together-webhooks-events

v2026.09.24

Convert Together AI batch, fine-tuning, upload, and dedicated-deployment job states into idempotent internal events using bounded polling and an optional owned callback. Use when integrating asynchronous Together work. Trigger with "Together job events", "Together callback", or "poll Together status".

GitHub
安装命令
npx skhub add jeremylongshore/together-webhooks-events
Markdown
SKILL.md

Together AI Job Events

Overview

Together documents asynchronous retrieval and polling for batch, fine-tune, upload, and deployment state. This skill emits internal events from that source of truth instead of inventing a provider-signed webhook.

Prerequisites

  • The job type, ID, project, terminal states, and retrieval method
  • A durable cursor/state store and idempotency key policy
  • Poll interval, deadline, retry budget, and event retention policy
  • An owned callback endpoint only if downstream push delivery is required

Tool Discipline

Use Read, Glob, and Grep to inspect job persistence, pollers, queues, and callback handlers. Use WebFetch to confirm current job states and retrieval methods. Use Write or Edit only after the event contract and storage boundary are approved.

Current Contract

  • Do not expect a universal Together webhook signature header; no general signed webhook surface is documented for these job APIs.
  • Persist the provider job ID before polling and derive internal idempotency from job ID plus observed state/version.
  • Treat terminal job status and per-item output/error artifacts as separate facts.
  • Deliver downstream callbacks from infrastructure you own and authenticate them with your own signing scheme.

Authentication

Poll Together with the project-scoped TOGETHER_API_KEY Bearer credential. For an owned callback, use a separate secret, timestamped signature, replay window, and rotation plan; never present that signature as Together-generated.

Instructions

  1. Map provider job states to a small versioned internal event schema.
  2. Persist job ID, last observed state, next poll time, attempt count, and deadline.
  3. Retrieve with bounded exponential backoff and jitter; stop at terminal state or deadline.
  4. Emit only on meaningful transitions and deduplicate by job/state key.
  5. On completion, fetch output and error artifacts before declaring record-level success.
  6. If needed, sign and deliver an internal callback with replay protection and a dead-letter path.

Approval Boundaries

Do not expose the Together key to callback consumers, invent provider signatures, or delete remote/local job artifacts before reconciliation and retention approval.

Output

Return the provider job reference, state mapping, poll schedule, transition ledger, reconciliation status, callback delivery evidence, and deadline/dead-letter disposition.

Error Handling

ConditionResponse
Retrieval is transiently unavailableRetry with jitter inside the overall deadline.
Job ID is missingStop; do not create a replacement job automatically.
Completion has an error fileEmit completed-with-errors and reconcile records.
Callback repeatedly failsPreserve the event in a dead-letter queue for replay.

Examples

The example below shows the minimum redacted evidence expected from a successful invocation of this operator workflow.

job=batch-redacted; transition=IN_PROGRESS->COMPLETED; records=reconciled; callback=owned-signed

Resources

发现
标签

此技能尚未发布标签。

版本
最新版本元数据

版本

v2026.09.24

发布时间

Sep 24, 2026

分类

未分类

许可证

MIT

源路径

skills/.curated/together-webhooks-events

默认分支

main

最新提交

e5a6c3b

Tree SHA

c2dc8e8