ormandj
ormandj
@cbodley everything look ok on this one?
Agreed, 106 is out now, hopefully the issues will be resolved.
Has anybody tried to contact @szabodanika via alternative means?
For the mTLS side: https://gateway-api.sigs.k8s.io/geps/gep-91/
@youngnick good point - this has been a major sticking point for us with moving towards Gateway API for everything; how to not just authenticate clients but handle authorization based...
feat(provider): add provider-specific cache configuration system (significant token usage reduction)
I tested with providers I have access to. I can confirm it works with with Anthropic (Opus 4.5), Google (Gemini 3 Pro preview), and Mistral (Devstral 2).
feat(provider): add provider-specific cache configuration system (significant token usage reduction)
Updated one of the comments to be more clear, but no functional changes.
feat(provider): add provider-specific cache configuration system (significant token usage reduction)
> i can also just read the PR/have opencode summarize haha. i'll do a pass once that llm-centralization branch is merged Ok, that's fine. I added comments throughout that should...
feat(provider): add provider-specific cache configuration system (significant token usage reduction)
> Hey, thanks for this PR. I started playing around with it. Can you do me a favor and add the following patch to visualize token cache statistics on the...
We've done exactly this for Gitea, and the secret is the sharing-key. Gitea values.yaml that's relevant: ``` service: ssh: type: LoadBalancer port: 22 annotations: lbipam.cilium.io/ips: "IPHERE" lbipam.cilium.io/sharing-key: gitea ``` Gitea...