2026-05-24 01:02:47 +00:00
|
|
|
|
# Audita LLM Runtime
|
|
|
|
|
|
|
2026-11-10 17:52:14 +00:00
|
|
|
|
`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 `PrepareExecution` and `RunPrepared` on the same handle, passes
|
|
|
|
|
|
Audita's per-call schema and repair budget, and decodes only validated results.
|
|
|
|
|
|
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.
|
|
|
|
|
|
|
2026-11-11 04:47:43 +00:00
|
|
|
|
When correction repair is enabled, the proposal call retains its prompt,
|
|
|
|
|
|
effective variables, prepared messages, and full final response for section-local
|
|
|
|
|
|
replay. The adapter renders the repair definition with the selected profile,
|
|
|
|
|
|
appends only that branch’s history, and checks the original prepared prefix
|
|
|
|
|
|
before execution. The complete conversation is sent to the selected provider;
|
|
|
|
|
|
provider rejection ends that branch as unavailable. The requested repair
|
|
|
|
|
|
definition is retained in call attribution alongside native base-prompt metadata.
|
2026-11-11 04:18:05 +00:00
|
|
|
|
|
2026-11-10 17:52:14 +00:00
|
|
|
|
The observation collector tracks logical calls and execution events. 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.
|
