Skip to content

FI5: Token streaming (async-completion + external pub/sub) #21

@frisbeeman

Description

@frisbeeman

Status: Future idea, not scheduled. Lives in the v0.5+ ""maybe"" bucket of the roadmap.

Summary

Stream LLM tokens to external consumers while the workflow itself sees only the final response. Pattern: activity streams tokens out-of-band via pub/sub (Redis, NATS, etc.) while the workflow waits on async-completion.

Why this matters

Modern UX expects token-by-token feedback for long-running agents. Currently impossible because streaming conflicts with deterministic replay.

Why not scheduled

Fundamental tension with Temporal's determinism. The async-completion + external pub/sub pattern is the only viable approach, but it requires careful design and a real consumer to validate.

Open questions

  • Default pub/sub backend (if any)?
  • How to handle partial-response retries?

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:llmLLM provider, pipeline, structured outputsenhancementNew feature or requestfuturev0.5+ future idea, uncommitted

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions