2026-05-24 00:47:27 +00:00
# Audita Configuration
2026-11-10 17:52:14 +00:00
Audita uses version 3 application configuration. See the [migration guide ](migrations/v3.md )
and [examples ](../examples/ ) for complete projects. Command syntax is owned by
[the CLI reference ](cli.md ).
## Loading and composition
An explicit `--config` selects one main YAML file. Without it, ConfigKit searches
the working directory, user configuration directory, and Unix system directories
for `audita` configuration. If no file is found, built-in defaults apply. An
explicit invalid selection or failure of a selected file is an error; search does
not continue after a selected file fails. An omitted version uses the v3 schema;
a supplied version must be `3` .
Operator sources may use ConfigKit imports. The selected main file provides the
base for an optional `overlays/<name>.yml` , optional `glossary.yml` , and recursive
`glossary/` YAML files. Without a main source, automatic companion files are not
loaded from the working directory. ConfigKit composes sources, resolves native
inheritance, applies explicit overrides, records derived defaults, and validates
the result. Its [configuration reference ](https://forge.maximumdirect.net/base-layer/configkit/src/tag/v1.2.0/docs/config.md )
owns native composition and provenance semantics.
2026-05-24 00:54:27 +00:00
2026-10-04 01:14:53 +00:00
### PromptKit profiles and operator prompts
2026-11-10 17:52:14 +00:00
PromptKit loads its default catalog and Audita's embedded prompts, followed by
optional `prompts.yml` and recursive `prompts/` YAML files beside the application
main. Native imports, resource collections, inheritance, and replacement apply.
Profiles, backends, models, credentials, admission, and provider parameters belong
2026-11-15 01:25:55 +00:00
to PromptKit configuration; see its [format reference ](https://forge.maximumdirect.net/base-layer/promptkit/src/tag/v0.23.0/docs/formats.md ).
2026-11-10 17:52:14 +00:00
The engine captures its sources for an invocation. Edit files and run a new
invocation to pick up changes. Inspection does not require model credentials.
## Pipeline and glossary selections
`glossary_collections` maps names to collections with an ordered `entries` list.
Each entry has an `id` , `name` , and `category` ; `description` , `aliases` , and
`plural` provide optional context. Entries are identified within their collection
by `id` . Root `glossaries` and `protected_terms` select collection names. If root
protection is omitted, it derives from the root glossary selection.
`pipeline.stages` is an ordered list of `module` records; supported modules are
`glossary` , `homophones` , `spoken_word` , and `grammar` . The default sequence is
`glossary` , `homophones` , `glossary` , `spoken_word` , `grammar` . Repeated modules
run separately; `[]` runs normalization without model processing. An optional
nonempty, unique `id` identifies a record in evidence. Each record may override
2026-11-11 17:05:52 +00:00
`glossaries` , `protected_terms` , and fields under `llm` ,
2026-11-10 17:52:14 +00:00
`validation` , and `context` . Omitted fields inherit their resolved root values.
Explicit empty lists and null list selections clear a selection.
Each entry receives its selected context and independent protection. Glossary
2026-11-10 20:33:24 +00:00
correction exempts active recognized spellings from protection for that entry.
A longer exempt name still takes precedence over a shorter protected spelling
inside it. A glossary correction must have at least one selected entry at
processing preflight. Empty definitions and empty protection remain valid
configuration.
2026-09-24 01:50:10 +00:00
2026-11-11 17:05:52 +00:00
The bundled prompts use English. The modules request complementary work:
- `glossary` : context-supported corrections toward selected glossary terms.
- `homophones` : plausible spoken-word mistranscriptions, including glossary terms.
- `spoken_word` : conservative filler, hesitation, and accidental repetition cleanup.
- `grammar` : punctuation, capitalization, spacing, and whole-word `a` /`an` cleanup.
Otherwise acceptable minor editorial cleanup may be accepted across modules, as
specified by the [editorial acceptance boundary ](policy/architecture.md#correction-and-concurrency-invariants ).
2026-09-24 01:33:03 +00:00
## Settings
2026-05-24 00:47:27 +00:00
2026-11-10 17:52:14 +00:00
| Setting | Default | Meaning |
2026-09-23 15:03:20 +00:00
| --- | --- | --- |
2026-11-10 17:52:14 +00:00
| `llm.proposal_profile` | unset | PromptKit profile for proposals; required for processing entries. |
| `llm.validation_profile` | effective proposal profile | Profile for model validation; null clears a selection before fallback. |
2026-11-11 04:20:23 +00:00
| `llm.correction_repair_profile` | effective proposal profile | Profile for correction repair; null clears an inherited selection before fallback. |
| `llm.correction_repair_attempts` | `1` | Nonnegative repair attempts per correction; zero disables correction repair. |
2026-11-10 17:52:14 +00:00
| `llm.transient_retries` | `2` | Additional transient attempts per generation. |
| `llm.repair_attempts` | `2` | Structural repairs, from zero through three. |
| `llm.operation_timeout` | `15m` | Positive duration per logical operation. |
2026-09-24 01:33:03 +00:00
| `validation.max_prompt_tokens` | `2048` | Positive validation batching budget. |
2026-11-10 17:52:14 +00:00
| `context.description` | empty | Prompt context; at most 500 bytes after trimming. |
2026-11-16 04:02:22 +00:00
| `chunking.target_sections` | unset | Optional positive count. Processing requires exactly this many nonempty sections when specified. An infeasible count is an input error. |
| `chunking.max_section_tokens` , `chunking.min_section_tokens` | `8192` , `2048` | The maximum bounds a section's estimated tokens, except for an oversized segment in a section of its own. The minimum is validated against the maximum and retained for compatibility. |
2026-11-10 17:52:14 +00:00
| `normalization.max_segment_gap` , `normalization.ellipsis_gap` | `4` , `3.5` | Nonnegative seconds. |
| `normalization.max_segment_duration` , `normalization.max_segment_tokens` | `60` , `2048` | Positive seconds and token estimate. |
| `output.schema` | `bare-segments` | Output format; see [output contracts ](integrations/output-files.md ). |
| `reporting.enabled` , `reporting.stdout_dir` | `true` , `.` | Ordinary report capture and default directory for stdout output. |
| `diagnostics.work_dir` | `/tmp/audita` | Parent directory for optional debug capture. |
2026-11-11 04:47:43 +00:00
For example, an entry can disable correction repair or select another profile:
```yaml
llm:
proposal_profile: local
correction_repair_attempts: 2
pipeline:
stages:
- module: grammar
llm:
correction_repair_profile: review
- module: spoken_word
llm:
correction_repair_attempts: 0
```
2026-11-10 17:52:14 +00:00
Processing profiles are selected explicitly; no profile or glossary is selected
automatically. The validation selection falls back after root and per-entry
2026-11-11 04:20:23 +00:00
settings are combined. An explicit root correction repair profile is inherited
by each entry unless overridden or cleared with null; otherwise the entry uses
its effective proposal profile. The repair profile is checked only when its
2026-11-11 04:47:43 +00:00
attempt budget is positive. Each correction repair attempt is a logical call
that can also use the configured transient retries and structural repairs. Null
does not disable validation. Numeric zero and false
2026-11-10 17:52:14 +00:00
retain their field meaning, subject to validation. Inspect recorded origins and
default dependencies using the [native commands ](cli.md ).