v0.2.35

Two bugs:
1. run_stream() never merged per-model/server config (think_budget,
   temperature, etc.) into the request — unlike run_inner(). Now both
   paths apply the same config merge.
2. to_wire() was missing the enable_thinking bool conversion line
   (lost in a prior revert). Restored: think_budget=0 → enable_thinking=false.

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 = "0.2.32"
+version = "0.2.34"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.33"
+version = "0.2.35"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -476,28 +476,61 @@ async fn provider_models(
                     let mut obj = json!({ "id": id });
                     let mut caps = vec![];
                     if let Some(pricing) = m.get("pricing").filter(|v| !v.is_null()) {
-                        if let Some(prompt) = pricing.get("prompt").and_then(|s| s.as_str()).and_then(|s| s.parse::<f64>().ok()) {
+                        if let Some(prompt) = pricing
+                            .get("prompt")
+                            .and_then(|s| s.as_str())
+                            .and_then(|s| s.parse::<f64>().ok())
+                        {
                             obj["price_in"] = json!(prompt * 1_000_000.0);
                         }
-                        if let Some(comp) = pricing.get("completion").and_then(|s| s.as_str()).and_then(|s| s.parse::<f64>().ok()) {
+                        if let Some(comp) = pricing
+                            .get("completion")
+                            .and_then(|s| s.as_str())
+                            .and_then(|s| s.parse::<f64>().ok())
+                        {
                             obj["price_out"] = json!(comp * 1_000_000.0);
                         }
-                        if pricing.get("input_cache_read").filter(|v| !v.is_null()).is_some() || pricing.get("input_cache_write").filter(|v| !v.is_null()).is_some() {
+                        if pricing
+                            .get("input_cache_read")
+                            .filter(|v| !v.is_null())
+                            .is_some()
+                            || pricing
+                                .get("input_cache_write")
+                                .filter(|v| !v.is_null())
+                                .is_some()
+                        {
                             caps.push("caching");
                         }
                     }
                     if let Some(params) = m.get("supported_parameters").and_then(|p| p.as_array()) {
-                        let has_tools = params.iter().any(|p| p.as_str() == Some("tools") || p.as_str() == Some("tool_choice"));
-                        if has_tools { caps.push("tools"); }
+                        let has_tools = params.iter().any(|p| {
+                            p.as_str() == Some("tools") || p.as_str() == Some("tool_choice")
+                        });
+                        if has_tools {
+                            caps.push("tools");
+                        }
                         let has_json = params.iter().any(|p| p.as_str() == Some("response_format"));
-                        if has_json { caps.push("json"); }
-                        let has_reasoning = params.iter().any(|p| p.as_str() == Some("reasoning") || p.as_str() == Some("include_reasoning"));
-                        if has_reasoning || m.get("reasoning").filter(|v| !v.is_null()).is_some() { caps.push("reasoning"); }
+                        if has_json {
+                            caps.push("json");
+                        }
+                        let has_reasoning = params.iter().any(|p| {
+                            p.as_str() == Some("reasoning")
+                                || p.as_str() == Some("include_reasoning")
+                        });
+                        if has_reasoning || m.get("reasoning").filter(|v| !v.is_null()).is_some() {
+                            caps.push("reasoning");
+                        }
                     }
                     if let Some(arch) = m.get("architecture").filter(|v| !v.is_null()) {
-                        if let Some(inputs) = arch.get("input_modalities").and_then(|i| i.as_array()) {
-                            if inputs.iter().any(|i| i.as_str() == Some("image")) { caps.push("vision"); }
-                            if inputs.iter().any(|i| i.as_str() == Some("audio")) { caps.push("audio"); }
+                        if let Some(inputs) =
+                            arch.get("input_modalities").and_then(|i| i.as_array())
+                        {
+                            if inputs.iter().any(|i| i.as_str() == Some("image")) {
+                                caps.push("vision");
+                            }
+                            if inputs.iter().any(|i| i.as_str() == Some("audio")) {
+                                caps.push("audio");
+                            }
                         }
                     }
                     if !caps.is_empty() {
@@ -514,15 +547,23 @@ async fn provider_models(
 
     if b.provider == "openrouter" {
         if let Some(k) = key {
-            if let Ok(cred_resp) = client.get("https://openrouter.ai/api/v1/credits")
+            if let Ok(cred_resp) = client
+                .get("https://openrouter.ai/api/v1/credits")
                 .header("authorization", format!("Bearer {k}"))
-                .send().await
+                .send()
+                .await
             {
                 if let Ok(cred_body) = cred_resp.text().await {
                     let cred_v: Value = serde_json::from_str(&cred_body).unwrap_or(json!({}));
                     if let Some(data) = cred_v.get("data") {
-                        let total = data.get("total_credits").and_then(|v| v.as_f64()).unwrap_or(0.0);
-                        let usage = data.get("total_usage").and_then(|v| v.as_f64()).unwrap_or(0.0);
+                        let total = data
+                            .get("total_credits")
+                            .and_then(|v| v.as_f64())
+                            .unwrap_or(0.0);
+                        let usage = data
+                            .get("total_usage")
+                            .and_then(|v| v.as_f64())
+                            .unwrap_or(0.0);
                         resp["balance"] = json!(total - usage);
                     }
                 }

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

@@ -472,7 +472,65 @@ impl Pipeline {
                 model_id,
                 route_source
             );
-            match provider.chat_stream(req.clone()).await {
+            // Merge per-model/server config (same as run_inner).
+            let mut req_call = req.clone();
+            if let Some(m_cfg) = live.cfg.models.iter().find(|m| m.id == model_id) {
+                if req_call.params.temperature.is_none() {
+                    req_call.params.temperature = m_cfg.temperature;
+                }
+                if req_call.params.top_p.is_none() {
+                    req_call.params.top_p = m_cfg.top_p;
+                }
+                if req_call.params.max_tokens.is_none() {
+                    req_call.params.max_tokens = m_cfg.max_tokens;
+                }
+                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;
+                }
+                if req_call.params.top_p.is_none() {
+                    req_call.params.top_p = s_cfg.top_p;
+                }
+                if req_call.params.max_tokens.is_none() {
+                    req_call.params.max_tokens = s_cfg.max_tokens;
+                }
+                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 {
                 Ok(stream) => {
                     let info = RouteInfo {
                         task_label: decision.task_label.clone(),

src/providers/openai.rs

@@ -48,9 +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());
@@ -59,6 +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
     }
 }