feat(ai): complete models runtime migration

packages/ai/CHANGELOG.md

@@ -8,6 +8,33 @@
 - Renamed the `Provider` type to `ProviderId`. `Provider` now names the runtime provider interface (id, name, auth, model listing, stream behavior).
 - API implementation modules moved from `src/providers/` to `@earendil-works/pi-ai/api/*`, renamed by API id (`anthropic` -> `api/anthropic-messages`, `google` -> `api/google-generative-ai`, `mistral` -> `api/mistral-conversations`, `amazon-bedrock` -> `api/bedrock-converse-stream`), each exporting exactly `stream` and `streamSimple`. The old per-impl export names (`streamAnthropic`, `streamSimpleAnthropic`, ...) are gone; the legacy package subpaths (`./anthropic`, `./google`, ...) keep working and point at the new modules.
 
+Migration guide:
+
+- To keep the old global API temporarily, change imports from `@earendil-works/pi-ai` to `@earendil-works/pi-ai/compat`. The compat entrypoint preserves `stream`/`complete`, generated catalog reads, API registry helpers, env API-key helpers, lazy API wrappers, and image globals, but it will be removed in a future release.
+- To migrate to the new runtime, create a `Models` collection and call methods on it:
+
+  ```ts
+  import { builtinModels } from "@earendil-works/pi-ai/providers/all";
+
+  const models = builtinModels();
+  const model = models.getModel("anthropic", "claude-haiku-4-5");
+  if (!model) throw new Error("model not found");
+
+  const message = await models.complete(model, {
+    messages: [{ role: "user", content: "Hello", timestamp: Date.now() }],
+  });
+  ```
+
+- For an isolated provider set, register provider factories explicitly:
+
+  ```ts
+  import { createModels } from "@earendil-works/pi-ai";
+  import { anthropicProvider } from "@earendil-works/pi-ai/providers/anthropic";
+
+  const models = createModels();
+  models.setProvider(anthropicProvider());
+  ```
+
 ### Added
 
 - New `Models` runtime: `createModels()` builds an isolated provider collection with sync model reads (`getModels`/`getModel` return the last-known lists), an explicit async `refresh(provider?)` for dynamic providers, auth resolution (`getAuth`), and `stream`/`complete`/`streamSimple`/`completeSimple` that resolve auth through the owning provider. `createProvider()` builds providers from parts (single API implementation or a map dispatched on `model.api`; static `models` array plus an optional `refreshModels` fetcher with in-flight dedupe); `hasApi()` narrows dynamically listed models.
@@ -22,6 +49,7 @@
 ### Fixed
 
 - Fixed Amazon Bedrock endpoint resolution to honor scoped `AWS_PROFILE` values.
+- Fixed Cloudflare providers to require account/gateway configuration and route built-in `/compat` requests through provider auth.
 - Fixed OpenAI Codex Responses WebSocket sessions to reconnect once when OpenAI's connection limit is reached before output starts ([#5973](https://github.com/earendil-works/pi/issues/5973)).
 - Fixed OpenCode Go GLM-5.2 metadata to expose `xhigh` reasoning and send `reasoning_effort: "max"` ([#5967](https://github.com/earendil-works/pi/issues/5967)).
 - Fixed Claude Fable 5 thinking-off requests to omit Anthropic's unsupported `thinking.type: "disabled"` payload ([#5567](https://github.com/earendil-works/pi/pull/5567) by [@tmustier](https://github.com/tmustier)).