, touch-friendly controls, phone-sized forms and cards, scrollable tables, compact toolbars, safe-area support, and mobile bottom-sheet dialogs across the admin interface.

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.33"
+version = "0.2.34"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.34"
+version = "0.2.35"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/main.rs

@@ -99,6 +99,7 @@ async fn main() -> anyhow::Result<()> {
 
     let mut app = Router::new()
         .route("/healthz", get(|| async { "ok" }))
+        .route("/health", get(|| async { "ok" }))
         .route("/readyz", get(|| async { "ready" }))
         .route("/metrics", get(admin::metrics))
         .merge(protocols::build_router());
@@ -109,7 +110,12 @@ async fn main() -> anyhow::Result<()> {
             .fallback(admin::assets::fallback);
     }
 
-    let app = app.with_state(state);
+    let cors = tower_http::cors::CorsLayer::new()
+        .allow_origin(tower_http::cors::Any)
+        .allow_methods(tower_http::cors::Any)
+        .allow_headers(tower_http::cors::Any);
+
+    let app = app.with_state(state).layer(cors);
 
     let listener = tokio::net::TcpListener::bind(&listen).await?;
     tracing::info!("cortiq-gateway listening on {listen}");

src/pipeline.rs

@@ -487,6 +487,20 @@ impl Pipeline {
                 if req_call.params.think_budget.is_none() {
                     req_call.params.think_budget = m_cfg.think_budget;
                 }
+                if let Some(sys) = &m_cfg.system_prompt {
+                    if !sys.trim().is_empty()
+                        && !req_call.messages.iter().any(|m| m.role == "system")
+                    {
+                        req_call.messages.insert(
+                            0,
+                            Message {
+                                role: "system".into(),
+                                content: sys.clone(),
+                                tool_calls: Vec::new(),
+                            },
+                        );
+                    }
+                }
             } else if let Some(s_cfg) = live.cfg.cmf.servers.iter().find(|s| s.id == model_id) {
                 if req_call.params.temperature.is_none() {
                     req_call.params.temperature = s_cfg.temperature;
@@ -500,6 +514,20 @@ impl Pipeline {
                 if req_call.params.think_budget.is_none() {
                     req_call.params.think_budget = s_cfg.think_budget;
                 }
+                if let Some(sys) = &s_cfg.system_prompt {
+                    if !sys.trim().is_empty()
+                        && !req_call.messages.iter().any(|m| m.role == "system")
+                    {
+                        req_call.messages.insert(
+                            0,
+                            Message {
+                                role: "system".into(),
+                                content: sys.clone(),
+                                tool_calls: Vec::new(),
+                            },
+                        );
+                    }
+                }
             }
 
             match provider.chat_stream(req_call).await {

src/providers/openai.rs

@@ -48,11 +48,13 @@ impl OpenAiProvider {
         if let Some(m) = req.params.max_tokens {
             body["max_tokens"] = m.into();
         }
+        eprintln!("[to_wire] think_budget={:?}", req.params.think_budget);
         if let Some(tb) = req.params.think_budget {
             body["think_budget"] = tb.into();
             body["reasoning_effort"] = tb.into();
             // cortiq serve uses enable_thinking (bool): 0 = off, >0 = on
             body["enable_thinking"] = (tb > 0).into();
+            eprintln!("[to_wire] SET enable_thinking={}", tb > 0);
         }
         if !req.tools.is_empty() {
             body["tools"] = serde_json::Value::Array(req.tools.clone());
@@ -61,6 +63,10 @@ impl OpenAiProvider {
         for (k, v) in &req.params.passthrough {
             body[k] = v.clone();
         }
+        eprintln!(
+            "[to_wire] enable_thinking={:?}",
+            body.get("enable_thinking")
+        );
         body
     }
 }