The lockfile chose the model
Google's Agent Development Kit gives any agent that names no model a default, and the default lives in the library. On its maintained 1.x line that default is still gemini-2.5-flash, the model the project's own commit history dates for earliest shutdown on 16 October. Pinning is what keeps you there.
When a framework supplies an agent's default model, the lockfile becomes the model selection, and semantic versioning has no correct number for retiring it, because changing the default breaks behaviour and keeping it breaks on a date.
Nothing to migrate to
A model vendor reissued its usage policy on 8 October, effective 12 November. Buried in it is a control-loop specification — hold a safe state when the connection drops, enforce limits below the model — delivered with thirty-five days' notice, no version number and no way to find out which of your systems it applies to.
A vendor's usage policy now specifies architecture rather than conduct, yet it arrives with no clause identifier, no published diff and no way to find which deployments it breaks — while the same vendor retires a model with sixty days' notice and a named successor.
Refused is not forbidden
On 17 September Anthropic began granting verified life-science teams access to models with the biology safeguards relaxed — team grants renewed yearly, project grants every six months, scoped to the use cases named on an application form. The API those teams call has no field for any of it.
A model's full capability is now an organisational grant with a declared scope and an expiry date, while the only machine-readable signal at the boundary is a policy category that cannot distinguish a permanent prohibition from a grant that quietly lapsed.
Change the model, not the question
A rule in Anthropic's fallback-credit reference decides what a declined request costs. Re-send it word for word on a different model and the cache you paid for is credited across; rewrite the question and you pay again. Opus 5.5 is the first flagship model to ship with that economics underneath it.
Refusal fallback refunds a retry only when the prompt is re-sent unchanged and lets the model be the one thing that varies, so the cheapest answer to a policy decline is now a weaker model rather than a better request.
Unhealthy does not evict anything
Kubernetes v1.37 promoted device taints to general availability and switched them on by default, so a vendor's driver can now delete a running pod off an accelerator. The device-health vocabulary the project did agree to define is three words in a status field, and it has nothing to do with it.
Kubernetes standardised the device-health words that carry no consequence and left undefined the ones that delete running pods, so the authority to evict a workload off an accelerator rests on a string the project never sees.
Conformant to everything except the decision
Three more gateways were certified against the Kubernetes inference extension this fortnight. What the certificate attests is that they will do as the endpoint picker tells them — and the endpoint picker, the only component that determines what serving a model costs you, left the standards repository in June.
The inference gateway standard specifies where to ask for a routing decision but not how to make one, so conformance now certifies obedience rather than competence, and the portability it promises stops precisely where the economics of serving a model begin.
You were your patch
Across 2026 GitHub has fitted a gate to every path a stranger could use to reach a maintainer — pull requests, then issues, and in August, security advisories. The platform calls the problem spam. What is actually being replaced is a cost nobody designed and everybody relied on.
Open source's intake was rationed not by admission control but by the price of producing something plausible, and the identity-based gates now replacing that price close an open system under load without giving it any signal to reopen.