# rakestraw.dnd_pipeline

Installs the D&D transcript-processing application suite by composing the
standalone Seriatim, Audita, Notarius, Scriptorium, and Narratio roles. It
supports Ubuntu 26.04 and Ansible Core 2.18 or newer. Downstream roles perform
their own task-level privilege escalation, so a play does not need `become`.
Supported host architectures are `amd64` and `arm64`.

## Installation

Install the role dependencies and their collection before applying this role:

```sh
ansible-galaxy role install -r requirements.yml
ansible-galaxy collection install -r collections/requirements.yml
```

The dependency manifest installs the roles under their canonical names:
`rakestraw.seriatim`, `rakestraw.audita`, `rakestraw.notarius`,
`rakestraw.scriptorium`, and `rakestraw.narratio`. It selects the compatible
`v0.1.0` releases where compatible and public commit pins for Narratio and
Notarius when the suite needs newer interfaces. This standalone role is named
`rakestraw.dnd_pipeline`.

```yaml
---
- name: Install the D&D pipeline foundation
  hosts: pipeline_hosts
  gather_facts: true
  roles:
    - role: rakestraw.dnd_pipeline
      vars:
        dnd_pipeline_whisperx_transcribe_url: https://whisperx.example/transcribe
```

The collection source exposes a reviewed snapshot of this role as
`rakestraw.dnd.pipeline`:

```yaml
---
- name: Install the D&D pipeline from the collection
  hosts: pipeline_hosts
  gather_facts: true
  roles:
    - role: rakestraw.dnd.pipeline
      vars:
        dnd_pipeline_whisperx_transcribe_url: https://whisperx.example/transcribe
```

Collection consumers should follow the unified bootstrap instructions in the
[`rakestraw.dnd` collection repository](https://gitea.maximumdirect.net/eric/ansible-collection-dnd).
This standalone repository remains authoritative for role changes; collection
maintainers import a reviewed, pushed commit or immutable tag as a snapshot.
Collection releases are published independently and are listed in the
collection repository.

## Variables

`dnd_pipeline_whisperx_transcribe_url` is required and is passed to Narratio.
The compatible application versions are selected through these variables:

| Variable | Default |
| --- | --- |
| `dnd_pipeline_audita_version` | `v0.9.1` |
| `dnd_pipeline_narratio_version` | `v2.2.0` |
| `dnd_pipeline_notarius_version` | `v0.7.1` |
| `dnd_pipeline_seriatim_version` | `v1.5.0` |
| `dnd_pipeline_scriptorium_version` | `v0.13.0` |
| `dnd_pipeline_manage_build_dependencies` | `true` |
| `dnd_pipeline_go_snap_channel` | `1.26/stable` |
| `dnd_pipeline_go_binary` | `/snap/bin/go` |
| `dnd_pipeline_campaigns_repository_url` | `https://gitea.maximumdirect.net/eric/campaigns.git` |
| `dnd_pipeline_campaigns_revision` | `main` |
| `dnd_pipeline_campaigns_root` | `/usr/local/share/narratio/campaigns` |
| `dnd_pipeline_prompt_library_repository_url` | `https://gitea.maximumdirect.net/eric/narratio-prompts.git` |
| `dnd_pipeline_prompt_library_revision` | `main` |
| `dnd_pipeline_prompt_library_root` | `/usr/local/share/narratio/prompt-library` |

The common dependency-management switch controls whether every application
role installs Git and Go. Callers that disable it must provide both Git and Go.
The Go channel and executable are likewise passed to all five roles. Advanced
callers may supply unmapped standalone-role variables directly through normal
Ansible variable precedence.

The following values are deliberate D&D suite policy passed through the
standalone roles' generic configuration interfaces; they are not standalone
defaults. Narratio runs first and establishes the selected runtime user and
group before the remaining configuration-bearing dependencies run.

| Variable | Default policy |
| --- | --- |
| `dnd_pipeline_runtime_user` | `narratio` |
| `dnd_pipeline_runtime_group` | `narratio` |
| `dnd_pipeline_operator_users` | `[]` |
| `dnd_pipeline_config_directory_mode` | `0755` |
| `dnd_pipeline_config_file_mode` | `0644` |

All application configuration, including pipeline-owned Narratio fragments,
is therefore `narratio:narratio`, world-readable, and Ansible-managed. It is
not an operator-editable configuration surface.

Narratio receives the standard Seriatim, Audita, Notarius, and Scriptorium
binary and configuration paths managed by the composed roles. Notarius is
enabled with the suite-owned `dnd-session` extraction pipeline.

The role deploys the campaign repository directly at the campaign root and
the prompt library directly at the prompt-library root. By default both follow
their `main` branches; callers can select an immutable commit, tag, or another
branch through the revision variables. Narratio receives the deployed campaign
root, while Scriptorium receives its `prompts/` and `schemas/` children.

### D&D processing policy

The variables below are deliberate D&D suite policy, not a copy of application
defaults. They remain ordinary inventory variables, so callers can replace a
chosen policy value when their deployment requires it.

| Variable group | Default policy |
| --- | --- |
| `dnd_pipeline_audita_pipeline_modules` | `glossary`, `homophones`, `glossary`, `spoken_word`, `grammar` |
| `dnd_pipeline_audita_output_schema` | `audita-v1` |
| `dnd_pipeline_audita_llm_proposal_*` | `https://inference.ai.rakestrawhome.com/v1`, `google/gemma-4-31b-it`, `AUDITA_LLM_API_KEY`, `900s`, `3` |
| `dnd_pipeline_audita_llm_validation_*` | `https://inference.ai.rakestrawhome.com/v1`, `google/gemma-4-31b-it`, `AUDITA_LLM_API_KEY`, `900s`, `3` |
| `dnd_pipeline_audita_concurrency_*` | total, proposal, and validation concurrency of `4` |
| `dnd_pipeline_audita_chunking_*` | `8` target sections, `6144` maximum and `2048` minimum section tokens |
| `dnd_pipeline_audita_normalization_*` | `3s` maximum and ellipsis gaps, `240s` maximum duration, `2048` maximum tokens |
| `dnd_pipeline_audita_thresholds_*` | `0.8` for glossary, homophones, spoken word, and grammar |
| `dnd_pipeline_audita_context_description` | D&D-game transcript context, including possible pre- and post-session banter |
| `dnd_pipeline_audita_diagnostics_*` | `/tmp/audita`, retained automatically |

Audita's proposal and validation settings independently remain overrideable,
but both default to the one typed `AUDITA_LLM_API_KEY` reference Narratio can
forward. Audita owns its endpoint, model, tuning, and diagnostics configuration;
Narratio receives its managed Audita configuration path and supplies the
run-specific output path.

| Variable | Default |
| --- | --- |
| `dnd_pipeline_narratio_seriatim_output_schema` | `seriatim-intermediate` |
| `dnd_pipeline_narratio_normalize_output_path` | `transcripts/final.json` |
| `dnd_pipeline_narratio_normalize_output_schema` | `seriatim-intermediate` |
| `dnd_pipeline_narratio_trim_enabled` | `true` |
| `dnd_pipeline_narratio_trim_output_path` | `transcripts/final.trimmed.json` |
| `dnd_pipeline_narratio_trim_bounds_prompt_id` | `dnd.session_bounds` |
| `dnd_pipeline_narratio_trim_bounds_transcript_input_name` | `transcript` |
| `dnd_pipeline_narratio_trim_bounds_output_path` | `artifacts/session_bounds.json` |
| `dnd_pipeline_narratio_render_enabled` | `true` |
| `dnd_pipeline_narratio_render_format` | `markdown` |
| `dnd_pipeline_narratio_testing_scriptorium_profile` | `gemini-flash-latest` |
| `dnd_pipeline_notarius_testing_llm_profile` | `gpt-luna-latest` |

`dnd_pipeline_audita_output_schema` is also the Narratio Audita-adapter schema;
it is the shared cross-application boundary. Other Narratio-local controls,
including reports, timeouts, debug rendering, presentation, and bounds prompt
profile selection, remain Narratio defaults.

### Storage and publication policy

The suite selects Narratio's S3 backend and the established Backblaze-compatible
archive. These are ordinary inventory variables, so deployments may replace
the selected policy through the role's public interface.

| Variable | Default policy |
| --- | --- |
| `dnd_pipeline_narratio_workspace_cleanup_after_publish` | `true` |
| `dnd_pipeline_narratio_storage_backend` | `s3` |
| `dnd_pipeline_narratio_storage_s3_bucket` | `rakestraw-assets` |
| `dnd_pipeline_narratio_storage_s3_root_prefix` | `dnd` |
| `dnd_pipeline_narratio_storage_s3_region` | `us-east-1` |
| `dnd_pipeline_narratio_storage_s3_endpoint` | `https://s3.us-east-005.backblazeb2.com` |
| `dnd_pipeline_narratio_storage_s3_force_path_style` | `true` |
| `dnd_pipeline_narratio_storage_s3_access_key_id` | `OBJECT_STORAGE_KEY_ID` |
| `dnd_pipeline_narratio_storage_s3_secret_access_key` | `OBJECT_STORAGE_KEY` |
| `dnd_pipeline_narratio_cache_s3_audio` | `true` |
| `dnd_pipeline_narratio_publish_enabled` | `true` |
| `dnd_pipeline_narratio_publish_upload_run` | `true` |

`dnd_pipeline_narratio_publish_outputs` is a complete native list, not a list
merged with the suite default. It publishes final and trimmed JSON, final and
trimmed Markdown, session recap, hostile rumors, and optional deranged rumors.
Every rule omits `dest`: Narratio derives transcript destinations from its
built-in sources and artifact destinations from the configured artifact output
paths.

S3 session audio uses the maximum available native cache beneath
`/var/cache/narratio`. After successful run publication, Narratio cleans the
published workspace target while preserving that cache. The suite deliberately
does not set `narratio_spool_delete_audio_after_publish`; spool-audio retention
continues to use Narratio's application default.

### Artifacts and profiles

The role owns these complete native mapping variables. Replacing one mapping
changes that source's configuration as a whole; it does not change the fixed
file name, import, or source key. Set `enabled: false` to retain an available
source while excluding it from normal analysis.

| Variable | Fixed source | Default state | Output |
| --- | --- | --- | --- |
| `dnd_pipeline_narratio_session_recap_artifact` | `session_recap` | enabled | `artifacts/session_recap.md` |
| `dnd_pipeline_narratio_hostile_rumors_artifact` | `hostile_rumors` | enabled | `artifacts/hostile_rumors.md` |
| `dnd_pipeline_narratio_deranged_rumors_artifact` | `deranged_rumors` | enabled | `artifacts/deranged_rumors.md` |
| `dnd_pipeline_narratio_scene_map_artifact` | `scene_map` | disabled | `artifacts/scene_map.json` |
| `dnd_pipeline_narratio_character_analysis_family` | `character_meta_analysis` | disabled | `artifacts/character_meta_analysis/{character_id}.md` |

The character-analysis family expands over campaign `party.characters` and
passes each member's name and class summary to its prompt. Recap and both rumor
sources are enabled; the rumor input derives its recap dependency without a
redundant explicit ordering edge. Production artifacts inherit each prompt's
declared profile.

Narratio's root file remains owned by the standalone role. It imports the
suite-owned base fragments in this fixed order:

```text
/usr/local/etc/narratio/
├── pipeline.yml
├── conf.d/processing.yml
├── artifacts/session-recap.yml
├── artifacts/hostile-rumors.yml
├── artifacts/deranged-rumors.yml
├── artifacts/scene-map.yml
├── artifact-families/character-meta-analysis.yml
└── profiles/testing.yml
```

Notarius follows the corresponding base-and-overlay layout:

```text
/usr/local/etc/notarius/
├── config.yml
├── pipelines/dnd-session.yml
└── profiles/testing.yml
```

The `testing` profile is an overlay, not a second configuration tree. It sets
the Scriptorium `profile_id` for the four artifact sources and the one family,
and explicitly selects Notarius's separately managed `testing` overlay. The
Scriptorium default, `gemini-flash-latest`, is an inexpensive development
choice, not a compatibility guarantee. Replace it through inventory when a
different testing profile is appropriate:

```yaml
dnd_pipeline_narratio_testing_scriptorium_profile: endpoint-profile
dnd_pipeline_notarius_testing_llm_profile: alternate-economy-profile
```

### Notarius extraction policy

The Notarius root configuration imports the fixed
`pipelines/dnd-session.yml` fragment. The suite owns that fragment at
`/usr/local/etc/notarius/pipelines/dnd-session.yml`; callers do not edit it.
The separate `/usr/local/etc/notarius/profiles/testing.yml` overlay changes only
the selected suite pipeline's LLM profile.

| Variable | Default policy |
| --- | --- |
| `dnd_pipeline_notarius_pipelines` | Complete native map containing `dnd-session` |
| `dnd_pipeline_notarius_cache_root` | `/var/cache/notarius` |
| `dnd_pipeline_notarius_cache_chunk_plans_mode` | `auto` |
| `dnd_pipeline_notarius_cache_checkpoints_enabled` | `true` |
| `dnd_pipeline_notarius_testing_llm_profile` | `gpt-luna-latest` |
| `dnd_pipeline_narratio_notarius_pipeline_id` | `dnd-session` |
| `dnd_pipeline_narratio_notarius_llm_api_key` | `OPENROUTER_API_KEY` |
| `dnd_pipeline_narratio_notarius_resume` | `true` |
| `dnd_pipeline_narratio_notarius_references` | `party`, `players`, and `glossary` prepared sources |
| `dnd_pipeline_narratio_notarius_outputs` | Complete native map of ten accepted D&D lanes |

The pipeline, reference, and output values are complete native mappings.
Inventory can replace them or compose additions with Jinja's `combine` filter;
a replacement pipeline map requires a matching selected pipeline ID. The base
`dnd-session` pipeline selects `gpt-terra-latest`, while the testing overlay
selects `gpt-luna-latest`. Both are moving catalog IDs rather than immutable
model promises. Pipeline and binding-level overrides retain Notarius's native
precedence; the suite does not rewrite caller-supplied bindings.

Narratio materializes the `party`, `players`, and `glossary` references for each
invocation. No campaign filesystem path appears in Notarius configuration. The
optional `spell_catalog` reference remains absent until a campaign supplies
that input. The accepted sources are
`narratio.extraction.item_registry`, `npc_registry`, `location_registry`,
`scene_descriptions`, `item_occurrences`, `spells`, `combat_turns`,
`npc_occurrences`, `location_occurrences`, and `enemy_events`.
They remain available as `narratio.extraction.<output_key>` inputs for future
analyze artifacts whether or not a source has a stable publication rule;
accepted extraction and published output selection are independent interfaces.

Narratio forwards the typed `OPENROUTER_API_KEY` reference to the selected
Notarius profile and ordinary extraction requests checkpoint reuse with
`resume: true`. Chunk plans use Notarius's root-owned `auto` policy; the
pipeline deliberately leaves Narratio's optional `chunk_cache` override unset.
The `chunk-plans` and `checkpoints` paths derive from the cache root and are
created by Notarius during use. Notarius v0.7.1 selects PromptKit v0.10.0 and
OpenRouter catalog v2.20260922.1, which supplies both suite-selected IDs.
Existing checkpoints with the previous profile-source identity are not reused;
source-keyed chunk plans and output artifacts remain compatible. No cache
deletion or forced extraction is performed by this role. A real testing run may
invoke Notarius; the integration suite performs offline configuration inspection
only and makes no provider request.

### Inspecting configuration

The following native Narratio commands resolve configuration without running
transcription or requesting a model provider. Select a deployed campaign for
the party-driven character family:

```sh
sudo -u narratio narratio config validate \
  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs
sudo -u narratio narratio config validate \
  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs --profile testing
sudo -u narratio narratio config artifacts \
  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs
sudo -u narratio narratio config diff default testing \
  --config /usr/local/etc/narratio/pipeline.yml --campaign centaurs
```

The first two commands validate production and testing resolution. Artifact
inspection shows enabled sources, inferred dependencies, and generated family
members; the diff shows the overlay's profile selections without modifying
managed files.

With valid object-storage credentials, the selected policy enables Narratio's
native [S3 session-audio](https://gitea.maximumdirect.net/eric/narratio/src/tag/v2.1.1/docs/config.md#session),
[publication](https://gitea.maximumdirect.net/eric/narratio/src/tag/v2.1.1/docs/operations.md#publish-workflow),
[restore](https://gitea.maximumdirect.net/eric/narratio/src/tag/v2.1.1/docs/operations.md#restore-workflow),
[publication locks](https://gitea.maximumdirect.net/eric/narratio/src/tag/v2.1.1/docs/operations.md#publish-locks),
[session status](https://gitea.maximumdirect.net/eric/narratio/src/tag/v2.1.1/docs/operations.md#standard-session-workflow),
and [cleanup](https://gitea.maximumdirect.net/eric/narratio/src/tag/v2.1.1/docs/operations.md#cleanup)
workflows. These remain application commands and lifecycle rules; scheduling
and real end-to-end execution remain deployment concerns.

### Shared execution filesystem

`/var/lib/narratio`, `/var/spool/narratio`, `/var/cache/narratio`, and
`/var/cache/notarius` are
`narratio:narratio` mode `2775` **setgid** directories. Their access and
default ACLs retain owner and group write access plus world read/traverse access
for newly created content. The pipeline may run as `narratio` or as a human
account in the selected runtime group. Consumers can enroll selected existing
human accounts through the role interface:

```yaml
dnd_pipeline_operator_users:
  - eric
  - alice
```

Every selected account must already exist; the role does not create human
accounts or manage their identity and login policy. Enrollment adds the
selected runtime group without replacing other supplementary groups. Removing
or omitting a name later does not revoke membership. A newly enrolled operator
must begin a new login session before the operating system exposes the added
supplementary group to that session.

Configuration, transcripts, caches, generated artifacts, campaign data,
prompts, and logs are non-secret D&D content. Credentials use the restricted
`/usr/local/etc/narratio/secrets` subtree, owned by the selected runtime user
and group with mode `0750`; managed files use mode `0640`. Runtime-group
membership, including enrollment through `dnd_pipeline_operator_users`,
authorizes use of these shared credentials, while the subtree grants no world
access. Ordinary configuration remains world-readable and contains only
reference names.

### Managed credentials

`dnd_pipeline_secrets` defaults to `{}`. Its keys must be valid environment
variable names, and each string value is managed as the exact named credential
file. Omitted names are unmanaged: the role neither mirrors nor purges the
directory. Narratio loads this conventional sibling directory before
configuration resolution; an already-set process environment value takes
precedence. The role adds no wrapper, service, or parallel credential loader.

Keep values in encrypted inventory, for example with Ansible Vault; Vault is a
consumer workflow, not role functionality:

```yaml
dnd_pipeline_secrets:
  AUDITA_LLM_API_KEY: "{{ vault_dnd_audita_llm_api_key }}"
  OPENROUTER_API_KEY: "{{ vault_dnd_openrouter_api_key }}"
  OBJECT_STORAGE_KEY_ID: "{{ vault_dnd_object_storage_key_id }}"
  OBJECT_STORAGE_KEY: "{{ vault_dnd_object_storage_key }}"
```

Only the reference names enter ordinary Narratio configuration; credential
values remain in encrypted inventory and the restricted managed secrets
directory. A deployment using Narratio's ambient AWS SDK provider chain can
set both `dnd_pipeline_narratio_storage_s3_access_key_id` and
`dnd_pipeline_narratio_storage_s3_secret_access_key` to `null`. The pair must
be omitted together.

Scriptorium profiles continue to own their `api_key_env` selection. To supply
that credential through the suite, add a `dnd_pipeline_secrets` entry whose
name matches the selected profile's `api_key_env`. Narratio's secrets bootstrap
loads the value, and its existing Scriptorium adapter forwards only the
profile-selected credential.

## Validation

`tests/integration` installs the pinned Git dependencies and collection into
private temporary paths, runs syntax and production-profile lint checks, then
applies the suite with a local syntactically valid WhisperX URL and explicit
immutable `file://` asset inputs. It uses native application
smoke/configuration commands, validates Notarius's imported pipeline and
effective cache policy, and validates Narratio for both deployed campaigns and
the testing overlay. It inspects enabled Notarius wiring through Narratio's
native effective configuration, validates the same imported Notarius pipeline
as a temporary existing-group-member fixture, exercises representative shared
cache access across the service and fixture identities, and confirms that
`nobody` can read ordinary configuration. It also composes an alternate pair of
version-5 pipeline maps through the public interface and requires clean repeats
for the baseline and override cases. Cleanup reapplies the asset-enabled
baseline suite and removes only the fixture account, its named test content,
and the driver's private temporary directory.