viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

[ci skip] Add Modal GLM-5 model to OpenClaw, fix streaming and download reliability

Browse source 
- Add modal provider (GLM-5-FP8) as primary model with non-streaming mode
  (GLM-5 uses non-standard reasoning_content field incompatible with streaming)
- Add curl --retry flags to init container downloads for reliability
- Fallback chain: GLM-5 → Gemini 2.5 Flash → Llama 3.3 70B
This commit is contained in:
Viktor Barzin 2026-02-19 23:17:08 +00:00
parent 66f1867ccb
commit dbab20995b
No known key found for this signature in database
GPG key ID: 0EB088298288D958
4 changed files with 21 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/kubernetes/main.tf
View file

@ -128,6 +128,7 @@ variable "health_postgresql_password" { type = string }
variable "health_secret_key" { type = string }
variable "openclaw_ssh_key" { type = string }
variable "openclaw_skill_secrets" { type = map(string) }
variable "modal_api_key" { type = string }
variable "gemini_api_key" { type = string }
variable "llama_api_key" { type = string }
variable "brave_api_key" { type = string }
@ -1175,6 +1176,7 @@ module "openclaw" {
gemini_api_key = var.gemini_api_key
llama_api_key = var.llama_api_key
brave_api_key = var.brave_api_key
modal_api_key = var.modal_api_key
tier = local.tiers.aux
depends_on = [null_resource.core_services]