Directories
¶
| Path | Synopsis |
|---|---|
|
Package cli implements every pluto command against injected dependencies.
|
Package cli implements every pluto command against injected dependencies. |
|
codepacks
|
|
|
capability
Package capability is Pluto's core-capability qualification pack: instruction-following and known-answer cases that need no special target capability, just plain text conversation.
|
Package capability is Pluto's core-capability qualification pack: instruction-following and known-answer cases that need no special target capability, just plain text conversation. |
|
operational
Package operational is Pluto's operational-stability qualification pack: bounded latency across prompt sizes, and tolerance for a bounded rate of tool-call errors.
|
Package operational is Pluto's operational-stability qualification pack: bounded latency across prompt sizes, and tolerance for a bounded rate of tool-call errors. |
|
safety
Package safety is Pluto's safety-conduct qualification pack: canary leak resistance, injection resistance, and the refusal/over-refusal control.
|
Package safety is Pluto's safety-conduct qualification pack: canary leak resistance, injection resistance, and the refusal/over-refusal control. |
|
structuredoutput
Package structuredoutput is Pluto's structured-output qualification pack: can the target produce schema-conformant output across shapes, and does it fail cleanly when it cannot.
|
Package structuredoutput is Pluto's structured-output qualification pack: can the target produce schema-conformant output across shapes, and does it fail cleanly when it cannot. |
|
tooluse
Package tooluse is Pluto's tool-use qualification pack: does the target invoke tools when the task requires them, and does it stay disciplined (no unnecessary or forbidden tool calls) when it does not.
|
Package tooluse is Pluto's tool-use qualification pack: does the target invoke tools when the task requires them, and does it stay disciplined (no unnecessary or forbidden tool calls) when it does not. |
|
Package compare rolls up an eval/compare diff between a candidate and an incumbent Pluto scorecard, aligned by (Pack, Table).
|
Package compare rolls up an eval/compare diff between a candidate and an incumbent Pluto scorecard, aligned by (Pack, Table). |
|
Package gen generates candidate scenarios for one table via a single structured-output call, then validates, dedupes, and appends them.
|
Package gen generates candidate scenarios for one table via a single structured-output call, then validates, dedupes, and appends them. |
|
Package packfile is the strict, versioned trust boundary between the YAML pack corpus and qual.
|
Package packfile is the strict, versioned trust boundary between the YAML pack corpus and qual. |
|
internal/genschema
command
Command genschema regenerates pkg/packfile/schema.json from the evaluator registry.
|
Command genschema regenerates pkg/packfile/schema.json from the evaluator registry. |
|
Package plutotest wires a Pluto pack execution into ordinary go test, and gates a test on the derived qualification disposition.
|
Package plutotest wires a Pluto pack execution into ordinary go test, and gates a test on the derived qualification disposition. |
|
Package pricing implements list-price estimation for qualification runs.
|
Package pricing implements list-price estimation for qualification runs. |
|
Package profile derives an organization's qualification disposition from an Pluto scorecard.
|
Package profile derives an organization's qualification disposition from an Pluto scorecard. |
|
Package qual qualifies a model or model configuration for enterprise use.
|
Package qual qualifies a model or model configuration for enterprise use. |
|
target
Package target provides deterministic eval.Target fixtures for offline pack tests.
|
Package target provides deterministic eval.Target fixtures for offline pack tests. |
|
Package ratelimit decorates an inference.Client with client-side rate limiting: a requests-per-minute pacing limiter, an in-flight concurrency cap, and automatic retry with exponential backoff on rate-limit (HTTP 429) and transient server (5xx) / network failures.
|
Package ratelimit decorates an inference.Client with client-side rate limiting: a requests-per-minute pacing limiter, an in-flight concurrency cap, and automatic retry with exponential backoff on rate-limit (HTTP 429) and transient server (5xx) / network failures. |
|
Package reportjson is Pluto's canonical, versioned JSON codec for a Scorecard plus an optional profile.Result.
|
Package reportjson is Pluto's canonical, versioned JSON codec for a Scorecard plus an optional profile.Result. |
|
Package run executes Pluto packs against a target and rolls the results up into a qual.Scorecard.
|
Package run executes Pluto packs against a target and rolls the results up into a qual.Scorecard. |
Click to show internal directories.
Click to hide internal directories.