Skip to content

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

feat(providers): declare reasoning efforts so xhigh/max surface in the UI

Sergey Kozyrenkode7db214486e
diff --git a/backend/pkg/providers/glm/models.yml b/backend/pkg/providers/glm/models.yml
index 5f59ee9c..882be3e8 100644
--- a/backend/pkg/providers/glm/models.yml
+++ b/backend/pkg/providers/glm/models.yml
@@ -2,6 +2,8 @@
- name: glm-5.2
description: GLM-5.2 - Newest flagship (improves on GLM-5.1), 200K context, hybrid thinking; supports reasoning_effort (high/max).
thinking: true
+ reasoning:
+ efforts: [high, max]
price:
input: 1.40
output: 4.40
diff --git a/backend/pkg/providers/openai/models.yml b/backend/pkg/providers/openai/models.yml
index d040cae3..20533a38 100644
--- a/backend/pkg/providers/openai/models.yml
+++ b/backend/pkg/providers/openai/models.yml
@@ -2,6 +2,8 @@
- name: gpt-5.4
description: Best intelligence at scale for agentic, coding, and professional workflows. Flagship model with 1M context window and configurable reasoning effort (none/low/medium/high/xhigh). Excels at complex professional work, sophisticated security research, and advanced autonomous penetration testing requiring maximum cognitive depth and accuracy.
thinking: true
+ reasoning:
+ efforts: [low, medium, high, xhigh]
release_date: 2026-01-15
price:
input: 2.5