eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Document the PromptKit configuration migration

Browse Source
This commit is contained in:
Eric Rakestraw
2026-10-04 01:14:53 +00:00
parent 5525fe875e
commit 9bcf18331e
9 changed files with 160 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/internal/cli-config.md
View File

@@ -42,6 +42,11 @@ go run ./cmd/audita config print-effective --config examples/minimal-config.yml
go run ./cmd/audita config print-effective --config examples/configkit-inheritance.yml --view explain
```
The local and ConfigKit inheritance files select `profiles/local`; the service
file selects `profiles/service`, including the service testing profiles. Keep
these roots separate because PromptKit validates every final definition in a
selected root, including definitions that are not selected for a role.
Only referenced credentials read environment values; use a controlled synthetic
value when validating the service example. Check affected CLI examples against the
parser and use schema tests for maintained transcript/glossary inputs. Example

27
docs/internal/llm-runtime.md
View File

@@ -2,11 +2,28 @@
## Client Boundary
`llm.NewRuntime` assembles one PromptKit engine for both roles. It loads embedded
prompt and schema assets, registers application backends, and inspects the
selected proposal and validation profiles offline. A role-bound `llm.RoleClient`
implements `structuredoutput.Client`; proposal and validator contracts alias that
interface. Both roles share engine-local backend capacity.
`llm.NewRuntime` assembles one PromptKit engine for both roles. PromptKit's
catalogs and defaults are followed by Audita's embedded prompt and schema
inputs, operator documents from `profiles_dir`, and the highest-priority
application backend mapping. Audita owns backend endpoints, capacity settings,
and resolved credentials; native PromptKit layering owns profile inheritance,
prompt overrides, and provider-specific fields. Imports are disabled. The
runtime inspects both selected roles offline, requiring complete model and
endpoint values and rejecting competing profile credential lookups. A
role-bound `llm.RoleClient` implements `structuredoutput.Client`; proposal and
validator contracts alias that interface. Both roles share engine-local backend
capacity.
Successful construction captures the final definitions and referenced message
contents. The runtime does not reload operator documents or message files during
calls. If final engine construction fails, an embedded-only diagnostic
construction distinguishes shipped asset failures from invalid operator input.
An asset failure remains an asset error; when embedded construction succeeds,
the original failure remains a configuration error. The diagnostic engine
never replaces or executes the requested configuration, and caller cancellation
skips this path. The captured inspection also supplies an internal source
ledger: all loaded host YAML plus effective, source-relative host
`content_file` resources are tracked for output-collision checks.
For each logical call, the adapter starts an operation context and a diagnostic
record before preparation. It supplies the reserved hardening text, the selected

31
docs/internal/prompts.md
View File

@@ -11,18 +11,27 @@
- `validators.meaning_reversal_review` (`v1`)
- `validators.editorial_review` (`v1`)
PromptKit reads the embedded definitions and renders their system and user
messages from named string variables. The role-bound adapter supplies
PromptKit reads the embedded definitions as shipped defaults and renders their
messages from named string variables. Operator documents in `profiles_dir` may
contribute native keyed prompt definitions and override an embedded
prompt/version, including its messages and definition-level output settings.
The effective operator text is captured when the runtime is constructed; the
embedded assets remain the source of Audita's shipped task instructions. The
role-bound adapter supplies
`HardeningPolicy` alongside `ProposalContract` and `ValidationContract` from
embedded fragments under `assets/shared`, after caller variables so callers cannot replace those
instructions. Common literal-span and identity guidance lives in the proposal
fragment; shared candidate-reference, context, and confidence guidance lives in
the validation fragment. Module-specific policies and examples remain in YAML.
Proposal prompts receive the section JSON, glossary JSON where used, and transcript description block.
Validator prompts receive the correction payload and description block.
The prompt assets retain the prior task instructions and output-schema
association. The role-bound runtime supplies the complete JSON Schema output contract
and repair count; the definition does not own an operator-facing repair default.
embedded fragments under `assets/shared`, after caller variables so callers
cannot replace those instructions. Common literal-span and identity guidance
lives in the proposal fragment; shared candidate-reference, context, and
confidence guidance lives in the validation fragment. Module-specific policies
and examples remain in YAML. Proposal prompts receive the section JSON, glossary
JSON where used, and transcript description block. Validator prompts receive
the correction payload and description block.
The embedded prompt assets retain the shipped task instructions and
output-schema association. An operator override controls which template
variables its messages reference: supplying a shared variable does not append
its text when the effective message omits that reference. The role-bound runtime
supplies the complete JSON Schema output contract and repair count; the
definition does not own an operator-facing repair default.
The correction-set schema requires a string replacement and accepts an empty
string. Proposal guidance uses it for eligible span deletion and permits literal
spacing edits; validator guidance evaluates the full before/after segment under