apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-09 07:42:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename session pinning to model affinity with x-model-affinity header

Browse source
This commit is contained in:
Adil Hafeez 2026-04-08 15:23:53 -07:00
parent 5789694d2f
commit da9792c2dd
14 changed files with 468 additions and 371 deletions
Download patch file Download diff file Expand all files Collapse all files

6
demos/llm_routing/model_routing_service/demo.sh
View file

@ -114,7 +114,7 @@ echo "--- 7. Session pinning - first call (fresh routing decision) ---"
echo ""
curl -s "$PLANO_URL/routing/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "X-Routing-Session-Id: demo-session-001" \
-H "X-Model-Affinity: demo-session-001" \
-d '{
"model": "gpt-4o-mini",
"messages": [
@ -129,7 +129,7 @@ echo " Notice: same model returned with \"pinned\": true, routing was skipped
echo ""
curl -s "$PLANO_URL/routing/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "X-Routing-Session-Id: demo-session-001" \
-H "X-Model-Affinity: demo-session-001" \
-d '{
"model": "gpt-4o-mini",
"messages": [
@ -143,7 +143,7 @@ echo "--- 9. Different session gets its own fresh routing ---"
echo ""
curl -s "$PLANO_URL/routing/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "X-Routing-Session-Id: demo-session-002" \
-H "X-Model-Affinity: demo-session-002" \
-d '{
"model": "gpt-4o-mini",
"messages": [