Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · claude-code

Orchestrate subagents at scale with dynamic workflows changed

workflows

Nearest release: v2.1.272, published 2 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+25added
Lines−12removed
From line 345 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits29to this page, all time

### When a run hits your usage limit

The whole hunk

from line 345, old and new numbered
/
lines
from line 345
345345 
346346The runtime applies the following constraints:
347347 
348| Constraint | Why |
349| :-------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------ |
350| No mid-run user input | Only agent permission prompts can pause a run. For sign-off between stages, run each stage as its own workflow |
351| No direct filesystem or shell access from the workflow itself | Agents read, write, and run commands. The script coordinates the agents |
352| No module loading: a script that contains `import()` fails before the run starts | The script body is plain JavaScript. Put work that needs a library in an agent's task |
353| Up to 16 concurrent agents, fewer when Claude Code has fewer CPUs available, including inside a CPU-limited container | Bounds local resource use |
354| In a fan-out, agents that share the first agent's prompt-cache prefix start up to 5 seconds after it by default | All but the first read the [prefix the first agent cached](#prompt-caching-in-a-fan-out) instead of each processing it uncached |
355| Up to 4,096 items in a single `parallel()` or `pipeline()` call: the runtime rejects a longer list with an error | A silent cap would drop part of the workload without telling the script |
356| 1,000 agents total per run | Prevents runaway loops |
348| Constraint | Why |
349| :-------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
350| No mid-run user input | A run pauses on its own only for agent permission prompts and a [usage-limit wait](#when-a-run-hits-your-usage-limit). For sign-off between stages, run each stage as its own workflow |
351| No direct filesystem or shell access from the workflow itself | Agents read, write, and run commands. The script coordinates the agents |
352| No module loading: a script that contains `import()` fails before the run starts | The script body is plain JavaScript. Put work that needs a library in an agent's task |
353| Up to 16 concurrent agents, fewer when Claude Code has fewer CPUs available, including inside a CPU-limited container | Bounds local resource use |
354| In a fan-out, agents that share the first agent's prompt-cache prefix start up to 5 seconds after it by default | All but the first read the [prefix the first agent cached](#prompt-caching-in-a-fan-out) instead of each processing it uncached |
355| Up to 4,096 items in a single `parallel()` or `pipeline()` call: the runtime rejects a longer list with an error | A silent cap would drop part of the workload without telling the script |
356| 1,000 agents total per run | Prevents runaway loops |
357357 
358358## Manage runs
359359 
from line 382
382382 
383383In local and cloud sessions alike, when Claude relaunches an earlier run and Claude Code can't find that run's saved results at all, the relaunch fails with a `nothing to resume` error instead of starting the run over on its own. Ask Claude to start the workflow over as a new run.
384384 
385### When a run hits your usage limit
386 
387When an agent hits your claude.ai [usage limit](/docs/en/interactive-mode#wait-for-a-usage-limit-to-reset), the run pauses rather than failing that agent: the agents that hit the limit wait for the reset, and no new agents start. Shortly after the limit resets, the waiting agents run again and the run continues on its own. Requires Claude Code v2.1.271 or later; on earlier versions, the affected agents fail.
388 
389While the run waits, its progress line in the task panel and the [`/workflows`](#watch-the-run) header show when the limit resets.
390 
391The run pauses only when all of these hold; when one doesn't, the affected agent fails instead:
392 
393* The session is interactive and signed in with a claude.ai subscription. A run doesn't pause in [non-interactive mode](/docs/en/headless) with `claude -p` or the [Agent SDK](/docs/en/agent-sdk/overview), in a [background session](/docs/en/agent-view), or in a [Remote Control](/docs/en/remote-control) or [agent team](/docs/en/agent-teams) teammate session.
394* [`autoContinueAtUsageLimit`](/docs/en/settings-reference#autocontinueatusagelimit) is on, the same setting that lets the session itself [wait for a usage limit to reset](/docs/en/interactive-mode#wait-for-a-usage-limit-to-reset). If you turn it off during a wait, the wait ends and the waiting agents fail.
395* The limit resets within 24 hours. A weekly limit can reset further out.
396* The run hasn't already waited twice. When it hits the limit a third time, the agent fails.
397 
385398### Cost
386399 
387A workflow spawns many agents, so a single run can use meaningfully more tokens than working through the same task in conversation. Runs count toward your plan's usage and rate limits like any other session.
400A workflow spawns many agents, so a single run can use meaningfully more tokens than working through the same task in conversation. Runs count toward your plan's usage and rate limits.
388401 
389402To gauge the spend before committing to a large task, run the workflow on a small slice first: one directory instead of the whole repo, or a narrow question instead of a broad one. The `/workflows` view shows each agent's token usage as the run progresses, and you can stop the run there at any time, usually without losing completed work. [Resume after a pause](#resume-after-a-pause) covers what a stopped run keeps. The runtime's [agent caps](#behavior-and-limits) limit how many agents a single run can spawn, which bounds the cost of a runaway script. To keep runs to fewer agents, choose the `small` [size guideline](#set-a-size-guideline).
390403 
from line 427
414427| :------------- | :-------------------------------------------------- |
415428| `unrestricted` | No guideline: Claude sizes the workflow to the task |
416429| `small` | Fewer than 5 agents |
417| `medium` | Fewer than 15 agents |
430| `medium` | Fewer than 10 agents |
418431| `large` | Fewer than 50 agents |
419432 
420The default is `medium`. Until you choose a value, the `/config` row shows `medium (default)` and the workflow's `Running in background` line shows `medium size (/config)`. Requires Claude Code v2.1.219 or later; earlier versions default to `unrestricted`.
433The default is `medium`, or `small` when you're signed in on a Pro plan with Claude Code v2.1.271 or later. Until you choose a value, the `/config` row marks the value as the default, and the workflow's `Running in background` line names the size in force. Requires Claude Code v2.1.219 or later; earlier versions default to `unrestricted`.
421434 
422435To change the guideline, pick a value for the Dynamic workflow size setting in `/config`, or run `/config workflowSizeGuideline=small`. On v2.1.219 and later, you can also set the [`workflowSizeGuideline` key](/docs/en/settings-reference#workflowsizeguideline) in any settings file; that value takes precedence over `/config`, and Claude Code hides the `/config` row while a settings file provides one.
423436 
Feedback