Skip to content

SingleShotResult

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/runtime/singleShot.ts:30

Result of a runSingleShot run: the pass/fail contract callers such as ask/exec have always used (ok), plus the SUT’s answer text and run stats (GS2-16’s GthRunStats) that were already computed internally but previously discarded. Extends GthRunStats rather than restating tokensInput/tokensOutput/tools as parallel fields.

optional advertisedTools?: GthAdvertisedTools

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/runtime/singleShot.ts:42

BATCH-32 — what the agent ADVERTISED to the model for this run: the full pre-allowedTools inventory, the tools the allow-list removed, and the count of nameless ones.

A sibling of the run stats rather than a field inside them: GthRunStats is the per-turn tally the accumulator folds messages into, and this is fixed at init. undefined means no inventory was observed (an agent that does not report one), which is a different answer from an inventory listing no tools.


answer: string

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/runtime/singleShot.ts:44

The SUT’s full answer text (runner.processMessages()’s return value). Empty on failure.


ok: boolean

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/runtime/singleShot.ts:32

true when the run completed without error, false when it failed.


terminationReason: GthTerminationReason | null

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/runtime/singleShot.ts:54

[[EXT-159]] — why the run ended, as a value.

The structural twin of the line this runtime prints: a caller (and a test) reads the classification here rather than matching the prose on the console, so no user-facing string is the only carrier of it. null means no site classified the ending, which by this taxonomy’s contract is a site we missed — never a stand-in for an ordinary finish, which is recorded as completed.


optional tokensInput?: number

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/core/types.ts:102

Total prompt/input tokens across the run’s LLM calls, when the provider reported usage.

GthRunStats.tokensInput


optional tokensOutput?: number

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/core/types.ts:104

Total completion/output tokens across the run’s LLM calls, when the provider reported usage.

GthRunStats.tokensOutput


optional toolResults?: GthToolResult[]

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/core/types.ts:114

BATCH-21 — one record per executed tool result (ToolMessage) observed during the run, in arrival order and NOT deduplicated (a tool called twice yields two records), so gth eval’s tool-RESULT assertions (must_error / tool_result_json_path) can grade what a tool returned, not just that it was called. Optional (additive): producers that predate the field simply omit it; runStats.js finalizeRunStats always sets it.

GthRunStats.toolResults


tools: string[]

Defined in: _worktrees/docs-release/gaunt-sloth/packages/core/src/core/types.ts:106

Names of tools invoked during the run (deduplicated); empty when no tools were used.

GthRunStats.tools