Packages

@flue/runtime

2.3.1 · 18 Nov 2026Apache-2.0524.4k / weekRepositoryHomepagenpmAtom feed

Your version

2.0.8

16 Sep 2026Where it was published

2.3.1 is the newest release of 2.x.

In short

8 fixed

Release note

Patch Changes

  • Interrupted submissions no longer retry forever when the recovery render throws: once the submission's durability deadline passes, a submission whose classification render keeps failing is settled as timed out instead of being re-rendered on every supervisor wake without ever consuming an attempt.

  • The Cloudflare binding's Anthropic gateway path now maps the agent's thinkingLevel to an adaptive-thinking effort (output_config.effort), so useModel thinking levels take effect on adaptive-thinking models instead of always running at Anthropic's default.

  • The Cloudflare binding provider now accepts a cacheRetention option ('short' or 'long') to enable Anthropic prompt caching for anthropic/… gateway models — repeated prefixes are served from cache at the cached input rate instead of paying full input price every turn. Default 'none' keeps the previous behavior.

  • The Cloudflare Sandbox documentation page now presents flue add sandbox cloudflare as a copyable prompt for your coding agent, with an explainer of what the blueprint-driven agent may do — installing @cloudflare/sandbox, wiring the Durable Object binding, migration, and container Dockerfile, and updating the agent to use the sandbox.

  • Fix the first streamed delta being delayed by the full coalescing interval: after a quiet period, the first delta now flushes to the durable stream immediately, so observers see output as soon as the model starts responding.

  • Fix duplicate responses appearing after a model stream fails partway through and Flue retries it successfully. Clients now see only the successful replacement response instead of the incomplete first attempt followed by the complete retry.

  • Models synthesized from a dynamic model template (providers that serve model IDs beyond their catalog, such as Workers AI) are now detectable via the exported isDynamicModel() helper, and the runtime warns once when such a model is first resolved — previously their cost silently read as $0 with no way to tell "free" apart from "unknown".

  • GenAI trace content now stays schema-valid when it cannot be fully represented: oversized, unserializable, or transform-failing messages under gen_ai.input.messages / gen_ai.output.messages fall back to a shape-preserving role: "flue" message (output fallbacks keep finish_reason) instead of a bare diagnostic string or an array element that violates the message schema.

A whole project to check? Paste its package.json in the dependency check: every deprecated, outdated or vulnerable dependency, with what to upgrade to. Free, no account.