Packages

@flue/react

2.3.1 · 18 Nov 2026Apache-2.0187.9k / weekRepositoryHomepagenpmAtom feed

Your version

16 stable releases, newest first, by release line. Notes are quoted as the maintainers published them.

  1. 2.3.1

    18 Nov 2026
    • 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.

    • 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 2026
    • 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.

    • 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).

    • 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).

  3. 2.2.1 – 2.2.22 releases that only update dependencies@flue/sdk 2.2.2Show each
  4. 2.2.0

    28 Sep 2026
    • 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.

  5. 2.1.1

    23 Sep 2026
    • Clarify useFlueAgent's status contract to match the reducer's actual aggregate behavior. status reflects the observed conversation's activity — including submissions admitted out-of-band (webhooks, dispatches, other clients) — combined with the hook's in-memory local admission recollection. The README now documents the full precedence order (failed-local-settlement error → streaming text → submitted → active/recollected submission streaming → retained-failed-send error → idle) and notes that a locally-admitted submission that has not yet settled keeps streaming across empty or absent observations until it settles. The reload fix covers submissions already represented by conversation messages; a submission admitted but not yet materialized into a message at reload time is documented as a residual window.

    • Keep useFlueAgent's status at streaming after a reload for an unsettled submission. The reducer now derives active (unsettled) submission ids from the observed conversation — message submissionIds minus settled ids — instead of relying only on the in-memory admission receipt, which does not survive a reload. Previously a fresh hook would report idle for an admitted-but-silent prompt or a running tool call until the next assistant text part streamed.

  6. 2.1.0

    18 Sep 2026
    • sendMessage now passes through every send control client.send() accepts (idempotencyKey, initialData, uid, signal, …) and resolves with the admission receipt (AgentSendResult) instead of void.

      Retry a send safely by keeping the key and reusing it when the request's outcome is uncertain:

      const agent = useFlueAgent({ url });
      const key = `prompt-${crypto.randomUUID()}`; // persist before sending
      
      try {
        const receipt = await agent.sendMessage('hello', { idempotencyKey: key });
        // receipt.submissionId correlates with settlements; receipt.deduplicated
        // is true when this retry converged on an already-admitted send.
      } catch {
        // A network failure does not prove the server rejected the prompt —
        // retry later with the same key to converge on the original submission.
      }
  7. 2.0.8

    16 Sep 2026

    Only updates a dependency:@flue/sdk 2.0.8

  8. 2.0.7

    15 Sep 2026
    • Fix useFlueAgent callbacks changing identity on every store update — they now stay stable until the underlying session changes, preventing unnecessary re-renders and stale-effect churn.

  9. 2.0.6

    14 Sep 2026
    • Published packages once again include the bundled Flue documentation. The 2.0.4 and 2.0.5 releases omitted the generated docs/ directories from @flue/cli, @flue/runtime, and @flue/sdk, causing commands such as flue docs read guide/sandboxes to fail.

  10. 2.0.5

    11 Sep 2026
    • Published packages once again resolve internal Flue dependencies to the release version. The 2.0.4 release accidentally shipped raw pnpm workspace: dependency specifiers, making affected packages impossible to install outside the workspace. The complete lockstep package set is republished as 2.0.5 through pnpm so every internal dependency resolves to 2.0.5 (#657).

  11. 2.0.4

    9 Sep 2026
    • "Connection error." is now classified as a retryable model error. The retryable-error matcher recognized connection reset/connection refused/connection lost but not a bare connection error — a transient "Connection error." (with its trailing period) fell through the pattern and terminated the submission as a hard failure. The matcher now also accepts connection error and the run retries it under the transient-error budget (#629).

  12. 2.0.3

    5 Aug 2026

    Reading the note…

  13. 2.0.2

    4 Aug 2026

    Reading the note…

  14. 2.0.1

    1 Aug 2026

    Reading the note…

  15. 2.0.0

    31 Jul 2026

    Reading the note…

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.