Skip to main content
POST
Run the consolidation pass

Body

application/json

What to run. Every field is optional.

mode
enum<string>
default:dry_run

dry_run reports and changes nothing, and never calls a model. apply acts.

Available options:
dry_run,
apply
trigger
enum<string>
default:manual

Recorded on the run, so the history says who started it.

Available options:
manual,
idle,
startup
passes
enum<string>[]

Run exactly these passes, ignoring the saved settings. Omit to use the settings, which is what every shipped surface does. This overrides the settings for the three paid passes too, so a caller can start a run that spends money while the Settings toggles are off. RECONCILE_ENABLED=0 still refuses it.

Available options:
invariants,
entities,
llm_entities,
llm_conflicts,
llm_recheck
budgetUsd
number

Keep re-checking past the per-run ceiling until nothing is due or this much has been billed, measured against the provider's own reported cost. Omit for one page and stop, which is the default. Capped at 50 because a typo here spends real money.

Required range: x <= 50

Response

What the run found and what it changed.

One run's own words. This is what the CLI prints and the Settings tab renders.

run
object

One run, and what it did.

actions
object[]
estimate
object

What re-checking everything currently due would cost, from the real prompt template and the actual content lengths. A dry run reports this instead of spending it. One run is capped at 200 beliefs, so on a store with a backlog this is what several runs add up to.

passes
string[]

The passes this run actually ran.

heldBack
object

Findings recorded but not surfaced, because a per-run cap was reached.

entities
object

What one resolution pass did.

arbitration
object

Present when the uncertain entity pairs pass ran.

autoResolved
object

Present when the memory conflicts pass ran.

recheck
object

Present when the contradiction re-check ran.