> ## Documentation Index
> Fetch the complete documentation index at: https://docs.platform.toloka.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Troubleshoot a pipeline run

> Find fixes for stuck runs, blocked deployments, unexpected charges, missing export results, and upload problems.

When a run behaves in a way you did not expect, find the symptom below that matches what you see. Each symptom explains what is going on and what to check, then links to the fix. For the exact text of a message on your screen, such as a red counter, an entry in the **Issues** window, or an item's failure reason, search [Pipeline errors and how to fix them](https://docs.platform.toloka.ai/docs/data/reference/errors.md) by the message instead.

## The run seems stuck

An item's row reads **In Progress** while it is still being labeled, and the filter chip above counts it as `in_progress`. Open the run's **Items** tab and see what state each item is actually in:

* The counter chips (**completed**, **in\_progress**, **paused**, **failed**, **canceled**) show where the batch is. Open an item's row for its own status.
* A **Quorum** node item can stay in progress through extra review rounds. When LLM review rejects every answer, the item may receive additional answers or fail. See [When review rejects every answer](https://docs.platform.toloka.ai/docs/data/reference/nodes/quorum.md#when-review-rejects-every-answer).
* A **Paused** badge on the held items, and a `paused: N` chip among the item filters, identify a paused run. See [Resume or cancel a pipeline run](https://docs.platform.toloka.ai/docs/data/guides/pause-resume-cancel.md).
* A run pauses itself and shows a top-up banner when the team balance runs out mid-run. Add funds, then **Resume**. See [Billing](https://docs.platform.toloka.ai/docs/core/billing.md#pipeline-runs).

## I need to stop everything

The run controls are on the deployed pipeline's **Pipeline** tab. The agent cannot cancel a run for you. The buttons appear only once the deploy has finished. Items can start processing before deployment finishes.

* **To end the run for good**, click **Cancel**.
* **You cannot hold a run yourself.** A run pauses only when the balance runs out; **Resume** then appears in its place until you continue it.

> [!WARNING]
>
> Canceling a run is permanent: you cannot resume a canceled run, and canceling a paused run cancels its held items rather than resuming them.

[Resume or cancel a pipeline run](https://docs.platform.toloka.ai/docs/data/guides/pause-resume-cancel.md) covers what each button does.

## The run charged more (or less) than I expected

Every run's **Cost breakdown (forecast)** carries two totals. The final bill uses the items the run actually processes. See [Pipeline pricing](https://docs.platform.toloka.ai/docs/data/concepts/pricing.md):

* **Expected** is the average forecast. **Maximum** is the ceiling if every item triggers every billable event. Billing is pay-as-you-go for the items the run actually processes, so a real total below **Expected** is normal forecast behavior.
* On a **Quorum** node, the **Maximum** column doubles the review calls to cover [rejection-driven escalation](https://docs.platform.toloka.ai/docs/data/reference/nodes/quorum.md#when-review-rejects-every-answer). Compare your bill against **Expected** rather than that doubled ceiling.
* A cloned pipeline is priced fresh and frozen at its own deploy. It does not inherit the first run's contract.

> [!WARNING]
>
> A clone still pointing at items an earlier run already labeled will label them again and charge for them again. Before you deploy the next batch, tick the output field's **No revision for this field** filter and check the Start node's matching-items count against the batch you expect. See [Label a large dataset in batches](https://docs.platform.toloka.ai/docs/data/guides/label-at-volume.md).

## My export is missing items

An export is a snapshot taken the moment you start it and does not update afterward. See [Export your labeled results](https://docs.platform.toloka.ai/docs/data/guides/export-results.md). An item that had not started when you began the export carries only its `index` and `status`. `input`, `output`, and per-node `metrics` fill in as the item reaches each state. See [Export format](https://docs.platform.toloka.ai/docs/data/reference/export-format.md). For a file that reflects every result, wait until the run has finished, then start a fresh export.

## The deploy is blocked

A blocked deploy names its reason, so search [Pipeline errors and how to fix them](https://docs.platform.toloka.ai/docs/data/reference/errors.md) for the exact message. The gates you can clear from here:

* **A red launch count over 10,000.** The Start node caps a run at 10,000 items. A selection above it turns red and blocks the deploy. Lower **Max items to launch** to 10,000 or fewer, or narrow the filter. A filter matching zero items blocks the deploy too. See [Label a large dataset in batches](https://docs.platform.toloka.ai/docs/data/guides/label-at-volume.md).
* **An issue in the Issues window.** It sorts problems into errors you must fix and warnings you can override. Any failed check blocks, and so does a built-in lint that has not finished: **Quality Requirements Lint** and **User Interface Types Lint** on labeling nodes, **Dataset Items Lint** on Start, and **Exam Golden Dataset Lint** on expert-labeling nodes with an enabled [exam](https://docs.platform.toloka.ai/docs/data/reference/nodes/generation.md#exam). Lints start automatically after saved edits. Use **Run lints** to retry a failed lint. Click a row to open the setting it refers to; **Fix all with agent** hands the agent the whole list. See [the deploy gate](https://docs.platform.toloka.ai/docs/data/concepts/self-check.md#the-deploy-gate).
* **An empty balance.** A run cannot deploy on an empty balance, below \$0.01. Add funds to your team, then deploy again. See [Billing](https://docs.platform.toloka.ai/docs/core/billing.md#pipeline-runs).

## The agent built the wrong thing

Describe the fix in the terms of the pipeline's nodes: which node labels, which routes, and which computes. This lets the agent act on it. [Pipelines](https://docs.platform.toloka.ai/docs/data/concepts/pipelines.md) names what each node does. There are two ways to change what the agent built:

* **Ask the agent**, in plain words, to change a node or rebuild the labeling interface. In the **Issues** window, **Fix all with agent** hands the agent every listed issue. See [Self-check](https://docs.platform.toloka.ai/docs/data/concepts/self-check.md).
* **Edit by hand** on the node's cards. The labeling interface has an **Edit** tab. See [Review the labeling interface](https://docs.platform.toloka.ai/docs/data/guides/review-labeling-interface.md).

> [!WARNING]
>
> Hand edits and agent rebuilds change the same interface, and the last change wins: ask the agent to rebuild after a hand edit, and its build replaces your edits, with no prompt. Make your hand edits after the agent's final pass. See [Review the labeling interface](https://docs.platform.toloka.ai/docs/data/guides/review-labeling-interface.md).

## The upload failed

An upload is validated in full before anything is written, so a rejected file adds nothing. The exception is the 150,000-item dataset cap: a file that validates but overflows the cap is imported up to the cap, and the upload then fails with `Dataset item cap reached; remaining rows were not imported.` Fix the file and upload again. See [Create and manage datasets](https://docs.platform.toloka.ai/docs/core/datasets.md). The exact messages are on the [dataset errors](https://docs.platform.toloka.ai/docs/data/reference/errors.md#on-the-dataset-page).

* **The whole file is rejected** when its format is not JSON, JSONL, or CSV, it is empty or over 1024 MB, or an item exceeds the per-item size cap. JSON needs an array root; JSONL needs one JSON object per nonempty line.
* **Item validation lists up to 50 problems** and writes nothing. Fix the listed items, then upload again.
* **An appended file must stay schema-compatible** with the first upload's fields. A missing field, or a changed type, fails the whole append and adds no items.

## I hit a limit

These caps are fixed. The linked page gives the exact message and the way around each cap. Search [Pipeline errors and how to fix them](https://docs.platform.toloka.ai/docs/data/reference/errors.md) for the message you saw.

| Limit | Cap | Where the rule lives |
| - | - | - |
| Items per run | 10,000 | [Label a large dataset in batches](https://docs.platform.toloka.ai/docs/data/guides/label-at-volume.md) |
| Items per dataset | 150,000 | [Create and manage datasets](https://docs.platform.toloka.ai/docs/core/datasets.md) |
| One uploaded item | 1024 KB | [Create and manage datasets](https://docs.platform.toloka.ai/docs/core/datasets.md) |
| Fields per dataset | 500 | [Create and manage datasets](https://docs.platform.toloka.ai/docs/core/datasets.md) |
| One uploaded file | 1024 MB | [Create and manage datasets](https://docs.platform.toloka.ai/docs/core/datasets.md) |

The 10,000-items-per-run cap has no override. Use more runs for more data. Label a large workload as a cycle of batches. See [Label a large dataset in batches](https://docs.platform.toloka.ai/docs/data/guides/label-at-volume.md).

## FAQ

**Can I edit or rerun a deployed pipeline?** No. Clone it to change the configuration or label another batch. If deployment failed, you can fix and redeploy the same pipeline. See [Clone for another batch](https://docs.platform.toloka.ai/docs/data/guides/label-at-volume.md#step-3--clone-the-pipeline-for-the-next-batch).

**Do the experts see my data?** During a run, experts see the items they label. Before the run, test checks use sample values you provide; **Dataset Items Lint** inspects the selected dataset items, and **Exam Golden Dataset Lint** checks the golden dataset when an [exam](https://docs.platform.toloka.ai/docs/data/reference/nodes/generation.md#exam) is enabled. See [Self-check](https://docs.platform.toloka.ai/docs/data/concepts/self-check.md).

**Why did switching the dataset clear my filter?** Switching the dataset in the editor always clears **Max items to launch**, and clears the item filter whenever the new dataset cannot carry it over — a filter is built against the old dataset's fields, so a genuinely different dataset drops it. See [Start and End nodes](https://docs.platform.toloka.ai/docs/data/reference/nodes/start-and-end.md#switching-the-dataset).

## Related

* [Pipeline errors and how to fix them](https://docs.platform.toloka.ai/docs/data/reference/errors.md) — the exact on-screen message, indexed by its text, with cause and fix
* [Resume or cancel a pipeline run](https://docs.platform.toloka.ai/docs/data/guides/pause-resume-cancel.md) — the run controls and what each one does
* [Self-check](https://docs.platform.toloka.ai/docs/data/concepts/self-check.md) — the Issues gate that blocks or clears a deploy
* [Pipeline pricing](https://docs.platform.toloka.ai/docs/data/concepts/pricing.md) — Expected vs Maximum and the cost contract for a pipeline run
* [Billing](https://docs.platform.toloka.ai/docs/core/billing.md#pipeline-runs) — funding and the automatic pause when the balance runs out


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.