From 850a54acdf6475209fa7305f98ec65bc2428ae06 Mon Sep 17 00:00:00 2001
From: infosave2007 <urevich55@gmail.com>
Date: Thu, 23 Jul 2026 16:34:49 +0300
Subject: [PATCH] fix: enable_thinking not sent in streaming path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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.
---
 src/pipeline.rs         | 32 +++++++++++++++++++++++++++++++-
 src/providers/openai.rs |  2 ++
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/src/pipeline.rs b/src/pipeline.rs
index 226b5e7..7f14e1b 100644
--- a/src/pipeline.rs
+++ b/src/pipeline.rs
@@ -472,7 +472,37 @@ 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;
+                }
+            } 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;
+                }
+            }
+
+            match provider.chat_stream(req_call).await {
                 Ok(stream) => {
                     let info = RouteInfo {
                         task_label: decision.task_label.clone(),
diff --git a/src/providers/openai.rs b/src/providers/openai.rs
index 33aeed1..a559bbb 100644
--- a/src/providers/openai.rs
+++ b/src/providers/openai.rs
@@ -51,6 +51,8 @@ impl OpenAiProvider {
         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();
         }
         if !req.tools.is_empty() {
             body["tools"] = serde_json::Value::Array(req.tools.clone());