Update claude-api skill: Claude Sonnet 5 and Managed Agents July updates (#1373)

This commit is contained in:
Lance Martin
2026-07-01 11:11:23 -07:00
committed by GitHub
parent 35414756ca
commit 9d2f1ae187
22 changed files with 348 additions and 58 deletions
@@ -104,7 +104,7 @@ for await (const run of client.beta.deploymentRuns.list({
}
```
Raw HTTP: `GET /v1/deployment_runs?deployment_id=...&has_error=true`.
Raw HTTP: `GET /v1/deployment_runs?deployment_id=...&has_error=true`. To retrieve a single run by ID, `GET /v1/deployment_runs/{deployment_run_id}` (SDK: `client.beta.deployment_runs.retrieve(run_id)`) — a `deployment_run.*` webhook event carries the run ID as its `data.id`.
A failed run looks like:
@@ -123,6 +123,8 @@ A failed run looks like:
Error types include `environment_archived`, `agent_archived`, `vault_not_found`, `session_rate_limited`, and `service_unavailable`.
The outcome of each **scheduled** run (started/succeeded/failed) and each deployment lifecycle change (created/updated/paused/unpaused/archived/deleted) is also delivered as a webhook event — see `shared/managed-agents-webhooks.md` for the `deployment.*` and `deployment_run.*` event types — so you can react without polling. Manual runs do **not** emit `deployment_run.*` webhook events.
## Lifecycle: pause / unpause / archive
| Operation | SDK | Effect |