> ## Documentation Index > Fetch the complete documentation index at: https://docs.leeroo.com/llms.txt > Use this file to discover all available pages before exploring further. # Resume a Kapso build and set its budgets > Continue an interrupted or budget-stopped build from its exact checkpoint; how the four budget dials resolve between the call, the brief, the launch record and the config; and how a campaign ends: the reserve, the finishing sessions and their obligations, the admission of a round, an unjudged attempt. A build that stopped, died or ran out of budget continues from its exact search state. Resume is strict: it never turns a missing, corrupt, incompatible or completed checkpoint into a new campaign. ## Resume ```bash theme={null} kapso watch campaign # DEAD or STALLED: it died; max_iterations: it ran out kapso build --output campaign --resume --detach ``` ```python theme={null} solution = Kapso().build(output="campaign", resume=True) ``` Nothing is retyped: the brief comes from the checkpoint and every launch flag from the launch record, `.kapso/launch.json`. Pass only what you mean to change, which is usually a bigger budget: ```bash theme={null} kapso build --output campaign --resume --budget-minutes 120 --budget-experiments 8 --detach ``` A campaign that paused for you resumes through `kapso inbox reply`, not `--resume`; a `--resume` with a request still open pauses again without running anything. See [The inbox](https://docs.leeroo.com/docs/build/inbox.md). ## What a resume requires * `--output` names an existing campaign directory, a non-bare git repository with `.kapso/run_state.json`. * The brief, when passed, matches the checkpoint's exactly; left out, it comes from the checkpoint. * The host (`--coding-agent`), evaluation directory, config and experience match the launch's. A difference is refused by name; start a new build in a new output directory instead. A bare resume is served the sources the launch pinned, at the same heads. * The campaign is not `completed`: only reaching the objective completes a campaign, and a completed one is not resumed. Validation happens before anything is touched: a refused resume creates no repository, renames no branch and overwrites no state. ## The budget Four dials, every one optional: | Dial | Brief token | Flag | Python | Config | | - | - | - | - | - | | Wall clock | `minutes=60` | `--budget-minutes 60` | `Budget(minutes=60)` | `budget.minutes` | | Experiments | `experiments=10` | `--budget-experiments 10` | `Budget(experiments=10)` | `budget.experiments` | | Model spend, USD | `usd=25` | `--budget-usd 25` | `Budget(usd=25)` | `budget.usd` | | Reserve, kept out of the search for finishing | `reserve_minutes=5` | `--budget-reserve-minutes 5` | `Budget(reserve_minutes=5)` | `budget.reserve_minutes` | Precedence, dial by dial: the flag or the `budget=` argument, then on a resume the launch record (the launch's own figures, so a bare `--resume` runs on what the campaign was launched with, not the brief's line), then the brief's `Budget` line, then the [config's `budget` block](https://docs.leeroo.com/docs/reference/configuration#budget). `experiments` is the number this call may run; the clock is durable across resumes (paused time does not count), and the result keeps both counts: ```python theme={null} solution.experiments # this call solution.experiments_total # the whole campaign ``` The trace's `budget` line says which won when the brief and the launch both named minutes, and the reserve in force. ## How a campaign ends A budget stop records why in `stopped_reason: budget_exhausted` and `stop_detail`, and leaves the checkpoint `running` for the next slice: | `stop_detail` | What happened | | - | - | | `time_budget` | The wall clock ran out | | `cost_budget` | The model spend reached its budget | | `attempt_would_not_fit` | A round was not admitted: the searchable remainder would not cover an attempt. The note says why, `the remaining 8.0 min would not cover an attempt (the last took 14.0 min)`. A node waiting on a request you have answered is not a round: its session continues whatever the remainder, and the round after it is admitted on what is left | | `finishing_cut` | A finishing session was not launched or was cut at the deadline: the note names it, `the verification of node 3 was not launched: …` | The mechanism behind the last two: **Two classes of session.** A *search* session (the harness setup, ideation and its members, the lens planner, the selector, the implementation) is clamped against the searchable remainder: the budget less the reserve. A *finishing* session completes an attempt that was already made (the candidate's evaluation run, the verification, the judge, the reconstruction of what went wrong): it is clamped against the whole remainder less the obligations that follow it. After the evaluation run come the verification when the harness verifies, then the judge, then the delivery's own slice; the evaluation and the verification are protected at the floor, `budget.min_agent_timeout_seconds` (a verification cut short is unverified, and the judge still speaks), the judge at its reserve: its last observed duration in the campaign, `budget.judge_reserve_seconds` before one, since a judge takes minutes. Time a session leaves unused flows to the next obligation. A session's deadline is the smaller of its configured timeout and this room, never raised to the floor; an unbudgeted campaign keeps its configured timeouts. **The reserve.** `reserve_minutes` set wins. Unset, the packaged default, it is derived each round from the obligations themselves: the harness's `verification_minutes` when it verifies, the judge's last observed duration (`judge_reserve_seconds` before the first), the delivery's slice. Either is bounded by a quarter of the budget, so a short budget keeps its search; a finishing session then takes what its room leaves. A budget whose search room is under the floor before anything ran (a harness setup session with no room) is refused at launch with the reason. **Admission.** A round starts only when the searchable remainder covers the larger of `budget.min_iteration_seconds` and the previous round's own duration, measured from its ideation's start to its last lane's judgment and recorded on the checkpoint, so a resume reasons from the history it restored. The duration counts the round's finishing (its verification and its judge), which the reserve holds back as well, so the admission errs early by about one finishing span rather than late. Before any round, the floor alone. **A session not launched says why.** Verification not launched leaves the attempt `unverified` with the reason; a judge not launched leaves it `unjudged`; a reconstruction not launched is noted on the attempt. **An unjudged attempt.** `unjudged` is the attempt's field, empty when the attempt was judged and otherwise the reason: `the budget left no time for the judge`, `the judge's session ended at the budget's deadline`, or `no tags after a retry` when the judge answered twice without its tags. The attempt keeps its score, is never a parent and is never delivered, as an `unverified` attempt is never delivered; the trace shows it on the attempt's `judge` line. A judge that answered in full without its tags is resumed once in its own session with the nudge, under a room computed again; a judge cut at its deadline is not retried. ## The checkpoint `.kapso/run_state.json` holds the brief, its hash, the configuration fingerprint, the search state (every node, with its commit at evaluation and whether it was judged), the durable clock, the last round's duration, the cumulative cost and the status. It is written atomically after every finalized experiment, so an interrupted write leaves the previous checkpoint readable. A resume restores the node history, the feedback for the next experiment, the clock and the cost, and continues. Resume errors are importable from `kapso`: | Error | Meaning | | - | - | | `RunCheckpointMissingError` | No checkpoint in the directory | | `RunCheckpointCorruptError` | The checkpoint's fields or state are invalid | | `RunCheckpointIncompatibleError` | The brief, strategy, configuration or schema does not match | | `RunCheckpointCompletedError` | The campaign already reached the objective | Fix the mismatch or name the right directory; never edit the checkpoint to force a resume. ## Related > [card] [Run and watch](https://docs.leeroo.com/docs/build/run-and-watch.md) > > Launching and following a build > [card] [The inbox](https://docs.leeroo.com/docs/build/inbox.md) > > The pause a reply resumes > [card] [Review the result](https://docs.leeroo.com/docs/build/review.md) > > What a stopped build delivered so far > [card] [Configuration](https://docs.leeroo.com/docs/reference/configuration.md#budget) > > The budget block Related pages: [Run and watch](https://docs.leeroo.com/docs/build/run-and-watch.md) · [The inbox](https://docs.leeroo.com/docs/build/inbox.md) · [Review the result](https://docs.leeroo.com/docs/build/review.md) · [Configuration](https://docs.leeroo.com/docs/reference/configuration.md#budget) · [CLI reference](https://docs.leeroo.com/docs/reference/cli.md#kapso-build) Kapso is an open-source framework by [Leeroo](https://leeroo.com) that builds software toward measurable goals through experiment campaigns. Source code: [github.com/Leeroo-AI/kapso](https://github.com/Leeroo-AI/kapso) · Install: `pip install leeroo-kapso` · Every page as plain text: [llms.txt](https://docs.leeroo.com/llms.txt). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.