gstack/docs/ship-budget.md

# /ship token budget and fresh-context handoffs

`/ship --token-cap 25M` (or `GSTACK_SHIP_TOKEN_CAP=25M`) bounds what one /ship run spends, and
long runs hand their heavy segments to fresh-context children. The helper is
`bin/gstack-ship-budget`; the skill's procedure is `ship/sections/budget-handoff.md`.
There is no default cap: without one, /ship meters usage when it can and prints it, and
nothing else changes.

## What the cap guarantees

It is an **admission cap**, not a hard ceiling. Before every step and every dispatch batch,
`check` admits the work only when

    used + open reservations + unknown charges + projection + tail reserve + stop overhead <= cap

Exactly at the cap is admitted; one token over is not. A parallel review batch is reserved as
one sum before any of it starts. Admitted work can still cost more than its projection, and
gstack cannot stop a host mid-turn from bash, so a run can finish above the cap by the
misprojection of work already admitted. The tail reserve (default 2M, `--reserve <n>`) keeps
room for the receipt steps, and the stop overhead (calibrated) keeps room to stop cleanly. Once
the run has measured a step, the tail reserve scales with its measured step cost (a `--reserve`
you set stays as given); the stop overhead never scales.

## Quickstart

**Capy.** Read the root counter in one execute program that returns only that number:

```js
return (await tools.thread.get({ thread_id: "this" })).cost.tokens;
```

then

```bash
gstack-ship-budget start --record <record> --token-cap 25M --reading <n>
gstack-ship-budget check --run <id> --step 6 --next 7 --reading <n> [--prior-reading <n from your previous call>]
```

The counter rolls up every subagent of the thread, outside voices included; Capy exposes no
per-subagent counter, so other work in the same thread counts too (it only stops earlier).

**Claude Code.** `gstack-ship-budget start --record <record> --token-cap 25M --session <id>`. Without the
session id, `start --meter claude` prints a nonce: echo it once, then rerun with `--nonce <value>`.
The helper reads the session journal, its subagent journals and the journals of headless
children it launched; you never pass `--reading`.

**Anywhere else.** `--meter estimate` projects with the calibration and prints `meter=estimate`.
With a cap set and no readable meter, start refuses
([BUDGET_METER_UNAVAILABLE](troubleshooting.md#budget-meter-unavailable)).

## The BUDGET line

    BUDGET: used=<n> reserved=<n> unknown=<n> admission_cap=<n|none> tail=<n> unit=<u> meter=<m> epoch=<n> call=<n|unknown> call_floor=<n> above_floor=<n|unknown> next=<id> projected=<n> calibration=step:<f|prior>,dispatch:<f|prior> verdict=continue|delegate|stop

| Field | Meaning |
|---|---|
| `used` | Metered usage since start (all epochs), or settled estimates under `meter=estimate` |
| `reserved` | Open reservations: admitted steps, started dispatches, and each open child's sub-cap counted as max(sub_cap, child_used), never both |
| `unknown` | Charges the meter cannot see (an external-CLI outside voice on Claude Code), counted at their reservation |
| `admission_cap` | The cap, or `none` |
| `tail` | Tail reserve (scaled by the step factor once measured) plus stop overhead, held back from every admission |
| `unit`, `meter`, `epoch` | The meter contract: `capy-tokens` (root counter), `claude-usage-tokens` (journal usage), `estimate-tokens`; a meter change opens a new epoch |
| `call` | The per-call charge: two Capy readings in consecutive calls, or the last Claude Code call's usage |
| `call_floor`, `above_floor` | The host's per-call floor (see Delegation) and the charge above it, max(0, call − floor); the delegate rule compares `above_floor` |
| `next`, `projected` | What the check was for and its projection: the prior times the run's factor for that kind |
| `calibration` | The run's step and dispatch factors (see Calibration), or `prior` before the first measurement |
| `verdict` | `continue` (exit 0, prints `RESERVATION:` under a cap), `delegate` (exit 0), `stop` (exit 3) |

Any exit other than 0 means the next step does not start. Exit 2 is a usage or validation
error on stderr with the code, the value and the repair. GSTACK_RESULT appears only on a stop,
an incomplete close and a child's return; /ship's real terminal line stays Step 22's.

## Dispatches

Under a cap, `gstack-review-log --start` refuses a dispatch without an unspent, one-shot
reservation ([BUDGET_CHECK_SKIPPED](troubleshooting.md#budget-check-skipped)):

```bash
gstack-ship-budget check --run <id> --step 9 --next dispatch:specialist,red-team --reading <n>
gstack-review-log --start review --reservation <id>
```

Each reader is priced at max(its projection, the run's measured mean for that role over settled
dispatches). When the whole batch does not fit, `check` admits the largest prefix that does and
prints `ADMIT: k of n (remaining=<roles>)`: dispatch those k, then re-check the remaining roles
once they settle. Only a batch whose first reader does not fit stops, and `close` flags remaining
roles no later check requested (`DROPPED:`, status=incomplete until the owner accepts).
Roles are review-depth's: `specialist`, `red-team`, `adversarial-native`, `outside-voice`,
`fix-check`. `--finish <token>` is the pass's completion receipt: it settles that reservation and
every other dispatch reservation started in the same step, so reviewers admitted one at a time
do not stay reserved. Name a reviewer that came back in your next check
(`check ... --returned <id>[,<id>...]`), or, when other work comes first, `settle --reservation <id>
--reading <n>` as it returns so its cost is measured alone. A check that moves to the next step
settles every dispatch a reviewer started in the step before.
`close` audits after the fact: each review-log row of the run with no reservation gets one
BUDGET_CHECK_SKIPPED line and the run ends status=incomplete for the owner to accept
(`close --approved-by <who> --words "<their words>"`); a reservation is never created after the fact.

## Delegation

The delegate rule measures context above the host's per-call floor: what one call costs in a
fresh session with the ship skill loaded, before any /ship work. The floor is `call_floor` per
unit in `lib/ship-budget-calibration.json` (150k on Capy, where a fresh thread's calls cost
150–230k; 40k on Claude Code; 0 for the estimate meter, whose charge is always unknown), or
`start --call-floor <n>`, which the ledger records and every child inherits. At start, 100k or
more above the floor delegates the whole /ship. Before Step 7 and before Step 12, 150k or more
above the floor (or an unknown charge) delegates the next segment (7–11.5, 12–22). The BUDGET
line prints `call`, `call_floor` and `above_floor`, so each verdict can be checked:

1. `gstack-ship-budget handoff --run <id> --from 12 --to 22 --base origin/<base> --reading <n>` writes a
   brief (mode 0600, under the run directory) with the pins (HEAD, merge base, working tree,
   reviewed tree), the record with its six headings and start tokens, the decisions in scope
   with the owner's words, the decision trail, the budget and the return contract. It reserves
   the child's sub-cap: min(cap − used − reserved − unknown − the calibrated tail reserve and stop
   overhead, the segment estimate), or `--sub-cap`. A child handing off reserves its whole
   remaining sub-cap instead (cap − used − reserved − unknown − its stop overhead).
2. The child is a Capy subagent on the shared machine, or on Claude Code
   `gstack-ship-budget launch --in <brief>`: a background `claude -p` (resolved through lib/claude-bin.ts)
   with explicit permission flags and the return file named.
3. The child runs `verify-handoff` first; a moved pin refuses
   ([HANDOFF_PIN_MOVED](troubleshooting.md#handoff-pin-moved)). It admits against its sub-cap
   with child_used = reading − reading at handoff and is the only writer of the record. The
   context rule never stops a child. When it fires at one of the child's boundaries:
   - once the child has completed a step since `verify-handoff`, `verdict=delegate` hands its
     remaining steps (the next step through the end of its segment) to a fresh grandchild
     through these same four steps. The chain depth (1 for a child, 2 for a grandchild, at most
     3) is recorded in the brief, the handoff and the new ledger;
   - before its first completed step, at depth 3, or when the next step is past its segment,
     `verdict=continue` with one `CONTEXT_HIGH:` line (call, floor, threshold, depth, reason).

   The admission cap still stops a child (`reason=budget_exhausted`). It reconciles any
   grandchild, then ends with `return` (at most 40 lines). `return` reports `status=incomplete`
   while one of the child's own handoffs is unreconciled (`UNRECONCILED:`) or an ADMIT remainder
   was never re-checked (`DROPPED:`), so a delegated segment cannot drop readers or leave a
   grandchild writing after the parent moves on.
4. `gstack-ship-budget reconcile --run <id> --return <file> --reading <n>`; idempotent per handoff hash,
   so a duplicate return charges nothing twice. A refused, incomplete or interrupted child
   exits 3: regenerate the handoff or stop. Up a chain each token is charged once: the Capy
   counter already includes the whole subtree, a session `launch` starts joins the Claude Code
   meter of every ancestor, and under `meter=estimate` a child's returned `used` carries its
   grandchild's.

`--delegate never` turns delegate into stop for a parent on a host without children; a child
continues with a `CONTEXT_HIGH:` note instead.

## Stop and resume

A stop prints

    STOP: reason=budget_exhausted spent=<n> reserved=<n> unknown=<n> admission_cap=<n> next=<id> projected=<n>
    RECOVER: /ship --resume <record> --token-cap <used + reserved + unknown + projected tail>
    GSTACK_RESULT: skill=ship status=incomplete run=<dir>

Raising the cap is the owner's call; the resume journals who raised it and their words:

```bash
gstack-ship-budget resume --record <record> --token-cap <n> --approved-by Garry --words "raise it to finish" --reading <n>
```

Every command takes `--run` or `--record`; runs are never found by branch or directory, and a
/ship without `--resume` or `--continue` always starts a new run. The ledger and record are
mirrored to a private Drive checkpoint (`GSTACK_SHIP_BUDGET_CHECKPOINT_DIR`, else the
project-user Drive folder on Capy) bound to the run id and their hashes, so after a machine
change `resume --run <id>` restores both. A corrupt ledger
([BUDGET_LEDGER_INVALID](troubleshooting.md#budget-ledger-invalid)) is rebuilt from the
record's block with `--rebuild-from-record`; open reservations are then charged as unknown.

## Calibration

`lib/ship-budget-calibration.json` holds per-meter constants (per call, per dispatch, stop
overhead, calls and dispatches per step) fitted from metered runs: each constant is the
largest observation times 1.5, rounded up to 10,000 tokens. The leave-one-out test
(test/ship-budget-calibration.test.ts) covers the per-call constant only, the one observed
across three runs; per-dispatch has two observations and stop overhead one. Only the Capy
meter has observations; the Claude Code and estimate units are seeded from it until a
Claude-metered /ship completes. Each unit's `call_floor` is calibrated separately, with its
evidence in `call_floor_why`; a floor is the largest 10,000 multiple at or below its smallest
observed fresh call.

These constants are the prior. Each settled step or dispatch is measured on the next fresh
reading (a step from its check's reading to the next one; dispatches settled together as one
group, split by role), and prints

    DRIFT: id=<reservation> kind=step|dispatch next=<id> projected=<n> actual=<n> ratio=<actual/projected>

From then on the run projects steps and dispatches with its own factor: the largest
actual/prior ratio among its last three measurements of that kind, times 1.5. The step factor
also scales the default tail reserve. Dispatches keep the prior until the first
dispatch is measured, so under a tight cap admit one reviewer first and let it calibrate the rest.
`close` prints `BUDGET_DRIFT:` with the run's projected and actual totals per kind. The estimate
meter has no readings, so it always projects at the prior.

## Token cap and USD spend cap

A lane's `--spend-cap` (USD) bounds paid gates and evals through lib/spend-ledger.ts; `--token-cap`
bounds the /ship run's model tokens through its own ledger. They are independent: set both
when a lane runs paid gates inside /ship, and neither converts into the other.

## Claiming savings

Savings count completed ships only. Preregister the comparison with `/eval-plan` (arms, bars,
stop rules) before claiming a saving from the cap or from delegation.

## Result codes

[BUDGET_CAP_REACHED](troubleshooting.md#budget-cap-reached) ·
[BUDGET_READING_MISSING](troubleshooting.md#budget-reading-missing) ·
[BUDGET_READING_REJECTED](troubleshooting.md#budget-reading-rejected) ·
[BUDGET_METER_UNAVAILABLE](troubleshooting.md#budget-meter-unavailable) ·
[BUDGET_LEDGER_INVALID](troubleshooting.md#budget-ledger-invalid) ·
[BUDGET_CHECK_SKIPPED](troubleshooting.md#budget-check-skipped) ·
[HANDOFF_PIN_MOVED](troubleshooting.md#handoff-pin-moved)