Packages

@flue/sdk

2.3.1 · 18 Nov 2026Apache-2.0309.1k / weekRepositoryHomepagenpmAtom feed

Upgrading @flue/sdk From 0.3.1 to 2.3.1

45 releases in betweennotes for 35

Other targets from 0.3.1Newest 0.x0.11.1
  1. 0.3.1yours
  2. 10 releases
  3. 0.4.0major
  4. 1 release
  5. 0.5.0major
  6. 4 releases
  7. 0.7.0major
  8. 1 release
  9. 0.8.0major
  10. 1 release
  11. 0.9.0major
  12. 2 releases
  13. 0.10.0major
  14. 2 releases
  15. 0.11.0major
  16. 1 release
  17. 2.0.0major
  18. 14 releases
  19. 2.3.1target
  20. 4 pre
74+
changes to make
0
advisories fixed
74+
new
124+
fixes

Counted from 35 of 45 release notes. Advisories are counted from the advisory database, in full.

Start here

Before you upgrade

Tick each one off as you go
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0
  • Breaking2.0.0

Release by release

  1. 2.3.1

    18 Nov 20262 fixes
    • Fixed

      Updated @earendil-works/pi-ai and @earendil-works/pi-agent-core to 1.5.2, fixing builds that picked up pi-ai 1.5. @flue/runtime 2.3.0 imported TypeBox through @earendil-works/pi-ai, which stopped re-exporting it in 1.5.0, so a fresh install failed vite build. Flue now depends on typebox directly and requires pi ^1.5.0; remove any overrides that held pi at 1.4. If your own code imports Type or Static from @earendil-works/pi-ai, import them from typebox instead. Pi now validates tool arguments with its own JSON Schema validator, which coerces a little more (for example "3" for a number) and words its validation errors differently. OpenAI-compatible requests with no tools no longer send "tools":; set compat.requiresToolsWithToolHistory: true on models behind proxies that require it, such as older LiteLLM versions in front of Anthropic.

    • Fixed

      Workers AI binding models on the Responses API declare tools the way pi's own OpenAI provider does. Since pi 1.4, the binding passed a boolean where pi expected a tool-support mode, so a model without deferred tool loading could leave tools added mid-conversation out of its request. Models that support mid-conversation tool additions now declare every tool through additional_tools input items.

  2. 2.3.0

    12 Oct 20261 new · 6 fixes
    • New

      Updated @earendil-works/pi-ai and @earendil-works/pi-agent-core to 1.1.0. New models resolve with no configuration, including Claude Sonnet 5.5 (anthropic/claude-sonnet-5-5), Claude Haiku 5.5 (anthropic/claude-haiku-5-5), and GPT-6.1 Sol (openai/gpt-6.1-sol). Azure users must update: Pi renamed the Azure provider from azure-openai-responses to azure, so change azure-openai-responses/... model specifiers and providers config entries to azure. The AZURE_OPENAI_* environment variables are unchanged. Tool and turn durationMs values now come from Pi's monotonic timing, so a tool's duration covers only its execution, not Flue's hooks or result storage.

    • Fixed

      useAgentFinish callbacks once again see state written during the response. Since 2.2.0, finish hooks ran against the agent render from before the response's final turn, so a durable guard set by a finish callback — the documented usePersistentState pattern for appending a reminder once — was never observed: the callback re-appended on every cycle until the response failed at the runaway-loop ceiling. The agent now re-renders before each finish-hook cycle (#818).

    • Fixed

      read_skill_resource accepts a packaged skill path without its leading /. Models often echo the advertised /.flue/packaged-skills/... path without the slash, and the read failed as not found (#781).

    • Fixed

      The local sandbox SIGKILLs a command's whole process group after the grace period, even when the shell exits first. On an exec() timeout or abort, the pending SIGKILL was cancelled once the shell's pipes closed, so a process that ignored SIGTERM and held none of the shell's output kept running after exec() returned (#809).

    • Fixed

      Execution interceptors see agentName on model, tool, and shell steps, not only on the outer agent operation. The root harness's execution context carried only the instance id, so an interceptor that branches per agent took its default branch on every step (#785).

    • Fixed

      flue init --target cloudflare scaffolds the Workers AI binding that keyless cloudflare/... models need, commented out in wrangler.jsonc. The generated agent suggested switching to a keyless Cloudflare model but nothing declared env.AI; it now points at the binding to uncomment. The binding stays off by default because it reaches your Cloudflare account even in local dev (#739).

    • Fixed

      The E2B sandbox blueprint returns a non-zero exit from exec() instead of throwing. E2B's commands.run() throws CommandExitError on a non-zero exit, so a failing command rejected with no command or stderr instead of resolving with its exitCode. The blueprint is bumped to version 2; run flue update sandbox e2b to update an existing integration (#805).

  3. 2.2.1 – 2.2.22 releases, nothing new or fixed in the notes

  4. 2.2.0

    28 Sep 20263 new
    • New

      Add bounded conversation history reads so long-running chats no longer transfer the whole transcript on every page load or reconnect.

    • New

      Support document attachments (PDFs) on user messages. DeliveredAttachment is now a union of image and document attachments — { type: 'document', data, mimeType: 'application/pdf', filename? } — accepted on dispatch(), the init() handle, and direct HTTP prompts. session.prompt(), skill(), and task() gain a documents option alongside images, and @flue/react's sendMessage() gains a documents option. Documents are forwarded to the model as native document content: Anthropic document blocks, OpenAI (and Azure OpenAI) Responses input_file parts, and Google inlineData. On other model APIs the document is replaced in model context with a text placeholder saying it was omitted. Documents are stored like images — as canonical attachments projected as file parts with mediaType: 'application/pdf' — so existing conversations and persistence adapters need no migration. The SDK also exports DeliveredImageAttachment and DeliveredDocumentAttachment.

    • New

      Conversation messages now carry a server-authored timestamp (ISO 8601 capture time of the underlying durable record) in history(), observe(), and useFlueAgent. It works for every role and for existing conversations. metadata remains entirely agent-authored. Conversation settlements carry the same timestamp for when the submission settled.

  5. 2.1.1

    23 Sep 20262 fixes
    • Fixed

      Clarify that a skill's allowed-tools field is guidance. Flue accepts it for Agent Skills spec compatibility and does not enforce it; enforce authorization in your own tools and approval gates.

    • Fixed

      Record tool arguments and results of every payload shape on the standard gen_ai.tool.call.arguments / gen_ai.tool.call.result attributes, so OTel backends can display them. The shape-based diversion to the vendor flue.tool.call.* fallback keys is removed — those keys are no longer emitted, and their constants are retained for source compatibility. Payloads record exactly as before: objects/arrays as JSON strings, strings byte-for-byte within the content budget, other scalars as their JSON form.

  6. 2.1.0

    18 Sep 20263 fixes
    • Fixed

      The OpenTelemetry ecosystem page and Cloudflare target guide now document contentBudgetBytes on createOpenTelemetryInstrumentation() / createCloudflareTracing(): an override for the default 56 KiB per-span content pool. Raising it ships fuller content only on backends not bound by workerd's span cap (the OpenTelemetry adapter); on the Cloudflare target it is a tightening control only, since workerd's 64 KiB span-attribute cap is a platform limit no setting raises.

    • Fixed

      The MCP guide and Agent API reference now document preserved MCP tool annotations, including how trusted applications can inspect them and why server-supplied hints are not a security boundary.

    • Fixed

      The Tools guide and agent API reference now document timeoutMs on tool definitions: a per-call execution bound that aborts the tool's context.signal and settles the call with a ToolTimeoutError instead of letting one hung call consume the submission's durability budget.

  7. 2.0.8

    16 Sep 20261 fix
    • Fixed

      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.

  8. 2.0.7

    15 Sep 20262 fixes
    • Fixed

      Installed packages once again include the bundled Flue documentation, so commands such as flue docs read guide/sandboxes work out of the box.

    • Fixed

      Fix delayed reconnects in observe(): after a stream has been healthy for a full stream lifetime, the reconnect backoff resets, so a subsequent disconnect reconnects promptly instead of applying a stale delay.

2 other lines we could not sort, mostly version bumps
  • With the new 'local' sandbox, the host shell is exposed directly. The agent's bash tool can run gh issue view, npm test, etc. with whatever's on $PATH and whatever env you launched flue with. The runner / container / VM is the isolation boundary.

    0.4.0
  • For non-'local' sandboxes, install the binaries inside the sandbox image, or wrap the operation as a custom tool with init({ tools: [...] }). Tools have a structured parameter schema, are visible to the model directly, and recover the "secrets stay on the host" property — the tool reads process.env, the agent only sees the tool's params and result.

    0.4.0

1 internal line (docs, tests, tooling) left out.

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.