url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

coli: honor THINK=1 in run mode

Browse Source 
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>
This commit is contained in:
andres-gb10
2026-07-18 16:45:19 +01:00
parent caa49f7fa0
commit 799fe41f88
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/coli
+5 -2
View File
@@ -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):