GitHub's device flow documents slow_down as a rate limit: a poll that
arrives inside the throttle window is answered with slow_down instead of
the token, and the response's interval field reports the new required
minimum ("adds 5 seconds to the last interval"). A client that only
tracks its own +5s increment can stay behind the server's ratcheting
requirement when its timers fire early - common with WSL/VM clock drift
(microsoft/WSL#10006) - so every subsequent poll keeps hitting the rate
limit and login appears to hang forever even after the browser reports
the device as authorized.
Adopt the server-provided interval when a slow_down poll result carries
one, falling back to the RFC 8628 section 3.5 +5s increment otherwise.
GitHub Copilot passes the interval field through.
This restores part of the #1994 mitigations that were lost in the #4788
device-code refactor.
refs #6187
Broaden the Fireworks GLM 5.2 special-case in generate-models.ts from
an exact id match to a glm-5p2 substring match, so the router variant
accounts/fireworks/routers/glm-5p2-fast also uses the OpenAI-compatible
endpoint and thinkingLevelMap instead of falling back to the default
Anthropic Messages config.
closes#6195
Add a shared normalizeProviderError helper in packages/ai/src/utils/error-body.ts
and route the 8 body-blind / status-only providers through it (amazon-bedrock,
azure-openai-responses, google, google-vertex, images/openrouter,
openai-codex-responses, openai-completions, openai-responses). Non-schema 4xx/5xx
responses from proxies / gateways now show the real reason carried in the response
body alongside the HTTP status, instead of "403 status code (no body)" or
"Unknown: UnknownError".
The helper probes status (statusCode, status, $metadata.httpStatusCode,
$response.statusCode) and body (body, parsed error object, $response.body) across
the Mistral, OpenAI, Google, and Bedrock SDK shapes, truncates the body at a 4000
char cap, and preserves error.message when the SDK already folded the body in
(Anthropic / Google happy path). mistral.ts and anthropic.ts are left untouched.
Provider prefixes and the OpenRouter metadata.raw append are preserved.
closes#5763
createImagesModels()/ImagesProvider/createImagesProvider() give image
generation the same shape as chat: sync model reads, explicit async
refresh(provider?) with in-flight dedupe, provider-resolved auth, and
never-rejecting generateImages() (failures return AssistantImages with
stopReason error). Auth resolution is shared with the chat side via the
free-standing resolveProviderAuth() in auth/resolve.ts, which also owns
ModelsError; both collections pass their store/context as arguments.
The OpenRouter implementation moves to api/openrouter-images.ts with a
lazy wrapper; openrouterImagesProvider() factory plus
builtinImagesProviders()/builtinImagesModels() land in providers/all.
The ImagesProvider id type alias is renamed to ImagesProviderId
(mirror of Provider -> ProviderId). The old global image API
(getImageModel*, generateImages, registerImagesApiProvider) stays on
/compat, its registration shim repointed at the moved implementation.
README: Quick Start uses builtinModels(), the full streaming event
switch, image generation and the development checklist are restored in
full, image generation documents the new collections with compat noted
for the old API, plus the review fixes (builtinModels options,
credential-store mention for browsers, ImagesModels notes).
Armin Ronacher