From 799fe41f88a963d039af3dd9c56f85c3b26f3e82 Mon Sep 17 00:00:00 2001
From: andres-gb10 <a@nextars.co>
Date: Sat, 18 Jul 2026 16:45:19 +0100
Subject: [PATCH] coli: honor THINK=1 in run mode

coli run hardcoded the nothink template (<|assistant|><think></think>),
so THINK=1 had no effect in one-shot runs while serve mode honors it
(glm.c serve template picks <think> vs <think></think> from the same
env var). Pick the template the same way here.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---
 c/coli | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/c/coli b/c/coli
index 0dd9de3..c7fdaa2 100755
--- a/c/coli
+++ b/c/coli
@@ -480,8 +480,11 @@ def cmd_run(a):
     need_model(a.model)
     prompt=" ".join(a.prompt) if a.prompt else sys.exit('usage: coli run "your prompt"')
     banner("run")
-    # template ufficiale GLM-5.2: niente \n dopo i ruoli; <think></think> = risposta diretta (nothink)
-    e=env_for(a); e["PROMPT"]=f"[gMASK]<sop><|user|>{prompt}<|assistant|><think></think>"
+    # template ufficiale GLM-5.2: niente \n dopo i ruoli; <think></think> = risposta diretta (nothink).
+    # THINK=1 lascia <think> aperto, stessa convenzione del serve mode (glm.c). EN: THINK=1 leaves
+    # <think> open so the engine emits its reasoning block; the default stays nothink.
+    tk="<think>" if os.environ.get("THINK","0")=="1" else "<think></think>"
+    e=env_for(a); e["PROMPT"]=f"[gMASK]<sop><|user|>{prompt}<|assistant|>{tk}"
     sys.exit(subprocess.call([GLM, str(a.cap)], env=e))
 
 def server_probe(base, api_key=None, timeout=1.5):