53 lines
3.5 KiB
Markdown
53 lines
3.5 KiB
Markdown
# Audita LLM Runtime
|
|
|
|
`llm.NewRuntime` assembles one captured PromptKit engine using its default
|
|
catalog, Audita's embedded prompts and schemas, and optional operator sources
|
|
anchored to the recorded application main context. Captured host sources and
|
|
message files are passed to output collision checks. An embedded-only diagnostic
|
|
construction distinguishes shipped asset failures from operator-source failures;
|
|
it never replaces the requested engine.
|
|
|
|
Each resolved pipeline entry receives role-bound clients with its selected
|
|
profiles and effective budgets. Clients share engine-local backend admission.
|
|
The adapter uses ordinary `Run` with `OperationTimeout` and `OnPrepared`, passes
|
|
Audita's per-call schema and repair budget, and decodes only validated results.
|
|
The operation budget includes preparation, admission, retries, and structural
|
|
repair. `ErrOperationTimeout` remains recoverable even when wrapped by a
|
|
preparation error. Parent cancellation remains distinct. The prepared notification
|
|
provides the actual request snapshot; failures before notification have no snapshot.
|
|
PromptKit owns backend and credential selection. The adapter uses captured
|
|
credential source names for artifact redaction without inspecting unrelated
|
|
environment values. See the [integration contract](../integrations/openai-compatible-llm.md)
|
|
for failure behavior and the [configuration reference](../config.md) for sources.
|
|
|
|
When correction repair is enabled, the proposal call captures a native immutable
|
|
PromptKit exchange. Each actionable correction starts an independent
|
|
`Engine.Coordinate` branch from that exchange. PromptKit assembles continuation
|
|
history, owns the additional-turn budget, and delivers the last permitted response
|
|
for assessment. Follow-ups select the repair prompt, profile, and output schema
|
|
directly; Audita does not rerender the original proposal or assemble replay messages.
|
|
An opaque exchange in the structured-output contract keeps provider state outside
|
|
modules and validators. The adapter shares request construction, notifications,
|
|
observers, and result/failure finalization between ordinary and coordinated calls.
|
|
|
|
Audita owns actionable rejection, revision decoding, withdrawal, current previews,
|
|
and full revalidation. Accepted siblings remain independent. Requesting more work
|
|
at the budget boundary produces exhaustion without allocating another logical call.
|
|
A canceled, undelivered response supplies diagnostic evidence only; it cannot enter
|
|
the approved set. Repair disabled in configuration bypasses coordination entirely.
|
|
The runner supplements each repair instruction with its current proposal preview
|
|
as described in the [module guide](modules.md#failure-and-outcome-behavior).
|
|
The bundled prompts separate durable system principles from the initial user
|
|
assignment so later repair instructions can allow acceptable minor cleanup;
|
|
see [prompt instruction ownership](prompts.md).
|
|
|
|
The observation collector tracks logical calls and execution events, and enrolls
|
|
selected runs in a native `ExecutionGroup`. Proposal, repair, and nested validator
|
|
clients explicitly share the invocation observer; history reuse adds no extra run.
|
|
Native summaries deduplicate terminal totals by run ID and retain terminal coverage
|
|
separately from usage presence and completeness. Logical calls and run membership
|
|
can differ, especially on failures before execution. Ordinary
|
|
reports use compact safe outcomes; request and response evidence is optional
|
|
debug material. The runner preserves ordered pipeline traversal and deterministic
|
|
section collection while canceling and joining peers on fatal errors.
|