Skip to content

DX-3022: docs: MCP Tasks failure behavior (isError, error details) #911

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
CahidArda merged 4 commits into from
Oct 8, 2026
Merged

DX-3022: docs: MCP Tasks failure behavior (isError, error details) #911

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
38b8a7f
DX-3022: docs: MCP Tasks failure behavior (isError, error details)
CahidArda Oct 8, 2026
1086052
chore(llms): regenerate llms.txt and llms-full.txt
github-actions[bot] Oct 8, 2026
fcc67e1
DX-3022: docs: what a handler threw is logged, not stored
CahidArda Oct 8, 2026
348d01d
chore(llms): regenerate llms.txt and llms-full.txt
github-actions[bot] Oct 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions llms-full.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88499,6 +88499,11 @@ tasks.define(
route throws on its first request instead of running anything unverified.
* When your handler throws, the task is not marked failed. Only the dispatcher marks it `failed`,
and only after QStash has stopped retrying. The failed message stays in the QStash DLQ.
* When your handler *returns* a tool error (`isError: true`), the task is `failed` at once, with no
retry, and `task_status` returns your content with `isError`, as the synchronous tool would.
* The model only sees a failure's `error.code` and `error.message`. The transport's details
(`error.data`: the QStash DLQ id, the Workflow run id) stay in Redis for you. What your handler
threw and a dispatch error are logged, never stored or returned.
* By default QStash tries 5 times with backoff `min(pow(3, retried) * 1000, 300000)`, about two
minutes in total, so a task survives a server restart. The free tier and the local dev server
allow at most 5 retries.
Expand Down Expand Up @@ -88913,6 +88918,11 @@ tasks.define(
route throws on its first request instead of running anything unverified.
* When your handler throws, the task is not marked failed. Only the dispatcher marks it `failed`,
and only after QStash has stopped retrying. The failed message stays in the QStash DLQ.
* When your handler *returns* a tool error (`isError: true`), the task is `failed` at once, with no
retry, and `task_status` returns your content with `isError`, as the synchronous tool would.
* The model only sees a failure's `error.code` and `error.message`. The transport's details
(`error.data`: the QStash DLQ id, the Workflow run id) stay in Redis for you. What your handler
threw and a dispatch error are logged, never stored or returned.
* By default QStash tries 5 times with backoff `min(pow(3, retried) * 1000, 300000)`, about two
minutes in total, so a task survives a server restart. The free tier and the local dev server
allow at most 5 retries.
Expand Down
5 changes: 5 additions & 0 deletions redis/sdks/agentkit/mcp-tasks.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,6 +320,11 @@ tasks.define(
route throws on its first request instead of running anything unverified.
- When your handler throws, the task is not marked failed. Only the dispatcher marks it `failed`,
and only after QStash has stopped retrying. The failed message stays in the QStash DLQ.
- When your handler *returns* a tool error (`isError: true`), the task is `failed` at once, with no
retry, and `task_status` returns your content with `isError`, as the synchronous tool would.
- The model only sees a failure's `error.code` and `error.message`. The transport's details
(`error.data`: the QStash DLQ id, the Workflow run id) stay in Redis for you. What your handler
threw and a dispatch error are logged, never stored or returned.
- By default QStash tries 5 times with backoff `min(pow(3, retried) * 1000, 300000)`, about two
minutes in total, so a task survives a server restart. The free tier and the local dev server
allow at most 5 retries.
Expand Down